Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.bin +3 -0
- pytorch_model_fsdp.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.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 +2253 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
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-3.1-8B-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": 16,
|
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 |
+
"down_proj",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_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 sha256:119750a9f008196ee3cc4f5ce3d027d9fce554618e285228070da75af91f9015
|
3 |
+
size 167832240
|
optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4c63359a37e0025bf7f49a72a7b4c3feed333906cbc2497cf41cc65b3d3df64
|
3 |
+
size 335945362
|
pytorch_model_fsdp.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:530cff329951b841ac5a945e43a5633bc8d12e5debdd503ea936ebad6c715f70
|
3 |
+
size 167939550
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cccaba5dc6f5eb3c168b418d217a224935e558bd55b4fe6def3b23979337cdc
|
3 |
+
size 15920
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a30480d2425793627680d380781b8e5db5694685835f260919cd17feeceb4d
|
3 |
+
size 15920
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91be907ab46ef7e4fbe20dec6fcf4c82f9f5d0ca17940357aa128b086acf529e
|
3 |
+
size 15920
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67324548240ed52f09147e3dec324bb4ce730e4e2253576e458ed17bcf6ce284
|
3 |
+
size 15920
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf55be4a441b189ae4fa820f62f8cd2df780c0fa68517e9c8261efe1c457d17a
|
3 |
+
size 15920
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:022512ff825b631ad2cff4866abb7e27af077da86791d938430acade7cd5abcb
|
3 |
+
size 15920
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19f4ae65ea0596b999d93486492ab9b261a470e6faf941b3926a08e0951954d6
|
3 |
+
size 15920
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:989365de43c5db9f3f3739006135f2aef225d431a3cadef2e0e26b064cc98f7d
|
3 |
+
size 15920
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:259a0916cf66068e5210076666f955ebbf9adbdc0d37a2e86fed6f481d1747fd
|
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": "<|finetune_right_pad_id|>",
|
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": "<|finetune_right_pad_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.974025974025974,
|
5 |
+
"eval_steps": 39,
|
6 |
+
"global_step": 308,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.006493506493506494,
|
13 |
+
"grad_norm": 0.39616659283638,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 1.6277,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.006493506493506494,
|
20 |
+
"eval_loss": 1.6379814147949219,
|
21 |
+
"eval_runtime": 25.2293,
|
22 |
+
"eval_samples_per_second": 11.693,
|
23 |
+
"eval_steps_per_second": 1.467,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.012987012987012988,
|
28 |
+
"grad_norm": 0.42422759532928467,
|
29 |
+
"learning_rate": 2.0000000000000003e-06,
|
30 |
+
"loss": 1.6549,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.01948051948051948,
|
35 |
+
"grad_norm": 0.40566202998161316,
|
36 |
+
"learning_rate": 3e-06,
|
37 |
+
"loss": 1.6115,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.025974025974025976,
|
42 |
+
"grad_norm": 0.3940100371837616,
|
43 |
+
"learning_rate": 4.000000000000001e-06,
|
44 |
+
"loss": 1.617,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.032467532467532464,
|
49 |
+
"grad_norm": 0.3876812756061554,
|
50 |
+
"learning_rate": 5e-06,
|
51 |
+
"loss": 1.6561,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.03896103896103896,
|
56 |
+
"grad_norm": 0.41130709648132324,
|
57 |
+
"learning_rate": 6e-06,
|
58 |
+
"loss": 1.606,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.045454545454545456,
|
63 |
+
"grad_norm": 0.3654179573059082,
|
64 |
+
"learning_rate": 7e-06,
|
65 |
+
"loss": 1.605,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.05194805194805195,
|
70 |
+
"grad_norm": 0.35875341296195984,
|
71 |
+
"learning_rate": 8.000000000000001e-06,
|
72 |
+
"loss": 1.5651,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.05844155844155844,
|
77 |
+
"grad_norm": 0.3530851900577545,
|
78 |
+
"learning_rate": 9e-06,
|
79 |
+
"loss": 1.5201,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.06493506493506493,
|
84 |
+
"grad_norm": 0.38295701146125793,
|
85 |
+
"learning_rate": 1e-05,
|
86 |
+
"loss": 1.6376,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.07142857142857142,
|
91 |
+
"grad_norm": 0.39765068888664246,
|
92 |
+
"learning_rate": 9.999722154604716e-06,
|
93 |
+
"loss": 1.5167,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.07792207792207792,
|
98 |
+
"grad_norm": 0.44107645750045776,
|
99 |
+
"learning_rate": 9.99888864929809e-06,
|
100 |
+
"loss": 1.6259,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.08441558441558442,
|
105 |
+
"grad_norm": 0.4228634238243103,
|
106 |
+
"learning_rate": 9.997499576714369e-06,
|
107 |
+
"loss": 1.6767,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.09090909090909091,
|
112 |
+
"grad_norm": 0.4122574031352997,
|
113 |
+
"learning_rate": 9.995555091232516e-06,
|
114 |
+
"loss": 1.6082,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.09740259740259741,
|
119 |
+
"grad_norm": 0.43088310956954956,
|
120 |
+
"learning_rate": 9.99305540895907e-06,
|
121 |
+
"loss": 1.6651,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.1038961038961039,
|
126 |
+
"grad_norm": 0.4325619637966156,
|
127 |
+
"learning_rate": 9.990000807704114e-06,
|
128 |
+
"loss": 1.6473,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.11038961038961038,
|
133 |
+
"grad_norm": 0.4201916456222534,
|
134 |
+
"learning_rate": 9.986391626950405e-06,
|
135 |
+
"loss": 1.5726,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.11688311688311688,
|
140 |
+
"grad_norm": 0.4616028070449829,
|
141 |
+
"learning_rate": 9.982228267815644e-06,
|
142 |
+
"loss": 1.5994,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.12337662337662338,
|
147 |
+
"grad_norm": 0.4239194989204407,
|
148 |
+
"learning_rate": 9.977511193007896e-06,
|
149 |
+
"loss": 1.6018,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.12987012987012986,
|
154 |
+
"grad_norm": 0.41312310099601746,
|
155 |
+
"learning_rate": 9.972240926774167e-06,
|
156 |
+
"loss": 1.6497,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.13636363636363635,
|
161 |
+
"grad_norm": 0.45023512840270996,
|
162 |
+
"learning_rate": 9.966418054842143e-06,
|
163 |
+
"loss": 1.557,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.14285714285714285,
|
168 |
+
"grad_norm": 0.4155130982398987,
|
169 |
+
"learning_rate": 9.960043224355081e-06,
|
170 |
+
"loss": 1.5782,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.14935064935064934,
|
175 |
+
"grad_norm": 0.39791709184646606,
|
176 |
+
"learning_rate": 9.9531171437999e-06,
|
177 |
+
"loss": 1.548,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.15584415584415584,
|
182 |
+
"grad_norm": 0.40294748544692993,
|
183 |
+
"learning_rate": 9.945640582928438e-06,
|
184 |
+
"loss": 1.5745,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.16233766233766234,
|
189 |
+
"grad_norm": 0.3911401927471161,
|
190 |
+
"learning_rate": 9.937614372671896e-06,
|
191 |
+
"loss": 1.5653,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.16883116883116883,
|
196 |
+
"grad_norm": 0.407604843378067,
|
197 |
+
"learning_rate": 9.929039405048502e-06,
|
198 |
+
"loss": 1.5627,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.17532467532467533,
|
203 |
+
"grad_norm": 0.4176672697067261,
|
204 |
+
"learning_rate": 9.919916633064363e-06,
|
205 |
+
"loss": 1.5413,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.18181818181818182,
|
210 |
+
"grad_norm": 0.40910884737968445,
|
211 |
+
"learning_rate": 9.91024707060755e-06,
|
212 |
+
"loss": 1.5688,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.18831168831168832,
|
217 |
+
"grad_norm": 0.393100768327713,
|
218 |
+
"learning_rate": 9.900031792335432e-06,
|
219 |
+
"loss": 1.5259,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.19480519480519481,
|
224 |
+
"grad_norm": 0.39668065309524536,
|
225 |
+
"learning_rate": 9.889271933555214e-06,
|
226 |
+
"loss": 1.5471,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.2012987012987013,
|
231 |
+
"grad_norm": 0.37264811992645264,
|
232 |
+
"learning_rate": 9.877968690097785e-06,
|
233 |
+
"loss": 1.488,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.2077922077922078,
|
238 |
+
"grad_norm": 0.39069730043411255,
|
239 |
+
"learning_rate": 9.866123318184803e-06,
|
240 |
+
"loss": 1.5863,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.21428571428571427,
