Hugging Face's logo

CharlesLi
/
mistral_llama_2_code_math_0_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
24db9d2
·
verified ·
1 Parent(s): faf156c

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_09-48-43_dgx-a100-16/events.out.tfevents.1737362936.dgx-a100-16.2871271.0 +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_0_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: 0.8717
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_0_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": 4.026,
7
  "eval_steps_per_second": 1.342,
8
  "total_flos": 261724569600.0,
9
- "train_loss": 1.163399616877238,
10
- "train_runtime": 18.7784,
11
  "train_samples": 480,
12
- "train_samples_per_second": 4.739,
13
- "train_steps_per_second": 0.16
14
  }
 
6
  "eval_samples_per_second": 4.026,
7
  "eval_steps_per_second": 1.342,
8
  "total_flos": 261724569600.0,
9
+ "train_loss": 1.1633186340332031,
10
+ "train_runtime": 18.98,
11
  "train_samples": 480,
12
+ "train_samples_per_second": 4.689,
13
+ "train_steps_per_second": 0.158
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:a07ea007d78bd0d48bd523688c14319944afea100bef7b3200d7bcb62a1c910f
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd254e65d320a79ebacba4e2402b465078560282d127b31cb1dbe68c780abc1c
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f15f81ace1df79e40f5925242e8fadcf464ba365d4bea49426331e231085a7f
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5037d118b41adcbfef244e0a85f5c229fb20d1db133366a6368c8b2a613a2b5f
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2cc112490fbbd711ae1844f5a9496379520ccd1d7d56a89d5d1fa279204fa9
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376be50743cabee86735b711968ef6ba0280359c674980ce32ed1f13b74a33b1
3
  size 4540516344
runs/Jan20_09-48-43_dgx-a100-16/events.out.tfevents.1737362936.dgx-a100-16.2871271.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4eddfbc21f4a0e0f9bc22e0d9de6cb7026d29c16e2c3f84a6a1e75f14bf169
3
+ size 6206
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 261724569600.0,
4
- "train_loss": 1.163399616877238,
5
- "train_runtime": 18.7784,
6
  "train_samples": 480,
7
- "train_samples_per_second": 4.739,
8
- "train_steps_per_second": 0.16
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 261724569600.0,
4
+ "train_loss": 1.1633186340332031,
5
+ "train_runtime": 18.98,
6
  "train_samples": 480,
7
+ "train_samples_per_second": 4.689,
8
+ "train_steps_per_second": 0.158
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b59feb474c59127d5f77cf70fa81c08363492b0eb2d92f761d9c18239efc01e
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befb9ba6db75092d6daef56d5255911938b1b3650b8c3cd2e2a2938c0d28f510
3
  size 7032