End of training

README.md

@@ -57,9 +57,9 @@ lora_target_modules:
 - query_key_value
 micro_batch_size: 4
 num_epochs: 4
-output_dir: ./outputs/lora-alpaca-pythia
+output_dir: ./outputs/lora-alpaca-pythia/taopanda-2_bcc7097d-6c73-48e3-aaee-f9f854afb9b4
 resume_from_checkpoint: null
-seed: 77054
+seed: 84664
 sequence_len: 512
 special_tokens:
   pad_token: <|endoftext|>
@@ -79,12 +79,12 @@ weight_decay: 0.1
 
 </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/qwfaghog)
+[<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/0tu4r381)
 # taopanda-2_bcc7097d-6c73-48e3-aaee-f9f854afb9b4
 
 This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2651
+- Loss: 2.2826
 
 ## Model description
 
@@ -106,7 +106,7 @@ The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 4
-- seed: 77054
+- seed: 84664
 - distributed_type: multi-GPU
 - num_devices: 2
 - total_train_batch_size: 8
@@ -120,22 +120,22 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 3.0118        | 0.0006 | 1    | 2.8035          |
-| 2.7361        | 0.2505 | 414  | 2.5480          |
-| 2.4912        | 0.5009 | 828  | 2.4415          |
-| 3.2917        | 0.7514 | 1242 | 2.3872          |
-| 2.9411        | 1.0018 | 1656 | 2.3535          |
-| 2.6596        | 1.2523 | 2070 | 2.3288          |
-| 2.0685        | 1.5027 | 2484 | 2.3111          |
-| 2.1828        | 1.7532 | 2898 | 2.2993          |
-| 2.1507        | 2.0036 | 3312 | 2.2905          |
-| 2.6897        | 2.2541 | 3726 | 2.2807          |
-| 2.5161        | 2.5045 | 4140 | 2.2778          |
-| 2.5809        | 2.7550 | 4554 | 2.2725          |
-| 2.7309        | 3.0054 | 4968 | 2.2687          |
-| 2.3226        | 3.2559 | 5382 | 2.2675          |
-| 2.7654        | 3.5064 | 5796 | 2.2657          |
-| 2.0191        | 3.7568 | 6210 | 2.2651          |
+| 2.7173        | 0.0006 | 1    | 2.8035          |
+| 2.3948        | 0.2505 | 414  | 2.5510          |
+| 2.6987        | 0.5009 | 828  | 2.4507          |
+| 2.2231        | 0.7514 | 1242 | 2.3969          |
+| 2.4612        | 1.0018 | 1656 | 2.3698          |
+| 2.9173        | 1.2523 | 2070 | 2.3450          |
+| 2.3121        | 1.5027 | 2484 | 2.3282          |
+| 2.8931        | 1.7532 | 2898 | 2.3154          |
+| 2.0185        | 2.0036 | 3312 | 2.3080          |
+| 2.2114        | 2.2541 | 3726 | 2.2980          |
+| 2.4148        | 2.5045 | 4140 | 2.2941          |
+| 2.2134        | 2.7550 | 4554 | 2.2887          |
+| 1.5517        | 3.0054 | 4968 | 2.2839          |
+| 2.2136        | 3.2559 | 5382 | 2.2811          |
+| 1.2004        | 3.5064 | 5796 | 2.2838          |
+| 2.374         | 3.7568 | 6210 | 2.2826          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2f625b7ea28763e089a48b202a0a393167ba29b6f9cd37b16d39d9c6af6715
+oid sha256:0b3c41bd57bc3c59ce309650c5b4eadf02e2e87c16aa5d4290355d83debe88b4
 size 6309438