Upload 13 files
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- llama3_lora_ppo.yaml +44 -0
- special_tokens_map.json +24 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- trainer_log.jsonl +30 -0
- trainer_state.json +239 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- training_reward.png +0 -0
- value_head.safetensors +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: mistralai/Ministral-8B-Instruct-2410
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Ministral-8B-Instruct-2410",
|
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": 0.0,
|
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 |
+
"gate_proj",
|
24 |
+
"down_proj",
|
25 |
+
"v_proj",
|
26 |
+
"k_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_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 sha256:071c31423afacdb75caf99b80b90d669af52a35a2dd07a16cb7cc423ea0d93f6
|
3 |
+
size 87360584
|
llama3_lora_ppo.yaml
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
### model
|
2 |
+
model_name_or_path: mistralai/Ministral-8B-Instruct-2410
|
3 |
+
reward_model: chchen/Ministral-8B-Instruct-2410-reward-1000
|
4 |
+
trust_remote_code: true
|
5 |
+
|
6 |
+
### method
|
7 |
+
stage: ppo
|
8 |
+
do_train: true
|
9 |
+
finetuning_type: lora
|
10 |
+
lora_target: all
|
11 |
+
|
12 |
+
### dataset
|
13 |
+
dataset: bct_non_cot_sft_1000
|
14 |
+
dataset_dir: data_private
|
15 |
+
template: mistral
|
16 |
+
cutoff_len: 1024
|
17 |
+
# max_samples: 1000
|
18 |
+
overwrite_cache: true
|
19 |
+
preprocessing_num_workers: 16
|
20 |
+
|
21 |
+
### output
|
22 |
+
output_dir: saves/Ministral-8B-Instruct-2410/ppo-1000/train
|
23 |
+
logging_steps: 10
|
24 |
+
save_steps: 50
|
25 |
+
plot_loss: true
|
26 |
+
overwrite_output_dir: true
|
27 |
+
save_total_limit: 3
|
28 |
+
push_to_hub: true
|
29 |
+
hub_model_id: chchen/Ministral-8B-Instruct-2410-ppo-1000
|
30 |
+
|
31 |
+
### train
|
32 |
+
per_device_train_batch_size: 4
|
33 |
+
gradient_accumulation_steps: 8
|
34 |
+
learning_rate: 1.0e-5
|
35 |
+
num_train_epochs: 10.0
|
36 |
+
lr_scheduler_type: cosine
|
37 |
+
warmup_ratio: 0.1
|
38 |
+
bf16: true
|
39 |
+
ddp_timeout: 180000000
|
40 |
+
|
41 |
+
### generate
|
42 |
+
max_new_tokens: 512
|
43 |
+
top_k: 0
|
44 |
+
top_p: 0.9
|
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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7edbeaf20dd7f571b5dd1c54d9ace4f9b6299127cc7ba2afb14a6d51a4a79a4
|
3 |
+
size 17078136
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 20, "total_steps": 310, "loss": 4.6766, "reward": 8.9945, "lr": 5.9375e-06, "epoch": 0.61, "percentage": 6.45, "elapsed_time": "0:38:37", "remaining_time": "9:20:07"}
|
2 |
+
{"current_steps": 30, "total_steps": 310, "loss": 4.0729, "reward": 9.3216, "lr": 9.0625e-06, "epoch": 0.94, "percentage": 9.68, "elapsed_time": "0:54:25", "remaining_time": "8:27:55"}
|
3 |
+
{"current_steps": 40, "total_steps": 310, "loss": 3.0501, "reward": 9.949, "lr": 9.985430661522333e-06, "epoch": 1.26, "percentage": 12.9, "elapsed_time": "1:10:44", "remaining_time": "7:57:28"}
|
4 |
+
{"current_steps": 50, "total_steps": 310, "loss": 1.148, "reward": 11.1044, "lr": 9.914274958326507e-06, "epoch": 1.58, "percentage": 16.13, "elapsed_time": "1:30:55", "remaining_time": "7:52:49"}
|
5 |
+
{"current_steps": 60, "total_steps": 310, "loss": 1.2929, "reward": 13.2822, "lr": 9.784701678661045e-06, "epoch": 1.9, "percentage": 19.35, "elapsed_time": "1:49:13", "remaining_time": "7:35:05"}
|
6 |
+
{"current_steps": 70, "total_steps": 310, "loss": 1.0175, "reward": 15.9296, "lr": 9.598251102025463e-06, "epoch": 2.23, "percentage": 22.58, "elapsed_time": "2:02:46", "remaining_time": "7:00:57"}
|
7 |
+