|
245 |
+
"grad_norm": 0.37075284123420715,
|
246 |
+
"learning_rate": 9.853737134289086e-06,
|
247 |
+
"loss": 1.4967,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.22077922077922077,
|
252 |
+
"grad_norm": 0.37381497025489807,
|
253 |
+
"learning_rate": 9.840811514988294e-06,
|
254 |
+
"loss": 1.4219,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.22727272727272727,
|
259 |
+
"grad_norm": 0.37528884410858154,
|
260 |
+
"learning_rate": 9.827347896811954e-06,
|
261 |
+
"loss": 1.4754,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.23376623376623376,
|
266 |
+
"grad_norm": 0.3899977505207062,
|
267 |
+
"learning_rate": 9.81334777608179e-06,
|
268 |
+
"loss": 1.5201,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.24025974025974026,
|
273 |
+
"grad_norm": 0.37340793013572693,
|
274 |
+
"learning_rate": 9.798812708745431e-06,
|
275 |
+
"loss": 1.4467,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.24675324675324675,
|
280 |
+
"grad_norm": 0.3682302236557007,
|
281 |
+
"learning_rate": 9.783744310203492e-06,
|
282 |
+
"loss": 1.3911,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.2532467532467532,
|
287 |
+
"grad_norm": 0.37759163975715637,
|
288 |
+
"learning_rate": 9.76814425513003e-06,
|
289 |
+
"loss": 1.4242,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.2532467532467532,
|
294 |
+
"eval_loss": 1.451162338256836,
|
295 |
+
"eval_runtime": 25.2272,
|
296 |
+
"eval_samples_per_second": 11.694,
|
297 |
+
"eval_steps_per_second": 1.467,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.2597402597402597,
|
302 |
+
"grad_norm": 0.3705059885978699,
|
303 |
+
"learning_rate": 9.752014277286433e-06,
|
304 |
+
"loss": 1.4542,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.2662337662337662,
|
309 |
+
"grad_norm": 0.34180477261543274,
|
310 |
+
"learning_rate": 9.73535616932873e-06,
|
311 |
+
"loss": 1.4108,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.2727272727272727,
|
316 |
+
"grad_norm": 0.34464818239212036,
|
317 |
+
"learning_rate": 9.718171782608355e-06,
|
318 |
+
"loss": 1.4691,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.2792207792207792,
|
323 |
+
"grad_norm": 0.37641096115112305,
|
324 |
+
"learning_rate": 9.7004630269664e-06,
|
325 |
+
"loss": 1.3784,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.2857142857142857,
|
330 |
+
"grad_norm": 0.335043340921402,
|
331 |
+
"learning_rate": 9.682231870521347e-06,
|
332 |
+
"loss": 1.4899,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.2922077922077922,
|
337 |
+
"grad_norm": 0.3437371551990509,
|
338 |
+
"learning_rate": 9.663480339450344e-06,
|
339 |
+
"loss": 1.4003,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.2987012987012987,
|
344 |
+
"grad_norm": 0.3729651868343353,
|
345 |
+
"learning_rate": 9.644210517764014e-06,
|
346 |
+
"loss": 1.3884,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.3051948051948052,
|
351 |
+
"grad_norm": 0.33896854519844055,
|
352 |
+
"learning_rate": 9.624424547074851e-06,
|
353 |
+
"loss": 1.4258,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.3116883116883117,
|
358 |
+
"grad_norm": 0.36020371317863464,
|
359 |
+
"learning_rate": 9.60412462635919e-06,
|
360 |
+
"loss": 1.3703,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.3181818181818182,
|
365 |
+
"grad_norm": 0.3405916392803192,
|
366 |
+
"learning_rate": 9.583313011712832e-06,
|
367 |
+
"loss": 1.3407,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.3246753246753247,
|
372 |
+
"grad_norm": 0.3447131812572479,
|
373 |
+
"learning_rate": 9.561992016100293e-06,
|
374 |
+
"loss": 1.3456,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.33116883116883117,
|
379 |
+
"grad_norm": 0.35361772775650024,
|
380 |
+
"learning_rate": 9.540164009097756e-06,
|
381 |
+
"loss": 1.3384,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.33766233766233766,
|
386 |
+
"grad_norm": 0.3525960147380829,
|
387 |
+
"learning_rate": 9.517831416629717e-06,
|
388 |
+
"loss": 1.3726,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.34415584415584416,
|
393 |
+
"grad_norm": 0.3269696831703186,
|
394 |
+
"learning_rate": 9.494996720699363e-06,
|
395 |
+
"loss": 1.3664,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.35064935064935066,
|
400 |
+
"grad_norm": 0.3153081238269806,
|
401 |
+
"learning_rate": 9.471662459112747e-06,
|
402 |
+
"loss": 1.3448,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.35714285714285715,
|
407 |
+
"grad_norm": 0.3017883002758026,
|
408 |
+
"learning_rate": 9.44783122519672e-06,
|
409 |
+
"loss": 1.3228,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.36363636363636365,
|
414 |
+
"grad_norm": 0.314627081155777,
|
415 |
+
"learning_rate": 9.423505667510724e-06,
|
416 |
+
"loss": 1.3565,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.37012987012987014,
|
421 |
+
"grad_norm": 0.3048722743988037,
|
422 |
+
"learning_rate": 9.398688489552437e-06,
|
423 |
+
"loss": 1.2669,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.37662337662337664,
|
428 |
+
"grad_norm": 0.3107397258281708,
|
429 |
+
"learning_rate": 9.373382449457305e-06,
|
430 |
+
"loss": 1.2871,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.38311688311688313,
|
435 |
+
"grad_norm": 0.3061436116695404,
|
436 |
+
"learning_rate": 9.347590359692015e-06,
|
437 |
+
"loss": 1.3015,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.38961038961038963,
|
442 |
+
"grad_norm": 0.31199324131011963,
|
443 |
+
"learning_rate": 9.321315086741916e-06,
|
444 |
+
"loss": 1.3196,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.3961038961038961,
|
449 |
+
"grad_norm": 0.3002881109714508,
|
450 |
+
"learning_rate": 9.294559550792451e-06,
|
451 |
+
"loss": 1.3404,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.4025974025974026,
|
456 |
+
"grad_norm": 0.2965368330478668,
|
457 |
+
"learning_rate": 9.2673267254046e-06,
|
458 |
+
"loss": 1.2931,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.4090909090909091,
|
463 |
+
"grad_norm": 0.2912820279598236,
|
464 |
+
"learning_rate": 9.23961963718442e-06,
|
465 |
+
"loss": 1.2941,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.4155844155844156,
|
470 |
+
"grad_norm": 0.29220762848854065,
|
471 |
+
"learning_rate": 9.211441365446661e-06,
|
472 |
+
"loss": 1.306,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.42207792207792205,
|
477 |
+
"grad_norm": 0.2802380323410034,
|
478 |
+
"learning_rate": 9.182795041872543e-06,
|
479 |
+
"loss": 1.2641,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.42857142857142855,
|
484 |
+
"grad_norm": 0.28170621395111084,
|
485 |
+
"learning_rate": 9.153683850161706e-06,
|
486 |
+
"loss": 1.2459,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.43506493506493504,
|
491 |
+
"grad_norm": 0.2919502854347229,
|
492 |
+
"learning_rate": 9.124111025678378e-06,
|
493 |
+
"loss": 1.2736,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.44155844155844154,
|
498 |
+
"grad_norm": 0.2793984115123749,
|
499 |
+
"learning_rate": 9.094079855091797e-06,
|
500 |
+
"loss": 1.265,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.44805194805194803,
|
505 |
+
"grad_norm": 0.2946363091468811,
|
506 |
+
"learning_rate": 9.063593676010954e-06,
|
507 |
+
"loss": 1.2669,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.45454545454545453,
|
512 |
+
"grad_norm": 0.2771857678890228,
|
513 |
+
"learning_rate": 9.032655876613636e-06,
|
514 |
+
"loss": 1.2479,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.461038961038961,
|
519 |
+
"grad_norm": 0.26628848910331726,
|
520 |
+
"learning_rate": 9.001269895269886e-06,
|
521 |
+
"loss": 1.2764,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.4675324675324675,
|
526 |
+
"grad_norm": 0.3006434440612793,
|
527 |
+
"learning_rate": 8.969439220159861e-06,
|
528 |
+
"loss": 1.2286,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.474025974025974,
|
533 |
+
"grad_norm": 0.27274397015571594,
|
534 |
+
"learning_rate": 8.937167388886163e-06,
|
535 |
+
"loss": 1.3059,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.4805194805194805,
|
540 |
+
"grad_norm": 0.2763414978981018,
|
541 |
+
"learning_rate": 8.904457988080682e-06,
|
542 |
+
"loss": 1.2095,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.487012987012987,
|
547 |
+
"grad_norm": 0.28402575850486755,
|
548 |
+
"learning_rate": 8.871314653005972e-06,
|
549 |
+
"loss": 1.2601,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.4935064935064935,
|
554 |
+
"grad_norm": 0.2892557680606842,
|
555 |
+
"learning_rate": 8.837741067151251e-06,
|
556 |
+
"loss": 1.2342,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.5,
|
561 |
+
"grad_norm": 0.2644696533679962,
|
562 |
+
"learning_rate": 8.80374096182301e-06,
|
563 |
+
