Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- trainer_state.json +3568 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"q_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:def362bea6166fe558d40b1c9b1bc16c285d6b5e9c0aaaf704cae545979ab4fa
|
3 |
+
size 828526568
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83c48e0ef4a6ee0d88763f0acb0fc6dee73a54d9dddbf91c8d705fa2ede598c1
|
3 |
+
size 1657442386
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc23f0450e3fe981c4f07a3217c6be7fb0dcea640e03748d933a3897bbc1873
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a856d0eb26df9431dc25b01dc473f063ff51f27e01a432bd57dfd4dcb1a22a03
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|end_of_text|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9972690572310614,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 50532,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003955070400253125,
|
13 |
+
"grad_norm": 0.3985116183757782,
|
14 |
+
"learning_rate": 1.5e-06,
|
15 |
+
"loss": 2.3445,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.00791014080050625,
|
20 |
+
"grad_norm": 0.5253750681877136,
|
21 |
+
"learning_rate": 3e-06,
|
22 |
+
"loss": 2.2315,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.011865211200759373,
|
27 |
+
"grad_norm": 0.7505590319633484,
|
28 |
+
"learning_rate": 4.5e-06,
|
29 |
+
"loss": 2.0777,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0158202816010125,
|
34 |
+
"grad_norm": 0.7067473530769348,
|
35 |
+
"learning_rate": 6e-06,
|
36 |
+
"loss": 2.0165,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.019775352001265623,
|
41 |
+
"grad_norm": 0.8964686393737793,
|
42 |
+
"learning_rate": 7.5e-06,
|
43 |
+
"loss": 1.9872,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.023730422401518746,
|
48 |
+
"grad_norm": 1.0233873128890991,
|
49 |
+
"learning_rate": 9e-06,
|
50 |
+
"loss": 1.9621,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02768549280177187,
|
55 |
+
"grad_norm": 1.0008875131607056,
|
56 |
+
"learning_rate": 1.05e-05,
|
57 |
+
"loss": 1.9519,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.031640563202025,
|
62 |
+
"grad_norm": 0.9941542148590088,
|
63 |
+
"learning_rate": 1.2e-05,
|
64 |
+
"loss": 1.922,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.03559563360227812,
|
69 |
+
"grad_norm": 1.0296485424041748,
|
70 |
+
"learning_rate": 1.3500000000000001e-05,
|
71 |
+
"loss": 1.9305,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.039550704002531245,
|
76 |
+
"grad_norm": 1.056834101676941,
|
77 |
+
"learning_rate": 1.5e-05,
|
78 |
+
"loss": 1.9199,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.04350577440278437,
|
83 |
+
"grad_norm": 1.1616301536560059,
|
84 |
+
"learning_rate": 1.4999976437535872e-05,
|
85 |
+
"loss": 1.9058,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04746084480303749,
|
90 |
+
"grad_norm": 1.0753331184387207,
|
91 |
+
"learning_rate": 1.4999905750291538e-05,
|
92 |
+
"loss": 1.9321,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05141591520329062,
|
97 |
+
"grad_norm": 1.3542801141738892,
|
98 |
+
"learning_rate": 1.4999787938711148e-05,
|
99 |
+
"loss": 1.8942,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.05537098560354374,
|
104 |
+
"grad_norm": 1.2391093969345093,
|
105 |
+
"learning_rate": 1.499962300353495e-05,
|
106 |
+
"loss": 1.8677,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.05932605600379687,
|
111 |
+
"grad_norm": 1.0844732522964478,
|
112 |
+
"learning_rate": 1.4999410945799291e-05,
|
113 |
+
"loss": 1.8723,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.06328112640405,
|
118 |
+
"grad_norm": 1.0814001560211182,
|
119 |
+
"learning_rate": 1.499915176683659e-05,
|
120 |
+
"loss": 1.8715,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.06723619680430312,
|
125 |
+
"grad_norm": 1.2003209590911865,
|
126 |
+
"learning_rate": 1.4998845468275357e-05,
|
127 |
+
"loss": 1.8739,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.07119126720455624,
|
132 |
+
"grad_norm": 1.2625234127044678,
|
133 |
+
"learning_rate": 1.4998492052040163e-05,
|
134 |
+
"loss": 1.8475,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07514633760480936,
|
139 |
+
"grad_norm": 1.144286870956421,
|
140 |
+
"learning_rate": 1.499809152035164e-05,
|
141 |
+
"loss": 1.8517,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.07910140800506249,
|
146 |
+
"grad_norm": 1.2154852151870728,
|
147 |
+
"learning_rate": 1.4997643875726454e-05,
|
148 |
+
"loss": 1.8262,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.08305647840531562,
|
153 |
+
"grad_norm": 1.389930009841919,
|
154 |
+
"learning_rate": 1.4997149120977304e-05,
|
155 |
+
"loss": 1.8419,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.08701154880556874,
|
160 |
+
"grad_norm": 1.265163779258728,
|
161 |
+
"learning_rate": 1.4996607259212892e-05,
|
162 |
+
"loss": 1.8344,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.09096661920582186,
|
167 |
+
"grad_norm": 1.1876202821731567,
|
168 |
+
"learning_rate": 1.4996018293837914e-05,
|
169 |
+
"loss": 1.8356,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.09492168960607499,
|
174 |
+
"grad_norm": 1.2677972316741943,
|
175 |
+
"learning_rate": 1.4995382228553028e-05,
|
176 |
+
"loss": 1.8463,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09887676000632811,
|
181 |
+
"grad_norm": 1.206444501876831,
|
182 |
+
"learning_rate": 1.4994699067354838e-05,
|
183 |
+
"loss": 1.8256,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.10283183040658124,
|
188 |
+
"grad_norm": 1.2112213373184204,
|
189 |
+
"learning_rate": 1.4993968814535867e-05,
|
190 |
+
"loss": 1.8627,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.10678690080683437,
|
195 |
+
"grad_norm": 1.1587677001953125,
|
196 |
+
"learning_rate": 1.4993191474684532e-05,
|
197 |
+
"loss": 1.8458,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.11074197120708748,
|
202 |
+
"grad_norm": 1.2365622520446777,
|
203 |
+
"learning_rate": 1.4992367052685107e-05,
|
204 |
+
"loss": 1.8383,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.11469704160734061,
|
209 |
+
"grad_norm": 1.179803490638733,
|
210 |
+
"learning_rate": 1.4991495553717708e-05,
|
211 |
+
"loss": 1.8305,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.11865211200759374,
|
216 |
+
"grad_norm": 1.336897850036621,
|
217 |
+
"learning_rate": 1.499057698325824e-05,
|
218 |
+
"loss": 1.8381,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.12260718240784686,
|
223 |
+
"grad_norm": 1.346336007118225,
|
224 |
+
"learning_rate": 1.498961134707838e-05,
|
225 |
+
"loss": 1.8467,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.1265622528081,
|
230 |
+
"grad_norm": 1.2718663215637207,
|
231 |
+
"learning_rate": 1.4988598651245534e-05,
|
232 |
+
"loss": 1.8076,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.1305173232083531,
|
237 |
+
"grad_norm": 1.1807332038879395,
|
238 |
+
"learning_rate": 1.4987538902122799e-05,
|
239 |
+
"loss": 1.8212,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.13447239360860624,
|
244 |
+
"grad_norm": 1.4749420881271362,
|
245 |
+
"learning_rate": 1.4986432106368917e-05,
|
246 |
+
"loss": 1.8039,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.13842746400885936,
|
251 |
+
"grad_norm": 1.2670525312423706,
|
252 |
+
"learning_rate": 1.4985278270938247e-05,
|
253 |
+
"loss": 1.8137,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.14238253440911247,
|
258 |
+
"grad_norm": 1.5255069732666016,
|
259 |
+
"learning_rate": 1.4984077403080711e-05,
|
260 |
+
"loss": 1.8161,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1463376048093656,
|
265 |
+
"grad_norm": 1.1995693445205688,
|
266 |
+
"learning_rate": 1.4982829510341751e-05,
|
267 |
+
"loss": 1.8104,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.15029267520961873,
|
272 |
+
"grad_norm": 1.3007076978683472,
|
273 |
+
"learning_rate": 1.4981534600562279e-05,
|
274 |
+
"loss": 1.7952,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.15424774560987187,
|
279 |
+
"grad_norm": 1.4348576068878174,
|
280 |
+
"learning_rate": 1.4980192681878635e-05,
|
281 |
+
"loss": 1.819,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.15820281601012498,
|
286 |
+
"grad_norm": 1.3245015144348145,
|
287 |
+
"learning_rate": 1.4978803762722526e-05,
|
288 |
+
"loss": 1.8043,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.1621578864103781,
|
293 |
+
"grad_norm": 1.3621593713760376,
|
294 |
+
"learning_rate": 1.4977367851820984e-05,
|
295 |
+
"loss": 1.7992,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.16611295681063123,
|
300 |
+
"grad_norm": 1.2361946105957031,
|
301 |
+
"learning_rate": 1.4975884958196297e-05,
|
302 |
+
"loss": 1.8179,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.17006802721088435,
|
307 |
+
"grad_norm": 1.5746525526046753,
|
308 |
+
"learning_rate": 1.4974355091165972e-05,
|
309 |
+
"loss": 1.8045,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1740230976111375,
|
314 |
+
"grad_norm": 1.4326754808425903,
|
315 |
+
"learning_rate": 1.497277826034265e-05,
|
316 |
+
"loss": 1.8155,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.1779781680113906,
|
321 |
+
"grad_norm": 1.3772553205490112,
|
322 |
+
"learning_rate": 1.4971154475634081e-05,
|
323 |
+
"loss": 1.7838,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.18193323841164372,
|
328 |
+
"grad_norm": 1.4580802917480469,
|
329 |
+
"learning_rate": 1.4969483747243023e-05,
|
330 |
+
"loss": 1.7997,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.18588830881189686,
|
335 |
+
"grad_norm": 1.2635383605957031,
|
336 |
+
"learning_rate": 1.4967766085667204e-05,
|
337 |
+
"loss": 1.8091,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.18984337921214997,
|
342 |
+
"grad_norm": 1.523247241973877,
|
343 |
+
"learning_rate": 1.496600150169925e-05,
|
344 |
+
"loss": 1.8086,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.1937984496124031,
|
349 |
+
"grad_norm": 1.4835641384124756,
|
350 |
+
"learning_rate": 1.496419000642661e-05,
|
351 |
+
"loss": 1.8001,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.19775352001265623,
|
356 |
+
"grad_norm": 1.3758567571640015,
|
357 |
+
"learning_rate": 1.4962331611231496e-05,
|
358 |
+
"loss": 1.7773,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.20170859041290934,
|
363 |
+
"grad_norm": 1.343885898590088,
|
364 |
+
"learning_rate": 1.4960426327790808e-05,
|
365 |
+
"loss": 1.7884,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.20566366081316248,
|
370 |
+
"grad_norm": 1.4712055921554565,
|
371 |
+
"learning_rate": 1.4958474168076061e-05,
|
372 |
+
"loss": 1.7904,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.2096187312134156,
|
377 |
+
"grad_norm": 1.3729618787765503,
|
378 |
+
"learning_rate": 1.4956475144353305e-05,
|
379 |
+
"loss": 1.7883,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.21357380161366873,
|
384 |
+
"grad_norm": 1.4087861776351929,
|
385 |
+
"learning_rate": 1.4954429269183049e-05,
|
386 |
+
"loss": 1.7764,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.21752887201392185,
|
391 |
+
"grad_norm": 1.359567642211914,
|
392 |
+
"learning_rate": 1.4952336555420194e-05,
|
393 |
+
"loss": 1.7522,
|
394 |
+
"step": 5500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.22148394241417496,
|
398 |
+
"grad_norm": 1.5321180820465088,
|
399 |
+
"learning_rate": 1.4950197016213935e-05,
|
400 |
+
"loss": 1.7858,
|
401 |
+
"step": 5600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2254390128144281,
|
405 |
+
"grad_norm": 1.4172133207321167,
|
406 |
+
"learning_rate": 1.4948010665007694e-05,
|
407 |
+
"loss": 1.7889,
|
408 |
+
"step": 5700
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.22939408321468122,
|
412 |
+
"grad_norm": 1.389819622039795,
|
413 |
+
"learning_rate": 1.4945777515539018e-05,
|
414 |
+
"loss": 1.7787,
|
415 |
+
"step": 5800
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.23334915361493436,
|
419 |
+
"grad_norm": 1.319344162940979,
|
420 |
+
"learning_rate": 1.4943497581839515e-05,
|
421 |
+
"loss": 1.7832,
|
422 |
+
"step": 5900
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.23730422401518747,
|
426 |
+
"grad_norm": 1.3472243547439575,
|
427 |
+
"learning_rate": 1.4941170878234739e-05,
|
428 |
+
"loss": 1.7708,
|
429 |
+
"step": 6000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.24125929441544058,
|
433 |
+
"grad_norm": 1.319574236869812,
|
434 |
+
"learning_rate": 1.4938797419344127e-05,
|
435 |
+
"loss": 1.8013,
|
436 |
+
"step": 6100
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.24521436481569373,
|
440 |
+
"grad_norm": 1.3281052112579346,
|
441 |
+
"learning_rate": 1.4936377220080886e-05,
|
442 |
+
"loss": 1.7657,
|
443 |
+
"step": 6200
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.24916943521594684,
|
447 |
+
"grad_norm": 1.4613900184631348,
|
448 |
+
"learning_rate": 1.4933910295651914e-05,
|
449 |
+
"loss": 1.7955,
|
450 |
+
"step": 6300
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.2531245056162,
|
454 |
+
"grad_norm": 1.6248208284378052,
|
455 |
+
"learning_rate": 1.4931396661557699e-05,
|
456 |
+
"loss": 1.7775,
|
457 |
+
"step": 6400
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.2570795760164531,
|
461 |
+
"grad_norm": 1.4050931930541992,
|
462 |
+
"learning_rate": 1.492883633359221e-05,
|
463 |
+
"loss": 1.749,
|
464 |
+
"step": 6500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.2610346464167062,
|
468 |
+
"grad_norm": 1.3959672451019287,
|
469 |
+
"learning_rate": 1.4926229327842822e-05,
|
470 |
+
"loss": 1.7735,
|
471 |
+
"step": 6600
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2649897168169593,
|
475 |
+
"grad_norm": 1.3407930135726929,
|
476 |
+
"learning_rate": 1.4923575660690197e-05,
|
477 |
+
"loss": 1.7685,
