Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b85f1c56b082a7adb0495b0e90157ba5009e506f69ca889a52976119ece1d8
+oid sha256:d06e3c8239dd42bbf550323003fefebf5fb1fcd33824f4874a1f2876fb05558b
 size 409103316

run-13/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
+oid sha256:030f068de82913a7e7c7a026971da2412c5e341d2deb1b60fed8cb4a7a98e5ec
 size 409103316

run-13/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
+oid sha256:4e39c7dbc0672a205f1c37e9ddcd39f3b311fc28afb4a6d4b98c3aaa8a99d035
 size 818327802

run-13/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2aa06609570d504e0cfaf6c3bd801e1681706921a7512c6ccb9eded784901f
+oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
 size 1064

run-13/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5776590704917908,
+  "best_metric": 0.603743851184845,
   "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7577464788732394,
-      "eval_loss": 0.6081846952438354,
-      "eval_runtime": 2.4174,
-      "eval_samples_per_second": 881.101,
-      "eval_steps_per_second": 55.431,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066303253173828,
+      "eval_runtime": 2.5344,
+      "eval_samples_per_second": 840.439,
+      "eval_steps_per_second": 52.873,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.532360076904297,
-      "learning_rate": 9.65168237740807e-06,
-      "loss": 0.6057,
+      "grad_norm": 9.449202537536621,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7657276995305164,
-      "eval_loss": 0.5776590704917908,
-      "eval_runtime": 2.4511,
-      "eval_samples_per_second": 868.982,
-      "eval_steps_per_second": 54.668,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.603743851184845,
+      "eval_runtime": 2.5041,
+      "eval_samples_per_second": 850.595,
+      "eval_steps_per_second": 53.512,
       "step": 534
     }
   ],
   "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": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 5
+    "weight_decay": 0.004730886773402456
   }
 }

run-13/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+oid sha256:c3f445057de0c2159585cd57bd78995f31933af19372c506bea5e6ecf22b5e03
 size 4856

run-14/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-14/checkpoint-267/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06e3c8239dd42bbf550323003fefebf5fb1fcd33824f4874a1f2876fb05558b
+size 409103316

run-14/checkpoint-267/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea50bde38d54faec355bcc0ce82de7b8fcb4f15e1da02ceb7f69a6a5c338a85
+size 818327802

run-14/checkpoint-267/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0980580128ccd5e578c966c8ffb616b8165a0951ed4f83a639bfa5862c1defb0
+size 14244

run-14/checkpoint-267/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
+size 1064

run-14/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-14/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-14/checkpoint-267/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": 0.6066302061080933,
+  "best_model_checkpoint": "BERT-WMM/run-14/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": 0.7535211267605634,
+      "eval_loss": 0.6066302061080933,
+      "eval_runtime": 2.5457,
+      "eval_samples_per_second": 836.715,
+      "eval_steps_per_second": 52.638,
+      "step": 267
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 534,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "weight_decay": 0.003128382575039317
+  }
+}

run-14/checkpoint-267/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31fd4c33e06c2a74949495a839ddc1f66203e1a3f2a1e69856fa796b17322695
+size 4856

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713523778.dcdaa3e6ec43.789.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f15ad7f4dfef8024073127538c1924dba69ed4a6ba84d83e7944185f7c0b18b
+size 6121

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f445057de0c2159585cd57bd78995f31933af19372c506bea5e6ecf22b5e03
+oid sha256:31fd4c33e06c2a74949495a839ddc1f66203e1a3f2a1e69856fa796b17322695
 size 4856