Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638ab00ccaa37bc4e7a65c38d74ec0becba8f345692e1517641e1b426eb57268
+oid sha256:ed3327f4a45624b24852d1cf0314edde5a2bd2f2bb844a21ee997f973958c068
 size 437958648

run-0/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ccc4a2e95bd2b2653f161c591af1fcdfe62e28c375d44d0e956d413bc497da
+oid sha256:5cf85fc6d5e2ef60e5e64a6fb70ce94d8841d221799ffb974816556602f0e398
 size 437958648

run-0/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ddaf4913f4d053484f528f60cea2824fe3a4e619ed5bb0b5b092f7c35a983c
+oid sha256:a11b12f8c02582d7c355b82a717aa50fe60862f12c6cfaa8a9fd1242ccaadb95
 size 876038394

run-0/checkpoint-156/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e0f5ae6036e913540954f3c4c2ba49572f7f604af80b7bb3f3e985813b6523
+oid sha256:2eff57ea012b46748c4f5614070290e7ba4293d5b39346f050d4913ecb484e67
 size 1064

run-0/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ece6cededb9f915c327a15ba1188753c24b9c888cd711a5f4244a16efa7ba29
+oid sha256:95028e7deee272cbc151f7568f076355b10d7dd155b317c34385edbac9e0a889
 size 5240

run-0/checkpoint-234/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdaef9a97089375c4e658abcb08ac2e6fca7bfc3fdc30794bdcd443d9cfd70ce
+oid sha256:f59adadc34587cfb4c4e1128b2f2e8af9d5b8ad97fbecf2f8f1edc6341369695
 size 437958648

run-0/checkpoint-234/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56e99fc4c712615b1f641e1c3fb5fc5d281952c8584d44fa6f9a4b3629b2546
+oid sha256:3d0cdb3c6a688502be425f16a58c9ce71322185b96362c9da337d5ae87d63387
 size 876038394

run-0/checkpoint-234/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d42019f8b85d5dcdac8972a5d8b6a2d111c8449167d033ec77bc2ff7b20e54e
+oid sha256:f68858c6d2b4a8247beef7e36f8e90a2a12cbb1ed8210c939bac3c91142f844c
 size 1064

run-0/checkpoint-234/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ece6cededb9f915c327a15ba1188753c24b9c888cd711a5f4244a16efa7ba29
+oid sha256:95028e7deee272cbc151f7568f076355b10d7dd155b317c34385edbac9e0a889
 size 5240

run-1/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88140c05f259aaddc82eb51574782767f1568e00aa3bc25319970a48b056319
+oid sha256:00707ab47588afd7df3888558fca57486c00817d71c0cff2cccab6e1d02e77d2
 size 437958648

run-1/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfed901b6317db723cfddb8b55ea9f79d15a2e1652612df0a9759ac9eb56bf5
+oid sha256:ecc432c858bd991665bdc79741e4e3dd79b4cc2c960cf1fdaeb292ece5771b81
 size 876038394

run-1/checkpoint-156/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37afe436ff072b7739639dc9f6572683accdeee6a0dd9d0e6b28272149bbeef4
+oid sha256:74301a894b78111d480f430984c4f67519c66f7237f0a78dd988c9c6fb5fee27
 size 1064

run-1/checkpoint-156/tokenizer.json

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

run-1/checkpoint-156/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5270758122743683,
+  "best_metric": 0.5884476534296029,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-1/checkpoint-156",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.6946967840194702,
-      "eval_runtime": 0.7014,
-      "eval_samples_per_second": 394.947,
-      "eval_steps_per_second": 12.832,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.6887229084968567,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 409.255,
+      "eval_steps_per_second": 13.297,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6909597516059875,
-      "eval_runtime": 0.7821,
-      "eval_samples_per_second": 354.163,
-      "eval_steps_per_second": 11.507,
+      "eval_accuracy": 0.5884476534296029,
+      "eval_loss": 0.672937273979187,
+      "eval_runtime": 0.6928,
+      "eval_samples_per_second": 399.854,
+      "eval_steps_per_second": 12.992,
       "step": 156
     }
   ],
   "logging_steps": 500,
-  "max_steps": 156,
+  "max_steps": 234,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -39,7 +39,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
@@ -48,10 +48,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.18603845325463833,
-    "learning_rate": 6.102762674151331e-06,
-    "max_seq_length": 32,
-    "num_train_epochs": 2,
+    "dropout_rate": 0.186349260590997,
+    "learning_rate": 8.992145512689151e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }
 }

run-1/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f895d42c1769322ac28364a8dd6983bd9b7f5639c365a3980ea0f78d6cbf1ab
+oid sha256:088703d1ec91cce96a1f78205fe905d0ccd04ee20140a96d92891d553f213068
 size 5240

run-1/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36b804eb13850dd70a161bdb5803e2d729d46462c92709d7a1d2bd3909781b9
+oid sha256:ed3327f4a45624b24852d1cf0314edde5a2bd2f2bb844a21ee997f973958c068
 size 437958648

run-1/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc911156caf5f9c7d8de9c4d2953764be517e2596008e6a18a15f6a8a74783b
+oid sha256:5484d4fdac1ada009b3fe3a19fe51d33042117d7ee91fd19c652a83b34375a2d
 size 876038394

run-1/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5db5d7e10d513d52815d7d3a489a0e271a5fa0b3d151a2c1bc49e6d12c12100
+oid sha256:8b8ca9d798a57d8b71fb3fbb475c75f7cd4df856c7938d8443e3c48ff3107c70
 size 1064

run-1/checkpoint-78/tokenizer.json

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

run-1/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4657039711191336,
+  "best_metric": 0.5523465703971119,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-1/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.6946967840194702,
-      "eval_runtime": 0.7014,
-      "eval_samples_per_second": 394.947,
-      "eval_steps_per_second": 12.832,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.6887229084968567,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 409.255,
+      "eval_steps_per_second": 13.297,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 156,
+  "max_steps": 234,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -39,10 +39,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.18603845325463833,
-    "learning_rate": 6.102762674151331e-06,
-    "max_seq_length": 32,
-    "num_train_epochs": 2,
+    "dropout_rate": 0.186349260590997,
+    "learning_rate": 8.992145512689151e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }
 }

run-1/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f895d42c1769322ac28364a8dd6983bd9b7f5639c365a3980ea0f78d6cbf1ab
+oid sha256:088703d1ec91cce96a1f78205fe905d0ccd04ee20140a96d92891d553f213068
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95028e7deee272cbc151f7568f076355b10d7dd155b317c34385edbac9e0a889
+oid sha256:088703d1ec91cce96a1f78205fe905d0ccd04ee20140a96d92891d553f213068
 size 5240