End of training

README.md

@@ -41,6 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
+- mixed_precision_training: Native AMP
 
 ### Training results
 
@@ -49,6 +50,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.40.0.dev0
-- Pytorch 2.2.2
+- Pytorch 2.2.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14aa25367d74aebe4b186c4ba0ce3dc033de09b96dc29d1ddfd8178eacf80425
+oid sha256:56fd96b28d6bfe2a5979cb057dfa816854dfa16ca25945ce819b2cfc8bfc3eb2
 size 809070744

runs/Apr08_15-37-44_gopal-MS-7A95/events.out.tfevents.1712615864.gopal-MS-7A95.40645.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdfb106b56918913e642b8cc03bf148bc9dd2f04676da613a480dfe10f6cc28
-size 9465
+oid sha256:6cc3ebaf64ddbd91cd30b6669737caf7239514208d84a07e6fd0363ea71b39a7
+size 11085

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,