Model save
Browse files- README.md +18 -27
- all_results.json +6 -7
- config.json +1 -2
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- tokenizer.json +0 -1
- tokenizer_config.json +1 -2
- train_results.json +6 -7
- trainer_state.json +0 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -13,20 +13,19 @@ model-index:
|
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sanqiang/wdpo/runs/dnn9mazg)
|
17 |
# zephyr-7b-dpo-full
|
18 |
|
19 |
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: -
|
23 |
-
- Rewards/rejected: -2.
|
24 |
-
- Rewards/accuracies: 0.
|
25 |
-
- Rewards/margins: 0.
|
26 |
-
- Logps/rejected: -
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected:
|
29 |
-
- Logits/chosen:
|
30 |
|
31 |
## Model description
|
32 |
|
@@ -48,7 +47,7 @@ The following hyperparameters were used during training:
|
|
48 |
- learning_rate: 5e-07
|
49 |
- train_batch_size: 8
|
50 |
- eval_batch_size: 8
|
51 |
-
- seed:
|
52 |
- distributed_type: multi-GPU
|
53 |
- num_devices: 8
|
54 |
- gradient_accumulation_steps: 2
|
@@ -61,25 +60,17 @@ The following hyperparameters were used during training:
|
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
-
| Training Loss | Epoch
|
65 |
-
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.5311 | 0.3979 | 500 | 0.5601 | -2.0743 | -2.7782 | 0.7248 | 0.7039 | -428.5196 | -351.6741 | 0.1321 | -0.1444 |
|
71 |
-
| 0.5658 | 0.4775 | 600 | 0.5562 | -1.9576 | -2.6629 | 0.7192 | 0.7053 | -416.9899 | -340.0069 | 0.9125 | 0.6661 |
|
72 |
-
| 0.556 | 0.5571 | 700 | 0.5502 | -2.1146 | -2.7825 | 0.7201 | 0.6678 | -428.9443 | -355.7084 | 0.9969 | 0.7302 |
|
73 |
-
| 0.5285 | 0.6367 | 800 | 0.5477 | -2.1980 | -2.9456 | 0.7229 | 0.7476 | -445.2567 | -364.0405 | 0.8564 | 0.6029 |
|
74 |
-
| 0.5299 | 0.7163 | 900 | 0.5450 | -2.1121 | -2.8512 | 0.7341 | 0.7391 | -435.8159 | -355.4508 | 0.9832 | 0.7089 |
|
75 |
-
| 0.5629 | 0.7959 | 1000 | 0.5440 | -2.1483 | -2.8941 | 0.7323 | 0.7457 | -440.1051 | -359.0749 | 0.7033 | 0.4600 |
|
76 |
-
| 0.5351 | 0.8754 | 1100 | 0.5423 | -2.1496 | -2.8571 | 0.7304 | 0.7074 | -436.4062 | -359.2066 | 0.5029 | 0.2753 |
|
77 |
-
| 0.5499 | 0.9550 | 1200 | 0.5417 | -2.1562 | -2.8807 | 0.7313 | 0.7245 | -438.7701 | -359.8675 | 0.5902 | 0.3561 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
-
- Transformers 4.
|
83 |
- Pytorch 2.1.2+cu121
|
84 |
- Datasets 2.14.6
|
85 |
-
- Tokenizers 0.
|
|
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
|
|
16 |
# zephyr-7b-dpo-full
|
17 |
|
18 |
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0632
|
21 |
+
- Rewards/chosen: -1.3406
|
22 |
+
- Rewards/rejected: -2.3147
|
23 |
+
- Rewards/accuracies: 0.7734
|
24 |
+
- Rewards/margins: 0.9740
|
25 |
+
- Logps/rejected: -488.8222
|
26 |
+
- Logps/chosen: -391.1042
|
27 |
+
- Logits/rejected: -2.0084
|
28 |
+
- Logits/chosen: -2.0472
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
47 |
- learning_rate: 5e-07
|
48 |
- train_batch_size: 8
|
49 |
- eval_batch_size: 8
|
50 |
+
- seed: 1
|
51 |
- distributed_type: multi-GPU
|
52 |
- num_devices: 8
|
53 |
- gradient_accumulation_steps: 2
|
|
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 0.0717 | 0.21 | 100 | 0.0733 | -0.5920 | -1.1062 | 0.7266 | 0.5142 | -367.9753 | -316.2405 | -2.7130 | -2.7290 |
|
66 |
+
| 0.0672 | 0.42 | 200 | 0.0662 | -0.9311 | -1.7199 | 0.7422 | 0.7888 | -429.3445 | -350.1472 | -2.2044 | -2.2377 |
|
67 |
+
| 0.0648 | 0.63 | 300 | 0.0643 | -1.2563 | -2.1377 | 0.7734 | 0.8814 | -471.1217 | -382.6705 | -2.0727 | -2.1098 |
|
68 |
+
| 0.0636 | 0.84 | 400 | 0.0632 | -1.3406 | -2.3147 | 0.7734 | 0.9740 | -488.8222 | -391.1042 | -2.0084 | -2.0472 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### Framework versions
|
72 |
|
73 |
+
- Transformers 4.35.2
|
74 |
- Pytorch 2.1.2+cu121
|
75 |
- Datasets 2.14.6
|
76 |
+
- Tokenizers 0.14.1
|
all_results.json
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 0
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"train_steps_per_second": 0.125
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.06801126423490596,
|
4 |
+
"train_runtime": 3957.1126,
|
5 |
+
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 15.449,
|
7 |
+
"train_steps_per_second": 0.121
|
|
|
8 |
}
|
config.json
CHANGED
@@ -3,7 +3,6 @@
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
@@ -20,7 +19,7 @@
|
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
|
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "bfloat16",
|
22 |
+
"transformers_version": "4.35.2",
|
23 |
"use_cache": false,
|
24 |
"vocab_size": 32000
|
25 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.35.2"
|
6 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35fc90854c79d5ffff8b99aeab6983babdeedf331e787883bdae0dad492b8a21
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5925362d3801dfbc04556ebaacf5fd331d68765762d80ac3fec9c141f4afdc4
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4be9c60eb07630e94cc8a646e8a301810416b15cc521bb510470dfae40f284b3
|
3 |
size 4540516344
|
tokenizer.json
CHANGED
@@ -134,7 +134,6 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
-
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -36,6 +34,7 @@
|
|
36 |
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
"eos_token": "</s>",
|
|
|
39 |
"model_max_length": 2048,
|
40 |
"pad_token": "</s>",
|
41 |
"sp_model_kwargs": {},
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
34 |
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
"eos_token": "</s>",
|
37 |
+
"legacy": true,
|
38 |
"model_max_length": 2048,
|
39 |
"pad_token": "</s>",
|
40 |
"sp_model_kwargs": {},
|
train_results.json
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 0
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"train_steps_per_second": 0.125
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.06801126423490596,
|
4 |
+
"train_runtime": 3957.1126,
|
5 |
+
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 15.449,
|
7 |
+
"train_steps_per_second": 0.121
|
|
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51d58bbae0c984db37a6e2fc40cc3202c5c85c5f6e2c92d3d9d3ec94f7f79a3d
|
3 |
+
size 5944
|