"loss": 1.2744,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.5064935064935064,
|
568 |
+
"grad_norm": 0.25198492407798767,
|
569 |
+
"learning_rate": 8.76931811573033e-06,
|
570 |
+
"loss": 1.2885,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.5064935064935064,
|
575 |
+
"eval_loss": 1.2617864608764648,
|
576 |
+
"eval_runtime": 25.3815,
|
577 |
+
"eval_samples_per_second": 11.623,
|
578 |
+
"eval_steps_per_second": 1.458,
|
579 |
+
"step": 78
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.512987012987013,
|
583 |
+
"grad_norm": 0.2804642915725708,
|
584 |
+
"learning_rate": 8.734476354564924e-06,
|
585 |
+
"loss": 1.2583,
|
586 |
+
"step": 79
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.5194805194805194,
|
590 |
+
"grad_norm": 0.2729627788066864,
|
591 |
+
"learning_rate": 8.699219550575954e-06,
|
592 |
+
"loss": 1.2246,
|
593 |
+
"step": 80
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.525974025974026,
|
597 |
+
"grad_norm": 0.2520177662372589,
|
598 |
+
"learning_rate": 8.663551622139674e-06,
|
599 |
+
"loss": 1.2599,
|
600 |
+
"step": 81
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.5324675324675324,
|
604 |
+
"grad_norm": 0.2614675760269165,
|
605 |
+
"learning_rate": 8.627476533323957e-06,
|
606 |
+
"loss": 1.2165,
|
607 |
+
"step": 82
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.538961038961039,
|
611 |
+
"grad_norm": 0.3191888928413391,
|
612 |
+
"learning_rate": 8.590998293447728e-06,
|
613 |
+
"loss": 1.2558,
|
614 |
+
"step": 83
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.5454545454545454,
|
618 |
+
"grad_norm": 0.27159151434898376,
|
619 |
+
"learning_rate": 8.554120956635375e-06,
|
620 |
+
"loss": 1.2197,
|
621 |
+
"step": 84
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.551948051948052,
|
625 |
+
"grad_norm": 0.291990727186203,
|
626 |
+
"learning_rate": 8.516848621366188e-06,
|
627 |
+
"loss": 1.219,
|
628 |
+
"step": 85
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.5584415584415584,
|
632 |
+
"grad_norm": 0.23849813640117645,
|
633 |
+
"learning_rate": 8.47918543001886e-06,
|
634 |
+
"loss": 1.2199,
|
635 |
+
"step": 86
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.564935064935065,
|
639 |
+
"grad_norm": 0.26883506774902344,
|
640 |
+
"learning_rate": 8.441135568411102e-06,
|
641 |
+
"loss": 1.1959,
|
642 |
+
"step": 87
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.5714285714285714,
|
646 |
+
"grad_norm": 0.2667544484138489,
|
647 |
+
"learning_rate": 8.402703265334455e-06,
|
648 |
+
"loss": 1.2682,
|
649 |
+
"step": 88
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.577922077922078,
|
653 |
+
"grad_norm": 0.24013420939445496,
|
654 |
+
"learning_rate": 8.363892792084291e-06,
|
655 |
+
"loss": 1.1649,
|
656 |
+
"step": 89
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.5844155844155844,
|
660 |
+
"grad_norm": 0.2544495463371277,
|
661 |
+
"learning_rate": 8.324708461985124e-06,
|
662 |
+
"loss": 1.1929,
|
663 |
+
"step": 90
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.5909090909090909,
|
667 |
+
"grad_norm": 0.2654297351837158,
|
668 |
+
"learning_rate": 8.285154629911227e-06,
|
669 |
+
"loss": 1.18,
|
670 |
+
"step": 91
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 0.5974025974025974,
|
674 |
+
"grad_norm": 0.26719850301742554,
|
675 |
+
"learning_rate": 8.245235691802644e-06,
|
676 |
+
"loss": 1.2933,
|
677 |
+
"step": 92
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.6038961038961039,
|
681 |
+
"grad_norm": 0.2760712802410126,
|
682 |
+
"learning_rate": 8.20495608417663e-06,
|
683 |
+
"loss": 1.1612,
|
684 |
+
"step": 93
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.6103896103896104,
|
688 |
+
"grad_norm": 0.2652733623981476,
|
689 |
+
"learning_rate": 8.164320283634585e-06,
|
690 |
+
"loss": 1.2125,
|
691 |
+
"step": 94
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.6168831168831169,
|
695 |
+
"grad_norm": 0.24604123830795288,
|
696 |
+
"learning_rate": 8.123332806364537e-06,
|
697 |
+
"loss": 1.1801,
|
698 |
+
"step": 95
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.6233766233766234,
|
702 |
+
"grad_norm": 0.23077791929244995,
|
703 |
+
"learning_rate": 8.081998207639212e-06,
|
704 |
+
"loss": 1.2016,
|
705 |
+
"step": 96
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.6298701298701299,
|
709 |
+
"grad_norm": 0.25489139556884766,
|
710 |
+
"learning_rate": 8.040321081309783e-06,
|
711 |
+
"loss": 1.2049,
|
712 |
+
"step": 97
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.6363636363636364,
|
716 |
+
"grad_norm": 0.2564036250114441,
|
717 |
+
"learning_rate": 7.998306059295302e-06,
|
718 |
+
"loss": 1.2377,
|
719 |
+
"step": 98
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.6428571428571429,
|
723 |
+
"grad_norm": 0.2734230160713196,
|
724 |
+
"learning_rate": 7.955957811067932e-06,
|
725 |
+
"loss": 1.1107,
|
726 |
+
"step": 99
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.6493506493506493,
|
730 |
+
"grad_norm": 0.2672719359397888,
|
731 |
+
"learning_rate": 7.913281043133978e-06,
|
732 |
+
"loss": 1.1863,
|
733 |
+
"step": 100
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.6558441558441559,
|
737 |
+
"grad_norm": 0.263724684715271,
|
738 |
+
"learning_rate": 7.870280498510824e-06,
|
739 |
+
"loss": 1.2678,
|
740 |
+
"step": 101
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.6623376623376623,
|
744 |
+
"grad_norm": 0.27098724246025085,
|
745 |
+
"learning_rate": 7.826960956199796e-06,
|
746 |
+
"loss": 1.1656,
|
747 |
+
"step": 102
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.6688311688311688,
|
751 |
+
"grad_norm": 0.29257479310035706,
|
752 |
+
"learning_rate": 7.783327230655036e-06,
|
753 |
+
"loss": 1.1749,
|
754 |
+
"step": 103
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.6753246753246753,
|
758 |
+
"grad_norm": 0.26874226331710815,
|
759 |
+
"learning_rate": 7.739384171248436e-06,
|
760 |
+
"loss": 1.2013,
|
761 |
+
"step": 104
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.6818181818181818,
|
765 |
+
"grad_norm": 0.26934632658958435,
|
766 |
+
"learning_rate": 7.695136661730677e-06,
|
767 |
+
"loss": 1.1507,
|
768 |
+
"step": 105
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.6883116883116883,
|
772 |
+
"grad_norm": 0.27807483077049255,
|
773 |
+
"learning_rate": 7.650589619688468e-06,
|
774 |
+
"loss": 1.1729,
|
775 |
+
"step": 106
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.6948051948051948,
|
779 |
+
"grad_norm": 0.2936646342277527,
|
780 |
+
"learning_rate": 7.6057479959980145e-06,
|
781 |
+
"loss": 1.1646,
|
782 |
+
"step": 107
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.7012987012987013,
|
786 |
+
"grad_norm": 0.28149378299713135,
|
787 |
+
"learning_rate": 7.560616774274775e-06,
|
788 |
+
"loss": 1.1939,
|
789 |
+
"step": 108
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.7077922077922078,
|
793 |
+
"grad_norm": 0.25706660747528076,
|
794 |
+
"learning_rate": 7.5152009703196105e-06,
|
795 |
+
"loss": 1.1708,
|
796 |
+
"step": 109
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.7142857142857143,
|
800 |
+
"grad_norm": 0.29964110255241394,
|
801 |
+
"learning_rate": 7.469505631561318e-06,
|
802 |
+
"loss": 1.2161,
|
803 |
+
"step": 110
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.7207792207792207,
|
807 |
+
"grad_norm": 0.24933487176895142,
|
808 |
+
"learning_rate": 7.423535836495683e-06,
|
809 |
+
"loss": 1.1641,
|
810 |
+
"step": 111
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.7272727272727273,
|
814 |
+
"grad_norm": 0.27039459347724915,
|
815 |
+
"learning_rate": 7.3772966941210585e-06,
|
816 |
+
"loss": 1.1563,
|
817 |
+
"step": 112
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.7337662337662337,
|
821 |
+
"grad_norm": 0.2490512579679489,
|
822 |
+
"learning_rate": 7.33079334337056e-06,
|
823 |
+
"loss": 1.1887,
|
824 |
+
"step": 113
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.7402597402597403,
|
828 |
+
"grad_norm": 0.28315550088882446,
|
829 |
+
"learning_rate": 7.284030952540937e-06,
|
830 |
+
"loss": 1.1189,
|
831 |
+
"step": 114
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.7467532467532467,
|
835 |
+
"grad_norm": 0.2557179033756256,
|
836 |
+
"learning_rate": 7.2370147187181736e-06,
|
837 |
+
"loss": 1.1812,
|
838 |
+
"step": 115
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 0.7532467532467533,
|
842 |
+
"grad_norm": 0.2875461280345917,
|
843 |
+
"learning_rate": 7.189749867199899e-06,
|
844 |
+
"loss": 1.1534,
|
845 |
+
"step": 116
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.7597402597402597,
|
849 |
+
"grad_norm": 0.26117077469825745,
|
850 |
+
"learning_rate": 7.142241650914654e-06,
|
851 |
+
"loss": 1.1618,
|
852 |
+
"step": 117
