Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68abf3d631fbb4906ee054df81e1193e2655201640c808c9162781d865bdfb7
+oid sha256:233e0ca437b71d6c7d5c0641a5be2221cb09f58cb1fbea8682f03123827ea378
 size 409103316

run-7/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-7/checkpoint-34/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233e0ca437b71d6c7d5c0641a5be2221cb09f58cb1fbea8682f03123827ea378
+size 409103316

run-7/checkpoint-34/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69596f4cb72fa468aaa86f6ef74e497e58a5a1b3bd7394b2ecc04e16a0804a9
+size 818327802

run-7/checkpoint-34/rng_state.pth

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

run-7/checkpoint-34/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5726217e5ce28328ebd69f7a801be2a7129a04073466c87e8d6fa6793f18a6e3
+size 1064

run-7/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-7/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-7/checkpoint-34/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6808687448501587,
+  "best_model_checkpoint": "BERT-WMM/run-7/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": 0.7136150234741784,
+      "eval_loss": 0.6808687448501587,
+      "eval_runtime": 2.0038,
+      "eval_samples_per_second": 1063.006,
+      "eval_steps_per_second": 66.875,
+      "step": 34
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 68,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.8228078127928265e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 256,
+    "weight_decay": 9.933633111626257e-05
+  }
+}

run-7/checkpoint-34/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0664cb84434137aa481b2ab8fa3a6ae86965cb1d2f9c1e6700ae921a512164
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713430276.da5e8340a418.15241.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbba89ef41f75069e5b1c3aa222f7adc33091383787d0cc79907e143015fc655
+size 5894

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4215a0d171c998e861cecce9e6a8128f9e991e45dd727f00231bb96a25c0a48c
+oid sha256:1d0664cb84434137aa481b2ab8fa3a6ae86965cb1d2f9c1e6700ae921a512164
 size 4856