Hugging Face's logo

VedaantJain
/
llama_check_tuned

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
alignment-handbook
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
VedaantJain commited on
Commit
cbde16a
·
verified ·
1 Parent(s): 3f4d70e

End of training

Browse files
Files changed (4) hide show
  1. README.md +1 -0
  2. all_results.json +4 -4
  3. config.json +1 -1
  4. eval_results.json +4 -4
README.md CHANGED
@@ -4,6 +4,7 @@ library_name: transformers
4
  model_name: llama_check_tuned
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - sft
9
  licence: license
 
4
  model_name: llama_check_tuned
5
  tags:
6
  - generated_from_trainer
7
+ - alignment-handbook
8
  - trl
9
  - sft
10
  licence: license
all_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "epoch": 40.0,
3
- "eval_loss": 0.0012466020416468382,
4
- "eval_runtime": 0.1713,
5
  "eval_samples": 10,
6
- "eval_samples_per_second": 58.378,
7
- "eval_steps_per_second": 11.676,
8
  "total_flos": 4849620932886528.0,
9
  "train_loss": 0.7576449837215478,
10
  "train_runtime": 31.485,
 
1
  {
2
  "epoch": 40.0,
3
+ "eval_loss": 0.0013022046769037843,
4
+ "eval_runtime": 0.1689,
5
  "eval_samples": 10,
6
+ "eval_samples_per_second": 59.221,
7
+ "eval_steps_per_second": 11.844,
8
  "total_flos": 4849620932886528.0,
9
  "train_loss": 0.7576449837215478,
10
  "train_runtime": 31.485,
config.json CHANGED
@@ -36,6 +36,6 @@
36
  "tie_word_embeddings": true,
37
  "torch_dtype": "bfloat16",
38
  "transformers_version": "4.46.3",
39
- "use_cache": false,
40
  "vocab_size": 128256
41
  }
 
36
  "tie_word_embeddings": true,
37
  "torch_dtype": "bfloat16",
38
  "transformers_version": "4.46.3",
39
+ "use_cache": true,
40
  "vocab_size": 128256
41
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 40.0,
3
- "eval_loss": 0.0012466020416468382,
4
- "eval_runtime": 0.1713,
5
  "eval_samples": 10,
6
- "eval_samples_per_second": 58.378,
7
- "eval_steps_per_second": 11.676
8
  }
 
1
  {
2
  "epoch": 40.0,
3
+ "eval_loss": 0.0013022046769037843,
4
+ "eval_runtime": 0.1689,
5
  "eval_samples": 10,
6
+ "eval_samples_per_second": 59.221,
7
+ "eval_steps_per_second": 11.844
8
  }