Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e38fd0bac0ea3630404563ae715c928ba270b92070c4c8aa5761218bacece08
+oid sha256:7390cebb2fda07dbf4ce8704393add4465636418aa81649aa3d6590ba3e2ead1
 size 409103316

run-10/checkpoint-3198/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-10/checkpoint-3198/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2efca40093794a6e689378d2f84df061c7644733d54481d511cd98e8887a650
+size 409103316

run-10/checkpoint-3198/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21429ce2d789592d60845d032a1b83570040c6227cf601c46d00e9fba1b4f56f
+size 818327802

run-10/checkpoint-3198/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bf02b30277d45e8a05d66b020d674535c6c4e043dedd2496b55e484a23858d
+size 14244

run-10/checkpoint-3198/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb5941b1f71e888827a8b3dbccd18b839bb265660209ed615c7c22e369a9471
+size 1064

run-10/checkpoint-3198/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-10/checkpoint-3198/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-10/checkpoint-3198/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 0.6108968257904053,
+  "best_model_checkpoint": "BERT-WMM/run-10/checkpoint-1066",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3198,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 11.003177642822266,
+      "learning_rate": 3.5116101047118276e-06,
+      "loss": 0.7883,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7370892018779343,
+      "eval_loss": 0.6418591737747192,
+      "eval_runtime": 2.0865,
+      "eval_samples_per_second": 1020.838,
+      "eval_steps_per_second": 64.222,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 22.481332778930664,
+      "learning_rate": 2.8608298777452175e-06,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6108968257904053,
+      "eval_runtime": 2.0305,
+      "eval_samples_per_second": 1049.022,
+      "eval_steps_per_second": 65.995,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 32.06578063964844,
+      "learning_rate": 2.2100496507786074e-06,
+      "loss": 0.4792,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7553990610328638,
+      "eval_loss": 0.6331790089607239,
+      "eval_runtime": 2.1296,
+      "eval_samples_per_second": 1000.171,
+      "eval_steps_per_second": 62.922,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 21.596628189086914,
+      "learning_rate": 1.5592694238119975e-06,
+      "loss": 0.4182,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6648078560829163,
+      "eval_runtime": 2.7647,
+      "eval_samples_per_second": 770.434,
+      "eval_steps_per_second": 48.469,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 17.562744140625,
+      "learning_rate": 9.084891968453876e-07,
+      "loss": 0.3558,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7586854460093897,
+      "eval_loss": 0.6886456608772278,
+      "eval_runtime": 2.0657,
+      "eval_samples_per_second": 1031.129,
+      "eval_steps_per_second": 64.869,
+      "step": 2665
+    },
+    {
+      "epoch": 5.63,
+      "grad_norm": 11.413674354553223,
+      "learning_rate": 2.5770896987877753e-07,
+      "loss": 0.3302,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7544600938967136,
+      "eval_loss": 0.6990614533424377,
+      "eval_runtime": 2.1424,
+      "eval_samples_per_second": 994.216,
+      "eval_steps_per_second": 62.547,
+      "step": 3198
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1205069731062120.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.162390331678438e-06,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.000561727996440909
+  }
+}

run-10/checkpoint-3198/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
+size 4856

run-11/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-11/checkpoint-267/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7390cebb2fda07dbf4ce8704393add4465636418aa81649aa3d6590ba3e2ead1
+size 409103316

run-11/checkpoint-267/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d680035e99ff6336dc88d930dd11cdefab8741081766cc9f9363aeef58afbb1
+size 818327802

run-11/checkpoint-267/rng_state.pth

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

run-11/checkpoint-267/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5f7c473073a9f5f85e8efdf276de73990732d8d4700d402ba129e80641182e
+size 1064

run-11/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-11/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-11/checkpoint-267/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6558942794799805,
+  "best_model_checkpoint": "BERT-WMM/run-11/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": 0.7323943661971831,
+      "eval_loss": 0.6558942794799805,
+      "eval_runtime": 2.0789,
+      "eval_samples_per_second": 1024.574,
+      "eval_steps_per_second": 64.457,
+      "step": 267
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1335,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.0198787515111195e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 0.0057124071319225814
+  }
+}

run-11/checkpoint-267/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1092e8ed116440f38011c35ab632ce1695d509c6c1c0410c7cb88310943e70d
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713430937.da5e8340a418.15241.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4514a66c18d10928e16b2a80066f031302797b6d75dfe6a29c8378074f62128b
+size 5768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
+oid sha256:d1092e8ed116440f38011c35ab632ce1695d509c6c1c0410c7cb88310943e70d
 size 4856