Hugging Face's logo

CharlesLi
/
mistral_llama_2_code_math_1_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
72a6b57
·
verified ·
1 Parent(s): 5d9cd0c

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_09-59-02_dgx-a100-16/events.out.tfevents.1737363554.dgx-a100-16.2881694.0 +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
@@ -23,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
23
  # mistral_llama_2_code_math_1_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: 0.7665
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_1_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": 5.45,
7
  "eval_steps_per_second": 1.362,
8
  "total_flos": 471104225280.0,
9
- "train_loss": 1.0510788440704346,
10
- "train_runtime": 29.8464,
11
  "train_samples": 980,
12
- "train_samples_per_second": 5.83,
13
- "train_steps_per_second": 0.168
14
  }
 
6
  "eval_samples_per_second": 5.45,
7
  "eval_steps_per_second": 1.362,
8
  "total_flos": 471104225280.0,
9
+ "train_loss": 1.0510477542877197,
10
+ "train_runtime": 30.0598,
11
  "train_samples": 980,
12
+ "train_samples_per_second": 5.788,
13
+ "train_steps_per_second": 0.166
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 sha256:8f5a77116d1ee373abdbcce9406f42576f6d9838bdd7a6fa47c57b47c08735b4
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c1cd68f8443898c856c053c4b2664fc8cfd51de4c57eaeec1abc98f68ef97d
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c81d3fe7444eff0ae0b55381ff631b8224bed42836ac69a115ef11170204bfd
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffd4fcad4923b2c46c4e5eab18fbfd3eb72035e5a3d1a518ea3591a55151d8a
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:541f53f11e1c7e30f53e5080d69117b8f12563250b42762f5bf7ef57e9c70927
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c5989ac185178c45ae1d53b60bc8c179c0da1ad847b0e424e96943f90f816f
3
  size 4540516344
runs/Jan20_09-59-02_dgx-a100-16/events.out.tfevents.1737363554.dgx-a100-16.2881694.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae4b70007f795547f79f053ab4f80f0d5bb035686580c81d918d19f696036e5
3
+ size 6206
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9090909090909091,
3
  "total_flos": 471104225280.0,
4
- "train_loss": 1.0510788440704346,
5
- "train_runtime": 29.8464,
6
  "train_samples": 980,
7
- "train_samples_per_second": 5.83,
8
- "train_steps_per_second": 0.168
9
  }
 
1
  {
2
  "epoch": 0.9090909090909091,
3
  "total_flos": 471104225280.0,
4
+ "train_loss": 1.0510477542877197,
5
+ "train_runtime": 30.0598,
6
  "train_samples": 980,
7
+ "train_samples_per_second": 5.788,
8
+ "train_steps_per_second": 0.166
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9755fe21f6372f15554e0ea42990c3799261feba0db41697190f7d9687a35c32
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b29ad49586c4e337d1f37e3eb1f6f090b2cdce6b7a0cc1d53b4c9b6f9e33112
3
  size 7032