Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b086d7f0cad5d7ac8b3ca97fb34babdfe6f393964f3cf519bcc614dcd789220
+oid sha256:1e6a27adaac0bbe2b5312f4f381977654281a67946bcc88757d4a1c1634bae36
 size 437958648

run-0/checkpoint-920/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-920/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a7457c09bc078492889e04698aadda5fae3c96db6480224c8b19a382008345
+size 437958648

run-0/checkpoint-920/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c643f8596c205e66c8ff8a8d7db7a62ae5c86f6e9823ac80fd09224f3f541daf
+size 876038394

run-0/checkpoint-920/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2fff0226e333e3d839d9a4e348a2682a77ecb1b2c7a09ecb103fcbdbf1c032f
+size 14244

run-0/checkpoint-920/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5da04b1b98a1e397682e37f83c7438fadbd0bf382dafe5e890dd0c91cc6d15a
+size 1064

run-0/checkpoint-920/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-920/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-0/checkpoint-920/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.8594229588704727,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-736",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 920,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7925107427869859,
+      "eval_loss": 0.46051156520843506,
+      "eval_runtime": 1.5937,
+      "eval_samples_per_second": 1022.13,
+      "eval_steps_per_second": 64.001,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8465316144874155,
+      "eval_loss": 0.43229982256889343,
+      "eval_runtime": 1.6666,
+      "eval_samples_per_second": 977.463,
+      "eval_steps_per_second": 61.204,
+      "step": 368
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 0.23171758651733398,
+      "learning_rate": 7.102447094738944e-06,
+      "loss": 0.3446,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8397790055248618,
+      "eval_loss": 0.6237844824790955,
+      "eval_runtime": 1.5569,
+      "eval_samples_per_second": 1046.301,
+      "eval_steps_per_second": 65.514,
+      "step": 552
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8594229588704727,
+      "eval_loss": 0.6028990745544434,
+      "eval_runtime": 1.5442,
+      "eval_samples_per_second": 1054.886,
+      "eval_steps_per_second": 66.052,
+      "step": 736
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.852670349907919,
+      "eval_loss": 0.6441431045532227,
+      "eval_runtime": 1.5731,
+      "eval_samples_per_second": 1035.524,
+      "eval_steps_per_second": 64.839,
+      "step": 920
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 91478369505360.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.555774125514245e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-920/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+size 5176

run-1/checkpoint-138/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ee7a111736cb9ce1ed2851f73fb0a692e984f01a4766aa252f42d325574210
+size 437958648

run-1/checkpoint-138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7774cbcb4af7c4ca85d3e09b4825debb50dd45e99f27b8b784e1efbaab1f5c5b
+size 876038394

run-1/checkpoint-138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6fdaf5f9b5fc8b85922b753f680b87ac15b39643871824d2f8cacd706c1fff
+size 14308

run-1/checkpoint-138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e9cf636587d8b361ef92837fa3e0296c9f550f08506447d9c47ff628c19a08
+size 1064

run-1/checkpoint-138/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-138/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-138/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.7532228360957642,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/checkpoint-138",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7084100675260896,
+      "eval_loss": 0.6070903539657593,
+      "eval_runtime": 1.5313,
+      "eval_samples_per_second": 1063.788,
+      "eval_steps_per_second": 66.609,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7397176181706568,
+      "eval_loss": 0.5197229981422424,
+      "eval_runtime": 1.5355,
+      "eval_samples_per_second": 1060.891,
+      "eval_steps_per_second": 66.428,
+      "step": 92
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7532228360957642,
+      "eval_loss": 0.48536670207977295,
+      "eval_runtime": 1.5219,
+      "eval_samples_per_second": 1070.366,
+      "eval_steps_per_second": 67.021,
+      "step": 138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.898987655729564e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 13
+  }
+}

run-1/checkpoint-138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8113b7e429ea470e612f76a7e7ca6fc50ba0ca9fa3adb882ab6eb707dee49d51
+size 5176

run-1/checkpoint-184/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-184/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986e6b12214f55cddc115ef2a81e351d533463363dc5764e38a7f0166f136b54
+size 437958648

run-1/checkpoint-184/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4d419e18706a557199dcfeb7f581a306cc99c19720efaa35d60a4d2626ca00
+size 876038394