|
478 |
+
"step": 6700
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.2689447872172125,
|
482 |
+
"grad_norm": 1.4229165315628052,
|
483 |
+
"learning_rate": 1.4920875348808181e-05,
|
484 |
+
"loss": 1.769,
|
485 |
+
"step": 6800
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.2728998576174656,
|
489 |
+
"grad_norm": 1.3997846841812134,
|
490 |
+
"learning_rate": 1.4918128409163712e-05,
|
491 |
+
"loss": 1.7804,
|
492 |
+
"step": 6900
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.2768549280177187,
|
496 |
+
"grad_norm": 1.7216688394546509,
|
497 |
+
"learning_rate": 1.4915334859016699e-05,
|
498 |
+
"loss": 1.7699,
|
499 |
+
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.28080999841797183,
|
503 |
+
"grad_norm": 1.4955641031265259,
|
504 |
+
"learning_rate": 1.491249471591992e-05,
|
505 |
+
"loss": 1.7615,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.28476506881822494,
|
510 |
+
"grad_norm": 1.631832480430603,
|
511 |
+
"learning_rate": 1.4909607997718917e-05,
|
512 |
+
"loss": 1.7708,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2887201392184781,
|
517 |
+
"grad_norm": 1.4372748136520386,
|
518 |
+
"learning_rate": 1.4906674722551872e-05,
|
519 |
+
"loss": 1.7618,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.2926752096187312,
|
524 |
+
"grad_norm": 1.3430101871490479,
|
525 |
+
"learning_rate": 1.4903694908849506e-05,
|
526 |
+
"loss": 1.7734,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.29663028001898434,
|
531 |
+
"grad_norm": 1.4826927185058594,
|
532 |
+
"learning_rate": 1.4900668575334953e-05,
|
533 |
+
"loss": 1.7679,
|
534 |
+
"step": 7500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.30058535041923745,
|
538 |
+
"grad_norm": 1.4105191230773926,
|
539 |
+
"learning_rate": 1.4897595741023642e-05,
|
540 |
+
"loss": 1.7666,
|
541 |
+
"step": 7600
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.30454042081949056,
|
545 |
+
"grad_norm": 1.3381356000900269,
|
546 |
+
"learning_rate": 1.4894476425223191e-05,
|
547 |
+
"loss": 1.7697,
|
548 |
+
"step": 7700
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.30849549121974373,
|
552 |
+
"grad_norm": 1.3745373487472534,
|
553 |
+
"learning_rate": 1.4891310647533266e-05,
|
554 |
+
"loss": 1.7707,
|
555 |
+
"step": 7800
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.31245056161999685,
|
559 |
+
"grad_norm": 1.3524316549301147,
|
560 |
+
"learning_rate": 1.488809842784548e-05,
|
561 |
+
"loss": 1.7515,
|
562 |
+
"step": 7900
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.31640563202024996,
|
566 |
+
"grad_norm": 1.4299299716949463,
|
567 |
+
"learning_rate": 1.4884839786343242e-05,
|
568 |
+
"loss": 1.7799,
|
569 |
+
"step": 8000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.3203607024205031,
|
573 |
+
"grad_norm": 1.4132308959960938,
|
574 |
+
"learning_rate": 1.4881534743501656e-05,
|
575 |
+
"loss": 1.7258,
|
576 |
+
"step": 8100
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.3243157728207562,
|
580 |
+
"grad_norm": 1.4797372817993164,
|
581 |
+
"learning_rate": 1.4878183320087377e-05,
|
582 |
+
"loss": 1.7657,
|
583 |
+
"step": 8200
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.32827084322100936,
|
587 |
+
"grad_norm": 1.3737105131149292,
|
588 |
+
"learning_rate": 1.4874785537158479e-05,
|
589 |
+
"loss": 1.7845,
|
590 |
+
"step": 8300
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.33222591362126247,
|
594 |
+
"grad_norm": 1.4676398038864136,
|
595 |
+
"learning_rate": 1.4871341416064337e-05,
|
596 |
+
"loss": 1.7652,
|
597 |
+
"step": 8400
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.3361809840215156,
|
601 |
+
"grad_norm": 1.3782434463500977,
|
602 |
+
"learning_rate": 1.4867850978445476e-05,
|
603 |
+
"loss": 1.7516,
|
604 |
+
"step": 8500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.3401360544217687,
|
608 |
+
"grad_norm": 1.5370761156082153,
|
609 |
+
"learning_rate": 1.4864314246233448e-05,
|
610 |
+
"loss": 1.75,
|
611 |
+
"step": 8600
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.3440911248220218,
|
615 |
+
"grad_norm": 1.4677528142929077,
|
616 |
+
"learning_rate": 1.486073124165068e-05,
|
617 |
+
"loss": 1.7518,
|
618 |
+
"step": 8700
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.348046195222275,
|
622 |
+
"grad_norm": 1.4215251207351685,
|
623 |
+
"learning_rate": 1.4857101987210359e-05,
|
624 |
+
"loss": 1.7634,
|
625 |
+
"step": 8800
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.3520012656225281,
|
629 |
+
"grad_norm": 1.4959337711334229,
|
630 |
+
"learning_rate": 1.4853426505716261e-05,
|
631 |
+
"loss": 1.7491,
|
632 |
+
"step": 8900
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.3559563360227812,
|
636 |
+
"grad_norm": 1.4005351066589355,
|
637 |
+
"learning_rate": 1.4849704820262627e-05,
|
638 |
+
"loss": 1.7713,
|
639 |
+
"step": 9000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.3599114064230343,
|
643 |
+
"grad_norm": 1.4689812660217285,
|
644 |
+
"learning_rate": 1.484593695423401e-05,
|
645 |
+
"loss": 1.7448,
|
646 |
+
"step": 9100
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.36386647682328743,
|
650 |
+
"grad_norm": 1.5371148586273193,
|
651 |
+
"learning_rate": 1.4842122931305133e-05,
|
652 |
+
"loss": 1.7452,
|
653 |
+
"step": 9200
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.3678215472235406,
|
657 |
+
"grad_norm": 1.4465723037719727,
|
658 |
+
"learning_rate": 1.4838262775440741e-05,
|
659 |
+
"loss": 1.7452,
|
660 |
+
"step": 9300
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.3717766176237937,
|
664 |
+
"grad_norm": 1.5890401601791382,
|
665 |
+
"learning_rate": 1.4834356510895436e-05,
|
666 |
+
"loss": 1.737,
|
667 |
+
"step": 9400
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.37573168802404683,
|
671 |
+
"grad_norm": 1.4862806797027588,
|
672 |
+
"learning_rate": 1.4830404162213549e-05,
|
673 |
+
"loss": 1.7426,
|
674 |
+
"step": 9500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.37968675842429994,
|
678 |
+
"grad_norm": 1.5449295043945312,
|
679 |
+
"learning_rate": 1.4826405754228963e-05,
|
680 |
+
"loss": 1.7379,
|
681 |
+
"step": 9600
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.38364182882455306,
|
685 |
+
"grad_norm": 1.5151877403259277,
|
686 |
+
"learning_rate": 1.482236131206497e-05,
|
687 |
+
"loss": 1.7269,
|
688 |
+
"step": 9700
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.3875968992248062,
|
692 |
+
"grad_norm": 1.600046157836914,
|
693 |
+
"learning_rate": 1.4818270861134113e-05,
|
694 |
+
"loss": 1.7556,
|
695 |
+
"step": 9800
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.39155196962505934,
|
699 |
+
"grad_norm": 1.4293779134750366,
|
700 |
+
"learning_rate": 1.4814134427138015e-05,
|
701 |
+
"loss": 1.7368,
|
702 |
+
"step": 9900
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.39550704002531245,
|
706 |
+
"grad_norm": 1.378175973892212,
|
707 |
+
"learning_rate": 1.4809952036067231e-05,
|
708 |
+
"loss": 1.7405,
|
709 |
+
"step": 10000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.39946211042556556,
|
713 |
+
"grad_norm": 1.417622447013855,
|
714 |
+
"learning_rate": 1.4805723714201079e-05,
|
715 |
+
"loss": 1.7484,
|
716 |
+
"step": 10100
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.4034171808258187,
|
720 |
+
"grad_norm": 1.5106312036514282,
|
721 |
+
"learning_rate": 1.4801449488107477e-05,
|
722 |
+
"loss": 1.7218,
|
723 |
+
"step": 10200
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.40737225122607185,
|
727 |
+
"grad_norm": 1.5248609781265259,
|
728 |
+
"learning_rate": 1.4797129384642768e-05,
|
729 |
+
"loss": 1.7328,
|
730 |
+
"step": 10300
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.41132732162632496,
|
734 |
+
"grad_norm": 1.4607023000717163,
|
735 |
+
"learning_rate": 1.4792763430951562e-05,
|
736 |
+
"loss": 1.7131,
|
737 |
+
"step": 10400
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.4152823920265781,
|
741 |
+
"grad_norm": 1.4600701332092285,
|
742 |
+
"learning_rate": 1.4788351654466556e-05,
|
743 |
+
"loss": 1.7418,
|
744 |
+
"step": 10500
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.4192374624268312,
|
748 |
+
"grad_norm": 1.3468823432922363,
|
749 |
+
"learning_rate": 1.4783894082908377e-05,
|
750 |
+
"loss": 1.7649,
|
751 |
+
"step": 10600
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.4231925328270843,
|
755 |
+
"grad_norm": 1.5118048191070557,
|
756 |
+
"learning_rate": 1.4779390744285386e-05,
|
757 |
+
"loss": 1.7233,
|
758 |
+
"step": 10700
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.42714760322733747,
|
762 |
+
"grad_norm": 1.5199166536331177,
|
763 |
+
"learning_rate": 1.4774841666893515e-05,
|
764 |
+
"loss": 1.7238,
|
765 |
+
"step": 10800
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.4311026736275906,
|
769 |
+
"grad_norm": 1.6537836790084839,
|
770 |
+
"learning_rate": 1.4770246879316097e-05,
|
771 |
+
"loss": 1.7216,
|
772 |
+
"step": 10900
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.4350577440278437,
|
776 |
+
"grad_norm": 1.37918221950531,
|
777 |
+
"learning_rate": 1.4765606410423666e-05,
|
778 |
+
"loss": 1.7481,
|
779 |
+
"step": 11000
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.4390128144280968,
|
783 |
+
"grad_norm": 1.526502013206482,
|
784 |
+
"learning_rate": 1.4760920289373791e-05,
|
785 |
+
"loss": 1.7141,
|
786 |
+
"step": 11100
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.4429678848283499,
|
790 |
+
"grad_norm": 1.3577282428741455,
|
791 |
+
"learning_rate": 1.4756188545610884e-05,
|
792 |
+
"loss": 1.7507,
|
793 |
+
"step": 11200
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.4469229552286031,
|
797 |
+
"grad_norm": 1.557986855506897,
|
798 |
+
"learning_rate": 1.475141120886603e-05,
|
799 |
+
"loss": 1.7103,
|
800 |
+
"step": 11300
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.4508780256288562,
|
804 |
+
"grad_norm": 1.638221025466919,
|
805 |
+
"learning_rate": 1.474658830915678e-05,
|
806 |
+
"loss": 1.7363,
|
807 |
+
"step": 11400
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.4548330960291093,
|
811 |
+
"grad_norm": 1.472142219543457,
|
812 |
+
"learning_rate": 1.474171987678697e-05,
|
813 |
+
"loss": 1.7331,
|
814 |
+
"step": 11500
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.45878816642936243,
|
818 |
+
"grad_norm": 1.4680249691009521,
|
819 |
+
"learning_rate": 1.4736805942346542e-05,
|
820 |
+
"loss": 1.7273,
|
821 |
+
"step": 11600
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.46274323682961555,
|
825 |
+
"grad_norm": 1.4165573120117188,
|
826 |
+
"learning_rate": 1.4731846536711337e-05,
|
827 |
+
"loss": 1.7159,
|
828 |
+
"step": 11700
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.4666983072298687,
|
832 |
+
"grad_norm": 2.1816458702087402,
|
833 |
+
"learning_rate": 1.4726841691042902e-05,
|
834 |
+
"loss": 1.7236,
|
835 |
+
"step": 11800
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.4706533776301218,
|
839 |
+
"grad_norm": 1.5376547574996948,
|
840 |
+
"learning_rate": 1.4721791436788307e-05,
|
841 |
+
"loss": 1.7227,
|
842 |
+
"step": 11900
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.47460844803037494,
|
846 |
+
"grad_norm": 1.6850054264068604,
|
847 |
+
"learning_rate": 1.4716695805679932e-05,
|
848 |
+
"loss": 1.7116,
|
849 |
+
"step": 12000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.47856351843062805,
|
853 |
+
"grad_norm": 1.7338590621948242,
|
854 |
+
"learning_rate": 1.471155482973528e-05,
|
855 |
+
"loss": 1.7129,
|
856 |
+
"step": 12100
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.48251858883088117,
|
860 |
+
"grad_norm": 1.4183164834976196,
|
861 |
+
"learning_rate": 1.4706368541256762e-05,
|
862 |
+
"loss": 1.7267,
|
863 |
+
"step": 12200
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.48647365923113434,
|
867 |
+
"grad_norm": 1.7117156982421875,
|
868 |
+
"learning_rate": 1.4701136972831513e-05,
|
869 |
+
"loss": 1.7149,
|
870 |
+
"step": 12300
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.49042872963138745,
|
874 |
+
"grad_norm": 1.4747951030731201,
|
875 |
+
"learning_rate": 1.4695860157331169e-05,
|
876 |
+
"loss": 1.7218,
|
877 |
+
"step": 12400
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.49438380003164056,
|
881 |
+
"grad_norm": 1.6341221332550049,
|
882 |
+
"learning_rate": 1.4690538127911672e-05,
|
883 |
+
"loss": 1.7331,
|
884 |
+
"step": 12500
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.4983388704318937,
|
888 |
+
"grad_norm": 1.4981880187988281,
|
889 |
+
"learning_rate": 1.4685170918013054e-05,
|
890 |
+
"loss": 1.7182,
|
891 |
+
"step": 12600
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.5022939408321468,
|
895 |
+
"grad_norm": 1.5774872303009033,
|
896 |
+
"learning_rate": 1.4679758561359232e-05,
|
897 |
+
"loss": 1.7154,
|
898 |
+
"step": 12700
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.5062490112324,
|
902 |
+
"grad_norm": 1.5503437519073486,
|
903 |
+
"learning_rate": 1.4674301091957795e-05,
|
904 |
+
"loss": 1.716,
|
905 |
+
"step": 12800
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.5102040816326531,
|
909 |
+
"grad_norm": 1.5208927392959595,
|
910 |
+
"learning_rate": 1.4668798544099795e-05,
|
911 |
+
"loss": 1.7041,
|
912 |
+
"step": 12900
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.5141591520329062,
|
916 |
+
"grad_norm": 1.8089638948440552,
|
917 |
+
"learning_rate": 1.4663250952359516e-05,
|
918 |
+
"loss": 1.7276,
|
919 |
+
"step": 13000
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.5181142224331593,
|
923 |
+
"grad_norm": 1.5653834342956543,
|
924 |
+
"learning_rate": 1.4657658351594275e-05,
|
925 |
+
"loss": 1.7164,
|
926 |
+
"step": 13100
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.5220692928334124,
