Hugging Face's logo

CharlesLi
/
llama_2_llama_2_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
775e748
·
verified ·
1 Parent(s): 7250bbf

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_14-58-10_dgx-a100-16/events.out.tfevents.1737381515.dgx-a100-16.3131827.0 +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: 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
  - alignment-handbook
@@ -24,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
24
  # llama_2_llama_2_code_math_2_full
25
 
26
  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.
27
- It achieves the following results on the evaluation set:
28
- - Loss: 0.6200
29
 
30
  ## Model description
31
 
 
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
  - alignment-handbook
 
20
  # llama_2_llama_2_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": 4.299,
7
  "eval_steps_per_second": 1.433,
8
  "total_flos": 1099243192320.0,
9
- "train_loss": 0.9574010155417703,
10
- "train_runtime": 61.1377,
11
  "train_samples": 1980,
12
- "train_samples_per_second": 5.97,
13
- "train_steps_per_second": 0.18
14
  }
 
6
  "eval_samples_per_second": 4.299,
7
  "eval_steps_per_second": 1.433,
8
  "total_flos": 1099243192320.0,
9
+ "train_loss": 0.9574380354447798,
10
+ "train_runtime": 61.4345,
11
  "train_samples": 1980,
12
+ "train_samples_per_second": 5.941,
13
+ "train_steps_per_second": 0.179
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:f6e20a574ff68516546064bc2956340ed9ddef740e48c18141f2bf0f56feae04
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbbbbfc110e5b347e1030739f45a6a0825c2a7b0964f95848e70c6b4e1adbe8
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dae3ea5197ea7b966bc7010a528cd7ffc0c7962a06fc094cb1d3ddcb0a0dc42
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739f03cb7184b4fa20e9699a358aed75bee3050e1119ad801e7aa909f4a69259
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:b1e5608e4168009c7f48b81e0e508ee7df2474833c6cb75973dc7204448b17ae
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b5453fce5572dca51777b3a1dc76804006a429efb8a878be2e95adce02806d
3
  size 3590488816
runs/Jan20_14-58-10_dgx-a100-16/events.out.tfevents.1737381515.dgx-a100-16.3131827.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8d1e7731bacd134fe27e40838d08f8ad173e7c14c9215aad8fc689290c3082
3
+ size 6232
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9565217391304348,
3
  "total_flos": 1099243192320.0,
4
- "train_loss": 0.9574010155417703,
5
- "train_runtime": 61.1377,
6
  "train_samples": 1980,
7
- "train_samples_per_second": 5.97,
8
- "train_steps_per_second": 0.18
9
  }
 
1
  {
2
  "epoch": 0.9565217391304348,
3
  "total_flos": 1099243192320.0,
4
+ "train_loss": 0.9574380354447798,
5
+ "train_runtime": 61.4345,
6
  "train_samples": 1980,
7
+ "train_samples_per_second": 5.941,
8
+ "train_steps_per_second": 0.179
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15f670718f9b90c35dcb495d8dc12a7f9007e47ab16c264353d9ea4741f49c2a
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044f1d951fccb86ee3ca98b30a0d59ed26a925f6cbfaa5c2515d8f820ae067c2
3
  size 7032