End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/Qwen2.5-0.5B-Instruct
+base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_e61a2e67-2ef6-4c56-bc3d-5981b6729822
+- Aivesa/dataset_34ad7f9d-ff58-4068-8537-2d15a40438a9
 model-index:
-- name: 0a3020fa-9065-4a04-b9c7-e0cadb2c120d
+- name: d8b02868-3f22-4fc4-bf4b-cd5c2a0ad840
   results: []
 ---
 
@@ -21,18 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/Qwen2.5-0.5B-Instruct
+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_e61a2e67-2ef6-4c56-bc3d-5981b6729822
+  path: Aivesa/dataset_34ad7f9d-ff58-4068-8537-2d15a40438a9
   type:
-    field_input: SMILES
-    field_instruction: Name
-    field_output: Descriptor
+    field_input: url
+    field_instruction: title
+    field_output: content
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/0a3020fa-9065-4a04-b9c7-e0cadb2c120d
+hub_model_id: Aivesa/d8b02868-3f22-4fc4-bf4b-cd5c2a0ad840
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,6 +78,8 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
+special_tokens:
+  pad_token: </s>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -88,10 +89,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: e61a2e67-2ef6-4c56-bc3d-5981b6729822
+wandb_name: 34ad7f9d-ff58-4068-8537-2d15a40438a9
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: e61a2e67-2ef6-4c56-bc3d-5981b6729822
+wandb_runid: 34ad7f9d-ff58-4068-8537-2d15a40438a9
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# 0a3020fa-9065-4a04-b9c7-e0cadb2c120d
+# d8b02868-3f22-4fc4-bf4b-cd5c2a0ad840
 
-This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct) on the Aivesa/dataset_e61a2e67-2ef6-4c56-bc3d-5981b6729822 dataset.
+This model is a fine-tuned version of [HuggingFaceH4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceH4/tiny-random-LlamaForCausalLM) on the Aivesa/dataset_34ad7f9d-ff58-4068-8537-2d15a40438a9 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6450
+- Loss: 10.3772
 
 ## Model description
 
@@ -138,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.5015        | 0.0019 | 3    | 2.8457          |
-| 2.8867        | 0.0037 | 6    | 2.7825          |
-| 2.7804        | 0.0056 | 9    | 2.6450          |
+| 10.3772       | 0.0013 | 3    | 10.3774         |
+| 10.3789       | 0.0026 | 6    | 10.3773         |
+| 10.3786       | 0.0038 | 9    | 10.3772         |
 
 
 ### Framework versions