andrewbai commited on
Commit
e0b5ed4
1 Parent(s): 5f5dc6f

End of training

Browse files
Files changed (4) hide show
  1. README.md +7 -1
  2. all_results.json +5 -0
  3. config.json +1 -1
  4. eval_results.json +8 -0
README.md CHANGED
@@ -2,9 +2,15 @@
2
  license: apache-2.0
3
  base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
 
 
 
 
 
8
  model-index:
9
  - name: tinyllama-sft-vicuna-full-rrr100-gaussian
10
  results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # tinyllama-sft-vicuna-full-rrr100-gaussian
17
 
18
- This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.7274
21
 
 
2
  license: apache-2.0
3
  base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
+ - trl
10
+ - sft
11
+ - generated_from_trainer
12
+ datasets:
13
+ - ucla-cmllab/vicuna_cleaned
14
  model-index:
15
  - name: tinyllama-sft-vicuna-full-rrr100-gaussian
16
  results: []
 
21
 
22
  # tinyllama-sft-vicuna-full-rrr100-gaussian
23
 
24
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the ucla-cmllab/vicuna_cleaned dataset.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 0.7274
27
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "total_flos": 106034689474560.0,
4
  "train_loss": 0.7575202535410397,
5
  "train_runtime": 8959.9133,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.7274145483970642,
4
+ "eval_runtime": 9.4155,
5
+ "eval_samples": 500,
6
+ "eval_samples_per_second": 53.104,
7
+ "eval_steps_per_second": 1.699,
8
  "total_flos": 106034689474560.0,
9
  "train_loss": 0.7575202535410397,
10
  "train_runtime": 8959.9133,
config.json CHANGED
@@ -23,6 +23,6 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.40.2",
26
- "use_cache": false,
27
  "vocab_size": 32001
28
  }
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.40.2",
26
+ "use_cache": true,
27
  "vocab_size": 32001
28
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.7274145483970642,
4
+ "eval_runtime": 9.4155,
5
+ "eval_samples": 500,
6
+ "eval_samples_per_second": 53.104,
7
+ "eval_steps_per_second": 1.699
8
+ }