Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee944b9080939e84b18aabc60e3f8c9ff20289ececb2fe3fabcaa0e5013f409
+oid sha256:79e693fdd79b3c65216e1e111a01de87a0a89a186a3ff2bf112dc7627a4ebf96
 size 437958648

run-3/checkpoint-117/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-3/checkpoint-117/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e693fdd79b3c65216e1e111a01de87a0a89a186a3ff2bf112dc7627a4ebf96
+size 437958648

run-3/checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342ff39735bf6f9e2bc4c91fd7ce109886c41adcfe8849c7e2add1f2beedb197
+size 876038394

run-3/checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6ef7001839c1d2af6340ecba7b523b0f2a4e44bd97f7e39ce88f55c07c8d7f
+size 14244

run-3/checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6598b28e4b688fcfc408839d1baf45a8cef8f9d14fb223fb14a61bb0dedb9f37
+size 1064

run-3/checkpoint-117/special_tokens_map.json

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

run-3/checkpoint-117/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-3/checkpoint-117/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.5379061371841155,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-3/checkpoint-117",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4620938628158845,
+      "eval_loss": 0.6993961334228516,
+      "eval_runtime": 2.0133,
+      "eval_samples_per_second": 137.583,
+      "eval_steps_per_second": 2.483,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5018050541516246,
+      "eval_loss": 0.6926687359809875,
+      "eval_runtime": 2.0406,
+      "eval_samples_per_second": 135.744,
+      "eval_steps_per_second": 2.45,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.690954864025116,
+      "eval_runtime": 2.0079,
+      "eval_samples_per_second": 137.952,
+      "eval_steps_per_second": 2.49,
+      "step": 117
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.19092511979807322,
+    "learning_rate": 5.546555906491602e-06,
+    "max_seq_length": 256,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-3/checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574977948b354aca70839ceacef71c7860dfc6ff222f5d96e1b3a99d03c6ab63
+size 5432

run-3/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613ab2f11f67deba298142f0cbdb4bc4c67ff0b7b66614cc22ed6e3bd4babbc4
+oid sha256:edd4913ce348f558d502ca01511ddb81e82587892b7e1f882077cabcd1b8a35d
 size 437958648

run-3/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e6bf6471ca75a62298056f5fda9d21872557a35f079e5051a6a7787cbfdd50
+oid sha256:671859db3ad9a98778b7e4b8e809d4705fdc307265d2f471178b4afa27f65754
 size 876038394

run-3/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e4479defecd3bb83c1ad034c31572c77f94ab48c50a0501bfa384217c33006
+oid sha256:589ecb2461e16e2216bde3fe5e91331709422e8f1c62ba8ff8dafc35616f6f84
 size 1064

run-3/checkpoint-78/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.4657039711191336,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-3/checkpoint-39",
+  "best_global_step": 78,
+  "best_metric": 0.5018050541516246,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-3/checkpoint-78",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 78,
@@ -11,27 +11,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.7040843963623047,
-      "eval_runtime": 2.0885,
-      "eval_samples_per_second": 132.634,
-      "eval_steps_per_second": 2.394,
+      "eval_accuracy": 0.4620938628158845,
+      "eval_loss": 0.6993961334228516,
+      "eval_runtime": 2.0133,
+      "eval_samples_per_second": 137.583,
+      "eval_steps_per_second": 2.483,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4584837545126354,
-      "eval_loss": 0.6989011168479919,
-      "eval_runtime": 2.0926,
-      "eval_samples_per_second": 132.371,
-      "eval_steps_per_second": 2.389,
+      "eval_accuracy": 0.5018050541516246,
+      "eval_loss": 0.6926687359809875,
+      "eval_runtime": 2.0406,
+      "eval_samples_per_second": 135.744,
+      "eval_steps_per_second": 2.45,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 78,
+  "max_steps": 117,
   "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": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.2582354383285764,
-    "learning_rate": 4.879924272675403e-06,
-    "max_seq_length": 128,
-    "num_train_epochs": 2,
+    "dropout_rate": 0.19092511979807322,
+    "learning_rate": 5.546555906491602e-06,
+    "max_seq_length": 256,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 64
   }
 }

run-3/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a607ee43ea4c4292bed708e312ebdc46626eeae019a3190ab6ab9067f61c85ce
+oid sha256:574977948b354aca70839ceacef71c7860dfc6ff222f5d96e1b3a99d03c6ab63
 size 5432