lillian039 commited on
Commit
a257541
1 Parent(s): d8b54c4

End of training

Browse files
README.md CHANGED
@@ -3,9 +3,17 @@ library_name: transformers
3
  license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
5
  tags:
 
6
  - trl
7
  - sft
8
  - generated_from_trainer
 
 
 
 
 
 
 
9
  model-index:
10
  - name: cot-400k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
11
  results: []
@@ -16,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # cot-400k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
18
 
19
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.2160
22
 
 
3
  license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
5
  tags:
6
+ - alignment-handbook
7
  - trl
8
  - sft
9
  - generated_from_trainer
10
+ - trl
11
+ - sft
12
+ - generated_from_trainer
13
+ datasets:
14
+ - barc0/cot_transduction_100k-gpt4omini-description
15
+ - barc0/cot_transduction_100k-gpt4-description
16
+ - barc0/cot_transduction_200k_HEAVY_gpt4o-description
17
  model-index:
18
  - name: cot-400k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
19
  results: []
 
24
 
25
  # cot-400k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
26
 
27
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/cot_transduction_100k-gpt4omini-description, the barc0/cot_transduction_100k-gpt4-description and the barc0/cot_transduction_200k_HEAVY_gpt4o-description datasets.
28
  It achieves the following results on the evaluation set:
29
  - Loss: 0.2160
30
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 2.999499081649691,
 
 
 
 
 
3
  "total_flos": 2.8091411711025807e+18,
4
  "train_loss": 0.2020581066641609,
5
  "train_runtime": 42907.438,
 
1
  {
2
  "epoch": 2.999499081649691,
3
+ "eval_loss": 0.21598096191883087,
4
+ "eval_runtime": 183.8055,
5
+ "eval_samples": 20173,
6
+ "eval_samples_per_second": 109.752,
7
+ "eval_steps_per_second": 1.719,
8
  "total_flos": 2.8091411711025807e+18,
9
  "train_loss": 0.2020581066641609,
10
  "train_runtime": 42907.438,
config.json CHANGED
@@ -35,6 +35,6 @@
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "bfloat16",
37
  "transformers_version": "4.45.0.dev0",
38
- "use_cache": false,
39
  "vocab_size": 128256
40
  }
 
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "bfloat16",
37
  "transformers_version": "4.45.0.dev0",
38
+ "use_cache": true,
39
  "vocab_size": 128256
40
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999499081649691,
3
+ "eval_loss": 0.21598096191883087,
4
+ "eval_runtime": 183.8055,
5
+ "eval_samples": 20173,
6
+ "eval_samples_per_second": 109.752,
7
+ "eval_steps_per_second": 1.719
8
+ }
runs/Nov04_04-48-11_ad3ba0212b1d/events.out.tfevents.1730740668.ad3ba0212b1d.3738.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de984ae1cca00fb3a53c1ca9e67abbe8d8a188451a8cf4cc718d6e2a0b32d3df
3
+ size 359