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.7597402597402597,
|
856 |
+
"eval_loss": 1.2008626461029053,
|
857 |
+
"eval_runtime": 25.2533,
|
858 |
+
"eval_samples_per_second": 11.682,
|
859 |
+
"eval_steps_per_second": 1.465,
|
860 |
+
"step": 117
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.7662337662337663,
|
864 |
+
"grad_norm": 0.29663676023483276,
|
865 |
+
"learning_rate": 7.094495349838093e-06,
|
866 |
+
"loss": 1.1064,
|
867 |
+
"step": 118
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.7727272727272727,
|
871 |
+
"grad_norm": 0.23107394576072693,
|
872 |
+
"learning_rate": 7.046516270406174e-06,
|
873 |
+
"loss": 1.1464,
|
874 |
+
"step": 119
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.7792207792207793,
|
878 |
+
"grad_norm": 0.2502164840698242,
|
879 |
+
"learning_rate": 6.998309744925411e-06,
|
880 |
+
"loss": 1.1998,
|
881 |
+
"step": 120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.7857142857142857,
|
885 |
+
"grad_norm": 0.25331148505210876,
|
886 |
+
"learning_rate": 6.9498811309802595e-06,
|
887 |
+
"loss": 1.1784,
|
888 |
+
"step": 121
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.7922077922077922,
|
892 |
+
"grad_norm": 0.2596096694469452,
|
893 |
+
"learning_rate": 6.901235810837668e-06,
|
894 |
+
"loss": 1.1034,
|
895 |
+
"step": 122
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.7987012987012987,
|
899 |
+
"grad_norm": 0.26797452569007874,
|
900 |
+
"learning_rate": 6.852379190848923e-06,
|
901 |
+
"loss": 1.1264,
|
902 |
+
"step": 123
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.8051948051948052,
|
906 |
+
"grad_norm": 0.31169766187667847,
|
907 |
+
"learning_rate": 6.8033167008487784e-06,
|
908 |
+
"loss": 1.1386,
|
909 |
+
"step": 124
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.8116883116883117,
|
913 |
+
"grad_norm": 0.26767072081565857,
|
914 |
+
"learning_rate": 6.754053793552005e-06,
|
915 |
+
"loss": 1.2137,
|
916 |
+
"step": 125
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.8181818181818182,
|
920 |
+
"grad_norm": 0.2596385180950165,
|
921 |
+
"learning_rate": 6.704595943947385e-06,
|
922 |
+
"loss": 1.1466,
|
923 |
+
"step": 126
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.8246753246753247,
|
927 |
+
"grad_norm": 0.27891236543655396,
|
928 |
+
"learning_rate": 6.654948648689228e-06,
|
929 |
+
"loss": 1.1371,
|
930 |
+
"step": 127
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.8311688311688312,
|
934 |
+
"grad_norm": 0.28439176082611084,
|
935 |
+
"learning_rate": 6.605117425486483e-06,
|
936 |
+
"loss": 1.1948,
|
937 |
+
"step": 128
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 0.8376623376623377,
|
941 |
+
"grad_norm": 0.2944129705429077,
|
942 |
+
"learning_rate": 6.555107812489513e-06,
|
943 |
+
"loss": 1.1169,
|
944 |
+
"step": 129
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.8441558441558441,
|
948 |
+
"grad_norm": 0.2609187960624695,
|
949 |
+
"learning_rate": 6.504925367674595e-06,
|
950 |
+
"loss": 1.1503,
|
951 |
+
"step": 130
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.8506493506493507,
|
955 |
+
"grad_norm": 0.27614086866378784,
|
956 |
+
"learning_rate": 6.454575668226215e-06,
|
957 |
+
"loss": 1.1835,
|
958 |
+
"step": 131
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.8571428571428571,
|
962 |
+
"grad_norm": 0.2971368134021759,
|
963 |
+
"learning_rate": 6.40406430991723e-06,
|
964 |
+
"loss": 1.1816,
|
965 |
+
"step": 132
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.8636363636363636,
|
969 |
+
"grad_norm": 0.28436651825904846,
|
970 |
+
"learning_rate": 6.353396906486971e-06,
|
971 |
+
"loss": 1.1947,
|
972 |
+
"step": 133
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.8701298701298701,
|
976 |
+
"grad_norm": 0.2339404821395874,
|
977 |
+
"learning_rate": 6.302579089017328e-06,
|
978 |
+
"loss": 1.1027,
|
979 |
+
"step": 134
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.8766233766233766,
|
983 |
+
"grad_norm": 0.27757248282432556,
|
984 |
+
"learning_rate": 6.251616505306933e-06,
|
985 |
+
"loss": 1.1294,
|
986 |
+
"step": 135
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.8831168831168831,
|
990 |
+
"grad_norm": 0.27656033635139465,
|
991 |
+
"learning_rate": 6.200514819243476e-06,
|
992 |
+
"loss": 1.1313,
|
993 |
+
"step": 136
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.8896103896103896,
|
997 |
+
"grad_norm": 0.26819008588790894,
|
998 |
+
"learning_rate": 6.149279710174219e-06,
|
999 |
+
"loss": 1.2036,
|
1000 |
+
"step": 137
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.8961038961038961,
|
1004 |
+
"grad_norm": 0.3008396029472351,
|
1005 |
+
"learning_rate": 6.097916872274815e-06,
|
1006 |
+
"loss": 1.1512,
|
1007 |
+
"step": 138
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 0.9025974025974026,
|
1011 |
+
"grad_norm": 0.29651182889938354,
|
1012 |
+
"learning_rate": 6.046432013916467e-06,
|
1013 |
+
"loss": 1.1412,
|
1014 |
+
"step": 139
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.9090909090909091,
|
1018 |
+
"grad_norm": 0.275259405374527,
|
1019 |
+
"learning_rate": 5.9948308570315e-06,
|
1020 |
+
"loss": 1.1726,
|
1021 |
+
"step": 140
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.9155844155844156,
|
1025 |
+
"grad_norm": 0.26858457922935486,
|
1026 |
+
"learning_rate": 5.943119136477449e-06,
|
1027 |
+
"loss": 1.1701,
|
1028 |
+
"step": 141
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.922077922077922,
|
1032 |
+
"grad_norm": 0.273671954870224,
|
1033 |
+
"learning_rate": 5.891302599399686e-06,
|
1034 |
+
"loss": 1.165,
|
1035 |
+
"step": 142
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.9285714285714286,
|
1039 |
+
"grad_norm": 0.26044774055480957,
|
1040 |
+
"learning_rate": 5.839387004592705e-06,
|
1041 |
+
"loss": 1.1119,
|
1042 |
+
"step": 143
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.935064935064935,
|
1046 |
+
"grad_norm": 0.24865947663784027,
|
1047 |
+
"learning_rate": 5.78737812186009e-06,
|
1048 |
+
"loss": 1.1598,
|
1049 |
+
"step": 144
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.9415584415584416,
|
1053 |
+
"grad_norm": 0.2713409960269928,
|
1054 |
+
"learning_rate": 5.735281731373271e-06,
|
1055 |
+
"loss": 1.1543,
|
1056 |
+
"step": 145
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.948051948051948,
|
1060 |
+
"grad_norm": 0.2865453362464905,
|
1061 |
+
"learning_rate": 5.6831036230291345e-06,
|
1062 |
+
"loss": 1.1379,
|
1063 |
+
"step": 146
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.9545454545454546,
|
1067 |
+
"grad_norm": 0.26891422271728516,
|
1068 |
+
"learning_rate": 5.630849595806534e-06,
|
1069 |
+
"loss": 1.1382,
|
1070 |
+
"step": 147
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.961038961038961,
|
1074 |
+
"grad_norm": 0.3001209795475006,
|
1075 |
+
"learning_rate": 5.578525457121807e-06,
|
1076 |
+
"loss": 1.1674,
|
1077 |
+
"step": 148
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.9675324675324676,
|
1081 |
+
"grad_norm": 0.2672886848449707,
|
1082 |
+
"learning_rate": 5.526137022183356e-06,
|
1083 |
+
"loss": 1.1209,
|
1084 |
+
"step": 149
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.974025974025974,
|
1088 |
+
"grad_norm": 0.27608615159988403,
|
1089 |
+
"learning_rate": 5.473690113345343e-06,
|
1090 |
+
"loss": 1.1855,
|
1091 |
+
"step": 150
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.9805194805194806,
|
1095 |
+
"grad_norm": 0.2823050618171692,
|
1096 |
+
"learning_rate": 5.4211905594606165e-06,
|
1097 |
+
"loss": 1.1433,
|
1098 |
+
"step": 151
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.987012987012987,
|
1102 |
+
"grad_norm": 0.2888166308403015,
|
1103 |
+
"learning_rate": 5.368644195232896e-06,
|
1104 |
+
"loss": 1.1413,
|
1105 |
+
"step": 152
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.9935064935064936,
|
1109 |
+
"grad_norm": 0.2720174193382263,
|
1110 |
+
"learning_rate": 5.316056860568318e-06,
|
1111 |
+
"loss": 1.1657,
|
1112 |
+
"step": 153
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 1.0,
|
1116 |
+
"grad_norm": 0.28704148530960083,
|
1117 |
+
"learning_rate": 5.2634343999263985e-06,
|
1118 |
+
"loss": 1.1606,
|
1119 |
+
"step": 154
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.0064935064935066,
|
1123 |
+
"grad_norm": 0.2424069494009018,
|
1124 |
+
"learning_rate": 5.210782661670486e-06,
|
1125 |
+
"loss": 1.1506,
|
1126 |
+
"step": 155
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 1.0129870129870129,
|
1130 |
+
"grad_norm": 0.2754787802696228,
|
1131 |
+
"learning_rate": 5.158107497417795e-06,
|
1132 |
+
"loss": 1.1186,
|
1133 |
+
"step": 156
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 1.0129870129870129,
|
1137 |
+
"eval_loss": 1.1744325160980225,
