End of training

README.md

@@ -33,8 +33,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

logs/events.out.tfevents.1695790193.u116734.1341192.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015ee917eefe50c176f0235d3119c34e76afd770a1e9c8cd1a2bf49408cf26f1
-size 5774
+oid sha256:6282d6169607a5ab4a2a788b980371ce1d566d7d91376a15c55e46e44d6cb03c
+size 6285

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3549b6d8f70b90e070158d7ab303a20e2d81d34f11901af1f4a587f4b461221f
+oid sha256:a435d5109c4befabf2c513059ecab18a0896bf9f8cd1aa21c774bd15a092af9f
 size 990408885

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 4,
+    "max_length": 10,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 4
+      "Fixed": 10
     },
     "direction": "Right",
     "pad_to_multiple_of": null,