Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a400be0e074411743f4d5e0630483b6c02c4436b27fd956ff81cb2de57670b
+oid sha256:f41389548935b1e2cf65361b04495cf53e596adb7a9d5abde9be5c3e6ef04678
 size 409103316

run-0/checkpoint-34/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-0/checkpoint-34/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41389548935b1e2cf65361b04495cf53e596adb7a9d5abde9be5c3e6ef04678
+size 409103316

run-0/checkpoint-34/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac96dda78f0e250f23da45fc5e77127c8a0acf4de4e634c31b04f702f965664
+size 818327802

run-0/checkpoint-34/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce99f59185c29fdd98b44ceeb7cbf04434a2c7491d08089d6457b99921cc29cd
+size 14244

run-0/checkpoint-34/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f91dccbcf926ce084e03950a1294262bbff4755673b306acbe05053d86f6d5
+size 1064

run-0/checkpoint-34/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-0/checkpoint-34/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-0/checkpoint-34/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 1.057793140411377,
+  "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-34",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 34,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4572769953051643,
+      "eval_loss": 1.057793140411377,
+      "eval_runtime": 2.1526,
+      "eval_samples_per_second": 989.489,
+      "eval_steps_per_second": 62.25,
+      "step": 34
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 136,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3245164890212277e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 256,
+    "weight_decay": 3.536833872428622e-05
+  }
+}

run-0/checkpoint-34/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0608c1059d788e034d271975d72fd13e4c51749f92b6a8bac6127d68ca536f7f
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429321.da5e8340a418.15241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16826b4f58f182242bdfb00cc438c2fc0e66916c7ce89638f183d8c4cd9f0b5b
+size 5229

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6516b334ea9aa4fa19c1f514f33bbe47dc1c65e603b04287264331965d5ea3f7
+oid sha256:0608c1059d788e034d271975d72fd13e4c51749f92b6a8bac6127d68ca536f7f
 size 4856