Hugging Face's logo

CharlesLi
/
llama_2_cot_simplest_code_math_2_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
0fb0e3f
·
verified ·
1 Parent(s): 816446f

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_12-46-00_dgx-a100-16/events.out.tfevents.1737373585.dgx-a100-16.3020951.0 +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_2_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: 0.5966
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_2_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": 4.358,
7
  "eval_steps_per_second": 1.453,
8
  "total_flos": 1203933020160.0,
9
- "train_loss": 0.9038037260373434,
10
- "train_runtime": 66.4635,
11
  "train_samples": 1980,
12
- "train_samples_per_second": 6.003,
13
- "train_steps_per_second": 0.181
14
  }
 
6
  "eval_samples_per_second": 4.358,
7
  "eval_steps_per_second": 1.453,
8
  "total_flos": 1203933020160.0,
9
+ "train_loss": 0.9035463134447733,
10
+ "train_runtime": 66.7538,
11
  "train_samples": 1980,
12
+ "train_samples_per_second": 5.977,
13
+ "train_steps_per_second": 0.18
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 sha256:2512b67c105edd7f0c81376797f479c115ac74611730e7a3e64b78c4cb712913
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7da9c99a48adc0cc161125a43f9a02655546270b1da3c7b6dcb632355e0bb9
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf684c7fd93044df20047eba46821ad90cf59f81dee4ff0f1ab412090a363f4
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa89eb53f3b0044b63edfdaeed7427074fbfac7411c0446afd5fb809f00aee8
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e62446246cd1cd4053515fbf852e99e158fd72207811b37aa26fd7d6118278f
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e1762738152584ae098751473c6ec9ebab81f53d5a99e60e2e63136862729a
3
  size 3590488816
runs/Jan20_12-46-00_dgx-a100-16/events.out.tfevents.1737373585.dgx-a100-16.3020951.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22eb9ad492fc4a917166a4490c4726eb3126dd686556e2a993c8c8d491ed04c1
3
+ size 6252
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.96,
3
  "total_flos": 1203933020160.0,
4
- "train_loss": 0.9038037260373434,
5
- "train_runtime": 66.4635,
6
  "train_samples": 1980,
7
- "train_samples_per_second": 6.003,
8
- "train_steps_per_second": 0.181
9
  }
 
1
  {
2
  "epoch": 0.96,
3
  "total_flos": 1203933020160.0,
4
+ "train_loss": 0.9035463134447733,
5
+ "train_runtime": 66.7538,
6
  "train_samples": 1980,
7
+ "train_samples_per_second": 5.977,
8
+ "train_steps_per_second": 0.18
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d8ae6ec1387ac91c62bfc1b1d8c2e3cb055fb099626fd39598b81c19428a619
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad72b7224f96c501acc18ffc8cdd3b6a4b55351c9deb12cc2855f76e4f95854
3
  size 7032