End of training

README.md

@@ -32,13 +32,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 3e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54bbe6309639cce6c15021a91e0efc96766108259ccdb7bd14d2602ac97e88e
+oid sha256:65e708a31f0e666dfb5f54be8391360b09f8210149513d14e5d0b8672fd0498e
 size 809078936

runs/Mar23_13-11-24_eb43e8f894f9/events.out.tfevents.1711199489.eb43e8f894f9.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9507d17e40e33d9909cc73910b37219d1fe80e2d158c92b23b8fd96cea471435
+size 16962

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "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>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015696f356bd04d7e24c860214d43e89ec06bd7ee5ccb471e029a81f66554a97
+oid sha256:f30c437c8075d52262ef6256c7b5e6dd09acb56f8d021434041e473003ddc53b
 size 5112