IeBoytsov commited on
Commit
ff4f387
1 Parent(s): fce79fe

End of training

Browse files
Files changed (4) hide show
  1. README.md +11 -2
  2. all_results.json +5 -0
  3. config.json +1 -1
  4. eval_results.json +8 -0
README.md CHANGED
@@ -3,11 +3,20 @@ library_name: transformers
3
  license: llama3.1
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  datasets:
10
- - generator
 
 
 
 
 
11
  model-index:
12
  - name: llama3-1-ox-llms-8b-sft-full-germany-data
13
  results: []
@@ -18,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # llama3-1-ox-llms-8b-sft-full-germany-data
20
 
21
- This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.7417
24
 
 
3
  license: llama3.1
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
+ - alignment-handbook
7
+ - trl
8
+ - sft
9
+ - generated_from_trainer
10
  - trl
11
  - sft
12
  - generated_from_trainer
13
  datasets:
14
+ - oxford-llms/ultrachat_filtered
15
+ - oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered
16
+ - oxford-llms/european_social_survey_2020_sft
17
+ - oxford-llms/european_social_survey_2023_sft
18
+ - oxford-llms/world_values_survey_2017_2022_sft
19
+ - oxford-llms/european_social_survey_2023_germany_sft
20
  model-index:
21
  - name: llama3-1-ox-llms-8b-sft-full-germany-data
22
  results: []
 
27
 
28
  # llama3-1-ox-llms-8b-sft-full-germany-data
29
 
30
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the oxford-llms/ultrachat_filtered, the oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered, the oxford-llms/european_social_survey_2020_sft, the oxford-llms/european_social_survey_2023_sft, the oxford-llms/world_values_survey_2017_2022_sft and the oxford-llms/european_social_survey_2023_germany_sft datasets.
31
  It achieves the following results on the evaluation set:
32
  - Loss: 0.7417
33
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 2.0,
 
 
 
 
 
3
  "total_flos": 879394553856000.0,
4
  "train_loss": 0.6596568237599872,
5
  "train_runtime": 12326.0183,
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_loss": 0.741725742816925,
4
+ "eval_runtime": 110.9341,
5
+ "eval_samples": 46460,
6
+ "eval_samples_per_second": 77.172,
7
+ "eval_steps_per_second": 1.208,
8
  "total_flos": 879394553856000.0,
9
  "train_loss": 0.6596568237599872,
10
  "train_runtime": 12326.0183,
config.json CHANGED
@@ -31,6 +31,6 @@
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.45.1",
34
- "use_cache": false,
35
  "vocab_size": 128256
36
  }
 
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.45.1",
34
+ "use_cache": true,
35
  "vocab_size": 128256
36
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.741725742816925,
4
+ "eval_runtime": 110.9341,
5
+ "eval_samples": 46460,
6
+ "eval_samples_per_second": 77.172,
7
+ "eval_steps_per_second": 1.208
8
+ }