Training complete.

README.md

@@ -34,11 +34,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 32
+- 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: 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8cf527905405d6eebdeffd4caf23fc96c7d8221f67e9ac28122c0a5bebd44ea
+oid sha256:54caaea56ecff8fd07edf06c710c076d4b2bbb394e56075f94a635b7bf2a6bdb
 size 2283652852

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a92310a250a5dd2a209a07ddc49b65e40cffec6021cabf446f3a9a6da7ecbc9
+oid sha256:e5cd52b41dfc02da0051c6b4ca6e6e266e6fbb8eeb442d11dcac11742f64e846
 size 4536