|
930 |
+
"grad_norm": 1.7017031908035278,
|
931 |
+
"learning_rate": 1.4652020776944194e-05,
|
932 |
+
"loss": 1.7053,
|
933 |
+
"step": 13200
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.5260243632336655,
|
937 |
+
"grad_norm": 1.6849620342254639,
|
938 |
+
"learning_rate": 1.4646338263831977e-05,
|
939 |
+
"loss": 1.7134,
|
940 |
+
"step": 13300
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.5299794336339186,
|
944 |
+
"grad_norm": 1.8098126649856567,
|
945 |
+
"learning_rate": 1.4640610847962699e-05,
|
946 |
+
"loss": 1.7158,
|
947 |
+
"step": 13400
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.5339345040341718,
|
951 |
+
"grad_norm": 1.7234479188919067,
|
952 |
+
"learning_rate": 1.4634838565323563e-05,
|
953 |
+
"loss": 1.7229,
|
954 |
+
"step": 13500
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.537889574434425,
|
958 |
+
"grad_norm": 1.35356867313385,
|
959 |
+
"learning_rate": 1.4629021452183695e-05,
|
960 |
+
"loss": 1.715,
|
961 |
+
"step": 13600
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.5418446448346781,
|
965 |
+
"grad_norm": 1.5286564826965332,
|
966 |
+
"learning_rate": 1.4623159545093895e-05,
|
967 |
+
"loss": 1.7011,
|
968 |
+
"step": 13700
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.5457997152349312,
|
972 |
+
"grad_norm": 1.5586360692977905,
|
973 |
+
"learning_rate": 1.4617252880886427e-05,
|
974 |
+
"loss": 1.6978,
|
975 |
+
"step": 13800
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.5497547856351843,
|
979 |
+
"grad_norm": 1.5301753282546997,
|
980 |
+
"learning_rate": 1.461130149667477e-05,
|
981 |
+
"loss": 1.6984,
|
982 |
+
"step": 13900
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.5537098560354374,
|
986 |
+
"grad_norm": 1.6551586389541626,
|
987 |
+
"learning_rate": 1.4605305429853402e-05,
|
988 |
+
"loss": 1.6935,
|
989 |
+
"step": 14000
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.5576649264356905,
|
993 |
+
"grad_norm": 1.522283911705017,
|
994 |
+
"learning_rate": 1.4599264718097552e-05,
|
995 |
+
"loss": 1.6795,
|
996 |
+
"step": 14100
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.5616199968359437,
|
1000 |
+
"grad_norm": 1.519173502922058,
|
1001 |
+
"learning_rate": 1.4593179399362967e-05,
|
1002 |
+
"loss": 1.6948,
|
1003 |
+
"step": 14200
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.5655750672361968,
|
1007 |
+
"grad_norm": 1.582780122756958,
|
1008 |
+
"learning_rate": 1.4587049511885675e-05,
|
1009 |
+
"loss": 1.7168,
|
1010 |
+
"step": 14300
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.5695301376364499,
|
1014 |
+
"grad_norm": 1.5130764245986938,
|
1015 |
+
"learning_rate": 1.458087509418174e-05,
|
1016 |
+
"loss": 1.7049,
|
1017 |
+
"step": 14400
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.573485208036703,
|
1021 |
+
"grad_norm": 1.581992268562317,
|
1022 |
+
"learning_rate": 1.4574656185047033e-05,
|
1023 |
+
"loss": 1.695,
|
1024 |
+
"step": 14500
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.5774402784369562,
|
1028 |
+
"grad_norm": 1.4675225019454956,
|
1029 |
+
"learning_rate": 1.456839282355697e-05,
|
1030 |
+
"loss": 1.7015,
|
1031 |
+
"step": 14600
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.5813953488372093,
|
1035 |
+
"grad_norm": 1.5948406457901,
|
1036 |
+
"learning_rate": 1.4562085049066282e-05,
|
1037 |
+
"loss": 1.7129,
|
1038 |
+
"step": 14700
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.5853504192374624,
|
1042 |
+
"grad_norm": 1.8901729583740234,
|
1043 |
+
"learning_rate": 1.4555732901208756e-05,
|
1044 |
+
"loss": 1.7062,
|
1045 |
+
"step": 14800
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.5893054896377156,
|
1049 |
+
"grad_norm": 1.6940269470214844,
|
1050 |
+
"learning_rate": 1.4549336419896993e-05,
|
1051 |
+
"loss": 1.7025,
|
1052 |
+
"step": 14900
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.5932605600379687,
|
1056 |
+
"grad_norm": 1.5160539150238037,
|
1057 |
+
"learning_rate": 1.454289564532216e-05,
|
1058 |
+
"loss": 1.688,
|
1059 |
+
"step": 15000
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5972156304382218,
|
1063 |
+
"grad_norm": 1.6424893140792847,
|
1064 |
+
"learning_rate": 1.4536410617953726e-05,
|
1065 |
+
"loss": 1.696,
|
1066 |
+
"step": 15100
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.6011707008384749,
|
1070 |
+
"grad_norm": 1.492990493774414,
|
1071 |
+
"learning_rate": 1.4529881378539218e-05,
|
1072 |
+
"loss": 1.6768,
|
1073 |
+
"step": 15200
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.605125771238728,
|
1077 |
+
"grad_norm": 1.7309181690216064,
|
1078 |
+
"learning_rate": 1.452330796810396e-05,
|
1079 |
+
"loss": 1.6972,
|
1080 |
+
"step": 15300
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.6090808416389811,
|
1084 |
+
"grad_norm": 1.684484601020813,
|
1085 |
+
"learning_rate": 1.451669042795082e-05,
|
1086 |
+
"loss": 1.6903,
|
1087 |
+
"step": 15400
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.6130359120392342,
|
1091 |
+
"grad_norm": 1.5465792417526245,
|
1092 |
+
"learning_rate": 1.4510028799659944e-05,
|
1093 |
+
"loss": 1.714,
|
1094 |
+
"step": 15500
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.6169909824394875,
|
1098 |
+
"grad_norm": 1.8257033824920654,
|
1099 |
+
"learning_rate": 1.4503323125088501e-05,
|
1100 |
+
"loss": 1.6894,
|
1101 |
+
"step": 15600
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.6209460528397406,
|
1105 |
+
"grad_norm": 1.5299944877624512,
|
1106 |
+
"learning_rate": 1.4496573446370414e-05,
|
1107 |
+
"loss": 1.6944,
|
1108 |
+
"step": 15700
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.6249011232399937,
|
1112 |
+
"grad_norm": 1.7090293169021606,
|
1113 |
+
"learning_rate": 1.44897798059161e-05,
|
1114 |
+
"loss": 1.6878,
|
1115 |
+
"step": 15800
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.6288561936402468,
|
1119 |
+
"grad_norm": 1.690470576286316,
|
1120 |
+
"learning_rate": 1.4482942246412203e-05,
|
1121 |
+
"loss": 1.6807,
|
1122 |
+
"step": 15900
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.6328112640404999,
|
1126 |
+
"grad_norm": 1.8261181116104126,
|
1127 |
+
"learning_rate": 1.4476060810821319e-05,
|
1128 |
+
"loss": 1.6887,
|
1129 |
+
"step": 16000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.636766334440753,
|
1133 |
+
"grad_norm": 1.5878318548202515,
|
1134 |
+
"learning_rate": 1.4469135542381741e-05,
|
1135 |
+
"loss": 1.6618,
|
1136 |
+
"step": 16100
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.6407214048410061,
|
1140 |
+
"grad_norm": 1.5003888607025146,
|
1141 |
+
"learning_rate": 1.4462166484607167e-05,
|
1142 |
+
"loss": 1.6734,
|
1143 |
+
"step": 16200
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.6446764752412593,
|
1147 |
+
"grad_norm": 1.7296781539916992,
|
1148 |
+
"learning_rate": 1.445515368128645e-05,
|
1149 |
+
"loss": 1.6712,
|
1150 |
+
"step": 16300
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.6486315456415124,
|
1154 |
+
"grad_norm": 1.6283060312271118,
|
1155 |
+
"learning_rate": 1.4448097176483299e-05,
|
1156 |
+
"loss": 1.6963,
|
1157 |
+
"step": 16400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.6525866160417655,
|
1161 |
+
"grad_norm": 1.5867258310317993,
|
1162 |
+
"learning_rate": 1.444099701453602e-05,
|
1163 |
+
"loss": 1.6834,
|
1164 |
+
"step": 16500
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6565416864420187,
|
1168 |
+
"grad_norm": 1.8763879537582397,
|
1169 |
+
"learning_rate": 1.4433853240057229e-05,
|
1170 |
+
"loss": 1.6811,
|
1171 |
+
"step": 16600
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.6604967568422718,
|
1175 |
+
"grad_norm": 1.5323275327682495,
|
1176 |
+
"learning_rate": 1.4426665897933574e-05,
|
1177 |
+
"loss": 1.6778,
|
1178 |
+
"step": 16700
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.6644518272425249,
|
1182 |
+
"grad_norm": 1.581667184829712,
|
1183 |
+
"learning_rate": 1.4419435033325455e-05,
|
1184 |
+
"loss": 1.6926,
|
1185 |
+
"step": 16800
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.668406897642778,
|
1189 |
+
"grad_norm": 1.6673179864883423,
|
1190 |
+
"learning_rate": 1.441216069166673e-05,
|
1191 |
+
"loss": 1.6806,
|
1192 |
+
"step": 16900
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.6723619680430312,
|
1196 |
+
"grad_norm": 1.8026336431503296,
|
1197 |
+
"learning_rate": 1.4404842918664446e-05,
|
1198 |
+
"loss": 1.6829,
|
1199 |
+
"step": 17000
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.6763170384432843,
|
1203 |
+
"grad_norm": 1.6094428300857544,
|
1204 |
+
"learning_rate": 1.4397481760298542e-05,
|
1205 |
+
"loss": 1.6763,
|
1206 |
+
"step": 17100
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.6802721088435374,
|
1210 |
+
"grad_norm": 1.565843105316162,
|
1211 |
+
"learning_rate": 1.4390077262821559e-05,
|
1212 |
+
"loss": 1.659,
|
1213 |
+
"step": 17200
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.6842271792437905,
|
1217 |
+
"grad_norm": 1.7567963600158691,
|
1218 |
+
"learning_rate": 1.4382629472758346e-05,
|
1219 |
+
"loss": 1.666,
|
1220 |
+
"step": 17300
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.6881822496440436,
|
1224 |
+
"grad_norm": 1.591693639755249,
|
1225 |
+
"learning_rate": 1.4375138436905786e-05,
|
1226 |
+
"loss": 1.6666,
|
1227 |
+
"step": 17400
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.6921373200442967,
|
1231 |
+
"grad_norm": 1.638576865196228,
|
1232 |
+
"learning_rate": 1.436760420233248e-05,
|
1233 |
+
"loss": 1.6554,
|
1234 |
+
"step": 17500
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.69609239044455,
|
1238 |
+
"grad_norm": 1.7055751085281372,
|
1239 |
+
"learning_rate": 1.4360026816378462e-05,
|
1240 |
+
"loss": 1.671,
|
1241 |
+
"step": 17600
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.7000474608448031,
|
1245 |
+
"grad_norm": 1.6867974996566772,
|
1246 |
+
"learning_rate": 1.4352406326654905e-05,
|
1247 |
+
"loss": 1.6722,
|
1248 |
+
"step": 17700
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.7040025312450562,
|
1252 |
+
"grad_norm": 1.7862675189971924,
|
1253 |
+
"learning_rate": 1.4344742781043809e-05,
|
1254 |
+
"loss": 1.6965,
|
1255 |
+
"step": 17800
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.7079576016453093,
|
1259 |
+
"grad_norm": 1.7989298105239868,
|
1260 |
+
"learning_rate": 1.4337036227697715e-05,
|
1261 |
+
"loss": 1.6762,
|
1262 |
+
"step": 17900
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.7119126720455624,
|
1266 |
+
"grad_norm": 1.7017799615859985,
|
1267 |
+
"learning_rate": 1.4329286715039392e-05,
|
1268 |
+
"loss": 1.6614,
|
1269 |
+
"step": 18000
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.7158677424458155,
|
1273 |
+
"grad_norm": 1.6665624380111694,
|
1274 |
+
"learning_rate": 1.4321494291761537e-05,
|
1275 |
+
"loss": 1.662,
|
1276 |
+
"step": 18100
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.7198228128460686,
|
1280 |
+
"grad_norm": 1.9826371669769287,
|
1281 |
+
"learning_rate": 1.4313659006826468e-05,
|
1282 |
+
"loss": 1.6638,
|
1283 |
+
"step": 18200
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.7237778832463218,
|
1287 |
+
"grad_norm": 1.7711797952651978,
|
1288 |
+
"learning_rate": 1.430578090946582e-05,
|
1289 |
+
"loss": 1.6625,
|
1290 |
+
"step": 18300
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.7277329536465749,
|
1294 |
+
"grad_norm": 1.8430758714675903,
|
1295 |
+
"learning_rate": 1.4297860049180223e-05,
|
1296 |
+
"loss": 1.6824,
|
1297 |
+
"step": 18400
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.731688024046828,
|
1301 |
+
"grad_norm": 1.8522826433181763,
|
1302 |
+
"learning_rate": 1.4289896475739012e-05,
|
1303 |
+
"loss": 1.6599,
|
1304 |
+
"step": 18500
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.7356430944470812,
|
1308 |
+
"grad_norm": 1.6422381401062012,
|
1309 |
+
"learning_rate": 1.4281890239179897e-05,
|
1310 |
+
"loss": 1.6584,
|
1311 |
+
"step": 18600
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.7395981648473343,
|
1315 |
+
"grad_norm": 1.7232320308685303,
|
1316 |
+
"learning_rate": 1.4273841389808653e-05,
|
1317 |
+
"loss": 1.6604,
|
1318 |
+
"step": 18700
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.7435532352475874,
|
1322 |
+
"grad_norm": 1.6723573207855225,
|
1323 |
+
"learning_rate": 1.4265749978198805e-05,
|
1324 |
+
"loss": 1.6654,
|
1325 |
+
"step": 18800
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.7475083056478405,
|
1329 |
+
"grad_norm": 1.776376485824585,
|
1330 |
+
"learning_rate": 1.4257616055191316e-05,
|
1331 |
+
"loss": 1.672,
|
1332 |
+
"step": 18900
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.7514633760480937,
|
1336 |
+
"grad_norm": 1.9001519680023193,
|
1337 |
+
"learning_rate": 1.4249439671894253e-05,
|
1338 |
+
"loss": 1.6473,
|
1339 |
+
"step": 19000
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.7554184464483468,
|
1343 |
+
"grad_norm": 1.5602456331253052,
|
1344 |
+
"learning_rate": 1.4241220879682484e-05,
|
1345 |
+
"loss": 1.6558,
|
1346 |
+
"step": 19100
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.7593735168485999,
|
1350 |
+
"grad_norm": 1.6195124387741089,
|
1351 |
+
"learning_rate": 1.423295973019734e-05,
|
1352 |
+
"loss": 1.6704,
|
1353 |
+
"step": 19200
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.763328587248853,
|
1357 |
+
"grad_norm": 1.7354437112808228,
|
1358 |
+
"learning_rate": 1.4224656275346295e-05,
|
1359 |
+
"loss": 1.6697,
|
1360 |
+
"step": 19300
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.7672836576491061,
|
1364 |
+
"grad_norm": 1.6655138731002808,
|
1365 |
+
"learning_rate": 1.4216310567302648e-05,
|
1366 |
+
"loss": 1.6567,
|
1367 |
+
"step": 19400
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.7712387280493592,
