End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8111217641418984
+      value: 0.7976989453499521
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4951
-- Accuracy: 0.8111
+- Loss: 0.4850
+- Accuracy: 0.7977
 
 ## Model description
 
@@ -56,6 +56,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 64
 - seed: 0
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 20
@@ -65,16 +67,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.576         | 0.19  | 50   | 0.6161          | 0.6913   |
-| 0.4767        | 0.37  | 100  | 0.5660          | 0.7641   |
-| 0.5155        | 0.56  | 150  | 0.4750          | 0.7996   |
-| 0.3959        | 0.75  | 200  | 0.4754          | 0.7996   |
-| 0.4453        | 0.93  | 250  | 0.4903          | 0.8111   |
+| 0.5604        | 0.37  | 50   | 0.5631          | 0.6913   |
+| 0.4593        | 0.75  | 100  | 0.4787          | 0.7919   |
 
 
 ### Framework versions
 
 - Transformers 4.34.1
-- Pytorch 2.1.0+cu118
-- Datasets 2.14.6
+- Pytorch 2.0.1+cu117
+- Datasets 2.9.0
 - Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7896cb1b60f58509d4d453b641239ef553d5473662d93baa5e7dc19312bc7c5d
-size 894094686
+oid sha256:e20dcea7070816c4fe5b649a8e8b136443b4069fa66ffd3a27da4c27f0b3be35
+size 894094241

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae170d0795f852d225ca2cf381069c3edd5c2fe1fb06b6a9103e71f52fad795
-size 4536
+oid sha256:8b6d1b097bc95fef0b73e23da42f53757f5055ff207b104d59e978a870928621
+size 4091