Hugging Face's logo

CharlesLi
/
mistral_llama_2_code_math_3_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
12ad0d4
·
verified ·
1 Parent(s): fe8551e

Model save

Browse files
Files changed (9) hide show
  1. README.md +0 -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_10-15-51_dgx-a100-16/events.out.tfevents.1737364564.dgx-a100-16.2895241.0 +3 -0
  8. train_results.json +4 -4
  9. training_args.bin +1 -1
README.md CHANGED
@@ -3,10 +3,6 @@ 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
  - alignment-handbook
@@ -24,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
24
  # mistral_llama_2_code_math_3_full
25
 
26
  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.
27
- It achieves the following results on the evaluation set:
28
- - Loss: 0.5203
29
 
30
  ## Model description
31
 
 
3
  license: apache-2.0
4
  base_model: mistralai/Mistral-7B-Instruct-v0.1
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
  - alignment-handbook
 
20
  # mistral_llama_2_code_math_3_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": 4.029,
7
  "eval_steps_per_second": 1.343,
8
  "total_flos": 2250831298560.0,
9
- "train_loss": 0.6714122566309842,
10
- "train_runtime": 124.2809,
11
  "train_samples": 3980,
12
- "train_samples_per_second": 5.721,
13
- "train_steps_per_second": 0.177
14
  }
 
6
  "eval_samples_per_second": 4.029,
7
  "eval_steps_per_second": 1.343,
8
  "total_flos": 2250831298560.0,
9
+ "train_loss": 0.6727288040247831,
10
+ "train_runtime": 125.1337,
11
  "train_samples": 3980,
12
+ "train_samples_per_second": 5.682,
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 sha256:5ab6c1dce9fc9fe3e80d241a48a835f5c6cd8ab9c7dea6f12b8b6ceeef7c89a6
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945908dfe4edf6829341f62d265e32e70ac799658075a937ff70aedc7f3ce2f0
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8569a0e447099b428d092f96237ca550cd2a15c235c81f15f7dfc43b2b283a15
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9115661306449cbd58149bc8580461b60254d7e3fd5536bb2c68b2999283e87
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:f06d0c19e04315ae2caedf95a769ed0db6c2fcab7efd1dc42502c10ae91866b6
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8aa5ab43bd976f1fd9f5b8f12095c3cac4836b8de6c2dd6eebd05264a60825
3
  size 4540516344
runs/Jan20_10-15-51_dgx-a100-16/events.out.tfevents.1737364564.dgx-a100-16.2895241.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3a6c952f0fc24dd0b98500a588b485226e475759547f2763980373e09f3710
3
+ size 6206
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9777777777777777,
3
  "total_flos": 2250831298560.0,
4
- "train_loss": 0.6714122566309842,
5
- "train_runtime": 124.2809,
6
  "train_samples": 3980,
7
- "train_samples_per_second": 5.721,
8
- "train_steps_per_second": 0.177
9
  }
 
1
  {
2
  "epoch": 0.9777777777777777,
3
  "total_flos": 2250831298560.0,
4
+ "train_loss": 0.6727288040247831,
5
+ "train_runtime": 125.1337,
6
  "train_samples": 3980,
7
+ "train_samples_per_second": 5.682,
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:a2c0ad1c7fd3d2b953ab634ee284d737f50746da04fb49280c72364bfbfa0ec3
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a0ae57bebd62d8b5e8215cb335515d40aec4c0da29d573143e1b02a75bb3bc
3
  size 7032