Upload folder using huggingface_hub
Browse files- checkpoint-90/README.md +202 -0
- checkpoint-90/adapter_config.json +29 -0
- checkpoint-90/adapter_model.safetensors +3 -0
- checkpoint-90/optimizer.pt +3 -0
- checkpoint-90/rng_state_0.pth +3 -0
- checkpoint-90/rng_state_1.pth +3 -0
- checkpoint-90/rng_state_2.pth +3 -0
- checkpoint-90/rng_state_3.pth +3 -0
- checkpoint-90/scheduler.pt +3 -0
- checkpoint-90/special_tokens_map.json +24 -0
- checkpoint-90/tokenizer.json +0 -0
- checkpoint-90/tokenizer.model +3 -0
- checkpoint-90/tokenizer_config.json +49 -0
- checkpoint-90/trainer_state.json +204 -0
- checkpoint-90/training_args.bin +3 -0
checkpoint-90/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged
|
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 0.10.0
|
checkpoint-90/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-90/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e11ddb49df1857036f58ba2d066491952d7bfa321b08da1c922e2f6aacea5ad4
|
3 |
+
size 13648432
|
checkpoint-90/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3093fdbfa72040cee375f6793558600f6d9087c3f8efa7ae6cf32884036a3b3
|
3 |
+
size 27370618
|
checkpoint-90/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:543ef05f530d40ee20b8d626b07a69b86597aca643e48897571062f973efe84f
|
3 |
+
size 15024
|
checkpoint-90/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a23f732e43838ce0398d2636885ac16badbb9bcbc04d1406069ba3027bc5ae0
|
3 |
+
size 15024
|
checkpoint-90/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e10cce960e7068b051c05e35ed6160656be9091c63f13796ac2ed7e9c84e5a72
|
3 |
+
size 15024
|
checkpoint-90/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f6049e212b1df5cefc5d834afcd8cc052c73f1457449e9fe8a38d514f54078
|
3 |
+
size 15024
|
checkpoint-90/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa5e8b12b9c814e867e9bad19493354b25d611955ef1f97df023b67375d67738
|
3 |
+
size 1064
|
checkpoint-90/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-90/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-90/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-90/tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + message['content'] + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"max_lenght": 8192,
|
37 |
+
"max_length": 8192,
|
38 |
+
"model_max_length": 1000000000000000019884624838656,
|
39 |
+
"pad_token": "<unk>",
|
40 |
+
"padding": true,
|
41 |
+
"sp_model_kwargs": {},
|
42 |
+
"spaces_between_special_tokens": false,
|
43 |
+
"stride": 0,
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"truncation_side": "right",
|
46 |
+
"truncation_strategy": "longest_first",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|
checkpoint-90/trainer_state.json
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4368760883808136,
|
3 |
+
"best_model_checkpoint": "./mistral/20-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.6-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-90_batch_16_2024-04-20_ppid_9/checkpoint-90",
|
4 |
+
"epoch": 5.806451612903226,
|
5 |
+
"eval_steps": 30,
|
6 |
+
"global_step": 90,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.65,
|
13 |
+
"grad_norm": 16.76080894470215,
|
14 |
+
"learning_rate": 4.770114942528735e-06,
|
15 |
+
"logits/chosen": -1.8055893182754517,
|
16 |
+
"logits/rejected": -1.828260064125061,
|
17 |
+
"logps/chosen": -46.100120544433594,
|
18 |
+
"logps/rejected": -82.48685455322266,
|
19 |
+
"loss": 0.6795,
|
20 |
+
"rewards/accuracies": 0.25,
|
21 |
+
"rewards/chosen": 0.04209427908062935,
|
22 |
+
"rewards/margins": 0.04848780483007431,