|
1371 |
+
"grad_norm": 1.9168803691864014,
|
1372 |
+
"learning_rate": 1.4207922658505184e-05,
|
1373 |
+
"loss": 1.6398,
|
1374 |
+
"step": 19500
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7751937984496124,
|
1378 |
+
"grad_norm": 1.7918130159378052,
|
1379 |
+
"learning_rate": 1.4199492601657848e-05,
|
1380 |
+
"loss": 1.654,
|
1381 |
+
"step": 19600
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.7791488688498656,
|
1385 |
+
"grad_norm": 1.7283716201782227,
|
1386 |
+
"learning_rate": 1.4191020449729417e-05,
|
1387 |
+
"loss": 1.6534,
|
1388 |
+
"step": 19700
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.7831039392501187,
|
1392 |
+
"grad_norm": 1.860144019126892,
|
1393 |
+
"learning_rate": 1.4182506255953167e-05,
|
1394 |
+
"loss": 1.6553,
|
1395 |
+
"step": 19800
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.7870590096503718,
|
1399 |
+
"grad_norm": 1.7320619821548462,
|
1400 |
+
"learning_rate": 1.4173950073826531e-05,
|
1401 |
+
"loss": 1.6586,
|
1402 |
+
"step": 19900
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.7910140800506249,
|
1406 |
+
"grad_norm": 1.7704521417617798,
|
1407 |
+
"learning_rate": 1.4165351957110772e-05,
|
1408 |
+
"loss": 1.6599,
|
1409 |
+
"step": 20000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.794969150450878,
|
1413 |
+
"grad_norm": 2.051400661468506,
|
1414 |
+
"learning_rate": 1.4156711959830644e-05,
|
1415 |
+
"loss": 1.6695,
|
1416 |
+
"step": 20100
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.7989242208511311,
|
1420 |
+
"grad_norm": 1.7863457202911377,
|
1421 |
+
"learning_rate": 1.4148030136274043e-05,
|
1422 |
+
"loss": 1.6538,
|
1423 |
+
"step": 20200
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.8028792912513842,
|
1427 |
+
"grad_norm": 1.85243558883667,
|
1428 |
+
"learning_rate": 1.413930654099168e-05,
|
1429 |
+
"loss": 1.63,
|
1430 |
+
"step": 20300
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.8068343616516374,
|
1434 |
+
"grad_norm": 1.7953428030014038,
|
1435 |
+
"learning_rate": 1.413054122879673e-05,
|
1436 |
+
"loss": 1.6374,
|
1437 |
+
"step": 20400
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.8107894320518905,
|
1441 |
+
"grad_norm": 1.8957959413528442,
|
1442 |
+
"learning_rate": 1.4121734254764482e-05,
|
1443 |
+
"loss": 1.6445,
|
1444 |
+
"step": 20500
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.8147445024521437,
|
1448 |
+
"grad_norm": 1.7762993574142456,
|
1449 |
+
"learning_rate": 1.4112885674232011e-05,
|
1450 |
+
"loss": 1.6503,
|
1451 |
+
"step": 20600
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.8186995728523968,
|
1455 |
+
"grad_norm": 1.723813772201538,
|
1456 |
+
"learning_rate": 1.410399554279781e-05,
|
1457 |
+
"loss": 1.6416,
|
1458 |
+
"step": 20700
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.8226546432526499,
|
1462 |
+
"grad_norm": 1.9667476415634155,
|
1463 |
+
"learning_rate": 1.4095063916321456e-05,
|
1464 |
+
"loss": 1.6297,
|
1465 |
+
"step": 20800
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.826609713652903,
|
1469 |
+
"grad_norm": 1.8855000734329224,
|
1470 |
+
"learning_rate": 1.4086090850923246e-05,
|
1471 |
+
"loss": 1.6684,
|
1472 |
+
"step": 20900
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.8305647840531561,
|
1476 |
+
"grad_norm": 1.8669531345367432,
|
1477 |
+
"learning_rate": 1.4077076402983857e-05,
|
1478 |
+
"loss": 1.6344,
|
1479 |
+
"step": 21000
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.8345198544534093,
|
1483 |
+
"grad_norm": 2.0968127250671387,
|
1484 |
+
"learning_rate": 1.4068020629143985e-05,
|
1485 |
+
"loss": 1.6524,
|
1486 |
+
"step": 21100
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.8384749248536624,
|
1490 |
+
"grad_norm": 1.712428092956543,
|
1491 |
+
"learning_rate": 1.4058923586303988e-05,
|
1492 |
+
"loss": 1.6333,
|
1493 |
+
"step": 21200
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.8424299952539155,
|
1497 |
+
"grad_norm": 1.7560315132141113,
|
1498 |
+
"learning_rate": 1.4049785331623534e-05,
|
1499 |
+
"loss": 1.6337,
|
1500 |
+
"step": 21300
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.8463850656541686,
|
1504 |
+
"grad_norm": 1.875779390335083,
|
1505 |
+
"learning_rate": 1.4040605922521231e-05,
|
1506 |
+
"loss": 1.6328,
|
1507 |
+
"step": 21400
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.8503401360544217,
|
1511 |
+
"grad_norm": 1.9142519235610962,
|
1512 |
+
"learning_rate": 1.403138541667428e-05,
|
1513 |
+
"loss": 1.6333,
|
1514 |
+
"step": 21500
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.8542952064546749,
|
1518 |
+
"grad_norm": 2.263770580291748,
|
1519 |
+
"learning_rate": 1.4022123872018107e-05,
|
1520 |
+
"loss": 1.635,
|
1521 |
+
"step": 21600
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.858250276854928,
|
1525 |
+
"grad_norm": 1.838889479637146,
|
1526 |
+
"learning_rate": 1.4012821346745995e-05,
|
1527 |
+
"loss": 1.6328,
|
1528 |
+
"step": 21700
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.8622053472551812,
|
1532 |
+
"grad_norm": 1.9877907037734985,
|
1533 |
+
"learning_rate": 1.400347789930872e-05,
|
1534 |
+
"loss": 1.6427,
|
1535 |
+
"step": 21800
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.8661604176554343,
|
1539 |
+
"grad_norm": 1.9885168075561523,
|
1540 |
+
"learning_rate": 1.399409358841419e-05,
|
1541 |
+
"loss": 1.637,
|
1542 |
+
"step": 21900
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.8701154880556874,
|
1546 |
+
"grad_norm": 1.8428804874420166,
|
1547 |
+
"learning_rate": 1.3984668473027065e-05,
|
1548 |
+
"loss": 1.6377,
|
1549 |
+
"step": 22000
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.8740705584559405,
|
1553 |
+
"grad_norm": 1.9875133037567139,
|
1554 |
+
"learning_rate": 1.39752026123684e-05,
|
1555 |
+
"loss": 1.6248,
|
1556 |
+
"step": 22100
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.8780256288561936,
|
1560 |
+
"grad_norm": 2.0525448322296143,
|
1561 |
+
"learning_rate": 1.3965696065915262e-05,
|
1562 |
+
"loss": 1.6501,
|
1563 |
+
"step": 22200
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.8819806992564467,
|
1567 |
+
"grad_norm": 1.9695172309875488,
|
1568 |
+
"learning_rate": 1.3956148893400357e-05,
|
1569 |
+
"loss": 1.6308,
|
1570 |
+
"step": 22300
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.8859357696566998,
|
1574 |
+
"grad_norm": 2.084592580795288,
|
1575 |
+
"learning_rate": 1.3946561154811664e-05,
|
1576 |
+
"loss": 1.6335,
|
1577 |
+
"step": 22400
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.889890840056953,
|
1581 |
+
"grad_norm": 1.7602378129959106,
|
1582 |
+
"learning_rate": 1.3936932910392048e-05,
|
1583 |
+
"loss": 1.6195,
|
1584 |
+
"step": 22500
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8938459104572062,
|
1588 |
+
"grad_norm": 2.0157277584075928,
|
1589 |
+
"learning_rate": 1.3927264220638889e-05,
|
1590 |
+
"loss": 1.6395,
|
1591 |
+
"step": 22600
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.8978009808574593,
|
1595 |
+
"grad_norm": 2.184307336807251,
|
1596 |
+
"learning_rate": 1.391755514630369e-05,
|
1597 |
+
"loss": 1.6448,
|
1598 |
+
"step": 22700
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.9017560512577124,
|
1602 |
+
"grad_norm": 1.9747377634048462,
|
1603 |
+
"learning_rate": 1.390780574839171e-05,
|
1604 |
+
"loss": 1.6302,
|
1605 |
+
"step": 22800
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.9057111216579655,
|
1609 |
+
"grad_norm": 2.1203644275665283,
|
1610 |
+
"learning_rate": 1.3898016088161575e-05,
|
1611 |
+
"loss": 1.6447,
|
1612 |
+
"step": 22900
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.9096661920582186,
|
1616 |
+
"grad_norm": 2.0279908180236816,
|
1617 |
+
"learning_rate": 1.3888186227124885e-05,
|
1618 |
+
"loss": 1.622,
|
1619 |
+
"step": 23000
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.9136212624584718,
|
1623 |
+
"grad_norm": 1.9809517860412598,
|
1624 |
+
"learning_rate": 1.3878316227045846e-05,
|
1625 |
+
"loss": 1.6189,
|
1626 |
+
"step": 23100
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.9175763328587249,
|
1630 |
+
"grad_norm": 2.1499814987182617,
|
1631 |
+
"learning_rate": 1.386840614994086e-05,
|
1632 |
+
"loss": 1.6192,
|
1633 |
+
"step": 23200
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.921531403258978,
|
1637 |
+
"grad_norm": 1.9230985641479492,
|
1638 |
+
"learning_rate": 1.3858456058078148e-05,
|
1639 |
+
"loss": 1.6251,
|
1640 |
+
"step": 23300
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.9254864736592311,
|
1644 |
+
"grad_norm": 2.1623005867004395,
|
1645 |
+
"learning_rate": 1.3848466013977365e-05,
|
1646 |
+
"loss": 1.6145,
|
1647 |
+
"step": 23400
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.9294415440594842,
|
1651 |
+
"grad_norm": 2.0579729080200195,
|
1652 |
+
"learning_rate": 1.3838436080409188e-05,
|
1653 |
+
"loss": 1.628,
|
1654 |
+
"step": 23500
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.9333966144597374,
|
1658 |
+
"grad_norm": 1.9566960334777832,
|
1659 |
+
"learning_rate": 1.3828366320394937e-05,
|
1660 |
+
"loss": 1.6317,
|
1661 |
+
"step": 23600
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.9373516848599905,
|
1665 |
+
"grad_norm": 1.9498804807662964,
|
1666 |
+
"learning_rate": 1.3818256797206177e-05,
|
1667 |
+
"loss": 1.6107,
|
1668 |
+
"step": 23700
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.9413067552602437,
|
1672 |
+
"grad_norm": 1.8530848026275635,
|
1673 |
+
"learning_rate": 1.3808107574364312e-05,
|
1674 |
+
"loss": 1.6186,
|
1675 |
+
"step": 23800
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.9452618256604968,
|
1679 |
+
"grad_norm": 2.0309464931488037,
|
1680 |
+
"learning_rate": 1.3797918715640197e-05,
|
1681 |
+
"loss": 1.6208,
|
1682 |
+
"step": 23900
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.9492168960607499,
|
1686 |
+
"grad_norm": 2.0447559356689453,
|
1687 |
+
"learning_rate": 1.3787690285053732e-05,
|
1688 |
+
"loss": 1.6226,
|
1689 |
+
"step": 24000
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.953171966461003,
|
1693 |
+
"grad_norm": 2.198214292526245,
|
1694 |
+
"learning_rate": 1.3777422346873453e-05,
|
1695 |
+
"loss": 1.5954,
|
1696 |
+
"step": 24100
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.9571270368612561,
|
1700 |
+
"grad_norm": 2.0797901153564453,
|
1701 |
+
"learning_rate": 1.3767114965616143e-05,
|
1702 |
+
"loss": 1.6378,
|
1703 |
+
"step": 24200
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.9610821072615092,
|
1707 |
+
"grad_norm": 2.361177444458008,
|
1708 |
+
"learning_rate": 1.3756768206046418e-05,
|
1709 |
+
"loss": 1.6207,
|
1710 |
+
"step": 24300
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.9650371776617623,
|
1714 |
+
"grad_norm": 2.194758653640747,
|
1715 |
+
"learning_rate": 1.3746382133176314e-05,
|
1716 |
+
"loss": 1.6147,
|
1717 |
+
"step": 24400
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.9689922480620154,
|
1721 |
+
"grad_norm": 2.1259610652923584,
|
1722 |
+
"learning_rate": 1.3735956812264893e-05,
|
1723 |
+
"loss": 1.583,
|
1724 |
+
"step": 24500
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.9729473184622687,
|
1728 |
+
"grad_norm": 2.084428548812866,
|
1729 |
+
"learning_rate": 1.372549230881782e-05,
|
1730 |
+
"loss": 1.6257,
|
1731 |
+
"step": 24600
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.9769023888625218,
|
1735 |
+
"grad_norm": 2.0704309940338135,
|
1736 |
+
"learning_rate": 1.3714988688586958e-05,
|
1737 |
+
"loss": 1.6062,
|
1738 |
+
"step": 24700
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.9808574592627749,
|
1742 |
+
"grad_norm": 1.9661308526992798,
|
1743 |
+
"learning_rate": 1.3704446017569953e-05,
|
1744 |
+
"loss": 1.6164,
|
1745 |
+
"step": 24800
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.984812529663028,
|
1749 |
+
"grad_norm": 2.1788337230682373,
|
1750 |
+
"learning_rate": 1.3693864362009821e-05,
|
1751 |
+
"loss": 1.6188,
|
1752 |
+
"step": 24900
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.9887676000632811,
|
1756 |
+
"grad_norm": 1.9492045640945435,
|
1757 |
+
"learning_rate": 1.3683243788394534e-05,
|
1758 |
+
"loss": 1.609,
|
1759 |
+
"step": 25000
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.9927226704635342,
|
1763 |
+
"grad_norm": 2.2324581146240234,
|
1764 |
+
"learning_rate": 1.3672584363456587e-05,
|
1765 |
+
"loss": 1.6058,
|
1766 |
+
"step": 25100
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.9966777408637874,
|
1770 |
+
"grad_norm": 2.14666485786438,
|
1771 |
+
"learning_rate": 1.3661886154172602e-05,
|
1772 |
+
"loss": 1.6059,
|
1773 |
+
"step": 25200
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.0006328112640406,
|
1777 |
+
"grad_norm": 2.1909172534942627,
|
1778 |
+
"learning_rate": 1.3651149227762893e-05,
|
1779 |
+
"loss": 1.6006,
|
1780 |
+
"step": 25300
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 1.0025726272461015,
|
1784 |
+
"grad_norm": 2.143050193786621,
|
1785 |
+
"learning_rate": 1.3640373651691044e-05,
|
1786 |
+
"loss": 1.5379,
|
1787 |
+
"step": 25400
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 1.0065305153170268,
|
1791 |
+
"grad_norm": 2.6964924335479736,
|
1792 |
+
"learning_rate": 1.3629559493663487e-05,
|
1793 |
+
"loss": 1.507,
|
1794 |
+
"step": 25500
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.0104884033879522,
|
1798 |
+
"grad_norm": 2.556349992752075,
|
1799 |
+
"learning_rate": 1.361870682162908e-05,
|
1800 |
+
"loss": 1.5266,
|
1801 |
+
"step": 25600
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 1.0144462914588774,
|
1805 |
+
"grad_norm": 2.2218785285949707,
|
1806 |
+
"learning_rate": 1.3607815703778673e-05,
|
1807 |
+
"loss": 1.4867,
|
1808 |
+
"step": 25700
