Hugging Face's logo

CharlesLi
/
llama_2_cot_simplest_code_math_4_full

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
CharlesLi commited on
Commit
abcd850
·
verified ·
1 Parent(s): eea30a6

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_13-05-32_dgx-a100-16/events.out.tfevents.1737374757.dgx-a100-16.3037652.0 +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_4_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: 0.6066
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_4_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": 7.164,
7
  "eval_steps_per_second": 1.433,
8
  "total_flos": 5286836305920.0,
9
- "train_loss": 0.6723248818341423,
10
- "train_runtime": 275.5684,
11
  "train_samples": 7980,
12
- "train_samples_per_second": 5.977,
13
- "train_steps_per_second": 0.185
14
  }
 
6
  "eval_samples_per_second": 7.164,
7
  "eval_steps_per_second": 1.433,
8
  "total_flos": 5286836305920.0,
9
+ "train_loss": 0.6707944402507707,
10
+ "train_runtime": 276.6532,
11
  "train_samples": 7980,
12
+ "train_samples_per_second": 5.953,
13
+ "train_steps_per_second": 0.184
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 sha256:78f936d55e999d9d4bd7c52a1ee571cad764f3e00ad8ce24f671bd6a05a17cd5
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12497161cb5f916a91cc735a4d3a5f861987c1c389c44b3124e253cc3a70897b
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:d88a917bd8a0964fe43a18a602e129111a02cd1e212807af4d424232e5b76029
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb8362c27867f9f5e0f0de4a15b3bb7459ddff5374cf71449689a82e87ba733
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:d31a10c5e1f64e63c27c2ea999c5be7a61913d3c886f34c0ac4af025d7abcbc3
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91db42bace84ce8ea15b460d5a217c9ba941e5cce0d4533f7b5f66e1e9686ac1
3
  size 3590488816
runs/Jan20_13-05-32_dgx-a100-16/events.out.tfevents.1737374757.dgx-a100-16.3037652.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c8126925297d82efbfffe2b1cb37b567f9c8937f54f41231a2d04449bd5fdb
3
+ size 6252
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9902912621359223,
3
  "total_flos": 5286836305920.0,
4
- "train_loss": 0.6723248818341423,
5
- "train_runtime": 275.5684,
6
  "train_samples": 7980,
7
- "train_samples_per_second": 5.977,
8
- "train_steps_per_second": 0.185
9
  }
 
1
  {
2
  "epoch": 0.9902912621359223,
3
  "total_flos": 5286836305920.0,
4
+ "train_loss": 0.6707944402507707,
5
+ "train_runtime": 276.6532,
6
  "train_samples": 7980,
7
+ "train_samples_per_second": 5.953,
8
+ "train_steps_per_second": 0.184
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4f20d9758dedbbcac1272cd9221379f6b7dc1d27254f22519e3e8f5d9f8b84e
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33618765af8902f271990bf253bd84cbaf1a871d705313b56e2bbee6fcd51b3
3
  size 7032