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: 25
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -50,7 +50,7 @@
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
-    "max_length": 512,
+    "max_length": 128,
     "max_position_embeddings": 1536,
     "min_length": 0,
     "model_type": "mbart",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bb2892b4b795d251b1dd67d8457e39290a959e604d4a55eb3d560ef9480425
+oid sha256:db08392cdb4152381fcb57399a64fd3a171a09271ff5d083995443ee55b1dc90
 size 809187097

runs/May26_17-14-07_1465e872ce98/1685121251.694105/events.out.tfevents.1685121251.1465e872ce98.729.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b3a9eb36d3f4d33e14dea26b2c8515f5fb27c909f6cc2b212d1d861c3ba5eb
+size 6199

runs/May26_17-14-07_1465e872ce98/events.out.tfevents.1685121251.1465e872ce98.729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5b70f973152183e9b6238cd23a18d42cbf804a381504fdc8009b69cd0f4516
+size 10780

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da784a8292b362ac667d70d168eb5fd34881899c5651b606f60c4d0d5b2d08d
+oid sha256:92998424433af82c10a66cea29abaf2283be7db4ac92fb9a030f292887aec8f5
 size 4091