Hugging Face's logo

CharlesLi
/
llama_2_cot_simplest_code_math_0_full

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
CharlesLi commited on
Commit
56665da
·
verified ·
1 Parent(s): d0d1ce4

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_12-28-48_dgx-a100-16/events.out.tfevents.1737372552.dgx-a100-16.3006990.0 +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: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
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
  # llama_2_cot_simplest_code_math_0_full
24
 
25
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
26
- It achieves the following results on the evaluation set:
27
- - Loss: 0.8126
28
 
29
  ## Model description
30
 
 
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  datasets:
11
  - generator
 
20
  # llama_2_cot_simplest_code_math_0_full
21
 
22
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
 
 
23
 
24
  ## Model description
25
 
all_results.json CHANGED
@@ -6,9 +6,9 @@
6
  "eval_samples_per_second": 4.306,
7
  "eval_steps_per_second": 1.435,
8
  "total_flos": 261724569600.0,
9
- "train_loss": 1.2943166097005208,
10
- "train_runtime": 18.2243,
11
  "train_samples": 480,
12
- "train_samples_per_second": 5.487,
13
- "train_steps_per_second": 0.165
14
  }
 
6
  "eval_samples_per_second": 4.306,
7
  "eval_steps_per_second": 1.435,
8
  "total_flos": 261724569600.0,
9
+ "train_loss": 1.2942499319712322,
10
+ "train_runtime": 18.319,
11
  "train_samples": 480,
12
+ "train_samples_per_second": 5.459,
13
+ "train_steps_per_second": 0.164
14
  }
config.json CHANGED
@@ -24,6 +24,6 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.2",
27
- "use_cache": true,
28
  "vocab_size": 32000
29
  }
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.2",
27
+ "use_cache": false,
28
  "vocab_size": 32000
29
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f33fb21ea90b0a66575247b0065c77730fce1b0acda340373a0564df379190c3
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfd8e358486529e549f1e4ceca3e0f4efa391908736815282b4a5465d8a4c41
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b29de26d01d0129f3dfa9806f30dc616bdd09fc91efa3a8f738b8c8486e0fcc5
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f87c9986e149cb62845f7e4a836ab776a9c6dafa22936ea653e89cf4c1ea4a
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd696e77b4ad16689c7689aee956336fd5944575d556127c3b4ddee017238870
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0d3a3265852392a5302ce0d712e46b8b1626db39ec049cce3899cc9fa2ffb6
3
  size 3590488816
runs/Jan20_12-28-48_dgx-a100-16/events.out.tfevents.1737372552.dgx-a100-16.3006990.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665d738242e1b13d0c00d8f6fe9b94f0e2be29c71cb57069bab50b981fc71526
3
+ size 6252
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.8571428571428571,
3
  "total_flos": 261724569600.0,
4
- "train_loss": 1.2943166097005208,
5
- "train_runtime": 18.2243,
6
  "train_samples": 480,
7
- "train_samples_per_second": 5.487,
8
- "train_steps_per_second": 0.165
9
  }
 
1
  {
2
  "epoch": 0.8571428571428571,
3
  "total_flos": 261724569600.0,
4
+ "train_loss": 1.2942499319712322,
5
+ "train_runtime": 18.319,
6
  "train_samples": 480,
7
+ "train_samples_per_second": 5.459,
8
+ "train_steps_per_second": 0.164
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8fb39e50368fd44aa5e27bed6fd3a78abae711c525d19fd0d0cc7e4fe2d02f9
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcdea815257fbef0fdd85fc5ae711de7bb826c1db60ec750409bd832684a43cf
3
  size 7032