Hugging Face's logo

CharlesLi
/
llama_2_llama_2_code_math_3_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
c2d9896
·
verified ·
1 Parent(s): 24fda6b

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_01-58-04_dgx-a100-13/events.out.tfevents.1737334709.dgx-a100-13.1064354.0 +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_3_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: 0.5600
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_3_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": 4.383,
7
  "eval_steps_per_second": 1.461,
8
  "total_flos": 2355521126400.0,
9
- "train_loss": 0.8079630913941757,
10
- "train_runtime": 124.3693,
11
  "train_samples": 3980,
12
- "train_samples_per_second": 5.886,
13
- "train_steps_per_second": 0.185
14
  }
 
6
  "eval_samples_per_second": 4.383,
7
  "eval_steps_per_second": 1.461,
8
  "total_flos": 2355521126400.0,
9
+ "train_loss": 0.8085134029388428,
10
+ "train_runtime": 124.957,
11
  "train_samples": 3980,
12
+ "train_samples_per_second": 5.858,
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:e36dd4ea81f220d377202b99b36a7b0b7eeee6256640e6c5bb0a3708a34c2940
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4040db42a46f7523836c71e1ab02b191a26c4e1fab25fb6338992b0b88187e6
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:f12be66eea3195e0d8c17c2b51fa8cf49ba60b01a02068922f59f2a914ab08ec
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec29cfc71810cfcd427d11f376f5c33c1e2eec187621f782cd17545075795be5
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d79ed781b4f1bd87cedb8ff421805f3f667fc934f84f0913dc7dbc096b34673
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486d0a9de5d9f1dc43d03127e3b712db9ac81eea34d60a869f30598c33ea3b8f
3
  size 3590488816
runs/Jan20_01-58-04_dgx-a100-13/events.out.tfevents.1737334709.dgx-a100-13.1064354.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40e209e0fc887aba0c7267c43ffb157e55a12659d1a5ac77eed5e4b832c7056
3
+ size 6232
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 2355521126400.0,
4
- "train_loss": 0.8079630913941757,
5
- "train_runtime": 124.3693,
6
  "train_samples": 3980,
7
- "train_samples_per_second": 5.886,
8
- "train_steps_per_second": 0.185
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 2355521126400.0,
4
+ "train_loss": 0.8085134029388428,
5
+ "train_runtime": 124.957,
6
  "train_samples": 3980,
7
+ "train_samples_per_second": 5.858,
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:b48bc61576e69d19b72e48a09f0d9ee2d7c52badcc5435bf328bc4b9b9da99d7
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c45e607b85af02a839d116f683965b85d55a2ac605b05ce9695567cee9dda5
3
  size 7032