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 1.0184041795298029,
|
1812 |
+
"grad_norm": 2.5236029624938965,
|
1813 |
+
"learning_rate": 1.3596886208544687e-05,
|
1814 |
+
"loss": 1.4879,
|
1815 |
+
"step": 25800
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.0223620676007283,
|
1819 |
+
"grad_norm": 2.5998125076293945,
|
1820 |
+
"learning_rate": 1.3585918404600679e-05,
|
1821 |
+
"loss": 1.524,
|
1822 |
+
"step": 25900
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 1.0263199556716536,
|
1826 |
+
"grad_norm": 2.6749346256256104,
|
1827 |
+
"learning_rate": 1.3574912360860912e-05,
|
1828 |
+
"loss": 1.5148,
|
1829 |
+
"step": 26000
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 1.030277843742579,
|
1833 |
+
"grad_norm": 2.4651994705200195,
|
1834 |
+
"learning_rate": 1.3563868146479921e-05,
|
1835 |
+
"loss": 1.4905,
|
1836 |
+
"step": 26100
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.0342357318135043,
|
1840 |
+
"grad_norm": 2.4166133403778076,
|
1841 |
+
"learning_rate": 1.3552785830852084e-05,
|
1842 |
+
"loss": 1.5155,
|
1843 |
+
"step": 26200
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 1.0381936198844297,
|
1847 |
+
"grad_norm": 2.2493224143981934,
|
1848 |
+
"learning_rate": 1.3541665483611175e-05,
|
1849 |
+
"loss": 1.515,
|
1850 |
+
"step": 26300
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.042151507955355,
|
1854 |
+
"grad_norm": 2.7555856704711914,
|
1855 |
+
"learning_rate": 1.3530507174629938e-05,
|
1856 |
+
"loss": 1.5136,
|
1857 |
+
"step": 26400
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 1.0461093960262804,
|
1861 |
+
"grad_norm": 2.7666208744049072,
|
1862 |
+
"learning_rate": 1.3519310974019639e-05,
|
1863 |
+
"loss": 1.4917,
|
1864 |
+
"step": 26500
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 1.0500672840972056,
|
1868 |
+
"grad_norm": 2.7659711837768555,
|
1869 |
+
"learning_rate": 1.3508076952129634e-05,
|
1870 |
+
"loss": 1.5076,
|
1871 |
+
"step": 26600
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 1.054025172168131,
|
1875 |
+
"grad_norm": 2.5507092475891113,
|
1876 |
+
"learning_rate": 1.3496805179546919e-05,
|
1877 |
+
"loss": 1.5052,
|
1878 |
+
"step": 26700
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 1.0579830602390565,
|
1882 |
+
"grad_norm": 2.302542209625244,
|
1883 |
+
"learning_rate": 1.3485495727095687e-05,
|
1884 |
+
"loss": 1.5034,
|
1885 |
+
"step": 26800
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 1.0619409483099818,
|
1889 |
+
"grad_norm": 2.578275203704834,
|
1890 |
+
"learning_rate": 1.3474148665836894e-05,
|
1891 |
+
"loss": 1.4886,
|
1892 |
+
"step": 26900
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 1.0658988363809072,
|
1896 |
+
"grad_norm": 2.354796886444092,
|
1897 |
+
"learning_rate": 1.3462764067067799e-05,
|
1898 |
+
"loss": 1.506,
|
1899 |
+
"step": 27000
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.0698567244518324,
|
1903 |
+
"grad_norm": 2.5606160163879395,
|
1904 |
+
"learning_rate": 1.345134200232152e-05,
|
1905 |
+
"loss": 1.4931,
|
1906 |
+
"step": 27100
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.073814612522758,
|
1910 |
+
"grad_norm": 2.46881365776062,
|
1911 |
+
"learning_rate": 1.343988254336659e-05,
|
1912 |
+
"loss": 1.503,
|
1913 |
+
"step": 27200
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 1.0777725005936831,
|
1917 |
+
"grad_norm": 2.657731771469116,
|
1918 |
+
"learning_rate": 1.3428385762206498e-05,
|
1919 |
+
"loss": 1.5064,
|
1920 |
+
"step": 27300
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 1.0817303886646086,
|
1924 |
+
"grad_norm": 2.3708932399749756,
|
1925 |
+
"learning_rate": 1.3416851731079244e-05,
|
1926 |
+
"loss": 1.4943,
|
1927 |
+
"step": 27400
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 1.0856882767355338,
|
1931 |
+
"grad_norm": 2.6182353496551514,
|
1932 |
+
"learning_rate": 1.340528052245688e-05,
|
1933 |
+
"loss": 1.5001,
|
1934 |
+
"step": 27500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 1.0896461648064593,
|
1938 |
+
"grad_norm": 2.7265477180480957,
|
1939 |
+
"learning_rate": 1.3393672209045055e-05,
|
1940 |
+
"loss": 1.4794,
|
1941 |
+
"step": 27600
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 1.0936040528773847,
|
1945 |
+
"grad_norm": 2.6186697483062744,
|
1946 |
+
"learning_rate": 1.3382026863782559e-05,
|
1947 |
+
"loss": 1.4878,
|
1948 |
+
"step": 27700
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.09756194094831,
|
1952 |
+
"grad_norm": 3.3754959106445312,
|
1953 |
+
"learning_rate": 1.3370344559840868e-05,
|
1954 |
+
"loss": 1.4769,
|
1955 |
+
"step": 27800
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 1.1015198290192354,
|
1959 |
+
"grad_norm": 3.0805869102478027,
|
1960 |
+
"learning_rate": 1.3358625370623684e-05,
|
1961 |
+
"loss": 1.5098,
|
1962 |
+
"step": 27900
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 1.1054777170901606,
|
1966 |
+
"grad_norm": 2.626561403274536,
|
1967 |
+
"learning_rate": 1.334686936976646e-05,
|
1968 |
+
"loss": 1.4965,
|
1969 |
+
"step": 28000
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 1.109435605161086,
|
1973 |
+
"grad_norm": 2.6148223876953125,
|
1974 |
+
"learning_rate": 1.333507663113596e-05,
|
1975 |
+
"loss": 1.4973,
|
1976 |
+
"step": 28100
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 1.1133934932320113,
|
1980 |
+
"grad_norm": 2.9437952041625977,
|
1981 |
+
"learning_rate": 1.3323247228829781e-05,
|
1982 |
+
"loss": 1.4861,
|
1983 |
+
"step": 28200
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 1.1173513813029368,
|
1987 |
+
"grad_norm": 2.7327873706817627,
|
1988 |
+
"learning_rate": 1.3311381237175882e-05,
|
1989 |
+
"loss": 1.4725,
|
1990 |
+
"step": 28300
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 1.121309269373862,
|
1994 |
+
"grad_norm": 2.8548924922943115,
|
1995 |
+
"learning_rate": 1.3299478730732134e-05,
|
1996 |
+
"loss": 1.4825,
|
1997 |
+
"step": 28400
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 1.1252671574447874,
|
2001 |
+
"grad_norm": 2.638568878173828,
|
2002 |
+
"learning_rate": 1.3287539784285839e-05,
|
2003 |
+
"loss": 1.4715,
|
2004 |
+
"step": 28500
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 1.129225045515713,
|
2008 |
+
"grad_norm": 3.1752021312713623,
|
2009 |
+
"learning_rate": 1.327556447285326e-05,
|
2010 |
+
"loss": 1.4749,
|
2011 |
+
"step": 28600
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 1.1331829335866381,
|
2015 |
+
"grad_norm": 2.8398923873901367,
|
2016 |
+
"learning_rate": 1.3263552871679156e-05,
|
2017 |
+
"loss": 1.4901,
|
2018 |
+
"step": 28700
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 1.1371408216575636,
|
2022 |
+
"grad_norm": 2.708963632583618,
|
2023 |
+
"learning_rate": 1.3251505056236312e-05,
|
2024 |
+
"loss": 1.4805,
|
2025 |
+
"step": 28800
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 1.1410987097284888,
|
2029 |
+
"grad_norm": 2.9168691635131836,
|
2030 |
+
"learning_rate": 1.3239421102225049e-05,
|
2031 |
+
"loss": 1.4653,
|
2032 |
+
"step": 28900
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 1.1450565977994143,
|
2036 |
+
"grad_norm": 2.523481845855713,
|
2037 |
+
"learning_rate": 1.322730108557276e-05,
|
2038 |
+
"loss": 1.4822,
|
2039 |
+
"step": 29000
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 1.1490144858703395,
|
2043 |
+
"grad_norm": 3.2788479328155518,
|
2044 |
+
"learning_rate": 1.3215145082433436e-05,
|
2045 |
+
"loss": 1.4685,
|
2046 |
+
"step": 29100
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 1.152972373941265,
|
2050 |
+
"grad_norm": 2.765491485595703,
|
2051 |
+
"learning_rate": 1.3202953169187181e-05,
|
2052 |
+
"loss": 1.4878,
|
2053 |
+
"step": 29200
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 1.1569302620121902,
|
2057 |
+
"grad_norm": 2.9480185508728027,
|
2058 |
+
"learning_rate": 1.3190725422439734e-05,
|
2059 |
+
"loss": 1.4607,
|
2060 |
+
"step": 29300
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 1.1608881500831156,
|
2064 |
+
"grad_norm": 2.9779725074768066,
|
2065 |
+
"learning_rate": 1.3178461919021984e-05,
|
2066 |
+
"loss": 1.4724,
|
2067 |
+
"step": 29400
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 1.164846038154041,
|
2071 |
+
"grad_norm": 2.768763780593872,
|
2072 |
+
"learning_rate": 1.3166162735989497e-05,
|
2073 |
+
"loss": 1.4989,
|
2074 |
+
"step": 29500
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 1.1688039262249663,
|
2078 |
+
"grad_norm": 3.2208807468414307,
|
2079 |
+
"learning_rate": 1.3153827950622019e-05,
|
2080 |
+
"loss": 1.4695,
|
2081 |
+
"step": 29600
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 1.1727618142958918,
|
2085 |
+
"grad_norm": 2.7532846927642822,
|
2086 |
+
"learning_rate": 1.3141457640423002e-05,
|
2087 |
+
"loss": 1.4841,
|
2088 |
+
"step": 29700
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 1.176719702366817,
|
2092 |
+
"grad_norm": 3.399897575378418,
|
2093 |
+
"learning_rate": 1.3129051883119107e-05,
|
2094 |
+
"loss": 1.4627,
|
2095 |
+
"step": 29800
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 1.1806775904377425,
|
2099 |
+
"grad_norm": 2.892542600631714,
|
2100 |
+
"learning_rate": 1.311661075665973e-05,
|
2101 |
+
"loss": 1.4754,
|
2102 |
+
"step": 29900
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 1.1846354785086677,
|
2106 |
+
"grad_norm": 2.6261606216430664,
|
2107 |
+
"learning_rate": 1.310413433921649e-05,
|
2108 |
+
"loss": 1.4847,
|
2109 |
+
"step": 30000
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 1.1885933665795931,
|
2113 |
+
"grad_norm": 2.6923210620880127,
|
2114 |
+
"learning_rate": 1.3091622709182762e-05,
|
2115 |
+
"loss": 1.4722,
|
2116 |
+
"step": 30100
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.1925512546505184,
|
2120 |
+
"grad_norm": 3.0266880989074707,
|
2121 |
+
"learning_rate": 1.3079075945173164e-05,
|
2122 |
+
"loss": 1.4922,
|
2123 |
+
"step": 30200
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 1.1965091427214438,
|
2127 |
+
"grad_norm": 2.9252758026123047,
|
2128 |
+
"learning_rate": 1.306649412602308e-05,
|
2129 |
+
"loss": 1.4692,
|
2130 |
+
"step": 30300
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 1.2004670307923693,
|
2134 |
+
"grad_norm": 2.757887125015259,
|
2135 |
+
"learning_rate": 1.305387733078815e-05,
|
2136 |
+
"loss": 1.465,
|
2137 |
+
"step": 30400
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 1.2044249188632945,
|
2141 |
+
"grad_norm": 3.536576271057129,
|
2142 |
+
"learning_rate": 1.304122563874379e-05,
|
2143 |
+
"loss": 1.4625,
|
2144 |
+
"step": 30500
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 1.20838280693422,
|
2148 |
+
"grad_norm": 2.765883684158325,
|
2149 |
+
"learning_rate": 1.3028539129384668e-05,
|
2150 |
+
"loss": 1.4509,
|
2151 |
+
"step": 30600
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 1.2123406950051452,
|
2155 |
+
"grad_norm": 2.8738183975219727,
|
2156 |
+
"learning_rate": 1.3015817882424235e-05,
|
2157 |
+
"loss": 1.4421,
|
2158 |
+
"step": 30700
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.2162985830760706,
|
2162 |
+
"grad_norm": 2.8780033588409424,
|
2163 |
+
"learning_rate": 1.3003061977794207e-05,
|
2164 |
+
"loss": 1.4749,
|
2165 |
+
"step": 30800
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 1.2202564711469959,
|
2169 |
+
"grad_norm": 3.499163866043091,
|
2170 |
+
"learning_rate": 1.2990271495644059e-05,
|
2171 |
+
"loss": 1.4564,
|
2172 |
+
"step": 30900
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 1.2242143592179213,
|
2176 |
+
"grad_norm": 2.900714159011841,
|
2177 |
+
"learning_rate": 1.297744651634053e-05,
|
2178 |
+
"loss": 1.4642,
|
2179 |
+
"step": 31000
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 1.2281722472888466,
|
2183 |
+
"grad_norm": 2.939680337905884,
|
2184 |
+
"learning_rate": 1.2964587120467122e-05,
|
2185 |
+
"loss": 1.4512,
|
2186 |
+
"step": 31100
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 1.232130135359772,
|
2190 |
+
"grad_norm": 3.2539045810699463,
|
2191 |
+
"learning_rate": 1.2951693388823577e-05,
|
2192 |
+
"loss": 1.4478,
|
2193 |
+
"step": 31200
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 1.2360880234306975,
|
2197 |
+
"grad_norm": 3.0612869262695312,
|
2198 |
+
"learning_rate": 1.293876540242539e-05,
|
2199 |
+
"loss": 1.4674,
|
2200 |
+
"step": 31300
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 1.2400459115016227,
|
2204 |
+
"grad_norm": 2.9142935276031494,
|
2205 |
+
"learning_rate": 1.2925803242503287e-05,
|
2206 |
+
"loss": 1.4704,
|
2207 |
+
"step": 31400
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 1.2440037995725481,
|
2211 |
+
"grad_norm": 3.0163750648498535,
|
2212 |
+
"learning_rate": 1.291280699050271e-05,
|
2213 |
+
"loss": 1.4433,
|
2214 |
+
"step": 31500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.2479616876434734,
|
2218 |
+
"grad_norm": 2.712174654006958,
|
2219 |
+
"learning_rate": 1.289977672808332e-05,
|
2220 |
+
"loss": 1.4637,
|
2221 |
+
"step": 31600
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 1.2519195757143988,
|
2225 |
+
"grad_norm": 2.7295100688934326,
|
2226 |
+
"learning_rate": 1.2886712537118475e-05,
|
2227 |
+
"loss": 1.4599,
|
2228 |
+
"step": 31700
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 1.2558774637853243,
|
2232 |
+
"grad_norm": 3.3285765647888184,
|
2233 |
+
"learning_rate": 1.2873614499694717e-05,
|
2234 |
+
"loss": 1.4432,
|
2235 |
+
"step": 31800
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 1.2598353518562495,
|
2239 |
+
"grad_norm": 3.4205710887908936,
|
2240 |
+
"learning_rate": 1.2860482698111254e-05,
|
2241 |
+
"loss": 1.4571,
|
2242 |
+
"step": 31900
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 1.2637932399271747,
|
2246 |
+
