Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652e72b4e0a2de346df01d712d1ac1f9558f88c28d6f024b603cc773696eee14
+oid sha256:e2391b1094930053ebaf8dda7d0798ceee4c7049619139a7d81ed992cf724e32
 size 430911284

run-6ibgkg60/checkpoint-500/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-S",
+    "2": "B-S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-S": 2,
+    "I-S": 1,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-6ibgkg60/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2391b1094930053ebaf8dda7d0798ceee4c7049619139a7d81ed992cf724e32
+size 430911284

run-6ibgkg60/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c23171a4d9d114c7e9f8b2da8a665c52e8f0a01da2756fefdf1bd53fa2582c9
+size 861942330

run-6ibgkg60/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a801e52b02802e184980e68632305a0661a666536a8c36170f2de2d9852f4e
+size 14244

run-6ibgkg60/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7b5921863db7b87e27f2fa213d465475cef500f2b7c3266757e189ee4c8ca2
+size 1064

run-6ibgkg60/checkpoint-500/special_tokens_map.json

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

run-6ibgkg60/checkpoint-500/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": false,
+  "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-6ibgkg60/checkpoint-500/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2679738562091503,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.3221016561964592,
+      "eval_f1_sklearn": 0.9412155041180373,
+      "eval_loss": 0.13979752361774445,
+      "eval_precision": 0.40869565217391307,
+      "eval_precision_sklearn": 0.9412155041180374,
+      "eval_recall": 0.26578699340245054,
+      "eval_recall_sklearn": 0.9412155041180374,
+      "eval_runtime": 4.3114,
+      "eval_samples_per_second": 94.633,
+      "eval_steps_per_second": 23.658,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5767022149302706,
+      "eval_f1_sklearn": 0.9512861548069792,
+      "eval_loss": 0.12371925264596939,
+      "eval_precision": 0.5105301379811183,
+      "eval_precision_sklearn": 0.9512861548069792,
+      "eval_recall": 0.6625824693685203,
+      "eval_recall_sklearn": 0.9512861548069792,
+      "eval_runtime": 4.9233,
+      "eval_samples_per_second": 82.872,
+      "eval_steps_per_second": 20.718,
+      "step": 306
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6020964360587001,
+      "eval_f1_sklearn": 0.9553846754361996,
+      "eval_loss": 0.14001785218715668,
+      "eval_precision": 0.5422960725075529,
+      "eval_precision_sklearn": 0.9553846754361996,
+      "eval_recall": 0.6767200754005656,
+      "eval_recall_sklearn": 0.9553846754361996,
+      "eval_runtime": 4.8292,
+      "eval_samples_per_second": 84.486,
+      "eval_steps_per_second": 21.121,
+      "step": 459
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.2875863313674927,
+      "learning_rate": 1.7320261437908496e-05,
+      "loss": 0.0663,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 765,
+  "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": 433135952304768.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-05,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 8
+  }
+}

run-6ibgkg60/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a619be009041f56db5b5b52efe0d24fa2d50ec4f6748bf57143936ddd0f2d4
+size 5112

run-85jxfgwi/checkpoint-1000/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-S",
+    "2": "B-S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-S": 2,
+    "I-S": 1,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-85jxfgwi/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5783cc58c4bcbad5914045c96c516cc3aad14908c3c1fb4034bb3fc94df8e8d2
+size 430911284

run-85jxfgwi/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270fa879d9c9e909c29890796fee8ff20b6c5c4d73ec9e2979da68fd52f26d00
+size 861942330

run-85jxfgwi/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6506071cda30ec363ad5c19299436106e9bc716569a13a88656f006a4610af
+size 14244

run-85jxfgwi/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228e62be4ec2a61884a81683ae6fcf9553d3058c3712d77efa73596ea9872a1f
+size 1064

run-85jxfgwi/checkpoint-1000/special_tokens_map.json

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

run-85jxfgwi/checkpoint-1000/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": false,
+  "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-85jxfgwi/checkpoint-1000/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2679738562091503,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2602449059486389,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.1187,
+      "eval_samples_per_second": 99.06,
+      "eval_steps_per_second": 24.765,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.6803117394447327,
+      "learning_rate": 0.00033660130718954253,
+      "loss": 0.2299,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2626122534275055,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.4895,
+      "eval_samples_per_second": 90.88,
+      "eval_steps_per_second": 22.72,
+      "step": 612
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2532053291797638,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.4164,
+      "eval_samples_per_second": 92.383,
+      "eval_steps_per_second": 23.096,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 1.0660701990127563,
+      "learning_rate": 0.00017320261437908497,
+      "loss": 0.2252,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1530,
+  "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": 318346024442760.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 0.0005,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-85jxfgwi/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9f771472677ce7d73955c223dc388592bf2909d4b94f594dff367948466552
+size 5112

run-85jxfgwi/checkpoint-1500/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-S",
+    "2": "B-S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-S": 2,
+    "I-S": 1,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-85jxfgwi/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a47157e953f6674cec1ff4ffc6df167da985e2713ed554d47f93cc8676d0de
+size 430911284

run-85jxfgwi/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f1d99b6b119d65344652df2b985de8ff28488cc9699399fc1d3e9a5bf4db0d
+size 861942330

run-85jxfgwi/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2623190ade7475a14422c6523b005c8acd111f240775a08c6f4ab59256d8d57
+size 14244

run-85jxfgwi/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94cef5de60a47a593c212285b0969bb84d81422dbfcf3350fb9399897e15b06
+size 1064

run-85jxfgwi/checkpoint-1500/special_tokens_map.json

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

run-85jxfgwi/checkpoint-1500/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": false,
+  "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-85jxfgwi/checkpoint-1500/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.901960784313726,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2602449059486389,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.1187,
+      "eval_samples_per_second": 99.06,
+      "eval_steps_per_second": 24.765,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.6803117394447327,
+      "learning_rate": 0.00033660130718954253,
+      "loss": 0.2299,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2626122534275055,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.4895,
+      "eval_samples_per_second": 90.88,
+      "eval_steps_per_second": 22.72,
+      "step": 612
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2532053291797638,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.4164,
+      "eval_samples_per_second": 92.383,
+      "eval_steps_per_second": 23.096,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 1.0660701990127563,
+      "learning_rate": 0.00017320261437908497,
+      "loss": 0.2252,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.25213053822517395,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.972,
+      "eval_samples_per_second": 82.06,
+      "eval_steps_per_second": 20.515,
+      "step": 1224
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.0557799339294434,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.2172,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1530,
+  "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": 470773232452584.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 0.0005,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-85jxfgwi/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9f771472677ce7d73955c223dc388592bf2909d4b94f594dff367948466552
+size 5112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9f771472677ce7d73955c223dc388592bf2909d4b94f594dff367948466552
+oid sha256:64a619be009041f56db5b5b52efe0d24fa2d50ec4f6748bf57143936ddd0f2d4
 size 5112