{"current_steps": 80, "total_steps": 310, "loss": 1.5542, "reward": 14.864, "lr": 9.357139626751308e-06, "epoch": 2.55, "percentage": 25.81, "elapsed_time": "2:16:57", "remaining_time": "6:33:44"}
|
8 |
+
{"current_steps": 90, "total_steps": 310, "loss": 1.3869, "reward": 15.363, "lr": 9.064233422958078e-06, "epoch": 2.87, "percentage": 29.03, "elapsed_time": "2:28:56", "remaining_time": "6:04:04"}
|
9 |
+
{"current_steps": 100, "total_steps": 310, "loss": 1.0299, "reward": 16.2821, "lr": 8.723014361461633e-06, "epoch": 3.19, "percentage": 32.26, "elapsed_time": "2:40:28", "remaining_time": "5:37:00"}
|
10 |
+
{"current_steps": 110, "total_steps": 310, "loss": 0.8473, "reward": 15.4689, "lr": 8.337538623649237e-06, "epoch": 3.52, "percentage": 35.48, "elapsed_time": "2:51:52", "remaining_time": "5:12:29"}
|
11 |
+
{"current_steps": 120, "total_steps": 310, "loss": 0.717, "reward": 17.3127, "lr": 7.912388484339012e-06, "epoch": 3.84, "percentage": 38.71, "elapsed_time": "3:04:48", "remaining_time": "4:52:36"}
|
12 |
+
{"current_steps": 130, "total_steps": 310, "loss": 0.5949, "reward": 17.6693, "lr": 7.4526178407965396e-06, "epoch": 4.16, "percentage": 41.94, "elapsed_time": "3:17:31", "remaining_time": "4:33:30"}
|
13 |
+
{"current_steps": 140, "total_steps": 310, "loss": 0.6247, "reward": 16.8791, "lr": 6.963692135422872e-06, "epoch": 4.48, "percentage": 45.16, "elapsed_time": "3:30:46", "remaining_time": "4:15:56"}
|
14 |
+
{"current_steps": 150, "total_steps": 310, "loss": 0.7098, "reward": 17.0654, "lr": 6.451423386272312e-06, "epoch": 4.81, "percentage": 48.39, "elapsed_time": "3:44:04", "remaining_time": "3:59:00"}
|
15 |
+
{"current_steps": 160, "total_steps": 310, "loss": 0.4663, "reward": 17.231, "lr": 5.921901097713317e-06, "epoch": 5.13, "percentage": 51.61, "elapsed_time": "3:56:51", "remaining_time": "3:42:03"}
|
16 |
+
{"current_steps": 170, "total_steps": 310, "loss": 0.5734, "reward": 17.4632, "lr": 5.381419872519763e-06, "epoch": 5.45, "percentage": 54.84, "elapsed_time": "4:10:39", "remaining_time": "3:26:25"}
|
17 |
+
{"current_steps": 180, "total_steps": 310, "loss": 0.3885, "reward": 17.9993, "lr": 4.83640458589112e-06, "epoch": 5.77, "percentage": 58.06, "elapsed_time": "4:24:10", "remaining_time": "3:10:47"}
|
18 |
+
{"current_steps": 190, "total_steps": 310, "loss": 0.2806, "reward": 17.2133, "lr": 4.293334010882164e-06, "epoch": 6.1, "percentage": 61.29, "elapsed_time": "4:36:22", "remaining_time": "2:54:33"}
|
19 |
+
{"current_steps": 200, "total_steps": 310, "loss": 0.3708, "reward": 17.0068, "lr": 3.7586638031314182e-06, "epoch": 6.42, "percentage": 64.52, "elapsed_time": "4:49:14", "remaining_time": "2:39:04"}
|
20 |
+
{"current_steps": 210, "total_steps": 310, "loss": 0.4041, "reward": 17.7468, "lr": 3.2387497603938327e-06, "epoch": 6.74, "percentage": 67.74, "elapsed_time": "5:01:58", "remaining_time": "2:23:48"}
|
21 |
+
{"current_steps": 220, "total_steps": 310, "loss": 0.3516, "reward": 18.2141, "lr": 2.739772269116402e-06, "epoch": 7.06, "percentage": 70.97, "elapsed_time": "5:14:17", "remaining_time": "2:08:34"}
|
22 |
+
{"current_steps": 230, "total_steps": 310, "loss": 0.2936, "reward": 17.5244, "lr": 2.2676628361847834e-06, "epoch": 7.39, "percentage": 74.19, "elapsed_time": "5:26:45", "remaining_time": "1:53:39"}
|
23 |
+
{"current_steps": 240, "total_steps": 310, "loss": 0.2178, "reward": 17.7584, "lr": 1.8280335791817733e-06, "epoch": 7.71, "percentage": 77.42, "elapsed_time": "5:39:20", "remaining_time": "1:38:58"}
|
24 |
+
{"current_steps": 250, "total_steps": 310, "loss": 0.2559, "reward": 17.8964, "lr": 1.4261105133297693e-06, "epoch": 8.03, "percentage": 80.65, "elapsed_time": "5:51:04", "remaining_time": "1:24:15"}
|
25 |
+
{"current_steps": 260, "total_steps": 310, "loss": 0.2617, "reward": 18.0355, "lr": 1.0666714281569152e-06, "epoch": 8.35, "percentage": 83.87, "elapsed_time": "6:02:31", "remaining_time": "1:09:42"}