"grad_norm": 2.865621328353882,
|
2247 |
+
"learning_rate": 1.2847317214879451e-05,
|
2248 |
+
"loss": 1.4434,
|
2249 |
+
"step": 32000
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 1.2677511279981002,
|
2253 |
+
"grad_norm": 2.7961373329162598,
|
2254 |
+
"learning_rate": 1.2834118132722296e-05,
|
2255 |
+
"loss": 1.4305,
|
2256 |
+
"step": 32100
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 1.2717090160690256,
|
2260 |
+
"grad_norm": 2.86441707611084,
|
2261 |
+
"learning_rate": 1.2820885534573903e-05,
|
2262 |
+
"loss": 1.4592,
|
2263 |
+
"step": 32200
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 1.2756669041399509,
|
2267 |
+
"grad_norm": 3.3199241161346436,
|
2268 |
+
"learning_rate": 1.2807619503578964e-05,
|
2269 |
+
"loss": 1.451,
|
2270 |
+
"step": 32300
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 1.2796247922108763,
|
2274 |
+
"grad_norm": 2.9922525882720947,
|
2275 |
+
"learning_rate": 1.2794320123092248e-05,
|
2276 |
+
"loss": 1.4447,
|
2277 |
+
"step": 32400
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 1.2835826802818016,
|
2281 |
+
"grad_norm": 2.9650540351867676,
|
2282 |
+
"learning_rate": 1.2780987476678072e-05,
|
2283 |
+
"loss": 1.4492,
|
2284 |
+
"step": 32500
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 1.287540568352727,
|
2288 |
+
"grad_norm": 3.2158126831054688,
|
2289 |
+
"learning_rate": 1.2767621648109765e-05,
|
2290 |
+
"loss": 1.428,
|
2291 |
+
"step": 32600
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 1.2914984564236525,
|
2295 |
+
"grad_norm": 3.462463617324829,
|
2296 |
+
"learning_rate": 1.275422272136916e-05,
|
2297 |
+
"loss": 1.4355,
|
2298 |
+
"step": 32700
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 1.2954563444945777,
|
2302 |
+
"grad_norm": 2.9805209636688232,
|
2303 |
+
"learning_rate": 1.2740790780646048e-05,
|
2304 |
+
"loss": 1.4153,
|
2305 |
+
"step": 32800
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 1.299414232565503,
|
2309 |
+
"grad_norm": 3.3206562995910645,
|
2310 |
+
"learning_rate": 1.2727325910337665e-05,
|
2311 |
+
"loss": 1.425,
|
2312 |
+
"step": 32900
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 1.3033721206364284,
|
2316 |
+
"grad_norm": 3.306009531021118,
|
2317 |
+
"learning_rate": 1.2713828195048149e-05,
|
2318 |
+
"loss": 1.4398,
|
2319 |
+
"step": 33000
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 1.3073300087073538,
|
2323 |
+
"grad_norm": 3.6652069091796875,
|
2324 |
+
"learning_rate": 1.2700297719588015e-05,
|
2325 |
+
"loss": 1.4126,
|
2326 |
+
"step": 33100
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 1.311287896778279,
|
2330 |
+
"grad_norm": 3.067331314086914,
|
2331 |
+
"learning_rate": 1.268673456897362e-05,
|
2332 |
+
"loss": 1.4453,
|
2333 |
+
"step": 33200
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 1.3152457848492045,
|
2337 |
+
"grad_norm": 3.4072649478912354,
|
2338 |
+
"learning_rate": 1.2673138828426633e-05,
|
2339 |
+
"loss": 1.4195,
|
2340 |
+
"step": 33300
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 1.3192036729201297,
|
2344 |
+
"grad_norm": 3.721276044845581,
|
2345 |
+
"learning_rate": 1.2659510583373492e-05,
|
2346 |
+
"loss": 1.4308,
|
2347 |
+
"step": 33400
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 1.3231615609910552,
|
2351 |
+
"grad_norm": 3.381657361984253,
|
2352 |
+
"learning_rate": 1.2645849919444875e-05,
|
2353 |
+
"loss": 1.4102,
|
2354 |
+
"step": 33500
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 1.3271194490619806,
|
2358 |
+
"grad_norm": 3.2021045684814453,
|
2359 |
+
"learning_rate": 1.2632156922475153e-05,
|
2360 |
+
"loss": 1.4248,
|
2361 |
+
"step": 33600
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 1.3310773371329059,
|
2365 |
+
"grad_norm": 3.0373260974884033,
|
2366 |
+
"learning_rate": 1.2618431678501862e-05,
|
2367 |
+
"loss": 1.4156,
|
2368 |
+
"step": 33700
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 1.335035225203831,
|
2372 |
+
"grad_norm": 2.7702269554138184,
|
2373 |
+
"learning_rate": 1.2604674273765154e-05,
|
2374 |
+
"loss": 1.4511,
|
2375 |
+
"step": 33800
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 1.3389931132747566,
|
2379 |
+
"grad_norm": 3.3153131008148193,
|
2380 |
+
"learning_rate": 1.2590884794707254e-05,
|
2381 |
+
"loss": 1.4523,
|
2382 |
+
"step": 33900
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 1.342951001345682,
|
2386 |
+
"grad_norm": 3.249516248703003,
|
2387 |
+
"learning_rate": 1.2577063327971927e-05,
|
2388 |
+
"loss": 1.4225,
|
2389 |
+
"step": 34000
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 1.3469088894166072,
|
2393 |
+
"grad_norm": 3.879835367202759,
|
2394 |
+
"learning_rate": 1.2563209960403921e-05,
|
2395 |
+
"loss": 1.4248,
|
2396 |
+
"step": 34100
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 1.3508667774875327,
|
2400 |
+
"grad_norm": 3.548116445541382,
|
2401 |
+
"learning_rate": 1.2549324779048432e-05,
|
2402 |
+
"loss": 1.4248,
|
2403 |
+
"step": 34200
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 1.354824665558458,
|
2407 |
+
"grad_norm": 3.109065294265747,
|
2408 |
+
"learning_rate": 1.253540787115055e-05,
|
2409 |
+
"loss": 1.4269,
|
2410 |
+
"step": 34300
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 1.3587825536293834,
|
2414 |
+
"grad_norm": 3.3330225944519043,
|
2415 |
+
"learning_rate": 1.2521459324154708e-05,
|
2416 |
+
"loss": 1.4354,
|
2417 |
+
"step": 34400
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 1.3627404417003088,
|
2421 |
+
"grad_norm": 3.0380284786224365,
|
2422 |
+
"learning_rate": 1.2507479225704149e-05,
|
2423 |
+
"loss": 1.3966,
|
2424 |
+
"step": 34500
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 1.366698329771234,
|
2428 |
+
"grad_norm": 3.3855364322662354,
|
2429 |
+
"learning_rate": 1.2493467663640356e-05,
|
2430 |
+
"loss": 1.402,
|
2431 |
+
"step": 34600
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 1.3706562178421593,
|
2435 |
+
"grad_norm": 3.3429582118988037,
|
2436 |
+
"learning_rate": 1.247942472600251e-05,
|
2437 |
+
"loss": 1.4315,
|
2438 |
+
"step": 34700
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 1.3746141059130847,
|
2442 |
+
"grad_norm": 3.0505242347717285,
|
2443 |
+
"learning_rate": 1.2465350501026931e-05,
|
2444 |
+
"loss": 1.425,
|
2445 |
+
"step": 34800
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 1.3785719939840102,
|
2449 |
+
"grad_norm": 3.4241063594818115,
|
2450 |
+
"learning_rate": 1.245124507714654e-05,
|
2451 |
+
"loss": 1.4179,
|
2452 |
+
"step": 34900
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 1.3825298820549354,
|
2456 |
+
"grad_norm": 3.458108901977539,
|
2457 |
+
"learning_rate": 1.2437108542990274e-05,
|
2458 |
+
"loss": 1.4133,
|
2459 |
+
"step": 35000
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 1.3864877701258609,
|
2463 |
+
"grad_norm": 3.9022340774536133,
|
2464 |
+
"learning_rate": 1.2422940987382556e-05,
|
2465 |
+
"loss": 1.4112,
|
2466 |
+
"step": 35100
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 1.3904456581967861,
|
2470 |
+
"grad_norm": 3.5141968727111816,
|
2471 |
+
"learning_rate": 1.240874249934273e-05,
|
2472 |
+
"loss": 1.4453,
|
2473 |
+
"step": 35200
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 1.3944035462677116,
|
2477 |
+
"grad_norm": 3.4254074096679688,
|
2478 |
+
"learning_rate": 1.2394513168084485e-05,
|
2479 |
+
"loss": 1.4096,
|
2480 |
+
"step": 35300
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 1.398361434338637,
|
2484 |
+
"grad_norm": 3.460205316543579,
|
2485 |
+
"learning_rate": 1.2380253083015321e-05,
|
2486 |
+
"loss": 1.4145,
|
2487 |
+
"step": 35400
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 1.4023193224095623,
|
2491 |
+
"grad_norm": 3.7515103816986084,
|
2492 |
+
"learning_rate": 1.236596233373597e-05,
|
2493 |
+
"loss": 1.4132,
|
2494 |
+
"step": 35500
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 1.4062772104804875,
|
2498 |
+
"grad_norm": 3.2565503120422363,
|
2499 |
+
"learning_rate": 1.2351641010039833e-05,
|
2500 |
+
"loss": 1.3945,
|
2501 |
+
"step": 35600
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 1.410235098551413,
|
2505 |
+
"grad_norm": 3.754737138748169,
|
2506 |
+
"learning_rate": 1.2337289201912429e-05,
|
2507 |
+
"loss": 1.381,
|
2508 |
+
"step": 35700
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 1.4141929866223384,
|
2512 |
+
"grad_norm": 3.7933449745178223,
|
2513 |
+
"learning_rate": 1.2322906999530811e-05,
|
2514 |
+
"loss": 1.3943,
|
2515 |
+
"step": 35800
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 1.4181508746932636,
|
2519 |
+
"grad_norm": 3.108177900314331,
|
2520 |
+
"learning_rate": 1.2308494493263014e-05,
|
2521 |
+
"loss": 1.4127,
|
2522 |
+
"step": 35900
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 1.422108762764189,
|
2526 |
+
"grad_norm": 3.393486499786377,
|
2527 |
+
"learning_rate": 1.2294051773667482e-05,
|
2528 |
+
"loss": 1.3921,
|
2529 |
+
"step": 36000
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 1.4260666508351143,
|
2533 |
+
"grad_norm": 3.9485793113708496,
|
2534 |
+
"learning_rate": 1.22795789314925e-05,
|
2535 |
+
"loss": 1.42,
|
2536 |
+
"step": 36100
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 1.4300245389060398,
|
2540 |
+
"grad_norm": 3.353940725326538,
|
2541 |
+
"learning_rate": 1.2265076057675615e-05,
|
2542 |
+
"loss": 1.412,
|
2543 |
+
"step": 36200
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 1.4339824269769652,
|
2547 |
+
"grad_norm": 3.861928939819336,
|
2548 |
+
"learning_rate": 1.2250543243343082e-05,
|
2549 |
+
"loss": 1.3952,
|
2550 |
+
"step": 36300
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 1.4379403150478904,
|
2554 |
+
"grad_norm": 2.9782791137695312,
|
2555 |
+
"learning_rate": 1.2235980579809283e-05,
|
2556 |
+
"loss": 1.3872,
|
2557 |
+
"step": 36400
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 1.4418982031188157,
|
2561 |
+
"grad_norm": 3.552558660507202,
|
2562 |
+
"learning_rate": 1.2221388158576142e-05,
|
2563 |
+
"loss": 1.3855,
|
2564 |
+
"step": 36500
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 1.4458560911897411,
|
2568 |
+
"grad_norm": 3.034158229827881,
|
2569 |
+
"learning_rate": 1.2206766071332568e-05,
|
2570 |
+
"loss": 1.4028,
|
2571 |
+
"step": 36600
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 1.4498139792606666,
|
2575 |
+
"grad_norm": 3.669677495956421,
|
2576 |
+
"learning_rate": 1.219211440995387e-05,
|
2577 |
+
"loss": 1.3865,
|
2578 |
+
"step": 36700
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 1.4537718673315918,
|
2582 |
+
"grad_norm": 3.4838759899139404,
|
2583 |
+
"learning_rate": 1.2177433266501182e-05,
|
2584 |
+
"loss": 1.3987,
|
2585 |
+
"step": 36800
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 1.4577297554025173,
|
2589 |
+
"grad_norm": 3.4691314697265625,
|
2590 |
+
"learning_rate": 1.2162722733220877e-05,
|
2591 |
+
"loss": 1.3939,
|
2592 |
+
"step": 36900
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 1.4616876434734425,
|
2596 |
+
"grad_norm": 3.5910284519195557,
|
2597 |
+
"learning_rate": 1.2147982902544004e-05,
|
2598 |
+
"loss": 1.3972,
|
2599 |
+
"step": 37000
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 1.465645531544368,
|
2603 |
+
"grad_norm": 3.2121059894561768,
|
2604 |
+
"learning_rate": 1.2133213867085686e-05,
|
2605 |
+
"loss": 1.3762,
|
2606 |
+
"step": 37100
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 1.4696034196152934,
|
2610 |
+
"grad_norm": 3.8289687633514404,
|
2611 |
+
"learning_rate": 1.2118415719644557e-05,
|
2612 |
+
"loss": 1.4032,
|
2613 |
+
"step": 37200
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 1.4735613076862186,
|
2617 |
+
"grad_norm": 3.597191095352173,
|
2618 |
+
"learning_rate": 1.2103588553202167e-05,
|
2619 |
+
"loss": 1.3925,
|
2620 |
+
"step": 37300
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 1.4775191957571439,
|
2624 |
+
"grad_norm": 3.4253151416778564,
|
2625 |
+
"learning_rate": 1.2088732460922407e-05,
|
2626 |
+
"loss": 1.3715,
|
2627 |
+
"step": 37400
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 1.4814770838280693,
|
2631 |
+
"grad_norm": 3.624340772628784,
|
2632 |
+
"learning_rate": 1.2073847536150912e-05,
|
2633 |
+
"loss": 1.387,
|
2634 |
+
"step": 37500
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 1.4854349718989948,
|
2638 |
+
"grad_norm": 3.2783761024475098,
|
2639 |
+
"learning_rate": 1.2058933872414484e-05,
|
2640 |
+
"loss": 1.3837,
|
2641 |
+
"step": 37600
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 1.48939285996992,
|
2645 |
+
"grad_norm": 3.377274990081787,
|
2646 |
+
"learning_rate": 1.2043991563420501e-05,
|
2647 |
+
"loss": 1.3515,
|
2648 |
+
"step": 37700
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 1.4933507480408454,
|
2652 |
+
"grad_norm": 3.676497459411621,
|
2653 |
+
"learning_rate": 1.2029020703056327e-05,
|
2654 |
+
"loss": 1.3647,
|
2655 |
+
"step": 37800
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 1.4973086361117707,
|
2659 |
+
"grad_norm": 4.441483020782471,
|
2660 |
+
"learning_rate": 1.2014021385388727e-05,
|
2661 |
+
"loss": 1.3594,
|
2662 |
+
"step": 37900
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 1.5012665241826961,
|
2666 |
+
"grad_norm": 4.011296272277832,
|
2667 |
+
"learning_rate": 1.1998993704663267e-05,
|
2668 |
+
"loss": 1.3855,
|
2669 |
+
"step": 38000
|
2670 |
+
},
|
2671 |
+
{
|
2672 |
+
"epoch": 1.5052244122536216,
|
2673 |
+
"grad_norm": 3.3986339569091797,
|
2674 |
+
"learning_rate": 1.1983937755303735e-05,
|
2675 |
+
"loss": 1.3549,
|
2676 |
+
"step": 38100
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 1.5091823003245468,
|
2680 |
+
"grad_norm": 3.2860589027404785,
|
2681 |
+
"learning_rate": 1.1968853631911532e-05,
