Training in progress, epoch 1

config.json

@@ -5,7 +5,7 @@
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.252995802694608,
+  "hidden_dropout_prob": 0.3100242319932239,
   "hidden_size": 512,
   "initializer_range": 0.02,
   "intermediate_size": 2048,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d838b3977b70e8586a409978d9c0cde2ea494988ec98fa59aaf4cf281e56a1f
+oid sha256:66e29aed8131a0b594f4af5837f995b42d5aa0652b5f781d7b395060e3ac93b6
 size 165512728

run-5/checkpoint-312/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.252995802694608,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "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-5/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974549cd0eda91fb9e8bc1ae1d37d780a8ff9c7369992b2cda5a0106f1b14eec
+size 165512728

run-5/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbf44d09436cb99b8c0edcb7c27f770f0f5d5a34095f5b3c4fcce143e8f930d
+size 331108474

run-5/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6866ec325c25834fbe2afc4a110637cde57b0e2b7245e62d1e01058cc29debe0
+size 14244

run-5/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977f6929d7e26393621e05d2290f20212ca31da72dfd54f141a4360680d850a6
+size 1064

run-5/checkpoint-312/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-312/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-312/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.5740072202166066,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-5/checkpoint-156",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5740072202166066,
+      "eval_loss": 0.6782364249229431,
+      "eval_runtime": 0.9517,
+      "eval_samples_per_second": 291.058,
+      "eval_steps_per_second": 5.254,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5631768953068592,
+      "eval_loss": 0.6750697493553162,
+      "eval_runtime": 0.9576,
+      "eval_samples_per_second": 289.279,
+      "eval_steps_per_second": 5.222,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 312,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.252995802694608,
+    "learning_rate": 2e-05
+  }
+}

run-5/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ca9a06a8c3177f164972aa5dcabf054195fcaa9e67baf9fe5bbdd8dca15278
+size 5496

run-6/checkpoint-156/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3100242319932239,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "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-6/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e29aed8131a0b594f4af5837f995b42d5aa0652b5f781d7b395060e3ac93b6
+size 165512728

run-6/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8a4052b85d9dc70a36d98a9d1e3ed75e9692bb5a5dc822a57673453c641fa9
+size 331108474

run-6/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957b2bc679131c2bcb60ab7040f6ead1f0d3b094fbfaabc3aba5dc3ab78ade86
+size 14244

run-6/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29afde6d2148f5bed68a601216924711accd006df1a59fa931b8b5c921299c4
+size 1064

run-6/checkpoint-156/special_tokens_map.json

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

run-6/checkpoint-156/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-156/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.5342960288808665,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-6/checkpoint-156",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.6863443851470947,
+      "eval_runtime": 0.9571,
+      "eval_samples_per_second": 289.431,
+      "eval_steps_per_second": 5.224,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 312,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.3100242319932239,
+    "learning_rate": 2e-05
+  }
+}

run-6/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ca9a06a8c3177f164972aa5dcabf054195fcaa9e67baf9fe5bbdd8dca15278
+size 5496

runs/Apr03_13-50-26_435476ce9a2d/events.out.tfevents.1743690887.435476ce9a2d.544.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f281654151bc29a68b07e34cef0310819116fc04a534fe4874cfe6dfd5945546
+size 6033