|
1138 |
+
"eval_runtime": 25.2167,
|
1139 |
+
"eval_samples_per_second": 11.699,
|
1140 |
+
"eval_steps_per_second": 1.467,
|
1141 |
+
"step": 156
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 1.0194805194805194,
|
1145 |
+
"grad_norm": 0.2637002170085907,
|
1146 |
+
"learning_rate": 5.105414761389056e-06,
|
1147 |
+
"loss": 1.178,
|
1148 |
+
"step": 157
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 1.025974025974026,
|
1152 |
+
"grad_norm": 0.26754647493362427,
|
1153 |
+
"learning_rate": 5.052710309757899e-06,
|
1154 |
+
"loss": 1.1329,
|
1155 |
+
"step": 158
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 1.0064935064935066,
|
1159 |
+
"grad_norm": 0.2765344977378845,
|
1160 |
+
"learning_rate": 5e-06,
|
1161 |
+
"loss": 1.0933,
|
1162 |
+
"step": 159
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 1.0129870129870129,
|
1166 |
+
"grad_norm": 0.2661243677139282,
|
1167 |
+
"learning_rate": 4.947289690242103e-06,
|
1168 |
+
"loss": 1.0931,
|
1169 |
+
"step": 160
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 1.0194805194805194,
|
1173 |
+
"grad_norm": 0.2913898527622223,
|
1174 |
+
"learning_rate": 4.894585238610946e-06,
|
1175 |
+
"loss": 1.0963,
|
1176 |
+
"step": 161
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 1.025974025974026,
|
1180 |
+
"grad_norm": 0.2579714357852936,
|
1181 |
+
"learning_rate": 4.841892502582206e-06,
|
1182 |
+
"loss": 1.1984,
|
1183 |
+
"step": 162
|
1184 |
+
},
|
1185 |
+
{
|
1186 |
+
"epoch": 1.0324675324675325,
|
1187 |
+
"grad_norm": 0.2802336513996124,
|
1188 |
+
"learning_rate": 4.789217338329515e-06,
|
1189 |
+
"loss": 1.1592,
|
1190 |
+
"step": 163
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 1.0389610389610389,
|
1194 |
+
"grad_norm": 0.27885061502456665,
|
1195 |
+
"learning_rate": 4.736565600073602e-06,
|
1196 |
+
"loss": 1.1184,
|
1197 |
+
"step": 164
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.0454545454545454,
|
1201 |
+
"grad_norm": 0.26521897315979004,
|
1202 |
+
"learning_rate": 4.683943139431683e-06,
|
1203 |
+
"loss": 1.1685,
|
1204 |
+
"step": 165
|
1205 |
+
},
|
1206 |
+
{
|
1207 |
+
"epoch": 1.051948051948052,
|
1208 |
+
"grad_norm": 0.30475732684135437,
|
1209 |
+
"learning_rate": 4.631355804767106e-06,
|
1210 |
+
"loss": 1.105,
|
1211 |
+
"step": 166
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"epoch": 1.0584415584415585,
|
1215 |
+
"grad_norm": 0.2804529070854187,
|
1216 |
+
"learning_rate": 4.578809440539386e-06,
|
1217 |
+
"loss": 1.0735,
|
1218 |
+
"step": 167
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 1.0649350649350648,
|
1222 |
+
"grad_norm": 0.2721943259239197,
|
1223 |
+
"learning_rate": 4.526309886654659e-06,
|
1224 |
+
"loss": 1.187,
|
1225 |
+
"step": 168
|
1226 |
+
},
|
1227 |
+
{
|
1228 |
+
"epoch": 1.0714285714285714,
|
1229 |
+
"grad_norm": 0.2899441421031952,
|
1230 |
+
"learning_rate": 4.473862977816647e-06,
|
1231 |
+
"loss": 1.1375,
|
1232 |
+
"step": 169
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 1.077922077922078,
|
1236 |
+
"grad_norm": 0.27229487895965576,
|
1237 |
+
"learning_rate": 4.4214745428781946e-06,
|
1238 |
+
"loss": 1.1079,
|
1239 |
+
"step": 170
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.0844155844155845,
|
1243 |
+
"grad_norm": 0.28253939747810364,
|
1244 |
+
"learning_rate": 4.369150404193467e-06,
|
1245 |
+
"loss": 1.1283,
|
1246 |
+
"step": 171
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 1.0909090909090908,
|
1250 |
+
"grad_norm": 0.31305843591690063,
|
1251 |
+
"learning_rate": 4.316896376970866e-06,
|
1252 |
+
"loss": 1.1576,
|
1253 |
+
"step": 172
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 1.0974025974025974,
|
1257 |
+
"grad_norm": 0.26900458335876465,
|
1258 |
+
"learning_rate": 4.264718268626729e-06,
|
1259 |
+
"loss": 1.1694,
|
1260 |
+
"step": 173
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 1.103896103896104,
|
1264 |
+
"grad_norm": 0.27618759870529175,
|
1265 |
+
"learning_rate": 4.212621878139912e-06,
|
1266 |
+
"loss": 1.0882,
|
1267 |
+
"step": 174
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 1.1103896103896105,
|
1271 |
+
"grad_norm": 0.3342863619327545,
|
1272 |
+
"learning_rate": 4.160612995407296e-06,
|
1273 |
+
"loss": 1.1103,
|
1274 |
+
"step": 175
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 1.1168831168831168,
|
1278 |
+
"grad_norm": 0.3191912770271301,
|
1279 |
+
"learning_rate": 4.108697400600316e-06,
|
1280 |
+
"loss": 1.1528,
|
1281 |
+
"step": 176
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.1233766233766234,
|
1285 |
+
"grad_norm": 0.28136956691741943,
|
1286 |
+
"learning_rate": 4.056880863522553e-06,
|
1287 |
+
"loss": 1.1239,
|
1288 |
+
"step": 177
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 1.12987012987013,
|
1292 |
+
"grad_norm": 0.3044598400592804,
|
1293 |
+
"learning_rate": 4.005169142968503e-06,
|
1294 |
+
"loss": 1.1396,
|
1295 |
+
"step": 178
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 1.1363636363636362,
|
1299 |
+
"grad_norm": 0.26966431736946106,
|
1300 |
+
"learning_rate": 3.953567986083535e-06,
|
1301 |
+
"loss": 1.1166,
|
1302 |
+
"step": 179
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 1.1428571428571428,
|
1306 |
+
"grad_norm": 0.2642230689525604,
|
1307 |
+
"learning_rate": 3.902083127725186e-06,
|
1308 |
+
"loss": 1.1156,
|
1309 |
+
"step": 180
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 1.1493506493506493,
|
1313 |
+
"grad_norm": 0.27723589539527893,
|
1314 |
+
"learning_rate": 3.850720289825783e-06,
|
1315 |
+
"loss": 1.106,
|
1316 |
+
"step": 181
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 1.155844155844156,
|
1320 |
+
"grad_norm": 0.25195732712745667,
|
1321 |
+
"learning_rate": 3.799485180756526e-06,
|
1322 |
+
"loss": 1.1473,
|
1323 |
+
"step": 182
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.1623376623376624,
|
1327 |
+
"grad_norm": 0.2634832561016083,
|
1328 |
+
"learning_rate": 3.7483834946930682e-06,
|
1329 |
+
"loss": 1.12,
|
1330 |
+
"step": 183
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 1.1688311688311688,
|
1334 |
+
"grad_norm": 0.2719174027442932,
|
1335 |
+
"learning_rate": 3.6974209109826724e-06,
|
1336 |
+
"loss": 1.1379,
|
1337 |
+
"step": 184
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 1.1753246753246753,
|
1341 |
+
"grad_norm": 0.2815384566783905,
|
1342 |
+
"learning_rate": 3.64660309351303e-06,
|
1343 |
+
"loss": 1.1548,
|
1344 |
+
"step": 185
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 1.1818181818181819,
|
1348 |
+
"grad_norm": 0.2685678005218506,
|
1349 |
+
"learning_rate": 3.595935690082769e-06,
|
1350 |
+
"loss": 1.1321,
|
1351 |
+
"step": 186
|
1352 |
+
},
|
1353 |
+
{
|
1354 |
+
"epoch": 1.1883116883116882,
|
1355 |
+
"grad_norm": 0.282886803150177,
|
1356 |
+
"learning_rate": 3.545424331773787e-06,
|
1357 |
+
"loss": 1.159,
|
1358 |
+
"step": 187
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 1.1948051948051948,
|
1362 |
+
"grad_norm": 0.2961716055870056,
|
1363 |
+
"learning_rate": 3.495074632325407e-06,
|
1364 |
+
"loss": 1.0941,
|
1365 |
+
"step": 188
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 1.2012987012987013,
|
1369 |
+
"grad_norm": 0.26541033387184143,
|
1370 |
+
"learning_rate": 3.4448921875104898e-06,
|
1371 |
+
"loss": 1.1487,
|
1372 |
+
"step": 189
|
1373 |
+
},
|
1374 |
+
{
|
1375 |
+
"epoch": 1.2077922077922079,
|
1376 |
+
"grad_norm": 0.3059718608856201,
|
1377 |
+
"learning_rate": 3.3948825745135196e-06,
|
1378 |
+
"loss": 1.1529,
|
1379 |
+
"step": 190
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 1.2142857142857142,
|
1383 |
+
"grad_norm": 0.2965088486671448,
|
1384 |
+
"learning_rate": 3.345051351310774e-06,
|
1385 |
+
"loss": 1.0652,
|
1386 |
+
"step": 191
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 1.2207792207792207,
|
1390 |
+
"grad_norm": 0.2668808102607727,
|
1391 |
+
"learning_rate": 3.295404056052616e-06,
|
1392 |
+
"loss": 1.1231,
|
1393 |
+
"step": 192
|
1394 |
+
},
|
1395 |
+
{
|
1396 |
+
"epoch": 1.2272727272727273,
|
1397 |
+
"grad_norm": 0.2890554666519165,
|
1398 |
+
"learning_rate": 3.2459462064479972e-06,
|
1399 |
+
"loss": 1.15,
|
1400 |
+
"step": 193
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 1.2337662337662338,
|
1404 |
+
"grad_norm": 0.25789421796798706,
|
1405 |
+
"learning_rate": 3.1966832991512232e-06,
|
1406 |
+
"loss": 1.1434,
|
1407 |
+
"step": 194
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 1.2402597402597402,
|
1411 |
+
"grad_norm": 0.28866487741470337,
|
1412 |
+
"learning_rate": 3.147620809151078e-06,
|
1413 |
+
"loss": 1.1237,
|
1414 |
+
"step": 195
|
1415 |
+
},
|
1416 |
+
{
|
1417 |
+
"epoch": 1.2402597402597402,
|
1418 |
+
"eval_loss": 1.1614325046539307,
