End of training

README.md

@@ -6,7 +6,7 @@ tags:
 - generated_from_trainer
 base_model: unsloth/Qwen2-0.5B
 model-index:
-- name: taopanda-1_expected_repo_name
+- name: expected_repo_name
   results: []
 ---
 
@@ -51,7 +51,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/taopanda-1_expected_repo_name
+hub_model_id: taopanda-1/expected_repo_name
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -71,7 +71,7 @@ pad_to_sequence_len: true
 resume_from_checkpoint: null
 sample_packing: true
 saves_per_epoch: 1
-seed: 12220
+seed: 1439
 sequence_len: 4096
 special_tokens: null
 strict: false
@@ -95,12 +95,12 @@ xformers_attention: null
 
 </details><br>
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/8gcofu8s)
-# taopanda-1_expected_repo_name
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/h6pimr9h)
+# expected_repo_name
 
 This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9101
+- Loss: 1.9074
 
 ## Model description
 
@@ -122,7 +122,7 @@ The following hyperparameters were used during training:
 - learning_rate: 0.0002
 - train_batch_size: 2
 - eval_batch_size: 2
-- seed: 12220
+- seed: 1439
 - distributed_type: multi-GPU
 - num_devices: 4
 - gradient_accumulation_steps: 4
@@ -136,7 +136,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.4391        | 1.0   | 1    | 1.9101          |
+| 1.4388        | 1.0   | 1    | 1.9074          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857784790288df0129c7674cb4aab7f1adb9fcb965e0b7687b1b834c940d3603
+oid sha256:31c20c5bbb272cbcfce24b78358ba591545ff3d32e0b2c04ffed36f870489801
 size 70506570