End of training

README.md

@@ -37,7 +37,7 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 200
+eval_steps: 20
 flash_attention: true
 gradient_checkpointing: true
 group_by_length: true
@@ -55,11 +55,13 @@ output_dir: /root/.sn56/axolotl/tmp/opt-125m
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 200
+save_steps: 20
 save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: GPT2TokenizerFast
 torch_dtype: bf16
+training_args_kwargs:
+  hub_private_repo: true
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
@@ -77,6 +79,8 @@ warmup_ratio: 0.05
 # opt-125m
 
 This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the argilla/databricks-dolly-15k-curated-en dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.2130
 
 ## Model description
 
@@ -110,9 +114,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.1667 | 1    | 3.2664          |
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| No log        | 0.1667  | 1    | 3.2664          |
+| 5.5113        | 3.3333  | 20   | 3.2161          |
+| 5.0084        | 6.6667  | 40   | 3.0989          |
+| 4.6384        | 10.0    | 60   | 3.1967          |
+| 4.484         | 13.3333 | 80   | 3.2199          |
+| 4.4609        | 16.6667 | 100  | 3.2130          |
 
 
 ### Framework versions