Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd8262bedc490fa8da89a40b7ede6e7928fc56601c695b3a5446194c45b4800
+oid sha256:5b26890bb284c97e2e3b88e32ae6b97cb46367de0bf1629ac099eeb00c30e3b1
 size 430911284

run-bklb73ki/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-bklb73ki/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b26890bb284c97e2e3b88e32ae6b97cb46367de0bf1629ac099eeb00c30e3b1
+size 430911284

run-bklb73ki/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff2fc2c86635b7ed0d6c039159b1b675a1fc02fedd616cadc14e5ec5ee7fe32
+size 861942330

run-bklb73ki/checkpoint-500/rng_state.pth

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

run-bklb73ki/checkpoint-500/scheduler.pt

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

run-bklb73ki/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-bklb73ki/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-bklb73ki/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": 0.13979755342006683,
+      "eval_precision": 0.40869565217391307,
+      "eval_precision_sklearn": 0.9412155041180374,
+      "eval_recall": 0.26578699340245054,
+      "eval_recall_sklearn": 0.9412155041180374,
+      "eval_runtime": 4.4935,
+      "eval_samples_per_second": 90.798,
+      "eval_steps_per_second": 22.7,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5764657646576465,
+      "eval_f1_sklearn": 0.9512471212771771,
+      "eval_loss": 0.12371943145990372,
+      "eval_precision": 0.5101596516690856,
+      "eval_precision_sklearn": 0.9512471212771771,
+      "eval_recall": 0.6625824693685203,
+      "eval_recall_sklearn": 0.9512471212771771,
+      "eval_runtime": 4.6481,
+      "eval_samples_per_second": 87.778,
+      "eval_steps_per_second": 21.945,
+      "step": 306
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6020964360587001,
+      "eval_f1_sklearn": 0.9553846754361996,
+      "eval_loss": 0.14001750946044922,
+      "eval_precision": 0.5422960725075529,
+      "eval_precision_sklearn": 0.9553846754361996,
+      "eval_recall": 0.6767200754005656,
+      "eval_recall_sklearn": 0.9553846754361996,
+      "eval_runtime": 5.0133,
+      "eval_samples_per_second": 81.383,
+      "eval_steps_per_second": 20.346,
+      "step": 459
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.28760242462158203,
+      "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-bklb73ki/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f49b4936f33521f010eddcfa7fcbccaa8b2b0592239fabce310a244ad3f1ea
+size 5112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7e2fd3907f08c3d3f1d7b65b177a44dd6fed1eef5fea87d4905bc0c5068016
+oid sha256:f2f49b4936f33521f010eddcfa7fcbccaa8b2b0592239fabce310a244ad3f1ea
 size 5112