|
26 |
+
{"current_steps": 270, "total_steps": 310, "loss": 0.2195, "reward": 17.893, "lr": 7.539890923671061e-07, "epoch": 8.68, "percentage": 87.1, "elapsed_time": "6:14:20", "remaining_time": "0:55:27"}
|
27 |
+
{"current_steps": 280, "total_steps": 310, "loss": 0.1847, "reward": 17.9483, "lr": 4.917804620559202e-07, "epoch": 9.0, "percentage": 90.32, "elapsed_time": "6:25:56", "remaining_time": "0:41:21"}
|
28 |
+
{"current_steps": 290, "total_steps": 310, "loss": 0.1887, "reward": 18.637, "lr": 2.8316249605087386e-07, "epoch": 9.32, "percentage": 93.55, "elapsed_time": "6:38:05", "remaining_time": "0:27:27"}
|
29 |
+
{"current_steps": 300, "total_steps": 310, "loss": 0.2198, "reward": 17.2751, "lr": 1.3061510361333186e-07, "epoch": 9.65, "percentage": 96.77, "elapsed_time": "6:48:09", "remaining_time": "0:13:36"}
|
30 |
+
{"current_steps": 310, "total_steps": 310, "loss": 0.2581, "reward": 18.2905, "lr": 3.59516649547248e-08, "epoch": 9.97, "percentage": 100.0, "elapsed_time": "6:59:41", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": null,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 310,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.29,
|
13 |
+
"learning_rate": 2.8125e-06,
|
14 |
+
"loss": 3.9546,
|
15 |
+
"reward": 9.563,
|
16 |
+
"step": 9
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.61,
|
20 |
+
"learning_rate": 5.9375e-06,
|
21 |
+
"loss": 4.6766,
|
22 |
+
"reward": 8.9945,
|
23 |
+
"step": 19
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.94,
|
27 |
+
"learning_rate": 9.0625e-06,
|
28 |
+
"loss": 4.0729,
|
29 |
+
"reward": 9.3216,
|
30 |
+
"step": 29
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.26,
|
34 |
+
"learning_rate": 9.985430661522333e-06,
|
35 |
+
"loss": 3.0501,
|
36 |
+
"reward": 9.949,
|
37 |
+
"step": 39
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.58,
|
41 |
+
"learning_rate": 9.914274958326507e-06,
|
42 |
+
"loss": 1.148,
|
43 |
+
"reward": 11.1044,
|
44 |
+
"step": 49
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.9,
|
48 |
+
"learning_rate": 9.784701678661045e-06,
|
49 |
+
"loss": 1.2929,
|
50 |
+
"reward": 13.2822,
|
51 |
+
"step": 59
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.23,
|
55 |
+
"learning_rate": 9.598251102025463e-06,
|
56 |
+
"loss": 1.0175,
|
57 |
+
"reward": 15.9296,
|
58 |
+
"step": 69
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 2.55,
|
62 |
+
"learning_rate": 9.357139626751308e-06,
|
63 |
+
"loss": 1.5542,
|
64 |
+
"reward": 14.864,
|
65 |
+
"step": 79
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.87,
|
69 |
+
"learning_rate": 9.064233422958078e-06,
|
70 |
+
"loss": 1.3869,
|
71 |
+
"reward": 15.363,
|
72 |
+
"step": 89
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 3.19,
|
76 |
+
"learning_rate": 8.723014361461633e-06,
|
77 |
+
"loss": 1.0299,
|
78 |
+
"reward": 16.2821,
|
79 |
+
"step": 99
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 3.52,
|
83 |
+
"learning_rate": 8.337538623649237e-06,
|
84 |
+
"loss": 0.8473,
|
85 |
+
"reward": 15.4689,
|
86 |
+
"step": 109
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.84,
|
90 |
+
"learning_rate": 7.912388484339012e-06,
|
91 |
+
"loss": 0.717,
|
92 |
+
"reward": 17.3127,
|
93 |
+
"step": 119
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 4.16,
|
97 |
+
"learning_rate": 7.4526178407965396e-06,
|
98 |
+
"loss": 0.5949,
|
99 |
+
"reward": 17.6693,
|
100 |
+
"step": 129
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 4.48,
|
104 |
+
"learning_rate": 6.963692135422872e-06,
|
105 |
+
"loss": 0.6247,
|
106 |
+
"reward": 16.8791,
|
107 |
+
"step": 139
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 4.81,
|
111 |
+
"learning_rate": 6.451423386272312e-06,