|
2682 |
+
"loss": 1.3481,
|
2683 |
+
"step": 38200
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 1.513140188395472,
|
2687 |
+
"grad_norm": 4.623264789581299,
|
2688 |
+
"learning_rate": 1.1953741429265089e-05,
|
2689 |
+
"loss": 1.3609,
|
2690 |
+
"step": 38300
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 1.5170980764663975,
|
2694 |
+
"grad_norm": 3.3357603549957275,
|
2695 |
+
"learning_rate": 1.1938601242319269e-05,
|
2696 |
+
"loss": 1.373,
|
2697 |
+
"step": 38400
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 1.521055964537323,
|
2701 |
+
"grad_norm": 3.6516709327697754,
|
2702 |
+
"learning_rate": 1.1923433166204768e-05,
|
2703 |
+
"loss": 1.3568,
|
2704 |
+
"step": 38500
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 1.5250138526082484,
|
2708 |
+
"grad_norm": 4.045721530914307,
|
2709 |
+
"learning_rate": 1.1908237296227522e-05,
|
2710 |
+
"loss": 1.3419,
|
2711 |
+
"step": 38600
|
2712 |
+
},
|
2713 |
+
{
|
2714 |
+
"epoch": 1.5289717406791736,
|
2715 |
+
"grad_norm": 3.331871271133423,
|
2716 |
+
"learning_rate": 1.1893013727868098e-05,
|
2717 |
+
"loss": 1.3575,
|
2718 |
+
"step": 38700
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 1.5329296287500989,
|
2722 |
+
"grad_norm": 3.959519624710083,
|
2723 |
+
"learning_rate": 1.1877762556781109e-05,
|
2724 |
+
"loss": 1.3464,
|
2725 |
+
"step": 38800
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 1.5368875168210243,
|
2729 |
+
"grad_norm": 4.424190998077393,
|
2730 |
+
"learning_rate": 1.1862483878794596e-05,
|
2731 |
+
"loss": 1.3593,
|
2732 |
+
"step": 38900
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 1.5408454048919498,
|
2736 |
+
"grad_norm": 4.052654266357422,
|
2737 |
+
"learning_rate": 1.1847177789909441e-05,
|
2738 |
+
"loss": 1.3474,
|
2739 |
+
"step": 39000
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 1.544803292962875,
|
2743 |
+
"grad_norm": 3.552598237991333,
|
2744 |
+
"learning_rate": 1.1831844386298758e-05,
|
2745 |
+
"loss": 1.346,
|
2746 |
+
"step": 39100
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 1.5487611810338002,
|
2750 |
+
"grad_norm": 3.979213237762451,
|
2751 |
+
"learning_rate": 1.1816483764307286e-05,
|
2752 |
+
"loss": 1.3557,
|
2753 |
+
"step": 39200
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 1.5527190691047257,
|
2757 |
+
"grad_norm": 4.073390960693359,
|
2758 |
+
"learning_rate": 1.1801096020450786e-05,
|
2759 |
+
"loss": 1.3658,
|
2760 |
+
"step": 39300
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 1.5566769571756511,
|
2764 |
+
"grad_norm": 4.211179256439209,
|
2765 |
+
"learning_rate": 1.1785681251415431e-05,
|
2766 |
+
"loss": 1.346,
|
2767 |
+
"step": 39400
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 1.5606348452465766,
|
2771 |
+
"grad_norm": 3.6185340881347656,
|
2772 |
+
"learning_rate": 1.177023955405721e-05,
|
2773 |
+
"loss": 1.3686,
|
2774 |
+
"step": 39500
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 1.5645927333175018,
|
2778 |
+
"grad_norm": 3.7389111518859863,
|
2779 |
+
"learning_rate": 1.1754771025401307e-05,
|
2780 |
+
"loss": 1.3536,
|
2781 |
+
"step": 39600
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 1.568550621388427,
|
2785 |
+
"grad_norm": 4.2574357986450195,
|
2786 |
+
"learning_rate": 1.1739275762641494e-05,
|
2787 |
+
"loss": 1.352,
|
2788 |
+
"step": 39700
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 1.5725085094593525,
|
2792 |
+
"grad_norm": 3.516805410385132,
|
2793 |
+
"learning_rate": 1.1723753863139529e-05,
|
2794 |
+
"loss": 1.3411,
|
2795 |
+
"step": 39800
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 1.576466397530278,
|
2799 |
+
"grad_norm": 3.5958383083343506,
|
2800 |
+
"learning_rate": 1.1708205424424521e-05,
|
2801 |
+
"loss": 1.3433,
|
2802 |
+
"step": 39900
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 1.5804242856012032,
|
2806 |
+
"grad_norm": 3.995814323425293,
|
2807 |
+
"learning_rate": 1.1692630544192354e-05,
|
2808 |
+
"loss": 1.3529,
|
2809 |
+
"step": 40000
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 1.5843821736721284,
|
2813 |
+
"grad_norm": 3.817218780517578,
|
2814 |
+
"learning_rate": 1.1677029320305041e-05,
|
2815 |
+
"loss": 1.3469,
|
2816 |
+
"step": 40100
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 1.5883400617430539,
|
2820 |
+
"grad_norm": 4.439276695251465,
|
2821 |
+
"learning_rate": 1.1661401850790119e-05,
|
2822 |
+
"loss": 1.3466,
|
2823 |
+
"step": 40200
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 1.5922979498139793,
|
2827 |
+
"grad_norm": 3.7181553840637207,
|
2828 |
+
"learning_rate": 1.1645748233840044e-05,
|
2829 |
+
"loss": 1.3476,
|
2830 |
+
"step": 40300
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 1.5962558378849048,
|
2834 |
+
"grad_norm": 10.218334197998047,
|
2835 |
+
"learning_rate": 1.1630068567811557e-05,
|
2836 |
+
"loss": 1.3602,
|
2837 |
+
"step": 40400
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 1.60021372595583,
|
2841 |
+
"grad_norm": 4.133950710296631,
|
2842 |
+
"learning_rate": 1.1614362951225075e-05,
|
2843 |
+
"loss": 1.3485,
|
2844 |
+
"step": 40500
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 1.6041716140267552,
|
2848 |
+
"grad_norm": 4.007839202880859,
|
2849 |
+
"learning_rate": 1.1598631482764074e-05,
|
2850 |
+
"loss": 1.3594,
|
2851 |
+
"step": 40600
|
2852 |
+
},
|
2853 |
+
{
|
2854 |
+
"epoch": 1.6081295020976807,
|
2855 |
+
"grad_norm": 4.194820404052734,
|
2856 |
+
"learning_rate": 1.1582874261274463e-05,
|
2857 |
+
"loss": 1.3383,
|
2858 |
+
"step": 40700
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 1.6120873901686061,
|
2862 |
+
"grad_norm": 4.193638801574707,
|
2863 |
+
"learning_rate": 1.1567091385763965e-05,
|
2864 |
+
"loss": 1.3715,
|
2865 |
+
"step": 40800
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 1.6160452782395314,
|
2869 |
+
"grad_norm": 3.5800745487213135,
|
2870 |
+
"learning_rate": 1.15512829554015e-05,
|
2871 |
+
"loss": 1.3494,
|
2872 |
+
"step": 40900
|
2873 |
+
},
|
2874 |
+
{
|
2875 |
+
"epoch": 1.6200031663104566,
|
2876 |
+
"grad_norm": 4.548177719116211,
|
2877 |
+
"learning_rate": 1.1535449069516552e-05,
|
2878 |
+
"loss": 1.3442,
|
2879 |
+
"step": 41000
|
2880 |
+
},
|
2881 |
+
{
|
2882 |
+
"epoch": 1.623961054381382,
|
2883 |
+
"grad_norm": 3.7496066093444824,
|
2884 |
+
"learning_rate": 1.1519589827598553e-05,
|
2885 |
+
"loss": 1.329,
|
2886 |
+
"step": 41100
|
2887 |
+
},
|
2888 |
+
{
|
2889 |
+
"epoch": 1.6279189424523075,
|
2890 |
+
"grad_norm": 4.815052032470703,
|
2891 |
+
"learning_rate": 1.1503705329296252e-05,
|
2892 |
+
"loss": 1.32,
|
2893 |
+
"step": 41200
|
2894 |
+
},
|
2895 |
+
{
|
2896 |
+
"epoch": 1.631876830523233,
|
2897 |
+
"grad_norm": 4.1927103996276855,
|
2898 |
+
"learning_rate": 1.14877956744171e-05,
|
2899 |
+
"loss": 1.3172,
|
2900 |
+
"step": 41300
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 1.6358347185941582,
|
2904 |
+
"grad_norm": 3.9431440830230713,
|
2905 |
+
"learning_rate": 1.1471860962926604e-05,
|
2906 |
+
"loss": 1.3271,
|
2907 |
+
"step": 41400
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 1.6397926066650834,
|
2911 |
+
"grad_norm": 4.615567684173584,
|
2912 |
+
"learning_rate": 1.1455901294947722e-05,
|
2913 |
+
"loss": 1.348,
|
2914 |
+
"step": 41500
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 1.6437504947360089,
|
2918 |
+
"grad_norm": 4.151221752166748,
|
2919 |
+
"learning_rate": 1.143991677076021e-05,
|
2920 |
+
"loss": 1.3336,
|
2921 |
+
"step": 41600
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 1.6477083828069343,
|
2925 |
+
"grad_norm": 4.409358978271484,
|
2926 |
+
"learning_rate": 1.142390749080001e-05,
|
2927 |
+
"loss": 1.3254,
|
2928 |
+
"step": 41700
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 1.6516662708778596,
|
2932 |
+
"grad_norm": 4.490970134735107,
|
2933 |
+
"learning_rate": 1.140787355565861e-05,
|
2934 |
+
"loss": 1.3303,
|
2935 |
+
"step": 41800
|
2936 |
+
},
|
2937 |
+
{
|
2938 |
+
"epoch": 1.6556241589487848,
|
2939 |
+
"grad_norm": 4.116312026977539,
|
2940 |
+
"learning_rate": 1.1391815066082418e-05,
|
2941 |
+
"loss": 1.3315,
|
2942 |
+
"step": 41900
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 1.6595820470197102,
|
2946 |
+
"grad_norm": 4.251399517059326,
|
2947 |
+
"learning_rate": 1.1375732122972124e-05,
|
2948 |
+
"loss": 1.3243,
|
2949 |
+
"step": 42000
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 1.6635399350906357,
|
2953 |
+
"grad_norm": 4.184506416320801,
|
2954 |
+
"learning_rate": 1.1359624827382062e-05,
|
2955 |
+
"loss": 1.3226,
|
2956 |
+
"step": 42100
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 1.6674978231615611,
|
2960 |
+
"grad_norm": 4.628664970397949,
|
2961 |
+
"learning_rate": 1.134349328051959e-05,
|
2962 |
+
"loss": 1.3399,
|
2963 |
+
"step": 42200
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 1.6714557112324864,
|
2967 |
+
"grad_norm": 4.529860496520996,
|
2968 |
+
"learning_rate": 1.132733758374444e-05,
|
2969 |
+
"loss": 1.2967,
|
2970 |
+
"step": 42300
|
2971 |
+
},
|
2972 |
+
{
|
2973 |
+
"epoch": 1.6754135993034116,
|
2974 |
+
"grad_norm": 4.5048699378967285,
|
2975 |
+
"learning_rate": 1.1311157838568083e-05,
|
2976 |
+
"loss": 1.3255,
|
2977 |
+
"step": 42400
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 1.679371487374337,
|
2981 |
+
"grad_norm": 4.321528911590576,
|
2982 |
+
"learning_rate": 1.1294954146653094e-05,
|
2983 |
+
"loss": 1.311,
|
2984 |
+
"step": 42500
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 1.6833293754452625,
|
2988 |
+
"grad_norm": 4.919022083282471,
|
2989 |
+
"learning_rate": 1.1278726609812523e-05,
|
2990 |
+
"loss": 1.3219,
|
2991 |
+
"step": 42600
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 1.6872872635161877,
|
2995 |
+
"grad_norm": 4.146111965179443,
|
2996 |
+
"learning_rate": 1.126247533000923e-05,
|
2997 |
+
"loss": 1.298,
|
2998 |
+
"step": 42700
|
2999 |
+
},
|
3000 |
+
{
|
3001 |
+
"epoch": 1.691245151587113,
|
3002 |
+
"grad_norm": 4.071747779846191,
|
3003 |
+
"learning_rate": 1.1246200409355271e-05,
|
3004 |
+
"loss": 1.313,
|
3005 |
+
"step": 42800
|
3006 |
+
},
|
3007 |
+
{
|
3008 |
+
"epoch": 1.6952030396580384,
|
3009 |
+
"grad_norm": 3.8871426582336426,
|
3010 |
+
"learning_rate": 1.1229901950111245e-05,
|
3011 |
+
"loss": 1.3176,
|
3012 |
+
"step": 42900
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 1.6991609277289639,
|
3016 |
+
"grad_norm": 3.9479401111602783,
|
3017 |
+
"learning_rate": 1.1213580054685644e-05,
|
3018 |
+
"loss": 1.3112,
|
3019 |
+
"step": 43000
|
3020 |
+
},
|
3021 |
+
{
|
3022 |
+
"epoch": 1.7031188157998893,
|
3023 |
+
"grad_norm": 4.039346694946289,
|
3024 |
+
"learning_rate": 1.1197234825634222e-05,
|
3025 |
+
"loss": 1.3109,
|
3026 |
+
"step": 43100
|
3027 |
+
},
|
3028 |
+
{
|
3029 |
+
"epoch": 1.7070767038708146,
|
3030 |
+
"grad_norm": 4.356393814086914,
|
3031 |
+
"learning_rate": 1.1180866365659346e-05,
|
3032 |
+
"loss": 1.3202,
|
3033 |
+
"step": 43200
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 1.7110345919417398,
|
3037 |
+
"grad_norm": 4.11832857131958,
|
3038 |
+
"learning_rate": 1.1164474777609351e-05,
|
3039 |
+
"loss": 1.313,
|
3040 |
+
"step": 43300
|
3041 |
+
},
|
3042 |
+
{
|
3043 |
+
"epoch": 1.7149924800126652,
|
3044 |
+
"grad_norm": 4.101129531860352,
|
3045 |
+
"learning_rate": 1.1148060164477887e-05,
|
3046 |
+
"loss": 1.2968,
|
3047 |
+
"step": 43400
|
3048 |
+
},
|
3049 |
+
{
|
3050 |
+
"epoch": 1.7189503680835907,
|
3051 |
+
"grad_norm": 3.728778600692749,
|
3052 |
+
"learning_rate": 1.1131622629403289e-05,
|
3053 |
+
"loss": 1.2869,
|
3054 |
+
"step": 43500
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 1.722908256154516,
|
3058 |
+
"grad_norm": 3.846654176712036,
|
3059 |
+
"learning_rate": 1.1115162275667909e-05,
|
3060 |
+
"loss": 1.3054,
|
3061 |
+
"step": 43600
|
3062 |
+
},
|
3063 |
+
{
|
3064 |
+
"epoch": 1.7268661442254412,
|
3065 |
+
"grad_norm": 4.967803478240967,
|
3066 |
+
"learning_rate": 1.1098679206697474e-05,
|
3067 |
+
"loss": 1.3165,
|
3068 |
+
"step": 43700
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 1.7308240322963666,
|
3072 |
+
"grad_norm": 4.610755443572998,
|
3073 |
+
"learning_rate": 1.1082173526060454e-05,
|
3074 |
+
"loss": 1.3234,
|
3075 |
+
"step": 43800
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 1.734781920367292,
|
3079 |
+
"grad_norm": 4.377742290496826,
|
3080 |
+
"learning_rate": 1.1065645337467375e-05,
|
3081 |
+
"loss": 1.3261,
|
3082 |
+
"step": 43900
|
3083 |
+
},
|
3084 |
+
{
|
3085 |
+
"epoch": 1.7387398084382175,
|
3086 |
+
"grad_norm": 5.010995864868164,
|
3087 |
+
"learning_rate": 1.1049094744770201e-05,
|
3088 |
+
"loss": 1.3026,
|
3089 |
+
"step": 44000
|
3090 |
+
},
|
3091 |
+
{
|
3092 |
+
"epoch": 1.7426976965091427,
|
3093 |
+
"grad_norm": 4.31913423538208,
|
3094 |
+
"learning_rate": 1.1032521851961665e-05,
|
3095 |
+
"loss": 1.2697,
|
3096 |
+
"step": 44100
|
3097 |
+
},
|
3098 |
+
{
|
3099 |
+
"epoch": 1.746655584580068,
|
3100 |
+
"grad_norm": 4.2657060623168945,
|
3101 |
+
"learning_rate": 1.1015926763174617e-05,
|
3102 |
+
"loss": 1.3101,
|
3103 |
+
"step": 44200
|
3104 |
+
},
|
3105 |
+
{
|
3106 |
+
"epoch": 1.7506134726509934,
|
3107 |
+
"grad_norm": 3.801684617996216,
|
3108 |
+
"learning_rate": 1.0999309582681372e-05,
|
3109 |
+
"loss": 1.268,
|
3110 |
+
"step": 44300
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 1.7545713607219189,
|
3114 |
+
"grad_norm": 4.505929946899414,
|
3115 |
+
"learning_rate": 1.0982670414893057e-05,
|
3116 |
+
"loss": 1.2957,
|
3117 |
+
"step": 44400
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 1.7585292487928441,
|
3121 |
+
"grad_norm": 3.837562084197998,
|
3122 |
+
"learning_rate": 1.0966009364358948e-05,
