Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849b2219b6f76700a8f32131536f6b6a9d2ed82dad4be3ec62b9fa941c15cf27
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-0/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0dc6ea72694ff54a88f458db9aff463c496bd6d83166f6fb57a4e51c5bb172
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-0/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48cb9fc1b51b7bace2ef2681653a2273be57b9f93ebfe5449c779ff48ae4a9e8
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-0/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6065725684165955,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7530516431924883,
-      "eval_loss": 0.6065725684165955,
-      "eval_runtime": 2.5073,
-      "eval_samples_per_second": 849.524,
-      "eval_steps_per_second": 53.444,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.6474,
+      "eval_samples_per_second": 804.575,
+      "eval_steps_per_second": 6.421,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 9.670788404941036e-05
+    "per_device_eval_batch_size": 128
   }
 }

run-0/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de07fd0528e0ec401b749f0d80d28e850e36f7e66780675fb859022ed638d382
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856

run-0/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6037774682044983,
+  "best_metric": 0.6037463545799255,
   "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7530516431924883,
-      "eval_loss": 0.6065725684165955,
-      "eval_runtime": 2.5073,
-      "eval_samples_per_second": 849.524,
-      "eval_steps_per_second": 53.444,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.6474,
+      "eval_samples_per_second": 804.575,
+      "eval_steps_per_second": 6.421,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.447751998901367,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7615023474178404,
-      "eval_loss": 0.6037774682044983,
-      "eval_runtime": 2.4998,
-      "eval_samples_per_second": 852.081,
-      "eval_steps_per_second": 53.605,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037463545799255,
+      "eval_runtime": 2.5974,
+      "eval_samples_per_second": 820.065,
+      "eval_steps_per_second": 6.545,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 9.670788404941036e-05
+    "per_device_eval_batch_size": 128
   }
 }

run-19/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-19/checkpoint-534/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef7d3121b6dcc55df087ce9fb15d483500f5343e0eca2000ec9bcf2ef62704a
+size 409103316

run-19/checkpoint-534/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd728cb17a1f39c51ba816ac5c872e91d596e39e2ba9b2329fbafc8cd72317e
+size 818327802

run-19/checkpoint-534/rng_state.pth

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

run-19/checkpoint-534/scheduler.pt

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

run-19/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-19/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-19/checkpoint-534/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.6036877632141113,
+  "best_model_checkpoint": "BERT-WMM/run-19/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": 0.7539906103286385,
+      "eval_loss": 0.6066781878471375,
+      "eval_runtime": 2.5156,
+      "eval_samples_per_second": 846.702,
+      "eval_steps_per_second": 53.267,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.447916030883789,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7615023474178404,
+      "eval_loss": 0.6036877632141113,
+      "eval_runtime": 2.4873,
+      "eval_samples_per_second": 856.361,
+      "eval_steps_per_second": 53.874,
+      "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": 0.051424292123722175
+  }
+}

run-19/checkpoint-534/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e18fed6d1d6cb4145ea5f498532a391408ab2f035069ebc34d88b7221a52d0a
+size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713525511.dcdaa3e6ec43.789.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afcdad88edab19cf3aa8b32f1e98632cf03b13460892e523ac1d33e867e87d5
+size 6123

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e18fed6d1d6cb4145ea5f498532a391408ab2f035069ebc34d88b7221a52d0a
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856