End of training

README.md

@@ -1,13 +1,13 @@
 ---
 library_name: peft
-base_model: samoline/c374ea20-5026-48ff-abab-3892b0b88cff
+base_model: katuni4ka/tiny-random-qwen1.5-moe
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_551340a2-0886-4fde-9e57-97a233c286c6
+- Aivesa/dataset_5e3967ba-d17c-4d93-91ec-a23620abb5dc
 model-index:
-- name: 443d5c77-12d0-4c91-b616-79db130ff2f3
+- name: f3fb782d-07a6-4d79-b96c-d3f4215f48c7
   results: []
 ---
 
@@ -20,16 +20,15 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: samoline/c374ea20-5026-48ff-abab-3892b0b88cff
+base_model: katuni4ka/tiny-random-qwen1.5-moe
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_551340a2-0886-4fde-9e57-97a233c286c6
+  path: Aivesa/dataset_5e3967ba-d17c-4d93-91ec-a23620abb5dc
   type:
-    field_input: input
     field_instruction: instruction
     field_output: output
     system_format: '{system}'
@@ -47,7 +46,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/443d5c77-12d0-4c91-b616-79db130ff2f3
+hub_model_id: Aivesa/f3fb782d-07a6-4d79-b96c-d3f4215f48c7
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -78,8 +77,6 @@ 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 +86,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 551340a2-0886-4fde-9e57-97a233c286c6
+wandb_name: 5e3967ba-d17c-4d93-91ec-a23620abb5dc
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 551340a2-0886-4fde-9e57-97a233c286c6
+wandb_runid: 5e3967ba-d17c-4d93-91ec-a23620abb5dc
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +98,11 @@ xformers_attention: null
 
 </details><br>
 
-# 443d5c77-12d0-4c91-b616-79db130ff2f3
+# f3fb782d-07a6-4d79-b96c-d3f4215f48c7
 
-This model is a fine-tuned version of [samoline/c374ea20-5026-48ff-abab-3892b0b88cff](https://huggingface.co/samoline/c374ea20-5026-48ff-abab-3892b0b88cff) on the Aivesa/dataset_551340a2-0886-4fde-9e57-97a233c286c6 dataset.
+This model is a fine-tuned version of [katuni4ka/tiny-random-qwen1.5-moe](https://huggingface.co/katuni4ka/tiny-random-qwen1.5-moe) on the Aivesa/dataset_5e3967ba-d17c-4d93-91ec-a23620abb5dc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1321
+- Loss: 11.9368
 
 ## Model description
 
@@ -139,9 +136,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.1408        | 0.0006 | 3    | 1.1933          |
-| 1.0982        | 0.0012 | 6    | 1.1558          |
-| 0.9538        | 0.0018 | 9    | 1.1321          |
+| 11.9333       | 0.0002 | 3    | 11.9376         |
+| 11.9358       | 0.0004 | 6    | 11.9373         |
+| 11.9336       | 0.0007 | 9    | 11.9368         |
 
 
 ### Framework versions