run-1/checkpoint-184/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27db5020d4a7d359804d6de43313d6baee996905e834889592d92c24f7a51ec
+size 14308

run-1/checkpoint-184/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516ac612b915074528a91375855f053625901c166266208a2d91207f29eba8f2
+size 1064

run-1/checkpoint-184/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-184/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-184/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.7771639042357275,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/checkpoint-184",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 184,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7084100675260896,
+      "eval_loss": 0.6070903539657593,
+      "eval_runtime": 1.5313,
+      "eval_samples_per_second": 1063.788,
+      "eval_steps_per_second": 66.609,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7397176181706568,
+      "eval_loss": 0.5197229981422424,
+      "eval_runtime": 1.5355,
+      "eval_samples_per_second": 1060.891,
+      "eval_steps_per_second": 66.428,
+      "step": 92
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7532228360957642,
+      "eval_loss": 0.48536670207977295,
+      "eval_runtime": 1.5219,
+      "eval_samples_per_second": 1070.366,
+      "eval_steps_per_second": 67.021,
+      "step": 138
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7771639042357275,
+      "eval_loss": 0.46350666880607605,
+      "eval_runtime": 1.5154,
+      "eval_samples_per_second": 1074.938,
+      "eval_steps_per_second": 67.307,
+      "step": 184
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.898987655729564e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 13
+  }
+}

run-1/checkpoint-184/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8113b7e429ea470e612f76a7e7ca6fc50ba0ca9fa3adb882ab6eb707dee49d51
+size 5176

run-1/checkpoint-230/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-230/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da3db15f28ad89cecd1e0dd8c0d26565a2e5323b287948eb0bc80796f239311
+size 437958648

run-1/checkpoint-230/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a1eceb24adfadb13e29badfb54ac24dd10da112375b1732844f6acfab3a44a
+size 876038394

run-1/checkpoint-230/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c50c709f5ba010e6ee12976c5d61a1e761d4d0428ab699ce8437cb85e91b36
+size 14308

run-1/checkpoint-230/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49370c1b8cc8a35c9693e4eae418a34992a42923f862ffc2416f0b8c0f2ffbc
+size 1064

run-1/checkpoint-230/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-230/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-230/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.7771639042357275,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/checkpoint-184",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7084100675260896,
+      "eval_loss": 0.6070903539657593,
+      "eval_runtime": 1.5313,
+      "eval_samples_per_second": 1063.788,
+      "eval_steps_per_second": 66.609,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7397176181706568,
+      "eval_loss": 0.5197229981422424,
+      "eval_runtime": 1.5355,
+      "eval_samples_per_second": 1060.891,
+      "eval_steps_per_second": 66.428,
+      "step": 92
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7532228360957642,
+      "eval_loss": 0.48536670207977295,
+      "eval_runtime": 1.5219,
+      "eval_samples_per_second": 1070.366,
+      "eval_steps_per_second": 67.021,
+      "step": 138
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7771639042357275,
+      "eval_loss": 0.46350666880607605,
+      "eval_runtime": 1.5154,
+      "eval_samples_per_second": 1074.938,
+      "eval_steps_per_second": 67.307,
+      "step": 184
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7740945365254758,
+      "eval_loss": 0.4589366018772125,
+      "eval_runtime": 3.5606,
+      "eval_samples_per_second": 457.506,
+      "eval_steps_per_second": 28.647,
+      "step": 230
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.898987655729564e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 13
+  }
+}

run-1/checkpoint-230/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8113b7e429ea470e612f76a7e7ca6fc50ba0ca9fa3adb882ab6eb707dee49d51
+size 5176

run-1/checkpoint-46/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-46/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c551ce278839d976fbb425701bec28361c7f0af5c056bb7b0445cd9e395031
+size 437958648

run-1/checkpoint-46/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f434397cafc46606beb6866d83cb4922b261c9c2a3beb4212b1506db4acd6f
+size 876038394

run-1/checkpoint-46/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c13c553e715437d2801903cd8d0429006a9a62710f90d54375d21795c240e72
+size 14308

run-1/checkpoint-46/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54cf70c3d1642dbdba1bc05ad51c002c6257e354e8b9086a25a7510aa52a848d
+size 1064