Hugging Face's logo

CharlesLi
/
llama_2_cot_simplest_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
156e4db
·
verified ·
1 Parent(s): 95f7554

Model save

Browse files
Files changed (9) hide show
  1. README.md +1 -6
  2. all_results.json +3 -3
  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_12-37-18_dgx-a100-16/events.out.tfevents.1737373062.dgx-a100-16.3013885.0 +3 -0
  8. train_results.json +3 -3
  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_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: 0.7908
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_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": 5.888,
7
  "eval_steps_per_second": 1.472,
8
  "total_flos": 575794053120.0,
9
- "train_loss": 1.0464420715967815,
10
- "train_runtime": 34.2195,
11
  "train_samples": 980,
12
- "train_samples_per_second": 5.757,
13
  "train_steps_per_second": 0.175
14
  }
 
6
  "eval_samples_per_second": 5.888,
7
  "eval_steps_per_second": 1.472,
8
  "total_flos": 575794053120.0,
9
+ "train_loss": 1.0462158918380737,
10
+ "train_runtime": 34.3419,
11
  "train_samples": 980,
12
+ "train_samples_per_second": 5.736,
13
  "train_steps_per_second": 0.175
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:ae43853091cd63bf48844902d3428ed16cd46440c8338cecf29ec0bc4b7c82bb
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35685eee5947eed673c075e2ef57727702caa3d9aab90113cbb64f190bcc434
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:dd11b23bdc09f0b51dd66c7dbb3dd45a977ab69dfc70a22c708fa023aed2f2bc
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6702647537cb7ca89fbcb10f504afb3854348c186f5ccf4d15447abf7b4866e8
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d5dacbcf4acd2ac5119fa0822ba0f217476fecab078b3ae72ddc9f506aff542
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3502ae6682046b68e1801479907fe1aa5a540bff349174a62f23090c25b8135
3
  size 3590488816
runs/Jan20_12-37-18_dgx-a100-16/events.out.tfevents.1737373062.dgx-a100-16.3013885.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c88e292b6baadb32b77411bbd9ea79a54452d93e7416429059d51b6dc3f224
3
+ size 6252
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9230769230769231,
3
  "total_flos": 575794053120.0,
4
- "train_loss": 1.0464420715967815,
5
- "train_runtime": 34.2195,
6
  "train_samples": 980,
7
- "train_samples_per_second": 5.757,
8
  "train_steps_per_second": 0.175
9
  }
 
1
  {
2
  "epoch": 0.9230769230769231,
3
  "total_flos": 575794053120.0,
4
+ "train_loss": 1.0462158918380737,
5
+ "train_runtime": 34.3419,
6
  "train_samples": 980,
7
+ "train_samples_per_second": 5.736,
8
  "train_steps_per_second": 0.175
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7019e2cf7d61ad44698a6f82d568d8d01a3be42377d6b869d471b3a72e10b313
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d062afaa97a20845bc9cc6a378320e678a09443360f846cebfdd19e46464026a
3
  size 7032