Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
+oid sha256:b2b85f1c56b082a7adb0495b0e90157ba5009e506f69ca889a52976119ece1d8
 size 409103316

run-11/checkpoint-534/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-534/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
+size 409103316

run-11/checkpoint-534/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
+size 818327802

run-11/checkpoint-534/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b42ca1a83d9e0487eef7bc4978f59ad97364890e28f585669fc8e766195ed9
+size 14244

run-11/checkpoint-534/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
+size 1064

run-11/checkpoint-534/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-534/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-534/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.6037464141845703,
+  "best_model_checkpoint": "BERT-WMM/run-11/checkpoint-534",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 534,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.5438,
+      "eval_samples_per_second": 837.339,
+      "eval_steps_per_second": 52.678,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.449368476867676,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037464141845703,
+      "eval_runtime": 2.5244,
+      "eval_samples_per_second": 843.764,
+      "eval_steps_per_second": 53.082,
+      "step": 534
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 534,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 349221394826640.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "weight_decay": 0.0027263761612904285
+  }
+}

run-11/checkpoint-534/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62383e532375de8f37d59431717cb0c3e1937ec5cc424535a33fcf1b1491022
+size 4856

run-12/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709e0174af7e7bfc36b2ca42177cb07663d435c4830e3ef2fd95156cc7684138
+oid sha256:b2b85f1c56b082a7adb0495b0e90157ba5009e506f69ca889a52976119ece1d8
 size 409103316

run-12/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ef4431d2c45c5021200b1e749d9a863141163026b276944e492c1db9ee3f59
+oid sha256:ec5a355db941c8cae8024ef34ca1e5c563cb9dc83c1891034be6bacc55a349b7
 size 818327802

run-12/checkpoint-267/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c8fc955f6ab66538b705aa40f6ebb08474ec445464a7a19ca29971b9fc42d4
+oid sha256:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
 size 1064

run-12/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6081846952438354,
+  "best_metric": 0.6066303253173828,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,23 +10,23 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7577464788732394,
-      "eval_loss": 0.6081846952438354,
-      "eval_runtime": 2.4539,
-      "eval_samples_per_second": 868.011,
-      "eval_steps_per_second": 54.607,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066303253173828,
+      "eval_runtime": 2.4997,
+      "eval_samples_per_second": 852.1,
+      "eval_steps_per_second": 53.606,
       "step": 267
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1335,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 5
+    "weight_decay": 0.004085209001694488
   }
 }

run-12/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+oid sha256:ec68cbfd2a5a3c649e3efda9c076e9ffd4b78b703a2ff9f07020202f0e1b9937
 size 4856

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713523430.dcdaa3e6ec43.789.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09355d1c40fb1adb553b4f124fe9d169ee42a0b1da9748b3f26e48af712f050c
+size 6121

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62383e532375de8f37d59431717cb0c3e1937ec5cc424535a33fcf1b1491022
+oid sha256:ec68cbfd2a5a3c649e3efda9c076e9ffd4b78b703a2ff9f07020202f0e1b9937
 size 4856