|
1419 |
+
"eval_runtime": 25.3147,
|
1420 |
+
"eval_samples_per_second": 11.653,
|
1421 |
+
"eval_steps_per_second": 1.462,
|
1422 |
+
"step": 195
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 1.2467532467532467,
|
1426 |
+
"grad_norm": 0.26898378133773804,
|
1427 |
+
"learning_rate": 3.098764189162332e-06,
|
1428 |
+
"loss": 1.1265,
|
1429 |
+
"step": 196
|
1430 |
+
},
|
1431 |
+
{
|
1432 |
+
"epoch": 1.2532467532467533,
|
1433 |
+
"grad_norm": 0.2718038260936737,
|
1434 |
+
"learning_rate": 3.0501188690197418e-06,
|
1435 |
+
"loss": 1.1012,
|
1436 |
+
"step": 197
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 1.2597402597402598,
|
1440 |
+
"grad_norm": 0.27878862619400024,
|
1441 |
+
"learning_rate": 3.0016902550745896e-06,
|
1442 |
+
"loss": 1.1454,
|
1443 |
+
"step": 198
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 1.2662337662337662,
|
1447 |
+
"grad_norm": 0.28224632143974304,
|
1448 |
+
"learning_rate": 2.9534837295938268e-06,
|
1449 |
+
"loss": 1.1561,
|
1450 |
+
"step": 199
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 1.2727272727272727,
|
1454 |
+
"grad_norm": 0.2997869849205017,
|
1455 |
+
"learning_rate": 2.9055046501619088e-06,
|
1456 |
+
"loss": 1.1408,
|
1457 |
+
"step": 200
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 1.2792207792207793,
|
1461 |
+
"grad_norm": 0.29859447479248047,
|
1462 |
+
"learning_rate": 2.857758349085348e-06,
|
1463 |
+
"loss": 1.1105,
|
1464 |
+
"step": 201
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 1.2857142857142856,
|
1468 |
+
"grad_norm": 0.2930034101009369,
|
1469 |
+
"learning_rate": 2.810250132800103e-06,
|
1470 |
+
"loss": 1.1113,
|
1471 |
+
"step": 202
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 1.2922077922077921,
|
1475 |
+
"grad_norm": 0.29845744371414185,
|
1476 |
+
"learning_rate": 2.762985281281828e-06,
|
1477 |
+
"loss": 1.1702,
|
1478 |
+
"step": 203
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 1.2987012987012987,
|
1482 |
+
"grad_norm": 0.27331170439720154,
|
1483 |
+
"learning_rate": 2.715969047459066e-06,
|
1484 |
+
"loss": 1.1197,
|
1485 |
+
"step": 204
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 1.3051948051948052,
|
1489 |
+
"grad_norm": 0.31652095913887024,
|
1490 |
+
"learning_rate": 2.6692066566294393e-06,
|
1491 |
+
"loss": 1.1422,
|
1492 |
+
"step": 205
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 1.3116883116883118,
|
1496 |
+
"grad_norm": 0.3164924383163452,
|
1497 |
+
"learning_rate": 2.622703305878941e-06,
|
1498 |
+
"loss": 1.1179,
|
1499 |
+
"step": 206
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 1.3181818181818181,
|
1503 |
+
"grad_norm": 0.25467604398727417,
|
1504 |
+
"learning_rate": 2.5764641635043174e-06,
|
1505 |
+
"loss": 1.0839,
|
1506 |
+
"step": 207
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 1.3246753246753247,
|
1510 |
+
"grad_norm": 0.2731601297855377,
|
1511 |
+
"learning_rate": 2.530494368438683e-06,
|
1512 |
+
"loss": 1.1033,
|
1513 |
+
"step": 208
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 1.3311688311688312,
|
1517 |
+
"grad_norm": 0.2869837284088135,
|
1518 |
+
"learning_rate": 2.4847990296803907e-06,
|
1519 |
+
"loss": 1.1179,
|
1520 |
+
"step": 209
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 1.3376623376623376,
|
1524 |
+
"grad_norm": 0.2819492816925049,
|
1525 |
+
"learning_rate": 2.4393832257252253e-06,
|
1526 |
+
"loss": 1.012,
|
1527 |
+
"step": 210
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 1.344155844155844,
|
1531 |
+
"grad_norm": 0.267045259475708,
|
1532 |
+
"learning_rate": 2.394252004001989e-06,
|
1533 |
+
"loss": 1.0931,
|
1534 |
+
"step": 211
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 1.3506493506493507,
|
1538 |
+
"grad_norm": 0.32312628626823425,
|
1539 |
+
"learning_rate": 2.349410380311532e-06,
|
1540 |
+
"loss": 1.1414,
|
1541 |
+
"step": 212
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 1.3571428571428572,
|
1545 |
+
"grad_norm": 0.25884246826171875,
|
1546 |
+
"learning_rate": 2.304863338269326e-06,
|
1547 |
+
"loss": 1.126,
|
1548 |
+
"step": 213
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 1.3636363636363638,
|
1552 |
+
"grad_norm": 0.3011741638183594,
|
1553 |
+
"learning_rate": 2.2606158287515662e-06,
|
1554 |
+
"loss": 1.1247,
|
1555 |
+
"step": 214
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 1.37012987012987,
|
1559 |
+
"grad_norm": 0.2756052017211914,
|
1560 |
+
"learning_rate": 2.216672769344965e-06,
|
1561 |
+
"loss": 1.1196,
|
1562 |
+
"step": 215
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 1.3766233766233766,
|
1566 |
+
"grad_norm": 0.2793034613132477,
|
1567 |
+
"learning_rate": 2.1730390438002056e-06,
|
1568 |
+
"loss": 1.1372,
|
1569 |
+
"step": 216
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.3831168831168832,
|
1573 |
+
"grad_norm": 0.2940700948238373,
|
1574 |
+
"learning_rate": 2.129719501489177e-06,
|
1575 |
+
"loss": 1.0846,
|
1576 |
+
"step": 217
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 1.3896103896103895,
|
1580 |
+
"grad_norm": 0.30984777212142944,
|
1581 |
+
"learning_rate": 2.086718956866024e-06,
|
1582 |
+
"loss": 1.1404,
|
1583 |
+
"step": 218
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 1.396103896103896,
|
1587 |
+
"grad_norm": 0.25352832674980164,
|
1588 |
+
"learning_rate": 2.044042188932068e-06,
|
1589 |
+
"loss": 1.1223,
|
1590 |
+
"step": 219
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 1.4025974025974026,
|
1594 |
+
"grad_norm": 0.31949445605278015,
|
1595 |
+
"learning_rate": 2.0016939407046987e-06,
|
1596 |
+
"loss": 1.0899,
|
1597 |
+
"step": 220
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 1.4090909090909092,
|
1601 |
+
"grad_norm": 0.2721538245677948,
|
1602 |
+
"learning_rate": 1.9596789186902184e-06,
|
1603 |
+
"loss": 1.0571,
|
1604 |
+
"step": 221
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 1.4155844155844157,
|
1608 |
+
"grad_norm": 0.2586475610733032,
|
1609 |
+
"learning_rate": 1.9180017923607884e-06,
|
1610 |
+
"loss": 1.0164,
|
1611 |
+
"step": 222
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.422077922077922,
|
1615 |
+
"grad_norm": 0.29858991503715515,
|
1616 |
+
"learning_rate": 1.8766671936354647e-06,
|
1617 |
+
"loss": 1.155,
|
1618 |
+
"step": 223
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 1.4285714285714286,
|
1622 |
+
"grad_norm": 0.31114456057548523,
|
1623 |
+
"learning_rate": 1.8356797163654172e-06,
|
1624 |
+
"loss": 1.1546,
|
1625 |
+
"step": 224
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 1.435064935064935,
|
1629 |
+
"grad_norm": 0.27457138895988464,
|
1630 |
+
"learning_rate": 1.795043915823373e-06,
|
1631 |
+
"loss": 1.1159,
|
1632 |
+
"step": 225
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 1.4415584415584415,
|
1636 |
+
"grad_norm": 0.31147733330726624,
|
1637 |
+
"learning_rate": 1.754764308197358e-06,
|
1638 |
+
"loss": 1.1316,
|
1639 |
+
"step": 226
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 1.448051948051948,
|
1643 |
+
"grad_norm": 0.30539748072624207,
|
1644 |
+
"learning_rate": 1.7148453700887747e-06,
|
1645 |
+
"loss": 1.1135,
|
1646 |
+
"step": 227
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 1.4545454545454546,
|
1650 |
+
"grad_norm": 0.2620432674884796,
|
1651 |
+
"learning_rate": 1.6752915380148772e-06,
|
1652 |
+
"loss": 1.136,
|
1653 |
+
"step": 228
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 1.4610389610389611,
|
1657 |
+
"grad_norm": 0.3202950060367584,
|
1658 |
+
"learning_rate": 1.6361072079157092e-06,
|
1659 |
+
"loss": 1.1635,
|
1660 |
+
"step": 229
|
1661 |
+
},
|
1662 |
+
{
|
1663 |
+
"epoch": 1.4675324675324675,
|
1664 |
+
"grad_norm": 0.3076479732990265,
|
1665 |
+
"learning_rate": 1.5972967346655449e-06,
|
1666 |
+
"loss": 1.1305,
|
1667 |
+
"step": 230
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"epoch": 1.474025974025974,
|
1671 |
+
"grad_norm": 0.2635696828365326,
|
1672 |
+
"learning_rate": 1.5588644315888978e-06,
|
1673 |
+
"loss": 1.0887,
|
1674 |
+
"step": 231
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 1.4805194805194806,
|
1678 |
+
"grad_norm": 0.30404505133628845,
|
1679 |
+
"learning_rate": 1.5208145699811417e-06,
|
1680 |
+
"loss": 1.1176,
|
1681 |
+
"step": 232
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 1.487012987012987,
|
1685 |
+
"grad_norm": 0.29464152455329895,
|
1686 |
+
"learning_rate": 1.4831513786338126e-06,
|
1687 |
+
"loss": 1.1724,
|
1688 |
+
"step": 233
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 1.4935064935064934,
|
1692 |
+
"grad_norm": 0.3045382499694824,
|
1693 |
+
"learning_rate": 1.4458790433646264e-06,
|
1694 |
+
"loss": 1.1151,
|
1695 |
+
"step": 234
