Model save

README.md

@@ -33,9 +33,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 0
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3.0

config.json

@@ -47,7 +47,7 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.33.2",
   "use_cache": true,
   "vocab_size": 50258,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218c0d4227a85203d3e6d6e03b225c24d12a4b7252ebad9fe09a655afed8e1a2
-size 500850253
+oid sha256:31b3f475bcc6b336278f3997ffb1c0a70f27d559e6163598fb12baa583fda88b
+size 655240785

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50257,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 50256,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e803a10fc47ea4d0bcb4d8a85f87eaeda1cabb74cef06b493c53397a5c0a43
-size 4091
+oid sha256:045202a1d5518caf1bd1d12f26b5b9ad8df8ed50c85f68545d40c326c2898b90
+size 5691