|
112 |
+
"loss": 0.7098,
|
113 |
+
"reward": 17.0654,
|
114 |
+
"step": 149
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 5.13,
|
118 |
+
"learning_rate": 5.921901097713317e-06,
|
119 |
+
"loss": 0.4663,
|
120 |
+
"reward": 17.231,
|
121 |
+
"step": 159
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 5.45,
|
125 |
+
"learning_rate": 5.381419872519763e-06,
|
126 |
+
"loss": 0.5734,
|
127 |
+
"reward": 17.4632,
|
128 |
+
"step": 169
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 5.77,
|
132 |
+
"learning_rate": 4.83640458589112e-06,
|
133 |
+
"loss": 0.3885,
|
134 |
+
"reward": 17.9993,
|
135 |
+
"step": 179
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 6.1,
|
139 |
+
"learning_rate": 4.293334010882164e-06,
|
140 |
+
"loss": 0.2806,
|
141 |
+
"reward": 17.2133,
|
142 |
+
"step": 189
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 6.42,
|
146 |
+
"learning_rate": 3.7586638031314182e-06,
|
147 |
+
"loss": 0.3708,
|
148 |
+
"reward": 17.0068,
|
149 |
+
"step": 199
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 6.74,
|
153 |
+
"learning_rate": 3.2387497603938327e-06,
|
154 |
+
"loss": 0.4041,
|
155 |
+
"reward": 17.7468,
|
156 |
+
"step": 209
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 7.06,
|
160 |
+
"learning_rate": 2.739772269116402e-06,
|
161 |
+
"loss": 0.3516,
|
162 |
+
"reward": 18.2141,
|
163 |
+
"step": 219
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 7.39,
|
167 |
+
"learning_rate": 2.2676628361847834e-06,
|
168 |
+
"loss": 0.2936,
|
169 |
+
"reward": 17.5244,
|
170 |
+
"step": 229
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 7.71,
|
174 |
+
"learning_rate": 1.8280335791817733e-06,
|
175 |
+
"loss": 0.2178,
|
176 |
+
"reward": 17.7584,
|
177 |
+
"step": 239
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 8.03,
|
181 |
+
"learning_rate": 1.4261105133297693e-06,
|
182 |
+
"loss": 0.2559,
|
183 |
+
"reward": 17.8964,
|
184 |
+
"step": 249
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 8.35,
|
188 |
+
"learning_rate": 1.0666714281569152e-06,
|
189 |
+
"loss": 0.2617,
|
190 |
+
"reward": 18.0355,
|
191 |
+
"step": 259
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 8.68,
|
195 |
+
"learning_rate": 7.539890923671061e-07,
|
196 |
+
"loss": 0.2195,
|
197 |
+
"reward": 17.893,
|
198 |
+
"step": 269
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 9.0,
|
202 |
+
"learning_rate": 4.917804620559202e-07,
|
203 |
+
"loss": 0.1847,
|
204 |
+
"reward": 17.9483,
|
205 |
+
"step": 279
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 9.32,
|
209 |
+
"learning_rate": 2.8316249605087386e-07,
|
210 |
+
"loss": 0.1887,
|
211 |
+
"reward": 18.637,
|
212 |
+
"step": 289
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 9.65,
|
216 |
+
"learning_rate": 1.3061510361333186e-07,
|
217 |
+
"loss": 0.2198,
|
218 |
+
"reward": 17.2751,
|
219 |
+
"step": 299
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 9.97,
|
223 |
+
"learning_rate": 3.59516649547248e-08,
|
224 |
+
"loss": 0.2581,
|
225 |
+
"reward": 18.2905,
|
226 |
+
"step": 309
|
227 |
+
}
|
228 |
+
],
|
229 |
+
"logging_steps": 500,
|
230 |
+
"max_steps": 310,
|
231 |
+
"num_input_tokens_seen": 0,
|
232 |
+
"num_train_epochs": 10.0,
|
233 |
+
"save_steps": 500,
|
234 |
+
"stateful_callbacks": {},
|
235 |
+
"total_flos": 0,
|
236 |
+
"train_batch_size": null,
|
237 |
+
"trial_name": null,
|
238 |
+
"trial_params": null
|
239 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a23ae21c38266e71e578d342bfc4139cc1cc2a4b433d5167693ea8652df184
|
3 |
+
size 5624
|
training_loss.png
ADDED
![]() |
training_reward.png
ADDED
![]() |
value_head.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2761f60ca79ab817f864324eda7859de479dd405b18bd4feade95cb615a7c6f
|
3 |
+
size 16588
|