Hugging Face's logo

CharlesLi
/
mistral_llama_2_code_math_2_full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
CharlesLi commited on
Commit
24e9b00
·
verified ·
1 Parent(s): d028337

Model save

Browse files
Files changed (9) hide show
  1. README.md +1 -6
  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/Jan20_00-45-21_dgx-a100-14/events.out.tfevents.1737330334.dgx-a100-14.626547.0 +2 -2
  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
@@ -23,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
23
  # mistral_llama_2_code_math_2_full
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: 0.5571
28
 
29
  ## Model description
30
 
 
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
 
20
  # mistral_llama_2_code_math_2_full
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
 
24
  ## Model description
25
 
all_results.json CHANGED
@@ -6,9 +6,9 @@
6
  "eval_samples_per_second": 4.092,
7
  "eval_steps_per_second": 1.364,
8
  "total_flos": 1099243192320.0,
9
- "train_loss": 0.7461842623623934,
10
- "train_runtime": 63.413,
11
  "train_samples": 1980,
12
- "train_samples_per_second": 5.582,
13
- "train_steps_per_second": 0.173
14
  }
 
6
  "eval_samples_per_second": 4.092,
7
  "eval_steps_per_second": 1.364,
8
  "total_flos": 1099243192320.0,
9
+ "train_loss": 0.7459995963356711,
10
+ "train_runtime": 63.2097,
11
  "train_samples": 1980,
12
+ "train_samples_per_second": 5.6,
13
+ "train_steps_per_second": 0.174
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:ff5a8e514779a26d1de89ec4ed74ff15c884a8eb35196477533fca165d31e764
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b49e6b689122420780d2bbc17bc62755f91fe714641a504349f2be94265a20b
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:d77eb5cc40f6c5877dc4d4e7189ae5482bc0bd276727aec85419533c40859327
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91ad53568792781574a517629b8d06e0303bff20842da6d179b5b7b6df8f47e
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3536b37df4213b22da5610719a90474982048df3b7ce732737c5815125a0120f
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9ea1713d9daedef8e967cfd8f10c243bdea5102c61b7c0ab13bb88e0666d4c
3
  size 4540516344
runs/Jan20_00-45-21_dgx-a100-14/events.out.tfevents.1737330334.dgx-a100-14.626547.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13b16fe9b93f10ac9717c5b2dc5993b8266761de1b88f1c6fa5b13ed2ea5cacd
3
- size 5858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cf596a4e967dbf027673f2ad66126c2b291e4848c538c0a2b1d7fa5ffdba91
3
+ size 6206
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9565217391304348,
3
  "total_flos": 1099243192320.0,
4
- "train_loss": 0.7461842623623934,
5
- "train_runtime": 63.413,
6
  "train_samples": 1980,
7
- "train_samples_per_second": 5.582,
8
- "train_steps_per_second": 0.173
9
  }
 
1
  {
2
  "epoch": 0.9565217391304348,
3
  "total_flos": 1099243192320.0,
4
+ "train_loss": 0.7459995963356711,
5
+ "train_runtime": 63.2097,
6
  "train_samples": 1980,
7
+ "train_samples_per_second": 5.6,
8
+ "train_steps_per_second": 0.174
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22ecb097f126e80a6663242ae15b983699273371b8a2e095464435822e07e6c5
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64aef40a95849903b90d6a81f7a5b8ceecf0739c1beb58d397cf5208d9ae0eb
3
  size 7032