Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9ffadd9b5852e37a0cc5d4af8aa0ed84a9ff4032847bfe01efecc9ea9a3247
+oid sha256:d7dcbeda55097af57b723f3c572c73a4ac0273f536f4983f245d3a89e00cc812
 size 437958648

run-1/checkpoint-1254/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-1254/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7dcbeda55097af57b723f3c572c73a4ac0273f536f4983f245d3a89e00cc812
+size 437958648

run-1/checkpoint-1254/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630dc0288a30e165cfcb5a0b61316d0f904e9b137a7a8b1f657d4166dfb82633
+size 876038394

run-1/checkpoint-1254/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16934ddb65a0cdde96ecdc5a40c32200e35b587e85a8aee6af23fd1ff50d843
+size 14308

run-1/checkpoint-1254/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ee60a7dbe0f6d8c5d94d17ba554afc467ce5d5fcb91b2f48697f8fe19f5ef6
+size 1064

run-1/checkpoint-1254/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-1254/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "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-1/checkpoint-1254/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.9800479328939484,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-1254",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1254,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.954104254044338,
+      "eval_loss": 0.19407691061496735,
+      "eval_runtime": 591.9344,
+      "eval_samples_per_second": 28.196,
+      "eval_steps_per_second": 1.764,
+      "step": 418
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.8940045833587646,
+      "learning_rate": 5.932776707197725e-05,
+      "loss": 0.2105,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9713600958657879,
+      "eval_loss": 0.1521669328212738,
+      "eval_runtime": 587.4301,
+      "eval_samples_per_second": 28.412,
+      "eval_steps_per_second": 1.777,
+      "step": 836
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.07928234338760376,
+      "learning_rate": 1.9985746467217804e-05,
+      "loss": 0.0822,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9800479328939484,
+      "eval_loss": 0.10306233912706375,
+      "eval_runtime": 588.0912,
+      "eval_samples_per_second": 28.38,
+      "eval_steps_per_second": 1.775,
+      "step": 1254
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1254,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 4182298224915840.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.86697876767367e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-1/checkpoint-1254/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1bc2ca1486d4354691d2859ca88c677e08f3269d34ab4a0a8373406db2ace6
+size 4920

run-1/checkpoint-836/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-836/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754b1f12d2941c2a4b7c82a04cd180fa1e21d612210cc0e5b26615124d22d073
+size 437958648

run-1/checkpoint-836/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4753cc331725be14961819c14a47d2d74975bd4008094bd86556c3a67d24ce48
+size 876038394

run-1/checkpoint-836/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e52d2f106a39352fe52613827135083798cde68853ad724f7d272acdf12e9d
+size 14308

run-1/checkpoint-836/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21d9f88cb55bb00ed8f28278606f452481cff66c77e80694f9fbee7391b9fd8
+size 1064

run-1/checkpoint-836/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-836/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "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-1/checkpoint-836/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.9713600958657879,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-836",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 836,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.954104254044338,
+      "eval_loss": 0.19407691061496735,
+      "eval_runtime": 591.9344,
+      "eval_samples_per_second": 28.196,
+      "eval_steps_per_second": 1.764,
+      "step": 418
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.8940045833587646,
+      "learning_rate": 5.932776707197725e-05,
+      "loss": 0.2105,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9713600958657879,
+      "eval_loss": 0.1521669328212738,
+      "eval_runtime": 587.4301,
+      "eval_samples_per_second": 28.412,
+      "eval_steps_per_second": 1.777,
+      "step": 836
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1254,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2092966223184000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.86697876767367e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-1/checkpoint-836/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1bc2ca1486d4354691d2859ca88c677e08f3269d34ab4a0a8373406db2ace6
+size 4920

runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711041077.43ee8d6b3d53.2090.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01765bf72033c08889b7f4d6635c39ca298302fe555276311ed4edbaaff2aa03
-size 4961
+oid sha256:ba45c38794d2fe122a395e147686e54dd890fba431221e8bbdf1163bd5c576a8
+size 6383