Training in progress, epoch 1

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -19,7 +20,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c25bd0d4c3c5fbbfc81dc027805a0e2737eac6a76b9836f2ea085d856bb60f
+oid sha256:d023ff1f80301e53a92b3c3c6b5f888c5149535556d173181510facd2d6fba70
 size 437958648

run-0/checkpoint-78/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -19,7 +20,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-0/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532996eb39933b67a6d0ba5dce91f0aea2e85cf61a20e817552f95c4befcabb5
+oid sha256:d023ff1f80301e53a92b3c3c6b5f888c5149535556d173181510facd2d6fba70
 size 437958648

run-0/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16840b93d9efd0eb91de04e2c73596fd19a1affcba82023b8f898764fbfeb23b
+oid sha256:e529112784d1c84ce71f514086762eeb48666f85e66f330770f1fb4d964813c7
 size 876038394

run-0/checkpoint-78/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
+oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
 size 14244

run-0/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0187697e6d0429dfd9640b6f1406fdc3fe2031aa1c15aafe207f79661c8563
+oid sha256:fa865013a2181a4e2c688faa3e540a9e1efb33a5f063c27a6bc538d18382b889
 size 1064

run-0/checkpoint-78/tokenizer_config.json

@@ -41,10 +41,9 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
-  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

run-0/checkpoint-78/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.4693140794223827,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-0/checkpoint-39",
-  "epoch": 2.0,
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-0/checkpoint-78",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 78,
   "is_hyper_param_search": true,
@@ -11,27 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7206186652183533,
-      "eval_runtime": 1.7488,
-      "eval_samples_per_second": 158.391,
-      "eval_steps_per_second": 2.859,
-      "step": 39
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.7172814011573792,
-      "eval_runtime": 1.8305,
-      "eval_samples_per_second": 151.323,
-      "eval_steps_per_second": 2.731,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7185945510864258,
+      "eval_runtime": 0.7057,
+      "eval_samples_per_second": 392.495,
+      "eval_steps_per_second": 12.753,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 78,
+  "max_steps": 234,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -40,19 +30,19 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.42550029226706054,
-    "learning_rate": 1.4679097568141911e-06,
-    "max_seq_length": 64,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 64
+    "dropout_rate": 0.27458370833953805,
+    "learning_rate": 1.0420263015685704e-06,
+    "max_seq_length": 32,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
   }
 }

run-0/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f8607d2e37a2f6dbecbc030c47d97f64db186e210b3b1396766c9f50fdf62b
-size 5432
+oid sha256:c9040c2653ebc0d7a419adcae990c297f257817a157f53cf1fbcd2d082d6f0d4
+size 5240

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 256
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -41,10 +41,9 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
-  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0700a167b6e74e336c767640e8ddec156e025d797cb99c1bdd6c0819e5b0d1f1
-size 5432
+oid sha256:c9040c2653ebc0d7a419adcae990c297f257817a157f53cf1fbcd2d082d6f0d4
+size 5240