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 1.4935064935064934,
|
1699 |
+
"eval_loss": 1.1553453207015991,
|
1700 |
+
"eval_runtime": 25.2983,
|
1701 |
+
"eval_samples_per_second": 11.661,
|
1702 |
+
"eval_steps_per_second": 1.463,
|
1703 |
+
"step": 234
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 1.5,
|
1707 |
+
"grad_norm": 0.2871938943862915,
|
1708 |
+
"learning_rate": 1.4090017065522731e-06,
|
1709 |
+
"loss": 1.1687,
|
1710 |
+
"step": 235
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 1.5064935064935066,
|
1714 |
+
"grad_norm": 0.2857874035835266,
|
1715 |
+
"learning_rate": 1.3725234666760428e-06,
|
1716 |
+
"loss": 1.1089,
|
1717 |
+
"step": 236
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 1.512987012987013,
|
1721 |
+
"grad_norm": 0.3428025245666504,
|
1722 |
+
"learning_rate": 1.3364483778603272e-06,
|
1723 |
+
"loss": 1.1335,
|
1724 |
+
"step": 237
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 1.5194805194805194,
|
1728 |
+
"grad_norm": 0.3187818229198456,
|
1729 |
+
"learning_rate": 1.3007804494240478e-06,
|
1730 |
+
"loss": 1.163,
|
1731 |
+
"step": 238
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 1.525974025974026,
|
1735 |
+
"grad_norm": 0.28887903690338135,
|
1736 |
+
"learning_rate": 1.2655236454350777e-06,
|
1737 |
+
"loss": 1.119,
|
1738 |
+
"step": 239
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.5324675324675323,
|
1742 |
+
"grad_norm": 0.28905734419822693,
|
1743 |
+
"learning_rate": 1.2306818842696716e-06,
|
1744 |
+
"loss": 1.1448,
|
1745 |
+
"step": 240
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 1.5389610389610389,
|
1749 |
+
"grad_norm": 0.25675976276397705,
|
1750 |
+
"learning_rate": 1.1962590381769923e-06,
|
1751 |
+
"loss": 1.1513,
|
1752 |
+
"step": 241
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 1.5454545454545454,
|
1756 |
+
"grad_norm": 0.2782272696495056,
|
1757 |
+
"learning_rate": 1.1622589328487505e-06,
|
1758 |
+
"loss": 1.0953,
|
1759 |
+
"step": 242
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 1.551948051948052,
|
1763 |
+
"grad_norm": 0.2892334461212158,
|
1764 |
+
"learning_rate": 1.128685346994028e-06,
|
1765 |
+
"loss": 1.1721,
|
1766 |
+
"step": 243
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 1.5584415584415585,
|
1770 |
+
"grad_norm": 0.31845828890800476,
|
1771 |
+
"learning_rate": 1.09554201191932e-06,
|
1772 |
+
"loss": 1.1076,
|
1773 |
+
"step": 244
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.564935064935065,
|
1777 |
+
"grad_norm": 0.27880439162254333,
|
1778 |
+
"learning_rate": 1.0628326111138377e-06,
|
1779 |
+
"loss": 1.1691,
|
1780 |
+
"step": 245
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 1.5714285714285714,
|
1784 |
+
"grad_norm": 0.2526175081729889,
|
1785 |
+
"learning_rate": 1.03056077984014e-06,
|
1786 |
+
"loss": 1.1443,
|
1787 |
+
"step": 246
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 1.577922077922078,
|
1791 |
+
"grad_norm": 0.2798580527305603,
|
1792 |
+
"learning_rate": 9.98730104730115e-07,
|
1793 |
+
"loss": 1.1156,
|
1794 |
+
"step": 247
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.5844155844155843,
|
1798 |
+
"grad_norm": 0.3181169927120209,
|
1799 |
+
"learning_rate": 9.673441233863661e-07,
|
1800 |
+
"loss": 1.0997,
|
1801 |
+
"step": 248
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 1.5909090909090908,
|
1805 |
+
"grad_norm": 0.2808782756328583,
|
1806 |
+
"learning_rate": 9.364063239890476e-07,
|
1807 |
+
"loss": 1.1658,
|
1808 |
+
"step": 249
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 1.5974025974025974,
|
1812 |
+
"grad_norm": 0.2726938724517822,
|
1813 |
+
"learning_rate": 9.059201449082045e-07,
|
1814 |
+
"loss": 1.0976,
|
1815 |
+
"step": 250
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.603896103896104,
|
1819 |
+
"grad_norm": 0.29625144600868225,
|
1820 |
+
"learning_rate": 8.758889743216247e-07,
|
1821 |
+
"loss": 1.1165,
|
1822 |
+
"step": 251
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 1.6103896103896105,
|
1826 |
+
"grad_norm": 0.29083919525146484,
|
1827 |
+
"learning_rate": 8.463161498382949e-07,
|
1828 |
+
"loss": 1.158,
|
1829 |
+
"step": 252
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 1.616883116883117,
|
1833 |
+
"grad_norm": 0.27802902460098267,
|
1834 |
+
"learning_rate": 8.172049581274571e-07,
|
1835 |
+
"loss": 1.1136,
|
1836 |
+
"step": 253
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.6233766233766234,
|
1840 |
+
"grad_norm": 0.2722671627998352,
|
1841 |
+
"learning_rate": 7.885586345533397e-07,
|
1842 |
+
"loss": 1.1543,
|
1843 |
+
"step": 254
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 1.62987012987013,
|
1847 |
+
"grad_norm": 0.26996558904647827,
|
1848 |
+
"learning_rate": 7.603803628155821e-07,
|
1849 |
+
"loss": 1.1196,
|
1850 |
+
"step": 255
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.6363636363636362,
|
1854 |
+
"grad_norm": 0.2988632023334503,
|
1855 |
+
"learning_rate": 7.326732745954001e-07,
|
1856 |
+
"loss": 1.1126,
|
1857 |
+
"step": 256
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 1.6428571428571428,
|
1861 |
+
"grad_norm": 0.2721429467201233,
|
1862 |
+
"learning_rate": 7.054404492075512e-07,
|
1863 |
+
"loss": 1.1334,
|
1864 |
+
"step": 257
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 1.6493506493506493,
|
1868 |
+
"grad_norm": 0.2960205078125,
|
1869 |
+
"learning_rate": 6.786849132580841e-07,
|
1870 |
+
"loss": 1.1289,
|
1871 |
+
"step": 258
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 1.655844155844156,
|
1875 |
+
"grad_norm": 0.2805614173412323,
|
1876 |
+
"learning_rate": 6.524096403079861e-07,
|
1877 |
+
"loss": 1.1566,
|
1878 |
+
"step": 259
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 1.6623376623376624,
|
1882 |
+
"grad_norm": 0.26631271839141846,
|
1883 |
+
"learning_rate": 6.266175505426958e-07,
|
1884 |
+
"loss": 1.1385,
|
1885 |
+
"step": 260
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 1.6688311688311688,
|
1889 |
+
"grad_norm": 0.2959340810775757,
|
1890 |
+
"learning_rate": 6.013115104475653e-07,
|
1891 |
+
"loss": 1.061,
|
1892 |
+
"step": 261
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 1.6753246753246753,
|
1896 |
+
"grad_norm": 0.3008975088596344,
|
1897 |
+
"learning_rate": 5.76494332489278e-07,
|
1898 |
+
"loss": 1.1383,
|
1899 |
+
"step": 262
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.6818181818181817,
|
1903 |
+
"grad_norm": 0.28491881489753723,
|
1904 |
+
"learning_rate": 5.521687748032805e-07,
|
1905 |
+
"loss": 1.1827,
|
1906 |
+
"step": 263
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.6883116883116882,
|
1910 |
+
"grad_norm": 0.2625648081302643,
|
1911 |
+
"learning_rate": 5.283375408872538e-07,
|
1912 |
+
"loss": 1.1496,
|
1913 |
+
"step": 264
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 1.6948051948051948,
|
1917 |
+
"grad_norm": 0.29310908913612366,
|
1918 |
+
"learning_rate": 5.05003279300637e-07,
|
1919 |
+
"loss": 1.1256,
|
1920 |
+
"step": 265
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 1.7012987012987013,
|
1924 |
+
"grad_norm": 0.28792184591293335,
|
1925 |
+
"learning_rate": 4.82168583370285e-07,
|
1926 |
+
"loss": 1.1269,
|
1927 |
+
"step": 266
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 1.7077922077922079,
|
1931 |
+
"grad_norm": 0.3059506118297577,
|
1932 |
+
"learning_rate": 4.598359909022443e-07,
|
1933 |
+
"loss": 1.1275,
|
1934 |
+
"step": 267
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 1.7142857142857144,
|
1938 |
+
"grad_norm": 0.2944253087043762,
|
1939 |
+
"learning_rate": 4.380079838997087e-07,
|
1940 |
+
"loss": 1.0612,
|
1941 |
+
"step": 268
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 1.7207792207792207,
|
1945 |
+
"grad_norm": 0.3492392599582672,
|
1946 |
+
"learning_rate": 4.1668698828716994e-07,
|
1947 |
+
"loss": 1.1408,
|
1948 |
+
"step": 269
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.7272727272727273,
|
1952 |
+
"grad_norm": 0.2833608090877533,
|
1953 |
+
"learning_rate": 3.958753736408105e-07,
|
1954 |
+
"loss": 1.1345,
|
1955 |
+
"step": 270
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 1.7337662337662336,
|
1959 |
+
"grad_norm": 0.30626702308654785,
|
1960 |
+
"learning_rate": 3.7557545292514987e-07,
|
1961 |
+
"loss": 1.1533,
|
1962 |
+
"step": 271
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 1.7402597402597402,
|
1966 |
+
"grad_norm": 0.2807121276855469,
|
1967 |
+
"learning_rate": 3.557894822359864e-07,
|
1968 |
+
"loss": 1.1166,
|
1969 |
+
"step": 272
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 1.7467532467532467,
|
1973 |
+
"grad_norm": 0.31310421228408813,
|
1974 |
+
"learning_rate": 3.3651966054965734e-07,
|
1975 |
+
"loss": 1.1238,
|
1976 |
