Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0418de77a9dc505b34ea88086b072ae48fac434cc5986f17b8ab783fb96fa3
+oid sha256:ba3f272ba28850e271d835a10c87730be852ab6db516e012cbc44531b94fa555
 size 409103316

run-3/checkpoint-267/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hfl/chinese-bert-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "NEUTRAL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "NEUTRAL": 2,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

run-3/checkpoint-267/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3f272ba28850e271d835a10c87730be852ab6db516e012cbc44531b94fa555
+size 409103316

run-3/checkpoint-267/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea04bf4d4dc68963e830fa326a725b939dbec10295f92535088a04bebc319a9
+size 818327802

run-3/checkpoint-267/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123e89548a83b33069b1dc6f7e79d621eac970b4e99c56bc48c19b6733a7f692
+size 14244

run-3/checkpoint-267/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d045169881a02b28adaee74c583304a18a3b191c8ca509dbc2cd1981404c448
+size 1064

run-3/checkpoint-267/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-3/checkpoint-267/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-267/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6716192960739136,
+  "best_model_checkpoint": "BERT-WMM/run-3/checkpoint-267",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 267,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7262910798122065,
+      "eval_loss": 0.6716192960739136,
+      "eval_runtime": 2.087,
+      "eval_samples_per_second": 1020.621,
+      "eval_steps_per_second": 64.208,
+      "step": 267
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1068,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.8808881478336665e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 1.7684940065509674e-05
+  }
+}

run-3/checkpoint-267/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429603.da5e8340a418.15241.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff45af27ef0616ed33cd09989d42c7e8ba2b0ed167dd66f6cf63bd558e74cc7
+size 5769

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb97fd1508a0d1018c1559729d50143162da69a9c591e65f302288ab7245d704
+oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
 size 4856