|
23 |
+
"rewards/rejected": -0.006393528077751398,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.29,
|
28 |
+
"grad_norm": 11.445436477661133,
|
29 |
+
"learning_rate": 4.1954022988505746e-06,
|
30 |
+
"logits/chosen": -1.8350013494491577,
|
31 |
+
"logits/rejected": -1.8602994680404663,
|
32 |
+
"logps/chosen": -37.913516998291016,
|
33 |
+
"logps/rejected": -67.64692687988281,
|
34 |
+
"loss": 0.6251,
|
35 |
+
"rewards/accuracies": 0.3499999940395355,
|
36 |
+
"rewards/chosen": 0.15703639388084412,
|
37 |
+
"rewards/margins": 0.1911666840314865,
|
38 |
+
"rewards/rejected": -0.0341302864253521,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.94,
|
43 |
+
"grad_norm": 11.545478820800781,
|
44 |
+
"learning_rate": 3.620689655172414e-06,
|
45 |
+
"logits/chosen": -1.8373997211456299,
|
46 |
+
"logits/rejected": -1.847825050354004,
|
47 |
+
"logps/chosen": -29.99410057067871,
|
48 |
+
"logps/rejected": -59.1256217956543,
|
49 |
+
"loss": 0.5772,
|
50 |
+
"rewards/accuracies": 0.30000001192092896,
|
51 |
+
"rewards/chosen": 0.27005138993263245,
|
52 |
+
"rewards/margins": 0.30424270033836365,
|
53 |
+
"rewards/rejected": -0.0341913141310215,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.94,
|
58 |
+
"eval_logits/chosen": -1.81316077709198,
|
59 |
+
"eval_logits/rejected": -1.8455785512924194,
|
60 |
+
"eval_logps/chosen": -36.48888397216797,
|
61 |
+
"eval_logps/rejected": -55.34504699707031,
|
62 |
+
"eval_loss": 0.5171023011207581,
|
63 |
+
"eval_rewards/accuracies": 0.5,
|
64 |
+
"eval_rewards/chosen": 0.5191236138343811,
|
65 |
+
"eval_rewards/margins": 0.5845221877098083,
|
66 |
+
"eval_rewards/rejected": -0.06539855152368546,
|
67 |
+
"eval_runtime": 2.4917,
|
68 |
+
"eval_samples_per_second": 11.237,
|
69 |
+
"eval_steps_per_second": 1.605,
|
70 |
+
"step": 30
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 2.58,
|
74 |
+
"grad_norm": 7.317459583282471,
|
75 |
+
"learning_rate": 3.0459770114942533e-06,
|
76 |
+
"logits/chosen": -1.7586491107940674,
|
77 |
+
"logits/rejected": -1.7903881072998047,
|
78 |
+
"logps/chosen": -52.9969367980957,
|
79 |
+
"logps/rejected": -87.54074096679688,
|
80 |
+
"loss": 0.5181,
|
81 |
+
"rewards/accuracies": 0.5,
|
82 |
+
"rewards/chosen": 0.6470302939414978,
|
83 |
+
"rewards/margins": 0.7092825174331665,
|
84 |
+
"rewards/rejected": -0.06225220113992691,
|
85 |
+
"step": 40
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 3.23,
|
89 |
+
"grad_norm": 5.132155418395996,
|
90 |
+
"learning_rate": 2.471264367816092e-06,
|
91 |
+
"logits/chosen": -1.8951135873794556,
|
92 |
+
"logits/rejected": -1.9210799932479858,
|
93 |
+
"logps/chosen": -34.33287811279297,
|
94 |
+
"logps/rejected": -68.03052520751953,
|
95 |
+
"loss": 0.5415,
|
96 |
+
"rewards/accuracies": 0.32499998807907104,
|
97 |
+
"rewards/chosen": 0.5781847238540649,
|
98 |
+
"rewards/margins": 0.6501666903495789,
|
99 |
+
"rewards/rejected": -0.07198190689086914,
|
100 |
+
"step": 50
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 3.87,
|
104 |
+
"grad_norm": 7.053220748901367,
|
105 |
+
"learning_rate": 1.896551724137931e-06,
|
106 |
+
"logits/chosen": -1.9114513397216797,
|
107 |
+
"logits/rejected": -1.9271589517593384,
|
108 |
+
"logps/chosen": -25.962200164794922,
|
109 |
+
"logps/rejected": -48.20077133178711,
|
110 |
+
"loss": 0.5125,
|
111 |
+
"rewards/accuracies": 0.25,
|
112 |
+
"rewards/chosen": 0.47203439474105835,
|
113 |
+
"rewards/margins": 0.5603113174438477,
|
114 |
+
"rewards/rejected": -0.08827687054872513,
|
115 |
+
"step": 60
