End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: EleutherAI/pythia-1b
+base_model: unsloth/gemma-2b-it
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_461352e1-3da4-46a2-a77a-265bfac04700
+- Aivesa/dataset_37ab15f2-5f4f-40b8-9361-d60418a07bc7
 model-index:
-- name: 6dd4d67e-276b-4a84-a5c8-a7851742b7b4
+- name: 6e568efa-70d1-4597-8684-fda43065c219
   results: []
 ---
 
@@ -21,17 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: EleutherAI/pythia-1b
+base_model: unsloth/gemma-2b-it
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_461352e1-3da4-46a2-a77a-265bfac04700
+  path: Aivesa/dataset_37ab15f2-5f4f-40b8-9361-d60418a07bc7
   type:
-    field_instruction: prompt
-    field_output: label
+    field_input: mt
+    field_instruction: src
+    field_output: ref
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -47,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/6dd4d67e-276b-4a84-a5c8-a7851742b7b4
+hub_model_id: Aivesa/6e568efa-70d1-4597-8684-fda43065c219
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -78,8 +79,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: <|endoftext|>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -89,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 461352e1-3da4-46a2-a77a-265bfac04700
+wandb_name: 37ab15f2-5f4f-40b8-9361-d60418a07bc7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 461352e1-3da4-46a2-a77a-265bfac04700
+wandb_runid: 37ab15f2-5f4f-40b8-9361-d60418a07bc7
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 6dd4d67e-276b-4a84-a5c8-a7851742b7b4
+# 6e568efa-70d1-4597-8684-fda43065c219
 
-This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) on the Aivesa/dataset_461352e1-3da4-46a2-a77a-265bfac04700 dataset.
+This model is a fine-tuned version of [unsloth/gemma-2b-it](https://huggingface.co/unsloth/gemma-2b-it) on the Aivesa/dataset_37ab15f2-5f4f-40b8-9361-d60418a07bc7 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1589
+- Loss: 1.9719
 
 ## Model description
 
@@ -139,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 9.3476        | 0.0002 | 3    | 2.3903          |
-| 10.2456       | 0.0003 | 6    | 2.3352          |
-| 8.507         | 0.0005 | 9    | 2.1589          |
+| 2.0648        | 0.0002 | 3    | 2.6449          |
+| 1.996         | 0.0003 | 6    | 2.4346          |
+| 2.3509        | 0.0005 | 9    | 1.9719          |
 
 
 ### Framework versions