Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589df5fc0493e56fec9b23f83d70d16f6932e46d250134668fddacbb314a449e
+oid sha256:7907eb1675a73ae93c0f2ccb58fc1f195bfb1363eaa313d7f04edb59e3d20baf
 size 430911284

run-3xly69qa/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-3xly69qa/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7907eb1675a73ae93c0f2ccb58fc1f195bfb1363eaa313d7f04edb59e3d20baf
+size 430911284

run-3xly69qa/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929a9d43c16f8cec27825ddd053d2ffa3cb66691d4da6b40c418012e86d37f31
+size 861942330

run-3xly69qa/checkpoint-500/rng_state.pth

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

run-3xly69qa/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a45273ad22b65d31b4ddbab0b373b72cd3797bbe9cf80bd03d4fa57ba21c48
+size 1064

run-3xly69qa/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-3xly69qa/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-3xly69qa/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": 0.381578947368421,
+      "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": 4.4092,
+      "eval_samples_per_second": 92.534,
+      "eval_steps_per_second": 23.133,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 5.414725303649902,
+      "learning_rate": 3.3660130718954253e-06,
+      "loss": 0.1668,
+      "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": 5e-06,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-3xly69qa/checkpoint-500/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4920f1462d08f2e7fa314c958ffbd48b002704b4b1cc85a30b5c8fab2ab912
+oid sha256:4dd8f94ddd2e13e36e8e4087657740657b7454f82c774d6be138ea401df8b124
 size 5112