Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbe36943eedb3184229a1a5974bcc08a70bed558ba6f4453cecbfadb1f62b89
+oid sha256:bb0b999fa1ee2eb12aa40a295fdf920a3e16129e1fe9392f463fa8cc159573fb
 size 437958648

run-11/checkpoint-422/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-11/checkpoint-422/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8d3cbaf588f2a855c2ca5c230dca1fdcca96835294b102d3fdf4b40587a2ab
+size 437958648

run-11/checkpoint-422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c624a1c6ecc255a7fab9b5b8af0c6ef71db0bab53dad976b98aec4f6cf5185
+size 876038394

run-11/checkpoint-422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa638805573ee53012c9c789c649fa8a5cd1d94fb6581ee938bf7a64c787bf5
+size 14244

run-11/checkpoint-422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9886b50e85f0d17b54b1c863528e5a0da942b7c16f492c23a778a0f9a05380a2
+size 1064

run-11/checkpoint-422/special_tokens_map.json

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

run-11/checkpoint-422/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-11/checkpoint-422/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.911697247706422,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-11/checkpoint-422",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 422,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9036697247706422,
+      "eval_loss": 0.22603479027748108,
+      "eval_runtime": 2.4304,
+      "eval_samples_per_second": 358.785,
+      "eval_steps_per_second": 22.63,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.2671126127243042,
+      "eval_runtime": 2.4233,
+      "eval_samples_per_second": 359.842,
+      "eval_steps_per_second": 22.696,
+      "step": 422
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 844,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.0602619122090524e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 5
+  }
+}

run-11/checkpoint-422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20f491bcd258cb2b04ee82e11e2d99e0be3d52fceef83399f1e08b07b63e13c
+size 4920

run-12/checkpoint-211/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-12/checkpoint-211/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b10d0da85e30ed73d9430fce3cacca57fe4620c2ad2e63be027a08629e94662
+size 437958648

run-12/checkpoint-211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bce8446bfeb748df8e7275859b535e97e475592db41b9b45b1a4b8017c62f95
+size 876038394

run-12/checkpoint-211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd536778dff8e09a3adf2e1ada791b7834e50ce1a519297f5a7325f25e66d5b
+size 14244

run-12/checkpoint-211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301262ee26e221ddb36ac241ea34e9a14f056079b389d3a8d9c382d344d1b3c2
+size 1064

run-12/checkpoint-211/special_tokens_map.json

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

run-12/checkpoint-211/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-12/checkpoint-211/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.9174311926605505,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-12/checkpoint-211",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 211,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.22459161281585693,
+      "eval_runtime": 2.4317,
+      "eval_samples_per_second": 358.604,
+      "eval_steps_per_second": 22.618,
+      "step": 211
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 633,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.4643506167208596e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 4
+  }
+}

run-12/checkpoint-211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef49558b7a46a1319d11066d16eece87680b6a33c1fba75612968a38df1f236
+size 4920

run-12/checkpoint-422/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-12/checkpoint-422/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b42d63d32d26354026c12e3fbebdf5ac5cab12b651caee968c20e069c161f13
+size 437958648

run-12/checkpoint-422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1827079b4d5a1f06528849466875618e32ebaf1d21f17a0efdc23a92fd0902a3
+size 876038394

run-12/checkpoint-422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a552a367005c08fc935fba6db0178fd612c11143da54160857b415e72c8168bd
+size 14244

run-12/checkpoint-422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa19fe6879a978b47ab135b0eaf0ca086e9f502e0fbf35a202b84efd10fd49c
+size 1064

run-12/checkpoint-422/special_tokens_map.json

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

run-12/checkpoint-422/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-12/checkpoint-422/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.9174311926605505,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-12/checkpoint-211",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 422,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.22459161281585693,
+      "eval_runtime": 2.4317,
+      "eval_samples_per_second": 358.604,
+      "eval_steps_per_second": 22.618,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9048165137614679,
+      "eval_loss": 0.2872973680496216,
+      "eval_runtime": 2.4585,
+      "eval_samples_per_second": 354.685,
+      "eval_steps_per_second": 22.371,
+      "step": 422
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 633,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.4643506167208596e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 4
+  }
+}

run-12/checkpoint-422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef49558b7a46a1319d11066d16eece87680b6a33c1fba75612968a38df1f236
+size 4920

run-13/checkpoint-211/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-13/checkpoint-211/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0b999fa1ee2eb12aa40a295fdf920a3e16129e1fe9392f463fa8cc159573fb
+size 437958648

run-13/checkpoint-211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720b8fbbb76dc1564f8fde85881b0da3e3869a614cb59adbd493f3e9ed9522c5
+size 876038394

run-13/checkpoint-211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb0dd1e13d8982c379f0b9f7b5eae142e6fc1e95814de9534e6934bfd6b9901
+size 14244

run-13/checkpoint-211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530c5ab8460bc06f0589e7d94cee8fc482fb2a0d116d0d653455b51c1af94e2a
+size 1064

run-13/checkpoint-211/special_tokens_map.json

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

run-13/checkpoint-211/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-13/checkpoint-211/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.911697247706422,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-13/checkpoint-211",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 211,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.22412490844726562,
+      "eval_runtime": 2.4274,
+      "eval_samples_per_second": 359.236,
+      "eval_steps_per_second": 22.658,
+      "step": 211
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 844,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.753483017575571e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 7
+  }
+}

run-13/checkpoint-211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51d8d59c5596bf2142132b64ad5dd777499bc79824c005ef44e203b20d6ffa8
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709499676.90708aaa767a.21824.30

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6914f25ad8482c132aa704233e3bf26c8c5f1db0b1a7a20b1364f7ffa4cf39
+size 5804

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709499844.90708aaa767a.21824.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f46ccc4089bf1c861ebfb6c9b35df3d4953bcc829c305fdd090743fc2796a4f
+size 6480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c20f491bcd258cb2b04ee82e11e2d99e0be3d52fceef83399f1e08b07b63e13c
+oid sha256:a51d8d59c5596bf2142132b64ad5dd777499bc79824c005ef44e203b20d6ffa8
 size 4920