End of training

README.md

@@ -1,13 +1,13 @@
 ---
 library_name: peft
-base_model: katuni4ka/tiny-random-codegen2
+base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_86c8d5cb-17ec-456e-b894-19c6e5e659a9
+- Aivesa/dataset_a5667e37-9a88-46c1-b8d0-368d1ad49cee
 model-index:
-- name: 286fd9a8-760d-4213-a477-b5ea1e7ce9a3
+- name: 90cc73f1-7712-4110-bc96-10bf0bf9bd01
   results: []
 ---
 
@@ -20,18 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: katuni4ka/tiny-random-codegen2
+base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_86c8d5cb-17ec-456e-b894-19c6e5e659a9
+  path: Aivesa/dataset_a5667e37-9a88-46c1-b8d0-368d1ad49cee
   type:
-    field_input: caption2
-    field_instruction: negative_caption
-    field_output: caption
+    field_instruction: question_text
+    field_output: question_title
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -47,7 +46,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/286fd9a8-760d-4213-a477-b5ea1e7ce9a3
+hub_model_id: Aivesa/90cc73f1-7712-4110-bc96-10bf0bf9bd01
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,7 +78,7 @@ save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
 special_tokens:
-  pad_token: <|endoftext|>
+  pad_token: </s>
 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: 86c8d5cb-17ec-456e-b894-19c6e5e659a9
+wandb_name: a5667e37-9a88-46c1-b8d0-368d1ad49cee
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 86c8d5cb-17ec-456e-b894-19c6e5e659a9
+wandb_runid: a5667e37-9a88-46c1-b8d0-368d1ad49cee
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 286fd9a8-760d-4213-a477-b5ea1e7ce9a3
+# 90cc73f1-7712-4110-bc96-10bf0bf9bd01
 
-This model is a fine-tuned version of [katuni4ka/tiny-random-codegen2](https://huggingface.co/katuni4ka/tiny-random-codegen2) on the Aivesa/dataset_86c8d5cb-17ec-456e-b894-19c6e5e659a9 dataset.
+This model is a fine-tuned version of [HuggingFaceH4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceH4/tiny-random-LlamaForCausalLM) on the Aivesa/dataset_a5667e37-9a88-46c1-b8d0-368d1ad49cee dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.8422
+- Loss: 10.3727
 
 ## Model description
 
@@ -139,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 43.3622       | 0.1143 | 3    | 10.8461         |
-| 43.3138       | 0.2286 | 6    | 10.8447         |
-| 43.3712       | 0.3429 | 9    | 10.8422         |
+| 10.3857       | 0.0080 | 3    | 10.3729         |
+| 10.3718       | 0.0160 | 6    | 10.3729         |
+| 10.3736       | 0.0239 | 9    | 10.3727         |
 
 
 ### Framework versions