Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c13564370fb612c94ee4bdbcea029a22500ba60e3dd6c74261dfd87d65a985e
+oid sha256:637071f6b94ca4846fdb162f4d57f6c6e63a66b4ea34a374baf7e778c56adfa2
 size 430911284

run-797xqzmq/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-797xqzmq/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0155bcffbbe6c3cbfb7145a28d0bac7a5d915b54dd57f1fe25d3578e7497d38d
+size 430911284

run-797xqzmq/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb6626b0e9a6948a42e5cecd4aa621069ea6705566aa80e89c459aa62bd28c7
+size 861942330

run-797xqzmq/checkpoint-1000/rng_state.pth

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

run-797xqzmq/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8817b5054667784af48d9e26890ad2db76283eee4da6599cf860dfd5afcb8e19
+size 1064

run-797xqzmq/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-797xqzmq/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-797xqzmq/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": 0.381578947368421,
+      "eval_f1_sklearn": 0.9460166282836957,
+      "eval_loss": 0.1464981883764267,
+      "eval_precision": 0.45609436435124506,
+      "eval_precision_sklearn": 0.9460166282836957,
+      "eval_recall": 0.32799245994344955,
+      "eval_recall_sklearn": 0.9460166282836957,
+      "eval_runtime": 4.8912,
+      "eval_samples_per_second": 83.415,
+      "eval_steps_per_second": 20.854,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 5.414730072021484,
+      "learning_rate": 3.3660130718954253e-06,
+      "loss": 0.1668,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.4384873145045477,
+      "eval_f1_sklearn": 0.9487099418400406,
+      "eval_loss": 0.1396203637123108,
+      "eval_precision": 0.4455252918287938,
+      "eval_precision_sklearn": 0.9487099418400406,
+      "eval_recall": 0.43166823751178135,
+      "eval_recall_sklearn": 0.9487099418400406,
+      "eval_runtime": 4.6437,
+      "eval_samples_per_second": 87.86,
+      "eval_steps_per_second": 21.965,
+      "step": 612
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.49019607843137253,
+      "eval_f1_sklearn": 0.9503103165619267,
+      "eval_loss": 0.14265619218349457,
+      "eval_precision": 0.46491969568892644,
+      "eval_precision_sklearn": 0.9503103165619267,
+      "eval_recall": 0.5183788878416589,
+      "eval_recall_sklearn": 0.9503103165619267,
+      "eval_runtime": 4.692,
+      "eval_samples_per_second": 86.957,
+      "eval_steps_per_second": 21.739,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 4.938509464263916,
+      "learning_rate": 1.7320261437908499e-06,
+      "loss": 0.0872,
+      "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": 5e-06,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-797xqzmq/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd8f94ddd2e13e36e8e4087657740657b7454f82c774d6be138ea401df8b124
+size 5112

run-797xqzmq/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-797xqzmq/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1cf73a4fadec10e3fedf820eb888ae61fae09daf962133a98d779882663ac6
+size 430911284

run-797xqzmq/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5c51969a4269a849df0dd252fb753a27373764e1aadc90a8629a119cd25ce1
+size 861942330

run-797xqzmq/checkpoint-1500/rng_state.pth

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

run-797xqzmq/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001b3e979cb1baf08147a47c664ea53728dbddc6de5c7fa4c4b1a0076090a670
+size 1064

