Hugging Face's logo

RikkiXu
/
zephyr-7b-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
llama
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
RikkiXu commited on
Commit
a077bdd
•
1 Parent(s): ba454db

Model save

Browse files
Files changed (6) hide show
  1. README.md +10 -6
  2. generation_config.json +1 -1
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. runs/Apr19_23-14-37_n136-148-198/events.out.tfevents.1713539756.n136-148-198.81772.0 +2 -2
README.md CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [imone/Mistral_7B_with_EOT_token](https://huggingface.co/imone/Mistral_7B_with_EOT_token) on the generator dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.7076
23
 
24
  ## Model description
25
 
@@ -49,18 +49,22 @@ The following hyperparameters were used during training:
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: cosine
51
  - lr_scheduler_warmup_ratio: 0.1
52
- - num_epochs: 1
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:-----:|:----:|:---------------:|
58
- | 0.7609 | 1.0 | 59 | 0.7076 |
 
 
 
 
59
 
60
 
61
  ### Framework versions
62
 
63
- - Transformers 4.38.2
64
  - Pytorch 2.1.2+cu118
65
- - Datasets 2.16.1
66
- - Tokenizers 0.15.2
 
19
 
20
  This model is a fine-tuned version of [imone/Mistral_7B_with_EOT_token](https://huggingface.co/imone/Mistral_7B_with_EOT_token) on the generator dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1581
23
 
24
  ## Model description
25
 
 
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: cosine
51
  - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 5
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.6823 | 1.0 | 565 | 0.6283 |
59
+ | 0.4922 | 2.0 | 1130 | 0.3859 |
60
+ | 0.3003 | 3.0 | 1695 | 0.2350 |
61
+ | 0.1776 | 4.0 | 2260 | 0.1633 |
62
+ | 0.0793 | 5.0 | 2825 | 0.1581 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - Transformers 4.40.0
68
  - Pytorch 2.1.2+cu118
69
+ - Datasets 2.18.0
70
+ - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 32000,
5
- "transformers_version": "4.38.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 32000,
5
+ "transformers_version": "4.40.0"
6
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fddeedc3cecfb5d520d1b02e0ce1a79543a346313812eeece2253412ff3bf8cd
3
  size 4943178720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23e38b93eb70a75bc1796a88024daae87822fa1048c276914b3345c1124fa371
3
  size 4943178720
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab40654940614e7eb9857f65a85e048e85554fe6dbf31df6a0ed5247f68e6aa4
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8587edd9d1965007b93ecb6e6421384db0ce99dfc1eaa7a6f08f8ea8d4dbe76d
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:a5600ba9c52e20be1b50a1037346408743643c56a08a26cc6cb39f2dde88ad21
3
  size 4540532728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59633e4e185330e9e5536ea22a6271ef1271c28f0017b294871f73c659a92a8f
3
  size 4540532728
runs/Apr19_23-14-37_n136-148-198/events.out.tfevents.1713539756.n136-148-198.81772.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4de97c27793dd4f1a128edb4058fda58f381bd4f034b78c149a4f1009c61d9d0
3
- size 124212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a4b7bd8c7397fb4cde6740a6a1d8c40a2d7b0d6014f003e04e24cb8a6c071fd
3
+ size 125892