Hugging Face's logo

CharlesLi
/
mistral_sky_o1_4_full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
CharlesLi commited on
Commit
25c2a58
·
verified ·
1 Parent(s): 28a60e4

Model save

Browse files
Files changed (9) hide show
  1. README.md +7 -10
  2. all_results.json +4 -4
  3. config.json +1 -1
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. runs/Jan15_01-37-59_dgx-a100-12/events.out.tfevents.1736901494.dgx-a100-12.2747584.0 +3 -0
  8. train_results.json +4 -4
  9. training_args.bin +1 -1
README.md CHANGED
@@ -3,12 +3,9 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: mistralai/Mistral-7B-Instruct-v0.1
5
  tags:
6
- - alignment-handbook
7
- - trl
8
- - sft
9
- - generated_from_trainer
10
  - trl
11
  - sft
 
12
  - generated_from_trainer
13
  datasets:
14
  - generator
@@ -24,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
24
 
25
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 0.6210
28
 
29
  ## Model description
30
 
@@ -61,11 +58,11 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss |
63
  |:-------------:|:------:|:----:|:---------------:|
64
- | 0.7194 | 0.1678 | 100 | 0.7477 |
65
- | 0.6594 | 0.3356 | 200 | 0.7239 |
66
- | 0.6202 | 0.5034 | 300 | 0.6907 |
67
- | 0.5893 | 0.6711 | 400 | 0.6459 |
68
- | 0.5357 | 0.8389 | 500 | 0.6271 |
69
 
70
 
71
  ### Framework versions
 
3
  license: apache-2.0
4
  base_model: mistralai/Mistral-7B-Instruct-v0.1
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  datasets:
11
  - generator
 
21
 
22
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.6199
25
 
26
  ## Model description
27
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss |
60
  |:-------------:|:------:|:----:|:---------------:|
61
+ | 0.719 | 0.1678 | 100 | 0.7392 |
62
+ | 0.6588 | 0.3356 | 200 | 0.7134 |
63
+ | 0.6216 | 0.5034 | 300 | 0.6813 |
64
+ | 0.5948 | 0.6711 | 400 | 0.6399 |
65
+ | 0.5367 | 0.8389 | 500 | 0.6199 |
66
 
67
 
68
  ### Framework versions
all_results.json CHANGED
@@ -6,9 +6,9 @@
6
  "eval_samples_per_second": 20.826,
7
  "eval_steps_per_second": 1.436,
8
  "total_flos": 62342792478720.0,
9
- "train_loss": 0.60753967898004,
10
- "train_runtime": 3648.7841,
11
  "train_samples": 7980,
12
- "train_samples_per_second": 5.227,
13
- "train_steps_per_second": 0.163
14
  }
 
6
  "eval_samples_per_second": 20.826,
7
  "eval_steps_per_second": 1.436,
8
  "total_flos": 62342792478720.0,
9
+ "train_loss": 0.6085060262840066,
10
+ "train_runtime": 3395.7329,
11
  "train_samples": 7980,
12
+ "train_samples_per_second": 5.616,
13
+ "train_steps_per_second": 0.176
14
  }
config.json CHANGED
@@ -22,6 +22,6 @@
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.44.2",
25
- "use_cache": true,
26
  "vocab_size": 32000
27
  }
 
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.44.2",
25
+ "use_cache": false,
26
  "vocab_size": 32000
27
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:550215e7fb7d5cdcf61fd0d4f71ed8ca1a05f7fb38b58ca1e1e9e5595a98e5ab
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23708962e201d64465336e287dd13ce4bdc6af8eaa10906e9e4571765ffbcd45
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:865e69ea76db5bdbb68d314ad0b37f576f6878a14bfa3a965151987b89cc3a8f
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2093368e228778812775cb4be007420e55fc24be7ae89e4abb8baf79ac052a22
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff5fbf2785f1de33d825ca11fa1968853d9fda710d0de9b8e30323813e383d8
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01c6356a0a5d7e2bce4c8ec7c045485203d3df430590e4fa378105e46b2e733
3
  size 4540516344
runs/Jan15_01-37-59_dgx-a100-12/events.out.tfevents.1736901494.dgx-a100-12.2747584.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4230ad576d937e13b68497a753e82f2f59d178622e5bbe34900ae3b2690211b6
3
+ size 8569
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 62342792478720.0,
4
- "train_loss": 0.60753967898004,
5
- "train_runtime": 3648.7841,
6
  "train_samples": 7980,
7
- "train_samples_per_second": 5.227,
8
- "train_steps_per_second": 0.163
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 62342792478720.0,
4
+ "train_loss": 0.6085060262840066,
5
+ "train_runtime": 3395.7329,
6
  "train_samples": 7980,
7
+ "train_samples_per_second": 5.616,
8
+ "train_steps_per_second": 0.176
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f59bb672d9b09a9ca332a54ed5d060bce6c5dfd8656964bdac06a83c51fc8cf
3
  size 6968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64b92998ae969041d234e075dd645b0417770b4dbe7f16443c9944eb0dfbf86
3
  size 6968