Model save
Browse files- README.md +29 -25
- all_results.json +6 -5
- config.json +2 -1
- 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 +1 -0
- tokenizer_config.json +2 -1
- train_results.json +6 -5
- trainer_state.json +0 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -13,19 +13,23 @@ 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 |
# 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.
|
21 |
-
- Rewards/chosen: -
|
22 |
-
- Rewards/rejected: -
|
23 |
-
- Rewards/accuracies: 0.
|
24 |
-
- Rewards/margins: 0.
|
25 |
-
- Logps/rejected: -
|
26 |
-
- Logps/chosen: -
|
27 |
-
- Logits/rejected:
|
28 |
-
- Logits/chosen:
|
|
|
|
|
|
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -60,25 +64,25 @@ The following hyperparameters were used during training:
|
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
-
| Training Loss | Epoch
|
64 |
-
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
|
78 |
|
79 |
### Framework versions
|
80 |
|
81 |
-
- Transformers 4.
|
82 |
- Pytorch 2.1.2+cu121
|
83 |
- Datasets 2.14.6
|
84 |
-
- 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 |
+
[<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/593342mu)
|
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: 0.0314
|
22 |
+
- Rewards/chosen: -1.8016
|
23 |
+
- Rewards/rejected: -2.3386
|
24 |
+
- Rewards/accuracies: 0.6996
|
25 |
+
- Rewards/margins: 0.5369
|
26 |
+
- Logps/rejected: -384.5558
|
27 |
+
- Logps/chosen: -324.4056
|
28 |
+
- Logits/rejected: -1.9462
|
29 |
+
- Logits/chosen: -1.9728
|
30 |
+
- Debug/policy Weights: 0.0527
|
31 |
+
- Debug/losses: 0.0295
|
32 |
+
- Debug/raw Losses: 0.5653
|
33 |
|
34 |
## Model description
|
35 |
|
|
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Debug/policy Weights | Debug/losses | Debug/raw Losses |
|
68 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------------------:|:------------:|:----------------:|
|
69 |
+
| 0.1733 | 0.0796 | 100 | 0.1633 | -0.1419 | -0.1761 | 0.5979 | 0.0341 | -168.3045 | -158.4381 | -2.7036 | -2.7117 | 0.2384 | 0.1618 | 0.6787 |
|
70 |
+
| 0.0826 | 0.1592 | 200 | 0.0750 | -0.7884 | -1.0004 | 0.6362 | 0.2120 | -250.7415 | -223.0814 | -2.5404 | -2.5508 | 0.1172 | 0.0736 | 0.6317 |
|
71 |
+
| 0.0515 | 0.2388 | 300 | 0.0573 | -1.2448 | -1.6060 | 0.6567 | 0.3612 | -311.3039 | -268.7243 | -2.3397 | -2.3553 | 0.0902 | 0.0558 | 0.6134 |
|
72 |
+
| 0.0343 | 0.3183 | 400 | 0.0302 | -1.7725 | -2.1338 | 0.6623 | 0.3614 | -364.0837 | -321.4913 | -2.2855 | -2.3007 | 0.0482 | 0.0284 | 0.5994 |
|
73 |
+
| 0.0432 | 0.3979 | 500 | 0.0432 | -1.5065 | -1.9835 | 0.6800 | 0.4770 | -349.0468 | -294.8951 | -2.2406 | -2.2643 | 0.0702 | 0.0407 | 0.5892 |
|
74 |
+
| 0.0342 | 0.4775 | 600 | 0.0321 | -1.8281 | -2.3049 | 0.6875 | 0.4769 | -381.1920 | -327.0503 | -2.1134 | -2.1351 | 0.0527 | 0.0302 | 0.5812 |
|
75 |
+
| 0.0283 | 0.5571 | 700 | 0.0283 | -1.8441 | -2.2808 | 0.6940 | 0.4366 | -378.7769 | -328.6566 | -1.9677 | -1.9900 | 0.0467 | 0.0268 | 0.5766 |
|
76 |
+
| 0.023 | 0.6367 | 800 | 0.0244 | -2.0670 | -2.5677 | 0.6884 | 0.5008 | -407.4723 | -350.9413 | -1.9268 | -1.9515 | 0.0400 | 0.0228 | 0.5787 |
|
77 |
+
| 0.032 | 0.7163 | 900 | 0.0335 | -1.7467 | -2.2731 | 0.6847 | 0.5264 | -378.0125 | -318.9173 | -1.9262 | -1.9521 | 0.0559 | 0.0316 | 0.5720 |
|
78 |
+
| 0.0294 | 0.7959 | 1000 | 0.0289 | -1.9406 | -2.4746 | 0.6866 | 0.5340 | -398.1603 | -338.3062 | -1.9318 | -1.9580 | 0.0484 | 0.0271 | 0.5695 |
|
79 |
+
| 0.0308 | 0.8754 | 1100 | 0.0311 | -1.8111 | -2.3364 | 0.7006 | 0.5253 | -384.3376 | -325.3560 | -1.9554 | -1.9814 | 0.0520 | 0.0291 | 0.5657 |
|
80 |
+
| 0.0303 | 0.9550 | 1200 | 0.0314 | -1.8016 | -2.3386 | 0.6996 | 0.5369 | -384.5558 | -324.4056 | -1.9462 | -1.9728 | 0.0527 | 0.0295 | 0.5653 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
84 |
|
85 |
+
- Transformers 4.41.0.dev0
|
86 |
- Pytorch 2.1.2+cu121
|
87 |
- Datasets 2.14.6
|
88 |
+
- Tokenizers 0.19.1
|
all_results.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
|
|
5 |
"train_samples": 160800,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9996020692399522,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.05419013021620595,
|
5 |
+
"train_runtime": 10439.8283,
|
6 |
"train_samples": 160800,
|
7 |
+
"train_samples_per_second": 15.403,
|
8 |
+
"train_steps_per_second": 0.12
|
9 |
}
|
config.json
CHANGED
@@ -3,6 +3,7 @@
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
@@ -19,7 +20,7 @@
|
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "bfloat16",
|
22 |
-
"transformers_version": "4.
|
23 |
"use_cache": false,
|
24 |
"vocab_size": 32000
|
25 |
}
|
|
|
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 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.41.0.dev0",
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
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": "4.41.0.dev0"
|
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 sha256:624756bc628d67c51f273fac678e315f8ba6fd54288ea173f833e9ae718b95a2
|
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:f15755f429340b206c16ed567b979564aececf809a2f9dd51e631db5b3263259
|
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 sha256:378e6024c6dcbae3d23d4d81403dcddd0b3c7461b5bd3d67ca94d6038178f1e8
|
3 |
size 4540516344
|
tokenizer.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
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,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -34,7 +36,6 @@
|
|
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": {},
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
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": {},
|
train_results.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
|
|
5 |
"train_samples": 160800,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9996020692399522,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.05419013021620595,
|
5 |
+
"train_runtime": 10439.8283,
|
6 |
"train_samples": 160800,
|
7 |
+
"train_samples_per_second": 15.403,
|
8 |
+
"train_steps_per_second": 0.12
|
9 |
}
|
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:a93e4ac4c3121c6e616e15a605b2e1203065f3210634f1848b3deea40c1d6c8d
|
3 |
+
size 6456
|