End of training

README.md

@@ -36,7 +36,7 @@ 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
@@ -54,7 +54,7 @@ output_dir: /root/.sn56/axolotl/tmp/tiny-random-LlamaForCausalLM
 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: LlamaTokenizerFast
@@ -78,6 +78,8 @@ warmup_ratio: 0.05
 # tiny-random-LlamaForCausalLM
 
 This model is a fine-tuned version of [trl-internal-testing/tiny-random-LlamaForCausalLM](https://huggingface.co/trl-internal-testing/tiny-random-LlamaForCausalLM) on the argilla/databricks-dolly-15k-curated-en dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.1817
 
 ## Model description
 
@@ -111,9 +113,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.1667 | 1    | 10.3764         |
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| No log        | 0.1667  | 1    | 10.3764         |
+| 10.3632       | 3.3333  | 20   | 10.3538         |
+| 10.3073       | 6.6667  | 40   | 10.2840         |
+| 10.2203       | 10.0    | 60   | 10.2082         |
+| 10.1812       | 13.3333 | 80   | 10.1828         |
+| 10.1767       | 16.6667 | 100  | 10.1817         |
 
 
 ### Framework versions