Model save

README.md

@@ -2,6 +2,8 @@
 library_name: transformers
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: maze_replicate_10_test
   results: []
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # maze_replicate_10_test
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6046
+- Accuracy: 0.0
 
 ## Model description
 
@@ -32,11 +37,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 128
+- train_batch_size: 32
 - eval_batch_size: 128
 - seed: 7658372
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 256
+- total_train_batch_size: 64
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -44,9 +49,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0     | 0    | 1.8216          | 0.0      |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0      | 0    | 1.8580          | 0.0      |
+| 3.4351        | 0.3175 | 10   | 1.6489          | 0.0      |
+| 3.3558        | 0.6349 | 20   | 1.6199          | 0.0      |
+| 3.3084        | 0.9524 | 30   | 1.6046          | 0.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620e49b4cb51f7a04e0840ec155eb094835205846d7c3cd470c9d9497f86e67b
+oid sha256:5bc5c3e40d6ebe19c7bd1d17bc7c055b6d0aba2bc30719836e111ee553b17682
 size 42640744

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2e5bd533653a5008eb7b89a712a043ec4d5cffcc1d2fbeca731172f4eba88d
+oid sha256:6e5340b2df97cae122dfd058699960bb5d2d7791b720f6e022984dad20381d4d
 size 5240