Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e523ef390379259e2d519e2d17198780a1cde58ae8503b3aba68131e7af118d0
+oid sha256:078050c05a159c17f622e1056af2571347b2bbe2ab5c3ccc32a831d6d2868e33
 size 165512728

run-0/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": 0.1891988684237177,
+  "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-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc17e9f2ae81fe18a5c6d515f5cb2431785306fbefb44ecb71e2565a957eb18
+size 165512728

run-0/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5450565e5844774a141b752e0423af96652f5dfb3e9c27070b1d28b9afa07de2
+size 331108474

run-0/checkpoint-312/rng_state.pth

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

run-0/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f764fd7cdcc0b0463342742e47bbc9e0d7c3560ee1d035f70206c0a260293bb6
+size 1064

run-0/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-0/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-0/checkpoint-312/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 312,
+  "best_metric": 0.5703971119133574,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-0/checkpoint-312",
+  "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": 0.5090252707581228,
+      "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
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 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-312/training_args.bin

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

run-0/checkpoint-468/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-468/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078050c05a159c17f622e1056af2571347b2bbe2ab5c3ccc32a831d6d2868e33
+size 165512728

run-0/checkpoint-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86095795db546e2bbe37a04b66aee27b49cfca303531e0e43b6db7a12c55eb5c
+size 331108474

run-0/checkpoint-468/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2387e19ff70ff52a1da549c008f866915edb34fdc632d8b4f2743f3894398c3
+size 14244

run-0/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfec2520d7de906fa0d65cba64e755e49b54e9e53b2cf74a010f3d8fad5d810
+size 1064

run-0/checkpoint-468/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-468/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-468/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_global_step": 468,
+  "best_metric": 0.5812274368231047,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-0/checkpoint-468",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 468,
+  "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
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 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-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5f34da6ceb66aad0eb63c414662f43a60eed98b09cbecadb2699ba48e9f997
+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 sha256:692e5a910a6cc37ed6bb0f89297927ee0f556fe28febe6017a182ae77a3e22ab
-size 5416
+oid sha256:616c5ea6cdfd2047b5f1964823c9aaf1ebc10c8cfb86e4c4e6c16bf917f5aac1
+size 6273