|
3123 |
+
"loss": 1.3078,
|
3124 |
+
"step": 44500
|
3125 |
+
},
|
3126 |
+
{
|
3127 |
+
"epoch": 1.7624871368637693,
|
3128 |
+
"grad_norm": 4.854923248291016,
|
3129 |
+
"learning_rate": 1.0949326535765823e-05,
|
3130 |
+
"loss": 1.3119,
|
3131 |
+
"step": 44600
|
3132 |
+
},
|
3133 |
+
{
|
3134 |
+
"epoch": 1.7664450249346948,
|
3135 |
+
"grad_norm": 5.621912002563477,
|
3136 |
+
"learning_rate": 1.0932622033937294e-05,
|
3137 |
+
"loss": 1.2847,
|
3138 |
+
"step": 44700
|
3139 |
+
},
|
3140 |
+
{
|
3141 |
+
"epoch": 1.7704029130056202,
|
3142 |
+
"grad_norm": 4.009350776672363,
|
3143 |
+
"learning_rate": 1.0915895963833152e-05,
|
3144 |
+
"loss": 1.3006,
|
3145 |
+
"step": 44800
|
3146 |
+
},
|
3147 |
+
{
|
3148 |
+
"epoch": 1.7743608010765457,
|
3149 |
+
"grad_norm": 3.6888113021850586,
|
3150 |
+
"learning_rate": 1.0899148430548716e-05,
|
3151 |
+
"loss": 1.3032,
|
3152 |
+
"step": 44900
|
3153 |
+
},
|
3154 |
+
{
|
3155 |
+
"epoch": 1.778318689147471,
|
3156 |
+
"grad_norm": 4.511534690856934,
|
3157 |
+
"learning_rate": 1.0882379539314155e-05,
|
3158 |
+
"loss": 1.2615,
|
3159 |
+
"step": 45000
|
3160 |
+
},
|
3161 |
+
{
|
3162 |
+
"epoch": 1.7822765772183962,
|
3163 |
+
"grad_norm": 5.086874485015869,
|
3164 |
+
"learning_rate": 1.0865589395493845e-05,
|
3165 |
+
"loss": 1.2634,
|
3166 |
+
"step": 45100
|
3167 |
+
},
|
3168 |
+
{
|
3169 |
+
"epoch": 1.7862344652893216,
|
3170 |
+
"grad_norm": 4.865400791168213,
|
3171 |
+
"learning_rate": 1.0848778104585692e-05,
|
3172 |
+
"loss": 1.2876,
|
3173 |
+
"step": 45200
|
3174 |
+
},
|
3175 |
+
{
|
3176 |
+
"epoch": 1.790192353360247,
|
3177 |
+
"grad_norm": 4.537430763244629,
|
3178 |
+
"learning_rate": 1.0831945772220487e-05,
|
3179 |
+
"loss": 1.2764,
|
3180 |
+
"step": 45300
|
3181 |
+
},
|
3182 |
+
{
|
3183 |
+
"epoch": 1.7941502414311723,
|
3184 |
+
"grad_norm": 4.448334693908691,
|
3185 |
+
"learning_rate": 1.0815092504161214e-05,
|
3186 |
+
"loss": 1.2814,
|
3187 |
+
"step": 45400
|
3188 |
+
},
|
3189 |
+
{
|
3190 |
+
"epoch": 1.7981081295020975,
|
3191 |
+
"grad_norm": 4.650451183319092,
|
3192 |
+
"learning_rate": 1.0798218406302422e-05,
|
3193 |
+
"loss": 1.2819,
|
3194 |
+
"step": 45500
|
3195 |
+
},
|
3196 |
+
{
|
3197 |
+
"epoch": 1.802066017573023,
|
3198 |
+
"grad_norm": 4.031219005584717,
|
3199 |
+
"learning_rate": 1.0781323584669524e-05,
|
3200 |
+
"loss": 1.2729,
|
3201 |
+
"step": 45600
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 1.8060239056439484,
|
3205 |
+
"grad_norm": 4.477336883544922,
|
3206 |
+
"learning_rate": 1.0764408145418157e-05,
|
3207 |
+
"loss": 1.2586,
|
3208 |
+
"step": 45700
|
3209 |
+
},
|
3210 |
+
{
|
3211 |
+
"epoch": 1.8099817937148739,
|
3212 |
+
"grad_norm": 4.118893146514893,
|
3213 |
+
"learning_rate": 1.0747472194833506e-05,
|
3214 |
+
"loss": 1.2591,
|
3215 |
+
"step": 45800
|
3216 |
+
},
|
3217 |
+
{
|
3218 |
+
"epoch": 1.8139396817857991,
|
3219 |
+
"grad_norm": 4.766265392303467,
|
3220 |
+
"learning_rate": 1.073051583932963e-05,
|
3221 |
+
"loss": 1.2693,
|
3222 |
+
"step": 45900
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 1.8178975698567243,
|
3226 |
+
"grad_norm": 5.545733451843262,
|
3227 |
+
"learning_rate": 1.0713539185448795e-05,
|
3228 |
+
"loss": 1.2691,
|
3229 |
+
"step": 46000
|
3230 |
+
},
|
3231 |
+
{
|
3232 |
+
"epoch": 1.8218554579276498,
|
3233 |
+
"grad_norm": 4.723430633544922,
|
3234 |
+
"learning_rate": 1.069654233986082e-05,
|
3235 |
+
"loss": 1.2582,
|
3236 |
+
"step": 46100
|
3237 |
+
},
|
3238 |
+
{
|
3239 |
+
"epoch": 1.8258133459985753,
|
3240 |
+
"grad_norm": 4.899106025695801,
|
3241 |
+
"learning_rate": 1.0679525409362387e-05,
|
3242 |
+
"loss": 1.2802,
|
3243 |
+
"step": 46200
|
3244 |
+
},
|
3245 |
+
{
|
3246 |
+
"epoch": 1.8297712340695005,
|
3247 |
+
"grad_norm": 4.531938552856445,
|
3248 |
+
"learning_rate": 1.066248850087638e-05,
|
3249 |
+
"loss": 1.2683,
|
3250 |
+
"step": 46300
|
3251 |
+
},
|
3252 |
+
{
|
3253 |
+
"epoch": 1.8337291221404257,
|
3254 |
+
"grad_norm": 4.174386501312256,
|
3255 |
+
"learning_rate": 1.0645431721451212e-05,
|
3256 |
+
"loss": 1.2538,
|
3257 |
+
"step": 46400
|
3258 |
+
},
|
3259 |
+
{
|
3260 |
+
"epoch": 1.8376870102113512,
|
3261 |
+
"grad_norm": 4.827451229095459,
|
3262 |
+
"learning_rate": 1.0628355178260147e-05,
|
3263 |
+
"loss": 1.2571,
|
3264 |
+
"step": 46500
|
3265 |
+
},
|
3266 |
+
{
|
3267 |
+
"epoch": 1.8416448982822766,
|
3268 |
+
"grad_norm": 4.749929904937744,
|
3269 |
+
"learning_rate": 1.0611258978600638e-05,
|
3270 |
+
"loss": 1.2759,
|
3271 |
+
"step": 46600
|
3272 |
+
},
|
3273 |
+
{
|
3274 |
+
"epoch": 1.845602786353202,
|
3275 |
+
"grad_norm": 4.659051418304443,
|
3276 |
+
"learning_rate": 1.0594143229893643e-05,
|
3277 |
+
"loss": 1.2698,
|
3278 |
+
"step": 46700
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 1.8495606744241273,
|
3282 |
+
"grad_norm": 4.492525100708008,
|
3283 |
+
"learning_rate": 1.057700803968295e-05,
|
3284 |
+
"loss": 1.2583,
|
3285 |
+
"step": 46800
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 1.8535185624950525,
|
3289 |
+
"grad_norm": 4.04518461227417,
|
3290 |
+
"learning_rate": 1.0559853515634509e-05,
|
3291 |
+
"loss": 1.268,
|
3292 |
+
"step": 46900
|
3293 |
+
},
|
3294 |
+
{
|
3295 |
+
"epoch": 1.857476450565978,
|
3296 |
+
"grad_norm": 5.029372215270996,
|
3297 |
+
"learning_rate": 1.054267976553575e-05,
|
3298 |
+
"loss": 1.238,
|
3299 |
+
"step": 47000
|
3300 |
+
},
|
3301 |
+
{
|
3302 |
+
"epoch": 1.8614343386369034,
|
3303 |
+
"grad_norm": 4.29434871673584,
|
3304 |
+
"learning_rate": 1.05254868972949e-05,
|
3305 |
+
"loss": 1.2431,
|
3306 |
+
"step": 47100
|
3307 |
+
},
|
3308 |
+
{
|
3309 |
+
"epoch": 1.8653922267078287,
|
3310 |
+
"grad_norm": 4.874353408813477,
|
3311 |
+
"learning_rate": 1.050827501894032e-05,
|
3312 |
+
"loss": 1.2339,
|
3313 |
+
"step": 47200
|
3314 |
+
},
|
3315 |
+
{
|
3316 |
+
"epoch": 1.869350114778754,
|
3317 |
+
"grad_norm": 4.865941047668457,
|
3318 |
+
"learning_rate": 1.0491044238619817e-05,
|
3319 |
+
"loss": 1.2427,
|
3320 |
+
"step": 47300
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 1.8733080028496794,
|
3324 |
+
"grad_norm": 4.548977375030518,
|
3325 |
+
"learning_rate": 1.0473794664599957e-05,
|
3326 |
+
"loss": 1.2586,
|
3327 |
+
"step": 47400
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 1.8772658909206048,
|
3331 |
+
"grad_norm": 5.584561824798584,
|
3332 |
+
"learning_rate": 1.0456526405265402e-05,
|
3333 |
+
"loss": 1.2388,
|
3334 |
+
"step": 47500
|
3335 |
+
},
|
3336 |
+
{
|
3337 |
+
"epoch": 1.8812237789915303,
|
3338 |
+
"grad_norm": 4.570620536804199,
|
3339 |
+
"learning_rate": 1.0439239569118215e-05,
|
3340 |
+
"loss": 1.2499,
|
3341 |
+
"step": 47600
|
3342 |
+
},
|
3343 |
+
{
|
3344 |
+
"epoch": 1.8851816670624555,
|
3345 |
+
"grad_norm": 4.9521379470825195,
|
3346 |
+
"learning_rate": 1.0421934264777186e-05,
|
3347 |
+
"loss": 1.2486,
|
3348 |
+
"step": 47700
|
3349 |
+
},
|
3350 |
+
{
|
3351 |
+
"epoch": 1.8891395551333807,
|
3352 |
+
"grad_norm": 4.744478702545166,
|
3353 |
+
"learning_rate": 1.0404610600977141e-05,
|
3354 |
+
"loss": 1.2428,
|
3355 |
+
"step": 47800
|
3356 |
+
},
|
3357 |
+
{
|
3358 |
+
"epoch": 1.8930974432043062,
|
3359 |
+
"grad_norm": 4.681623935699463,
|
3360 |
+
"learning_rate": 1.0387268686568275e-05,
|
3361 |
+
"loss": 1.2577,
|
3362 |
+
"step": 47900
|
3363 |
+
},
|
3364 |
+
{
|
3365 |
+
"epoch": 1.8970553312752316,
|
3366 |
+
"grad_norm": 4.406890392303467,
|
3367 |
+
"learning_rate": 1.0369908630515445e-05,
|
3368 |
+
"loss": 1.2367,
|
3369 |
+
"step": 48000
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 1.9010132193461569,
|
3373 |
+
"grad_norm": 4.650542259216309,
|
3374 |
+
"learning_rate": 1.0352530541897507e-05,
|
3375 |
+
"loss": 1.243,
|
3376 |
+
"step": 48100
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 1.904971107417082,
|
3380 |
+
"grad_norm": 5.0188164710998535,
|
3381 |
+
"learning_rate": 1.0335134529906619e-05,
|
3382 |
+
"loss": 1.2222,
|
3383 |
+
"step": 48200
|
3384 |
+
},
|
3385 |
+
{
|
3386 |
+
"epoch": 1.9089289954880075,
|
3387 |
+
"grad_norm": 4.498706340789795,
|
3388 |
+
"learning_rate": 1.0317720703847554e-05,
|
3389 |
+
"loss": 1.2508,
|
3390 |
+
"step": 48300
|
3391 |
+
},
|
3392 |
+
{
|
3393 |
+
"epoch": 1.912886883558933,
|
3394 |
+
"grad_norm": 4.909203052520752,
|
3395 |
+
"learning_rate": 1.0300289173137021e-05,
|
3396 |
+
"loss": 1.2241,
|
3397 |
+
"step": 48400
|
3398 |
+
},
|
3399 |
+
{
|
3400 |
+
"epoch": 1.9168447716298584,
|
3401 |
+
"grad_norm": 4.85788631439209,
|
3402 |
+
"learning_rate": 1.0282840047302967e-05,
|
3403 |
+
"loss": 1.2268,
|
3404 |
+
"step": 48500
|
3405 |
+
},
|
3406 |
+
{
|
3407 |
+
"epoch": 1.9208026597007837,
|
3408 |
+
"grad_norm": 4.537557601928711,
|
3409 |
+
"learning_rate": 1.0265373435983907e-05,
|
3410 |
+
"loss": 1.2515,
|
3411 |
+
"step": 48600
|
3412 |
+
},
|
3413 |
+
{
|
3414 |
+
"epoch": 1.924760547771709,
|
3415 |
+
"grad_norm": 4.660990238189697,
|
3416 |
+
"learning_rate": 1.0247889448928208e-05,
|
3417 |
+
"loss": 1.2531,
|
3418 |
+
"step": 48700
|
3419 |
+
},
|
3420 |
+
{
|
3421 |
+
"epoch": 1.9287184358426344,
|
3422 |
+
"grad_norm": 4.9931511878967285,
|
3423 |
+
"learning_rate": 1.0230388195993424e-05,
|
3424 |
+
"loss": 1.2336,
|
3425 |
+
"step": 48800
|
3426 |
+
},
|
3427 |
+
{
|
3428 |
+
"epoch": 1.9326763239135598,
|
3429 |
+
"grad_norm": 4.516580581665039,
|
3430 |
+
"learning_rate": 1.0212869787145594e-05,
|
3431 |
+
"loss": 1.2292,
|
3432 |
+
"step": 48900
|
3433 |
+
},
|
3434 |
+
{
|
3435 |
+
"epoch": 1.936634211984485,
|
3436 |
+
"grad_norm": 4.5982255935668945,
|
3437 |
+
"learning_rate": 1.0195334332458552e-05,
|
3438 |
+
"loss": 1.2417,
|
3439 |
+
"step": 49000
|
3440 |
+
},
|
3441 |
+
{
|
3442 |
+
"epoch": 1.9405921000554103,
|
3443 |
+
"grad_norm": 5.071137428283691,
|
3444 |
+
"learning_rate": 1.0177781942113238e-05,
|
3445 |
+
"loss": 1.2194,
|
3446 |
+
"step": 49100
|
3447 |
+
},
|
3448 |
+
{
|
3449 |
+
"epoch": 1.9445499881263357,
|
3450 |
+
"grad_norm": 4.76341438293457,
|
3451 |
+
"learning_rate": 1.0160212726397001e-05,
|
3452 |
+
"loss": 1.2207,
|
3453 |
+
"step": 49200
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 1.9485078761972612,
|
3457 |
+
"grad_norm": 4.945827484130859,
|
3458 |
+
"learning_rate": 1.0142626795702916e-05,
|
3459 |
+
"loss": 1.208,
|
3460 |
+
"step": 49300
|
3461 |
+
},
|
3462 |
+
{
|
3463 |
+
"epoch": 1.9524657642681866,
|
3464 |
+
"grad_norm": 5.068126678466797,
|
3465 |
+
"learning_rate": 1.0125024260529075e-05,
|
3466 |
+
"loss": 1.2372,
|
3467 |
+
"step": 49400
|
3468 |
+
},
|
3469 |
+
{
|
3470 |
+
"epoch": 1.9564236523391119,
|
3471 |
+
"grad_norm": 5.238717079162598,
|
3472 |
+
"learning_rate": 1.010740523147791e-05,
|
3473 |
+
"loss": 1.2287,
|
3474 |
+
"step": 49500
|
3475 |
+
},
|
3476 |
+
{
|
3477 |
+
"epoch": 1.960381540410037,
|
3478 |
+
"grad_norm": 4.586404800415039,
|
3479 |
+
"learning_rate": 1.008976981925548e-05,
|
3480 |
+
"loss": 1.2023,
|
3481 |
+
"step": 49600
|
3482 |
+
},
|
3483 |
+
{
|
3484 |
+
"epoch": 1.9643394284809625,
|
3485 |
+
"grad_norm": 5.284154415130615,
|
3486 |
+
"learning_rate": 1.0072118134670792e-05,
|
3487 |
+
"loss": 1.2254,
|
3488 |
+
"step": 49700
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 1.968297316551888,
|
3492 |
+
"grad_norm": 4.639484882354736,
|
3493 |
+
"learning_rate": 1.0054450288635098e-05,
|
3494 |
+
"loss": 1.2298,
|
3495 |
+
"step": 49800
|
3496 |
+
},
|
3497 |
+
{
|
3498 |
+
"epoch": 1.9722552046228132,
|
3499 |
+
"grad_norm": 5.642242908477783,
|
3500 |
+
"learning_rate": 1.003676639216119e-05,
|
3501 |
+
"loss": 1.2196,
|
3502 |
+
"step": 49900
|
3503 |
+
},
|
3504 |
+
{
|
3505 |
+
"epoch": 1.9762130926937385,
|
3506 |
+
"grad_norm": 5.445943355560303,
|
3507 |
+
"learning_rate": 1.0019066556362718e-05,
|
3508 |
+
"loss": 1.2035,
|
3509 |
+
"step": 50000
|
3510 |
+
},
|
3511 |
+
{
|
3512 |
+
"epoch": 1.980170980764664,
|
3513 |
+
"grad_norm": 5.127743244171143,
|
3514 |
+
"learning_rate": 1.000135089245348e-05,
|
3515 |
+
"loss": 1.2281,
|
3516 |
+
"step": 50100
|
3517 |
+
},
|
3518 |
+
{
|
3519 |
+
"epoch": 1.9841288688355894,
|
3520 |
+
"grad_norm": 4.978102684020996,
|
3521 |
+
"learning_rate": 9.98361951174673e-06,
|
3522 |
+
"loss": 1.22,
|
3523 |
+
"step": 50200
|
3524 |
+
},
|
3525 |
+
{
|
3526 |
+
"epoch": 1.9880867569065148,
|
3527 |
+
"grad_norm": 4.681839466094971,
|
3528 |
+
"learning_rate": 9.965872525654468e-06,
|
3529 |
+
"loss": 1.2011,
|
3530 |
+
"step": 50300
|
3531 |
+
},
|
3532 |
+
{
|
3533 |
+
"epoch": 1.99204464497744,
|
3534 |
+
"grad_norm": 5.249551296234131,
|
3535 |
+
"learning_rate": 9.948110045686763e-06,
|
3536 |
+
"loss": 1.1931,
|
3537 |
+
"step": 50400
|
3538 |
+
},
|
3539 |
+
{
|
3540 |
+
"epoch": 1.9960025330483653,
|
3541 |
+
"grad_norm": 4.80012845993042,
|
3542 |
+
"learning_rate": 9.930332183451022e-06,
|
3543 |
+
"loss": 1.2282,
|
3544 |
+
"step": 50500
|
3545 |
+
}
|
3546 |
+
],
|
3547 |
+
"logging_steps": 100,
|
3548 |
+
"max_steps": 126330,
|
3549 |
+
"num_input_tokens_seen": 0,
|
3550 |
+
"num_train_epochs": 5,
|
3551 |
+
"save_steps": 25266,
|
3552 |
+
"stateful_callbacks": {
|
3553 |
+
"TrainerControl": {
|
3554 |
+
"args": {
|
3555 |
+
"should_epoch_stop": false,
|
3556 |
+
"should_evaluate": false,
|
3557 |
+
"should_log": false,
|
3558 |
+
"should_save": true,
|
3559 |
+
"should_training_stop": false
|
3560 |
+
},
|
3561 |
+
"attributes": {}
|
3562 |
+
}
|
3563 |
+
},
|
3564 |
+
"total_flos": 5.9517716845075366e+19,
|
3565 |
+
"train_batch_size": 2,
|
3566 |
+
"trial_name": null,
|
3567 |
+
"trial_params": null
|
3568 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eed14ab5b16ff32fa17eac0c8d9f69cad950a9c6a6384dd381ab4cb73af8dd02
|
3 |
+
size 6200
|