Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6019332a2405ed45327de26e1fab37257eda70217b9e85d82c7fa6039c4973d
+oid sha256:545b0222ddb4e5ec34d7c2f527d26a1c503d66c1e81b72dff1a86ec43efa165a
 size 437958648

run-13/checkpoint-78/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d18b287a2c4f6d4bed1b30a0b29506bd78bc9f429e65828538a7967a45ce444
+size 437958648

run-13/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cb509ca4b3b981d466b98cfe75b3254dbf85390337b056729858ae399f8137
+size 876038394

run-13/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3115cbdc08b9836a393efb499f011b65a6649e6c5cc563d236e33e683532ac2
+size 14244

run-13/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebf02ca9dd9c1d98ba5ce7e4a1e20869748ba8b638ebaee4c02922556c84127
+size 1064

run-13/checkpoint-78/special_tokens_map.json

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

run-13/checkpoint-78/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-13/checkpoint-78/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_global_step": 78,
+  "best_metric": 0.631768953068592,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-13/checkpoint-78",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5956678700361011,
+      "eval_loss": 0.6718657612800598,
+      "eval_runtime": 0.6364,
+      "eval_samples_per_second": 435.249,
+      "eval_steps_per_second": 14.142,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.631768953068592,
+      "eval_loss": 0.6457917094230652,
+      "eval_runtime": 0.6366,
+      "eval_samples_per_second": 435.144,
+      "eval_steps_per_second": 14.138,
+      "step": 78
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 78,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": {
+    "learning_rate": 5.879377704760648e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23a0a2a7111710f92f2d16d832bc9c9e37aa87c708e0778665c9b74b4307367
+size 5432

run-14/checkpoint-39/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-14/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545b0222ddb4e5ec34d7c2f527d26a1c503d66c1e81b72dff1a86ec43efa165a
+size 437958648

run-14/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d89261e0434a27676e233637839caa6c66eafd789143ec39e9b8d2b42b4fe6
+size 876038394

run-14/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce2001d6c41d462c4a530df5214c4ba6ac04088f8883ec9b91629a00a7da50d
+size 14244

run-14/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1dddc0b50a591a24505c6dea7bdb620207a094fcc13ce363cafbaffa340f2bb
+size 1064

run-14/checkpoint-39/special_tokens_map.json

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

run-14/checkpoint-39/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-14/checkpoint-39/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.6245487364620939,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-14/checkpoint-39",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.644602358341217,
+      "eval_runtime": 0.637,
+      "eval_samples_per_second": 434.826,
+      "eval_steps_per_second": 14.128,
+      "step": 39
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 78,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.916253135444006e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64
+  }
+}

run-14/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3391318194abd0f0bb6c6657e27a34504d8e78a4e41d8a102fbed5ded6b3e0
+size 5432

run-14/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:954d87e977a72816e490bca266e9cf1360a598ceb5a3dc902aa55af45f379db8
+oid sha256:dc4c40a3436f9b58030759d886ca6ca7056c85bf59b3c3af0d2102b007456075
 size 437958648

run-14/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b525b75f84c943f49f25532ea0ae1c9d01ed39b8b2f07c85ed8582b9422ba5
+oid sha256:766cc11806f0cdcc9de0b846fa877eac19f572f79a1a2ff249a6fb33ec02ae66
 size 876038394

run-14/checkpoint-78/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ab796df965c74c106f46f16854d55804fecfe14c1d69ae73ebe7269fc9ed28
+oid sha256:c3115cbdc08b9836a393efb499f011b65a6649e6c5cc563d236e33e683532ac2
 size 14244

run-14/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6e669d28218ff97479ed952f343adfc032380e112f212662377b21c9dfc580
+oid sha256:e00d9ede21e2edec5bdbfce1dfaafcec1e1fdbdd904cefa929d2dcb5f86af0ce
 size 1064

run-14/checkpoint-78/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_global_step": 78,
-  "best_metric": 0.6570397111913358,
+  "best_metric": 0.6678700361010831,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-14/checkpoint-78",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 78,
   "is_hyper_param_search": true,
@@ -11,18 +11,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.6404402852058411,
-      "eval_runtime": 0.6557,
-      "eval_samples_per_second": 422.45,
-      "eval_steps_per_second": 7.625,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.644602358341217,
+      "eval_runtime": 0.637,
+      "eval_samples_per_second": 434.826,
+      "eval_steps_per_second": 14.128,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.6472871899604797,
+      "eval_runtime": 0.6372,
+      "eval_samples_per_second": 434.719,
+      "eval_steps_per_second": 14.124,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 234,
+  "max_steps": 78,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -31,17 +40,17 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.3998157432672416e-05,
-    "num_train_epochs": 3,
-    "per_device_train_batch_size": 32
+    "learning_rate": 6.916253135444006e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64
   }
 }

run-14/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a51f6f6a73ae207417b743655b2a56f5f44686c5e517b0bb8272dd8637d5b6
+oid sha256:ab3391318194abd0f0bb6c6657e27a34504d8e78a4e41d8a102fbed5ded6b3e0
 size 5432

runs/Apr01_21-40-42_1357c7d90830/events.out.tfevents.1743547502.1357c7d90830.592.109

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e178b426fc75ee41e811af72fca27b15c8c7863364218a01d00cd50ed8d434
+size 6083

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23a0a2a7111710f92f2d16d832bc9c9e37aa87c708e0778665c9b74b4307367
+oid sha256:ab3391318194abd0f0bb6c6657e27a34504d8e78a4e41d8a102fbed5ded6b3e0
 size 5432