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
dfa2819
·
verified ·
1 Parent(s): c84b80d

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_15-07-38_dgx-a100-16/events.out.tfevents.1737382083.dgx-a100-16.3139806.0 +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_3_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: 0.5615
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_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": 4.337,
7
  "eval_steps_per_second": 1.446,
8
  "total_flos": 2355521126400.0,
9
- "train_loss": 0.8084725193355394,
10
- "train_runtime": 125.7743,
11
  "train_samples": 3980,
12
- "train_samples_per_second": 5.82,
13
- "train_steps_per_second": 0.183
14
  }
 
6
  "eval_samples_per_second": 4.337,
7
  "eval_steps_per_second": 1.446,
8
  "total_flos": 2355521126400.0,
9
+ "train_loss": 0.8085391936094865,
10
+ "train_runtime": 126.1132,
11
  "train_samples": 3980,
12
+ "train_samples_per_second": 5.804,
13
+ "train_steps_per_second": 0.182
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 sha256:636a85180f2ac52850678d66ab727480df261e80775f938c5119c8ec46246a00
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7b42198bf7c5d906d4b94624cdbd4d5ddddf5e61fc474baadb944ba13a9778
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:f75a8ff2f95f380d1f05e466150a1a8e326ddcd3fcad7a57b33858fe1addc36b
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e38743fdfd8815b2f20fa490f9f60626813a95182aca6937570d67207cc6a7
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:c19900aad8079005574fa258b6b37a6e32f77775b8bfac3ca27b7a96240941f2
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e67f075c85ca76b2e2f7bcbbd673d6034ee6a46140f32deb28d9ba50f1088b6
3
  size 3590488816
runs/Jan20_15-07-38_dgx-a100-16/events.out.tfevents.1737382083.dgx-a100-16.3139806.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af87d9b02d67ff30d7174dc06be9d8f95f518e984324cd84ec546d19854af37
3
+ size 6232
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 2355521126400.0,
4
- "train_loss": 0.8084725193355394,
5
- "train_runtime": 125.7743,
6
  "train_samples": 3980,
7
- "train_samples_per_second": 5.82,
8
- "train_steps_per_second": 0.183
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 2355521126400.0,
4
+ "train_loss": 0.8085391936094865,
5
+ "train_runtime": 126.1132,
6
  "train_samples": 3980,
7
+ "train_samples_per_second": 5.804,
8
+ "train_steps_per_second": 0.182
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e86e54df8f53b46fefb78106bf7b0bda377c1e22374566132f0b60a91ecbf4bc
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7672fb6c8908d910f48fca0cbdfcf47b93e9031afd0f85fd590c2f677044512f
3
  size 7032