Hugging Face's logo

CharlesLi
/
llama_2_llama_2_code_math_1_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
7610825
·
verified ·
1 Parent(s): 7cd54bc

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_01-39-20_dgx-a100-13/events.out.tfevents.1737333584.dgx-a100-13.1048645.0 +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_llama_2_code_math_1_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: 0.8347
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_llama_2_code_math_1_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": 5.893,
7
  "eval_steps_per_second": 1.473,
8
  "total_flos": 575794053120.0,
9
- "train_loss": 1.0952184995015461,
10
- "train_runtime": 33.9128,
11
  "train_samples": 980,
12
- "train_samples_per_second": 5.278,
13
- "train_steps_per_second": 0.177
14
  }
 
6
  "eval_samples_per_second": 5.893,
7
  "eval_steps_per_second": 1.473,
8
  "total_flos": 575794053120.0,
9
+ "train_loss": 1.0956947803497314,
10
+ "train_runtime": 34.0419,
11
  "train_samples": 980,
12
+ "train_samples_per_second": 5.258,
13
+ "train_steps_per_second": 0.176
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 sha256:975b7d044e84d980e3e594354b6f3913aa6debf9cb9fba50a7ffcb84d372d5e6
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668b741f618b824309ca2979b545587be37bb45370e4a19da6d0d30d141db4e3
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:d1c2d8e99f902eca2ab7b6fee2e35dc9e85b7b30afb7da278d2976b6a03c70af
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe54da6c852dc98f43958707f3bffe27ff31791bad102a4433b02c577c35107
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:a868696dd1f0b9d24cf36c86551a19d566e4d723b1a364b9c4e0e29ea97f77f1
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe270ea436a36ce500feaca503a60f3654ad5c09f5687d80205db9bbcd34fbc1
3
  size 3590488816
runs/Jan20_01-39-20_dgx-a100-13/events.out.tfevents.1737333584.dgx-a100-13.1048645.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a032e7268d6eb259a1235da364a99937db61af51301560b3303fe157f1e1fb1d
3
+ size 6232
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 575794053120.0,
4
- "train_loss": 1.0952184995015461,
5
- "train_runtime": 33.9128,
6
  "train_samples": 980,
7
- "train_samples_per_second": 5.278,
8
- "train_steps_per_second": 0.177
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 575794053120.0,
4
+ "train_loss": 1.0956947803497314,
5
+ "train_runtime": 34.0419,
6
  "train_samples": 980,
7
+ "train_samples_per_second": 5.258,
8
+ "train_steps_per_second": 0.176
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:927aa3b0d7c6a4c9b16c9c4792ef05712d18be98ff103a0fa3babc2509080b1c
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09a603c768db55c439e659e341ce1c028c855d6514c6d1bb80f5b485e048008
3
  size 7032