Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e5fa2ca4a4cae7f98b1663d6182ac2fefde37765be941091bcab70c5ac42fe
+oid sha256:33f026545e1f6c450e94e760b46f1a49d0327791e6b3eaf99eb7321c36ab2aad
 size 437958648

run-5/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9284fda87751e5e2e1535b77f42acd5daebf6b8d9b72aea56b784e0236a5a8f6
+oid sha256:ac209d84629c3d04189eb4b033cdcb05731ab1330583f77c010d059ba1973d44
 size 437958648

run-5/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d67f20a06b5a754cdf9ad275f3a140c4082e319a84d923e1a951a9af5faabf
+oid sha256:222ea1e568af5f062d69762bd02ceb8cdc3dbd3e6da452f23859a6f90938d716
 size 876038394

run-5/checkpoint-156/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9d183ca84f2a08654a3c884f30c2574cd3f79993558b875cd3aa83f7a79c3e
+oid sha256:1a1792a89d743d72bcf8e07a4f87dca29dec32f1f11810817c2cf714cad6a76d
 size 1064

run-5/checkpoint-156/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 156,
-  "best_metric": 0.5884476534296029,
+  "best_metric": 0.6028880866425993,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-156",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -12,26 +12,26 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.5595667870036101,
-      "eval_loss": 0.6888958215713501,
-      "eval_runtime": 0.4632,
-      "eval_samples_per_second": 598.068,
-      "eval_steps_per_second": 19.432,
+      "eval_loss": 0.6858518123626709,
+      "eval_runtime": 0.4624,
+      "eval_samples_per_second": 599.013,
+      "eval_steps_per_second": 19.463,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5884476534296029,
-      "eval_loss": 0.6790053248405457,
-      "eval_runtime": 0.4646,
-      "eval_samples_per_second": 596.165,
-      "eval_steps_per_second": 19.37,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 0.6532068252563477,
+      "eval_runtime": 0.4681,
+      "eval_samples_per_second": 591.766,
+      "eval_steps_per_second": 19.227,
       "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": {
@@ -40,7 +40,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
@@ -49,10 +49,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout": 0.5,
-    "learning_rate": 2.312919001524447e-05,
-    "max_length": 128,
-    "num_train_epochs": 2,
+    "dropout": 0.30000000000000004,
+    "learning_rate": 1.8075217428758282e-05,
+    "max_length": 64,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }
 }

run-5/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c7e44a2ef9a2bcca8ab37c73b0c2d587f6887fd981085a27b0b77d003d836e
+oid sha256:a0e2f380cc23eb89fbfd2b30890ce4558fe69ded039963c49290f9161089cbb1
 size 5432

run-5/checkpoint-234/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-5/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73367153e5b234403c3987ff86e8684e6c4eecf86ca7d84148164040517cdbe5
+size 437958648

run-5/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d258e8e40dc3b7317fb2916705e1556078fa51c26114b8f97ecdb385e6e3552
+size 876038394

run-5/checkpoint-234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99f77297975f2151eb6303e1a631021acacf8da2aec44c1ba93649616a73fe7
+size 14244

run-5/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16174dde069882c8622cdac90bd4bee25b0eeccb79fe4e323a615ad26976ba9a
+size 1064

run-5/checkpoint-234/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-234/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-234/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_global_step": 234,
+  "best_metric": 0.631768953068592,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-234",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 234,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5595667870036101,
+      "eval_loss": 0.6858518123626709,
+      "eval_runtime": 0.4624,
+      "eval_samples_per_second": 599.013,
+      "eval_steps_per_second": 19.463,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 0.6532068252563477,
+      "eval_runtime": 0.4681,
+      "eval_samples_per_second": 591.766,
+      "eval_steps_per_second": 19.227,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.631768953068592,
+      "eval_loss": 0.6704250574111938,
+      "eval_runtime": 0.4628,
+      "eval_samples_per_second": 598.553,
+      "eval_steps_per_second": 19.448,
+      "step": 234
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout": 0.30000000000000004,
+    "learning_rate": 1.8075217428758282e-05,
+    "max_length": 64,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-5/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e2f380cc23eb89fbfd2b30890ce4558fe69ded039963c49290f9161089cbb1
+size 5432

run-7/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8149a9bf51c263fdbebf53b93f33748d1ec9448297a082cf17c983584898da4f
+oid sha256:33f026545e1f6c450e94e760b46f1a49d0327791e6b3eaf99eb7321c36ab2aad
 size 437958648

run-7/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956e54c1295aa5b766f1fa5e78e200a770652eadc2adfe2a71a2694c26b7d83f
+oid sha256:9694b31976191fb66807b457fb47af300ed68c1ff409b2413d8b7a7a2b7abaef
 size 876038394

run-7/checkpoint-39/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9d75225831e9955fede3b2d004809f8a35dbd2208354c70b53a96923288fdc
+oid sha256:033b7547d54be169bcdf3d364106c67eb24ca2e8b201668408672b1942d82647
 size 14244

run-7/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39718c6a2e0c0d85576c09570e52bdea913f598af880c8d2a415c9ce41ac25e9
+oid sha256:50b90e0fd73f5c587aff08b3634d1a14dd762b93fb0c9ff24dd08f4fcadc0dfd
 size 1064

run-7/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.516245487364621,
+  "best_metric": 0.5270758122743683,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,18 +11,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.516245487364621,
-      "eval_loss": 0.6922807693481445,
-      "eval_runtime": 2.0324,
-      "eval_samples_per_second": 136.293,
-      "eval_steps_per_second": 1.476,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6871797442436218,
+      "eval_runtime": 0.4624,
+      "eval_samples_per_second": 599.043,
+      "eval_steps_per_second": 19.463,
       "step": 39
     }
   ],
   "logging_steps": 500,
-  "max_steps": 117,
+  "max_steps": 195,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -40,10 +40,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout": 0.5,
-    "learning_rate": 1.0208515068263659e-05,
+    "dropout": 0.2,
+    "learning_rate": 1.0227908312651503e-05,
     "max_length": 64,
-    "num_train_epochs": 3,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 64
   }
 }

run-7/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40167e75ecf9e5a172909eb5a1108260f4631310c1c90d96da8b3d871fbd3cab
+oid sha256:c3c0d10f61e17d71a323468259be20cf778ab0e5cb49a81ab869fa68120b076e
 size 5432

runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056646.578d22db0b7b.632.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d775eb403c4a808224501f3dc434d2558a361c474533b2707c67cc72e1e1189
+size 5425

runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056663.578d22db0b7b.632.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1b021ffda963ed72271310412b80dfae95b2617675ba744d01521cc9921b9f
+size 7053

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e2f380cc23eb89fbfd2b30890ce4558fe69ded039963c49290f9161089cbb1
+oid sha256:c3c0d10f61e17d71a323468259be20cf778ab0e5cb49a81ab869fa68120b076e
 size 5432