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": 0.1891988684237177,
+  "hidden_dropout_prob": 0.10807485811873185,
   "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 sha256:078050c05a159c17f622e1056af2571347b2bbe2ab5c3ccc32a831d6d2868e33
+oid sha256:4e263c139f8de8f1e8341a963f5dc15c8b21e164f56f144f9138bf69b438ae70
 size 165512728

run-0/checkpoint-624/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1891988684237177,
+  "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-0/checkpoint-624/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59ee5daf4e83f3709b397fa10f93d3864c9448118b16f869f3397c27bc44f1b
+size 165512728

run-0/checkpoint-624/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc62d10ba85f9049f555808322166d3a9e2791fae1c976a2045c549a00a8eaa
+size 331108474

run-0/checkpoint-624/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356d94ef9cb3451fddc555952f295086c52490a8fe8697275f7fcf3d2f04e479
+size 14244

run-0/checkpoint-624/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5714b142bec505140e88fa9f25aa8de5860509ab75cb1af27cc2c029d80a00f
+size 1064

run-0/checkpoint-624/special_tokens_map.json

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

run-0/checkpoint-624/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-0/checkpoint-624/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_global_step": 624,
+  "best_metric": 0.592057761732852,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-0/checkpoint-624",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 624,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5090252707581228,
+      "eval_loss": 0.690215528011322,
+      "eval_runtime": 0.9783,
+      "eval_samples_per_second": 283.148,
+      "eval_steps_per_second": 5.111,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5703971119133574,
+      "eval_loss": 0.6809557676315308,
+      "eval_runtime": 0.9817,
+      "eval_samples_per_second": 282.165,
+      "eval_steps_per_second": 5.093,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5812274368231047,
+      "eval_loss": 0.6777123212814331,
+      "eval_runtime": 0.9494,
+      "eval_samples_per_second": 291.776,
+      "eval_steps_per_second": 5.267,
+      "step": 468
+    },
+    {
+      "epoch": 3.2051282051282053,
+      "grad_norm": 3.2472236156463623,
+      "learning_rate": 9.033763394114273e-07,
+      "loss": 0.694,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.592057761732852,
+      "eval_loss": 0.67612224817276,
+      "eval_runtime": 0.94,
+      "eval_samples_per_second": 294.682,
+      "eval_steps_per_second": 5.319,
+      "step": 624
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 199409237693544.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.1891988684237177,
+    "learning_rate": 4.546022869296215e-06,
+    "max_length": 256,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-0/checkpoint-624/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5f34da6ceb66aad0eb63c414662f43a60eed98b09cbecadb2699ba48e9f997
+size 5432

run-1/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": 0.10807485811873185,
+  "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-1/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e263c139f8de8f1e8341a963f5dc15c8b21e164f56f144f9138bf69b438ae70
+size 165512728

run-1/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f161fa1bdbb6040fe4f6d7ec9713d19fbd87ef4307d59f80a95fec0b56eea46
+size 331108474

run-1/checkpoint-156/rng_state.pth

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

run-1/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a60d322c19805e7d9b07636b0db45ca46f58317d500468b9150309e309fe72
+size 1064

run-1/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-1/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-1/checkpoint-156/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.6137184115523465,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-1/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": 0.6137184115523465,
+      "eval_loss": 0.6537649631500244,
+      "eval_runtime": 0.9914,
+      "eval_samples_per_second": 279.403,
+      "eval_steps_per_second": 5.043,
+      "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": 0.10807485811873185,
+    "learning_rate": 2.9512691618493915e-05,
+    "max_length": 512,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:397c8b0b400495fc92935712b7103c95ccb0961c113e74bb162f509ad182e4d0
+size 5432

runs/Apr03_13-50-26_435476ce9a2d/events.out.tfevents.1743689038.435476ce9a2d.544.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616c5ea6cdfd2047b5f1964823c9aaf1ebc10c8cfb86e4c4e6c16bf917f5aac1
-size 6273
+oid sha256:0f48775b95d714e043b0c7706843462919278f9a1d0e93b21f26625984abd3a2
+size 6950

runs/Apr03_13-50-26_435476ce9a2d/events.out.tfevents.1743689158.435476ce9a2d.544.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127d166b45fcd9ba1a96b9bb5cf036bb2b89683b784a4f6a1958030d03bf6114
+size 5374

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5f34da6ceb66aad0eb63c414662f43a60eed98b09cbecadb2699ba48e9f997
+oid sha256:397c8b0b400495fc92935712b7103c95ccb0961c113e74bb162f509ad182e4d0
 size 5432