Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b851075172d50769116d12249a9cff22e8c21976931d8165a57d7498ec6667c1
+oid sha256:5fe11cc49e11e0123425fda3a05ae0b741c41d169bf70c6dad1b58358a85657e
 size 430911284

run-us7ec15y/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-us7ec15y/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe11cc49e11e0123425fda3a05ae0b741c41d169bf70c6dad1b58358a85657e
+size 430911284

run-us7ec15y/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b46dbbec65582a460be0c1e8f1b9a982dad80cf914d6a4514df4bc2ff2b997e
+size 861942330

run-us7ec15y/checkpoint-500/rng_state.pth

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

run-us7ec15y/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd7de7fd0120a20e774c319ad7b6841b81940ed516a2aa829ceab088db5d1a7
+size 1064

run-us7ec15y/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-us7ec15y/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-us7ec15y/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": 0.49378714208535923,
+      "eval_f1_sklearn": 0.9530816971778758,
+      "eval_loss": 0.1254858672618866,
+      "eval_precision": 0.5784810126582278,
+      "eval_precision_sklearn": 0.9530816971778758,
+      "eval_recall": 0.43072573044297835,
+      "eval_recall_sklearn": 0.9530816971778758,
+      "eval_runtime": 4.6944,
+      "eval_samples_per_second": 86.912,
+      "eval_steps_per_second": 21.728,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5957261229829918,
+      "eval_f1_sklearn": 0.9530036301182716,
+      "eval_loss": 0.11604669690132141,
+      "eval_precision": 0.5543831168831169,
+      "eval_precision_sklearn": 0.9530036301182716,
+      "eval_recall": 0.6437323279924599,
+      "eval_recall_sklearn": 0.9530036301182716,
+      "eval_runtime": 4.9096,
+      "eval_samples_per_second": 83.103,
+      "eval_steps_per_second": 20.776,
+      "step": 306
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.5958316305680426,
+      "eval_f1_sklearn": 0.9507396853897498,
+      "eval_loss": 0.145028218626976,
+      "eval_precision": 0.525974025974026,
+      "eval_precision_sklearn": 0.9507396853897498,
+      "eval_recall": 0.6870876531573987,
+      "eval_recall_sklearn": 0.9507396853897498,
+      "eval_runtime": 4.3254,
+      "eval_samples_per_second": 94.328,
+      "eval_steps_per_second": 23.582,
+      "step": 459
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.39576607942581177,
+      "learning_rate": 3.464052287581699e-05,
+      "loss": 0.0651,
+      "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": 0.0001,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 8
+  }
+}

run-us7ec15y/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dcd74215346e2f5a5002931c68c43a8f3f9cf81e131bb351b3945e2486dcef
+size 5112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0faac25d416a58bb76b05100d0033c9bd328d14d03906ad62dab5d8d399b71
+oid sha256:c7dcd74215346e2f5a5002931c68c43a8f3f9cf81e131bb351b3945e2486dcef
 size 5112