End of training

README.md

@@ -71,7 +71,7 @@ pad_to_sequence_len: true
 resume_from_checkpoint: null
 sample_packing: true
 saves_per_epoch: 1
-seed: 54308
+seed: 58426
 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/ozxli2sy)
+[<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/zpzfcink)
 # taopanda-3_c71cc5c5-b4a1-43b5-93ac-4f9fe77ee451
 
 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: 1.8497
+- Loss: 1.8121
 
 ## 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: 54308
+- seed: 58426
 - distributed_type: multi-GPU
 - num_devices: 4
 - gradient_accumulation_steps: 4
@@ -136,8 +136,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.9997        | 1.0    | 1    | 1.9384          |
-| 0.4516        | 1.3333 | 2    | 1.8497          |
+| 1.4385        | 1.0    | 1    | 1.9115          |
+| 0.4521        | 1.3333 | 2    | 1.8121          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5900f919a77e8e1cc62c4a1bd434cc05d014e74ba115a9ece85125d921a87c
+oid sha256:ed4e88c24615c980519e73fb26b06c300d60627f2f9060fb5dfce610c4eb4284
 size 70506570