End of training

README.md

@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 100
+- num_epochs: 350
 
 ### Training results
 

runs/Jul27_05-31-40_cdr2647.int.cedar.computecanada.ca/events.out.tfevents.1690461107.cdr2647.int.cedar.computecanada.ca.108270.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87706f2e0d451333557e217f7410bc7b8c64cb341ef33aa4a5b3f6b948cc9e1
-size 30507
+oid sha256:2cf57391e2d6673693742240bb7a5b5e4a472291562773dbfeb4bc7300f74ea0
+size 30861

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 1024
     },
     "direction": "Right",
     "pad_to_multiple_of": null,