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 3.87,
|
119 |
+
"eval_logits/chosen": -1.817034363746643,
|
120 |
+
"eval_logits/rejected": -1.8500827550888062,
|
121 |
+
"eval_logps/chosen": -35.225791931152344,
|
122 |
+
"eval_logps/rejected": -55.629276275634766,
|
123 |
+
"eval_loss": 0.4517291486263275,
|
124 |
+
"eval_rewards/accuracies": 0.5,
|
125 |
+
"eval_rewards/chosen": 0.8980507254600525,
|
126 |
+
"eval_rewards/margins": 1.048719048500061,
|
127 |
+
"eval_rewards/rejected": -0.15066833794116974,
|
128 |
+
"eval_runtime": 2.4913,
|
129 |
+
"eval_samples_per_second": 11.239,
|
130 |
+
"eval_steps_per_second": 1.606,
|
131 |
+
"step": 60
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 4.52,
|
135 |
+
"grad_norm": 3.6152443885803223,
|
136 |
+
"learning_rate": 1.3218390804597702e-06,
|
137 |
+
"logits/chosen": -1.8332040309906006,
|
138 |
+
"logits/rejected": -1.8538074493408203,
|
139 |
+
"logps/chosen": -34.457115173339844,
|
140 |
+
"logps/rejected": -72.48670959472656,
|
141 |
+
"loss": 0.4838,
|
142 |
+
"rewards/accuracies": 0.375,
|
143 |
+
"rewards/chosen": 0.6265449523925781,
|
144 |
+
"rewards/margins": 0.7487497329711914,
|
145 |
+
"rewards/rejected": -0.12220476567745209,
|
146 |
+
"step": 70
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 5.16,
|
150 |
+
"grad_norm": 3.271343231201172,
|
151 |
+
"learning_rate": 7.471264367816093e-07,
|
152 |
+
"logits/chosen": -1.7745481729507446,
|
153 |
+
"logits/rejected": -1.784841537475586,
|
154 |
+
"logps/chosen": -52.409339904785156,
|
155 |
+
"logps/rejected": -76.24700164794922,
|
156 |
+
"loss": 0.4665,
|
157 |
+
"rewards/accuracies": 0.4749999940395355,
|
158 |
+
"rewards/chosen": 0.939862847328186,
|
159 |
+
"rewards/margins": 1.0275475978851318,
|
160 |
+
"rewards/rejected": -0.08768495172262192,
|
161 |
+
"step": 80
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 5.81,
|
165 |
+
"grad_norm": 2.297419786453247,
|
166 |
+
"learning_rate": 1.7241379310344828e-07,
|
167 |
+
"logits/chosen": -1.8448705673217773,
|
168 |
+
"logits/rejected": -1.8637123107910156,
|
169 |
+
"logps/chosen": -33.81181335449219,
|
170 |
+
"logps/rejected": -63.00860595703125,
|
171 |
+
"loss": 0.491,
|
172 |
+
"rewards/accuracies": 0.3499999940395355,
|
173 |
+
"rewards/chosen": 0.6832905411720276,
|
174 |
+
"rewards/margins": 0.8434805870056152,
|
175 |
+
"rewards/rejected": -0.1601901352405548,
|
176 |
+
"step": 90
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.81,
|
180 |
+
"eval_logits/chosen": -1.8184903860092163,
|
181 |
+
"eval_logits/rejected": -1.8517436981201172,
|
182 |
+
"eval_logps/chosen": -34.81117630004883,
|
183 |
+
"eval_logps/rejected": -55.731048583984375,
|
184 |
+
"eval_loss": 0.4368760883808136,
|
185 |
+
"eval_rewards/accuracies": 0.5,
|
186 |
+
"eval_rewards/chosen": 1.0224344730377197,
|
187 |
+
"eval_rewards/margins": 1.2036339044570923,
|
188 |
+
"eval_rewards/rejected": -0.18119940161705017,
|
189 |
+
"eval_runtime": 2.4928,
|
190 |
+
"eval_samples_per_second": 11.232,
|
191 |
+
"eval_steps_per_second": 1.605,
|
192 |
+
"step": 90
|
193 |
+
}
|
194 |
+
],
|
195 |
+
"logging_steps": 10,
|
196 |
+
"max_steps": 90,
|
197 |
+
"num_input_tokens_seen": 0,
|
198 |
+
"num_train_epochs": 6,
|
199 |
+
"save_steps": 90,
|
200 |
+
"total_flos": 0.0,
|
201 |
+
"train_batch_size": 2,
|
202 |
+
"trial_name": null,
|
203 |
+
"trial_params": null
|
204 |
+
}
|
checkpoint-90/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c20933681c819e3eca9593cd0c21a0b47ebbfa7455cec09dcd232391e6516e9
|
3 |
+
size 5304
|