Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68b909ecf8ea4e5f34ca883c8a6d373b38b1a7816d735ce1181deb34971fe0a
+oid sha256:050918e5820244364467afc532f5d784b6fd7de82aaebcba6c2011c1f8914324
 size 430911284

run-b4o51kp9/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-b4o51kp9/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9181f0832fd34448c4590a38eeecc537241c100b70e84681cda9ccf3af8a63a
+size 430911284

run-b4o51kp9/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e4803e3de6f23e1a309cee59b3085d88189f68655a5f51f1276161313ad327
+size 861942330

run-b4o51kp9/checkpoint-1000/rng_state.pth

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

run-b4o51kp9/checkpoint-1000/scheduler.pt

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

run-b4o51kp9/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-b4o51kp9/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-b4o51kp9/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": 0.26024484634399414,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.1329,
+      "eval_samples_per_second": 98.721,
+      "eval_steps_per_second": 24.68,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.6803091168403625,
+      "learning_rate": 0.00033660130718954253,
+      "loss": 0.2299,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2626124322414398,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 6.0422,
+      "eval_samples_per_second": 67.525,
+      "eval_steps_per_second": 16.881,
+      "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": 5.8629,
+      "eval_samples_per_second": 69.59,
+      "eval_steps_per_second": 17.397,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 1.0660769939422607,
+      "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-b4o51kp9/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4920f1462d08f2e7fa314c958ffbd48b002704b4b1cc85a30b5c8fab2ab912
+size 5112

run-b4o51kp9/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-b4o51kp9/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050918e5820244364467afc532f5d784b6fd7de82aaebcba6c2011c1f8914324
+size 430911284

run-b4o51kp9/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d006315130b0f2708b403d6db476ffd0fb64ff4df3d8ac010242cfe84ad989
+size 861942330

run-b4o51kp9/checkpoint-1500/rng_state.pth

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

run-b4o51kp9/checkpoint-1500/scheduler.pt

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

run-b4o51kp9/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-b4o51kp9/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-b4o51kp9/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": 0.26024484634399414,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.1329,
+      "eval_samples_per_second": 98.721,
+      "eval_steps_per_second": 24.68,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.6803091168403625,
+      "learning_rate": 0.00033660130718954253,
+      "loss": 0.2299,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.2626124322414398,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 6.0422,
+      "eval_samples_per_second": 67.525,
+      "eval_steps_per_second": 16.881,
+      "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": 5.8629,
+      "eval_samples_per_second": 69.59,
+      "eval_steps_per_second": 17.397,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 1.0660769939422607,
+      "learning_rate": 0.00017320261437908497,
+      "loss": 0.2252,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.0,
+      "eval_f1_sklearn": 0.938717358210703,
+      "eval_loss": 0.252130389213562,
+      "eval_precision": 0.0,
+      "eval_precision_sklearn": 0.938717358210703,
+      "eval_recall": 0.0,
+      "eval_recall_sklearn": 0.938717358210703,
+      "eval_runtime": 4.2115,
+      "eval_samples_per_second": 96.877,
+      "eval_steps_per_second": 24.219,
+      "step": 1224
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.0557856559753418,
+      "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-b4o51kp9/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4920f1462d08f2e7fa314c958ffbd48b002704b4b1cc85a30b5c8fab2ab912
+size 5112