+
"step": 273
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 1.7467532467532467,
|
1980 |
+
"eval_loss": 1.153025507926941,
|
1981 |
+
"eval_runtime": 25.365,
|
1982 |
+
"eval_samples_per_second": 11.63,
|
1983 |
+
"eval_steps_per_second": 1.459,
|
1984 |
+
"step": 273
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 1.7532467532467533,
|
1988 |
+
"grad_norm": 0.29958927631378174,
|
1989 |
+
"learning_rate": 3.177681294786539e-07,
|
1990 |
+
"loss": 1.1579,
|
1991 |
+
"step": 274
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 1.7597402597402598,
|
1995 |
+
"grad_norm": 0.3180530071258545,
|
1996 |
+
"learning_rate": 2.995369730336012e-07,
|
1997 |
+
"loss": 1.0656,
|
1998 |
+
"step": 275
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.7662337662337664,
|
2002 |
+
"grad_norm": 0.30499908328056335,
|
2003 |
+
"learning_rate": 2.8182821739164534e-07,
|
2004 |
+
"loss": 1.0744,
|
2005 |
+
"step": 276
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 1.7727272727272727,
|
2009 |
+
"grad_norm": 0.2803168296813965,
|
2010 |
+
"learning_rate": 2.6464383067127175e-07,
|
2011 |
+
"loss": 1.0652,
|
2012 |
+
"step": 277
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 1.7792207792207793,
|
2016 |
+
"grad_norm": 0.2866427004337311,
|
2017 |
+
"learning_rate": 2.479857227135685e-07,
|
2018 |
+
"loss": 1.1175,
|
2019 |
+
"step": 278
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.7857142857142856,
|
2023 |
+
"grad_norm": 0.26658734679222107,
|
2024 |
+
"learning_rate": 2.3185574486997264e-07,
|
2025 |
+
"loss": 1.1494,
|
2026 |
+
"step": 279
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 1.7922077922077921,
|
2030 |
+
"grad_norm": 0.3132326602935791,
|
2031 |
+
"learning_rate": 2.1625568979651012e-07,
|
2032 |
+
"loss": 1.0939,
|
2033 |
+
"step": 280
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 1.7987012987012987,
|
2037 |
+
"grad_norm": 0.29077062010765076,
|
2038 |
+
"learning_rate": 2.0118729125457036e-07,
|
2039 |
+
"loss": 1.1686,
|
2040 |
+
"step": 281
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.8051948051948052,
|
2044 |
+
"grad_norm": 0.2711000144481659,
|
2045 |
+
"learning_rate": 1.866522239182117e-07,
|
2046 |
+
"loss": 1.1246,
|
2047 |
+
"step": 282
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 1.8116883116883118,
|
2051 |
+
"grad_norm": 0.28556856513023376,
|
2052 |
+
"learning_rate": 1.7265210318804683e-07,
|
2053 |
+
"loss": 1.0459,
|
2054 |
+
"step": 283
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.8181818181818183,
|
2058 |
+
"grad_norm": 0.30168288946151733,
|
2059 |
+
"learning_rate": 1.5918848501170647e-07,
|
2060 |
+
"loss": 1.1087,
|
2061 |
+
"step": 284
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.8246753246753247,
|
2065 |
+
"grad_norm": 0.30205830931663513,
|
2066 |
+
"learning_rate": 1.4626286571091664e-07,
|
2067 |
+
"loss": 1.1333,
|
2068 |
+
"step": 285
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 1.8311688311688312,
|
2072 |
+
"grad_norm": 0.2765739858150482,
|
2073 |
+
"learning_rate": 1.338766818151982e-07,
|
2074 |
+
"loss": 1.0988,
|
2075 |
+
"step": 286
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 1.8376623376623376,
|
2079 |
+
"grad_norm": 0.3049326241016388,
|
2080 |
+
"learning_rate": 1.2203130990221635e-07,
|
2081 |
+
"loss": 1.0979,
|
2082 |
+
"step": 287
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 1.844155844155844,
|
2086 |
+
"grad_norm": 0.2744823694229126,
|
2087 |
+
"learning_rate": 1.107280664447874e-07,
|
2088 |
+
"loss": 1.1496,
|
2089 |
+
"step": 288
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 1.8506493506493507,
|
2093 |
+
"grad_norm": 0.2835923731327057,
|
2094 |
+
"learning_rate": 9.996820766456916e-08,
|
2095 |
+
"loss": 1.0894,
|
2096 |
+
"step": 289
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 1.8571428571428572,
|
2100 |
+
"grad_norm": 0.31562480330467224,
|
2101 |
+
"learning_rate": 8.975292939244928e-08,
|
2102 |
+
"loss": 1.1204,
|
2103 |
+
"step": 290
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 1.8636363636363638,
|
2107 |
+
"grad_norm": 0.26750344038009644,
|
2108 |
+
"learning_rate": 8.008336693563823e-08,
|
2109 |
+
"loss": 1.1243,
|
2110 |
+
"step": 291
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 1.87012987012987,
|
2114 |
+
"grad_norm": 0.26439955830574036,
|
2115 |
+
"learning_rate": 7.096059495149855e-08,
|
2116 |
+
"loss": 1.1027,
|
2117 |
+
"step": 292
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 1.8766233766233766,
|
2121 |
+
"grad_norm": 0.2618618905544281,
|
2122 |
+
"learning_rate": 6.238562732810427e-08,
|
2123 |
+
"loss": 1.0328,
|
2124 |
+
"step": 293
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 1.883116883116883,
|
2128 |
+
"grad_norm": 0.3233661949634552,
|
2129 |
+
"learning_rate": 5.435941707156389e-08,
|
2130 |
+
"loss": 1.1159,
|
2131 |
+
"step": 294
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 1.8896103896103895,
|
2135 |
+
"grad_norm": 0.28882384300231934,
|
2136 |
+
"learning_rate": 4.6882856200101135e-08,
|
2137 |
+
"loss": 1.1039,
|
2138 |
+
"step": 295
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 1.896103896103896,
|
2142 |
+
"grad_norm": 0.3103022277355194,
|
2143 |
+
"learning_rate": 3.99567756449204e-08,
|
2144 |
+
"loss": 1.1315,
|
2145 |
+
"step": 296
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 1.9025974025974026,
|
2149 |
+
"grad_norm": 0.2719733715057373,
|
2150 |
+
"learning_rate": 3.358194515785784e-08,
|
2151 |
+
"loss": 1.1128,
|
2152 |
+
"step": 297
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.9090909090909092,
|
2156 |
+
"grad_norm": 0.266874223947525,
|
2157 |
+
"learning_rate": 2.77590732258326e-08,
|
2158 |
+
"loss": 1.1333,
|
2159 |
+
"step": 298
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 1.9155844155844157,
|
2163 |
+
"grad_norm": 0.2862412631511688,
|
2164 |
+
"learning_rate": 2.2488806992105317e-08,
|
2165 |
+
"loss": 1.1387,
|
2166 |
+
"step": 299
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 1.922077922077922,
|
2170 |
+
"grad_norm": 0.3009204864501953,
|
2171 |
+
"learning_rate": 1.7771732184357905e-08,
|
2172 |
+
"loss": 1.1328,
|
2173 |
+
"step": 300
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 1.9285714285714286,
|
2177 |
+
"grad_norm": 0.28494757413864136,
|
2178 |
+
"learning_rate": 1.3608373049596724e-08,
|
2179 |
+
"loss": 1.1189,
|
2180 |
+
"step": 301
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 1.935064935064935,
|
2184 |
+
"grad_norm": 0.26805561780929565,
|
2185 |
+
"learning_rate": 9.999192295886973e-09,
|
2186 |
+
"loss": 1.0664,
|
2187 |
+
"step": 302
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 1.9415584415584415,
|
2191 |
+
"grad_norm": 0.3299916088581085,
|
2192 |
+
"learning_rate": 6.944591040930481e-09,
|
2193 |
+
"loss": 1.1117,
|
2194 |
+
"step": 303
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.948051948051948,
|
2198 |
+
"grad_norm": 0.2890622913837433,
|
2199 |
+
"learning_rate": 4.444908767484712e-09,
|
2200 |
+
"loss": 1.1396,
|
2201 |
+
"step": 304
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 1.9545454545454546,
|
2205 |
+
"grad_norm": 0.28758740425109863,
|
2206 |
+
"learning_rate": 2.500423285632381e-09,
|
2207 |
+
"loss": 1.1277,
|
2208 |
+
"step": 305
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.9610389610389611,
|
2212 |
+
"grad_norm": 0.2983172535896301,
|
2213 |
+
"learning_rate": 1.111350701909486e-09,
|
2214 |
+
"loss": 1.1452,
|
2215 |
+
"step": 306
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 1.9675324675324677,
|
2219 |
+
"grad_norm": 0.30814212560653687,
|
2220 |
+
"learning_rate": 2.7784539528397104e-10,
|
2221 |
+
"loss": 1.0888,
|
2222 |
+
"step": 307
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 1.974025974025974,
|
2226 |
+
"grad_norm": 0.2840464115142822,
|
2227 |
+
"learning_rate": 0.0,
|
2228 |
+
"loss": 1.1205,
|
2229 |
+
"step": 308
|
2230 |
+
}
|
2231 |
+
],
|
2232 |
+
"logging_steps": 1,
|
2233 |
+
"max_steps": 308,
|
2234 |
+
"num_input_tokens_seen": 0,
|
2235 |
+
"num_train_epochs": 2,
|
2236 |
+
"save_steps": 77,
|
2237 |
+
"stateful_callbacks": {
|
2238 |
+
"TrainerControl": {
|
2239 |
+
"args": {
|
2240 |
+
"should_epoch_stop": false,
|
2241 |
+
"should_evaluate": false,
|
2242 |
+
"should_log": false,
|
2243 |
+
"should_save": true,
|
2244 |
+
"should_training_stop": true
|
2245 |
+
},
|
2246 |
+
"attributes": {}
|
2247 |
+
}
|
2248 |
+
},
|
2249 |
+
"total_flos": 1.703755799815258e+18,
|
2250 |
+
"train_batch_size": 1,
|
2251 |
+
"trial_name": null,
|
2252 |
+
"trial_params": null
|
2253 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddde11bed37219d584c782f12b054aa1c87cae28da3b23f1cfb6b6fc3ac31251
|
3 |
+
size 6648
|