Model save
Browse files- README.md +7 -13
- all_results.json +5 -5
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +0 -0
README.md
CHANGED
@@ -2,16 +2,9 @@
|
|
2 |
license: mit
|
3 |
base_model: HuggingFaceH4/mistral-7b-sft-beta
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
-
- trl
|
10 |
-
- dpo
|
11 |
-
- alignment-handbook
|
12 |
-
- generated_from_trainer
|
13 |
-
datasets:
|
14 |
-
- HuggingFaceH4/ultrafeedback_binarized
|
15 |
model-index:
|
16 |
- name: DPO-Zephyr-7B
|
17 |
results: []
|
@@ -22,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
22 |
|
23 |
# DPO-Zephyr-7B
|
24 |
|
25 |
-
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -42,13 +35,14 @@ More information needed
|
|
42 |
|
43 |
The following hyperparameters were used during training:
|
44 |
- learning_rate: 5e-07
|
45 |
-
- train_batch_size:
|
46 |
-
- eval_batch_size:
|
47 |
- seed: 42
|
48 |
- distributed_type: multi-GPU
|
49 |
- num_devices: 3
|
50 |
-
-
|
51 |
-
-
|
|
|
52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
- lr_scheduler_type: cosine
|
54 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -61,6 +55,6 @@ The following hyperparameters were used during training:
|
|
61 |
### Framework versions
|
62 |
|
63 |
- Transformers 4.41.2
|
64 |
-
- Pytorch 2.
|
65 |
- Datasets 2.19.1
|
66 |
- Tokenizers 0.19.1
|
|
|
2 |
license: mit
|
3 |
base_model: HuggingFaceH4/mistral-7b-sft-beta
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: DPO-Zephyr-7B
|
10 |
results: []
|
|
|
15 |
|
16 |
# DPO-Zephyr-7B
|
17 |
|
18 |
+
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on an unknown dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- distributed_type: multi-GPU
|
42 |
- num_devices: 3
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 96
|
45 |
+
- total_eval_batch_size: 24
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.41.2
|
58 |
+
- Pytorch 2.3.0+cu121
|
59 |
- Datasets 2.19.1
|
60 |
- Tokenizers 0.19.1
|
all_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 15283,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9984301412872841,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6094696866641255,
|
5 |
+
"train_runtime": 4741.6763,
|
6 |
"train_samples": 15283,
|
7 |
+
"train_samples_per_second": 3.223,
|
8 |
+
"train_steps_per_second": 0.034
|
9 |
}
|
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:f7a71fd86983200a0e9da467d2d7f8faa5ae8e9b0300040f8833bb139b00c1e2
|
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 sha256:3b32a56026769897ec6a84df6af5e995510cdf30f166051e86cf2731a21e2760
|
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 sha256:16c9c1d861d6afe007e669a5c048323be406c2e23f14ccde55c7157235e33b86
|
3 |
size 4540516344
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 15283,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9984301412872841,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6094696866641255,
|
5 |
+
"train_runtime": 4741.6763,
|
6 |
"train_samples": 15283,
|
7 |
+
"train_samples_per_second": 3.223,
|
8 |
+
"train_steps_per_second": 0.034
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|