End of training

README.md

@@ -33,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
+- num_epochs: 35
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -50,7 +50,7 @@
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
-    "max_length": 128,
+    "max_length": 512,
     "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 sha256:37a633a8c02dc0193a3ae6f2f3cc0a898f2eb8ef6dd9e1dd7f44fd7af66dfac9
+oid sha256:15318c3fda4403ad5f3b555d41455fa181c3e589fa4dbadc7ef882ad8791f61a
 size 809187097

runs/May27_15-18-23_608f40e247da/1685200708.0785553/events.out.tfevents.1685200708.608f40e247da.388.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8766e0052e17fd4b10e194f79716293c96147352a8ef67057dc4ff3941f96d
+size 6199

runs/May27_15-18-23_608f40e247da/1685201465.3469906/events.out.tfevents.1685201465.608f40e247da.388.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb46ac8d0fdd19a0300702b04d682145b87212048a296fbba62dda821c5b9863
+size 6199

runs/May27_15-18-23_608f40e247da/events.out.tfevents.1685200708.608f40e247da.388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a992aa45aebf957dd344fefeff6bb7c8aee0332201a0f496af79bf1c8aa07d6e
+size 18572

runs/May27_15-31-16_608f40e247da/1685201477.1743934/events.out.tfevents.1685201477.608f40e247da.388.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeebe1aab3d5f05e466eca36acd20d35b6d356881b2fea06f1eeaf885f25837d
+size 6199

runs/May27_15-31-16_608f40e247da/events.out.tfevents.1685201477.608f40e247da.388.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45500de6728d097944b16eb3b23f6e7eef3acd770978f33f2139d45772c12ab6
+size 12508

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051e3ddd2df8c2ab6ac9e504b1aea119c8124df3066c26f05377abe722acd76a
+oid sha256:2961ec6531b92d34af2e01a7e9582e0fdb6879b956193fe7ef42504712eea0cf
 size 4091