run-797xqzmq/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-797xqzmq/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-797xqzmq/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": 0.381578947368421,
+      "eval_f1_sklearn": 0.9460166282836957,
+      "eval_loss": 0.1464981883764267,
+      "eval_precision": 0.45609436435124506,
+      "eval_precision_sklearn": 0.9460166282836957,
+      "eval_recall": 0.32799245994344955,
+      "eval_recall_sklearn": 0.9460166282836957,
+      "eval_runtime": 4.8912,
+      "eval_samples_per_second": 83.415,
+      "eval_steps_per_second": 20.854,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 5.414730072021484,
+      "learning_rate": 3.3660130718954253e-06,
+      "loss": 0.1668,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.4384873145045477,
+      "eval_f1_sklearn": 0.9487099418400406,
+      "eval_loss": 0.1396203637123108,
+      "eval_precision": 0.4455252918287938,
+      "eval_precision_sklearn": 0.9487099418400406,
+      "eval_recall": 0.43166823751178135,
+      "eval_recall_sklearn": 0.9487099418400406,
+      "eval_runtime": 4.6437,
+      "eval_samples_per_second": 87.86,
+      "eval_steps_per_second": 21.965,
+      "step": 612
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.49019607843137253,
+      "eval_f1_sklearn": 0.9503103165619267,
+      "eval_loss": 0.14265619218349457,
+      "eval_precision": 0.46491969568892644,
+      "eval_precision_sklearn": 0.9503103165619267,
+      "eval_recall": 0.5183788878416589,
+      "eval_recall_sklearn": 0.9503103165619267,
+      "eval_runtime": 4.692,
+      "eval_samples_per_second": 86.957,
+      "eval_steps_per_second": 21.739,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 4.938509464263916,
+      "learning_rate": 1.7320261437908499e-06,
+      "loss": 0.0872,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.503803888419273,
+      "eval_f1_sklearn": 0.9477731371247902,
+      "eval_loss": 0.15120969712734222,
+      "eval_precision": 0.4567049808429119,
+      "eval_precision_sklearn": 0.9477731371247902,
+      "eval_recall": 0.5617342130065975,
+      "eval_recall_sklearn": 0.9477731371247902,
+      "eval_runtime": 6.0205,
+      "eval_samples_per_second": 67.769,
+      "eval_steps_per_second": 16.942,
+      "step": 1224
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.531068205833435,
+      "learning_rate": 9.803921568627452e-08,
+      "loss": 0.0617,
+      "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": 5e-06,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-797xqzmq/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd8f94ddd2e13e36e8e4087657740657b7454f82c774d6be138ea401df8b124
+size 5112

run-zhekmzi0/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-zhekmzi0/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637071f6b94ca4846fdb162f4d57f6c6e63a66b4ea34a374baf7e778c56adfa2
+size 430911284

run-zhekmzi0/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b12b5b2bfcb7d3bc3793d3ca6ccb9df55c4715cacebd136a404c01eed846bc
+size 861942330

run-zhekmzi0/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cf6712a80c786c6516b565e21ebf119dfb938fa91f074f5c2e6ac6eb8a3d9f
+size 14244

run-zhekmzi0/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5323f0063b38e41b8b1d7249d7671d3eef375e28ec9f0547aa5f9ad7614e142d
+size 1064

run-zhekmzi0/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-zhekmzi0/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-zhekmzi0/checkpoint-500/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6339869281045751,
+  "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": 0.515569167942828,
+      "eval_f1_sklearn": 0.9512861548069792,
+      "eval_loss": 0.1222936138510704,
+      "eval_precision": 0.5623608017817372,
+      "eval_precision_sklearn": 0.9512861548069792,
+      "eval_recall": 0.4759660697455231,
+      "eval_recall_sklearn": 0.9512861548069792,
+      "eval_runtime": 4.769,
+      "eval_samples_per_second": 85.553,
+      "eval_steps_per_second": 21.388,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 1.8479167222976685,
+      "learning_rate": 6.73202614379085e-05,
+      "loss": 0.1033,
+      "step": 500
+    }
+  ],
+  "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": 156577372924968.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 0.0001,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-zhekmzi0/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5e8846bf2c23aa1f92199215b96f27a6aef16cc262f5408c515283e6c3691b
+size 5112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd8f94ddd2e13e36e8e4087657740657b7454f82c774d6be138ea401df8b124
+oid sha256:ca5e8846bf2c23aa1f92199215b96f27a6aef16cc262f5408c515283e6c3691b
 size 5112