Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fadc71a72125e03f5838a56bfadbd4602fa066c074a14f472a32a55cecf283e9
+oid sha256:390b87a07ea0f9d6a4d87537c546b85c20c7024933ff57eb2812b09c2682daad
 size 433270768

run-2/checkpoint-1101/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "AIMH/mental-bert-base-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -23,5 +23,5 @@
   "transformers_version": "4.42.4",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 28996
 }

run-2/checkpoint-1101/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f779546e5d9b6f9135ee088f0f2964d2cf38ba87e922bee184ea20d63557abfe
-size 437958648
+oid sha256:58532fc3e6e1a792d6eb422fdeaa2ba2aec556a1473580e392c144e6dacd0dd3
+size 433270768

run-2/checkpoint-1101/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eab4a8bec2860524e20618eb23b1dbd2dc3e704b1d873cf473fd144e519e89d
-size 876038394
+oid sha256:186aefc95e967cccdee9c7e6d071af5f570d869ed965183ee610232d59082858
+size 866662650

run-2/checkpoint-1101/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933286e0cb9dcea1f2c440bb26c48c8f37234f07f09a7914eca4e8dc98672017
+oid sha256:62544c3cadf55a8d18579328e5981c8ef34e618dca083fe5c9460fac4bcc9ee2
 size 14244

run-2/checkpoint-1101/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77cb59fcda7e06ca900ff873508b1edd0916052514a9aa26ce5a07cecd3ad2a6
+oid sha256:64ac2d15bb8efc796f5dc6b11142a1c7de8e9e03a6bed927a5bb8c773c4277b1
 size 1064

run-2/checkpoint-1101/special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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-2/checkpoint-1101/tokenizer_config.json

@@ -43,13 +43,17 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

run-2/checkpoint-1101/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.861878453038674,
-  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-2/checkpoint-734",
+  "best_metric": 0.8256599140577041,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-2/checkpoint-1101",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 1101,
@@ -10,50 +10,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8207489257213014,
-      "eval_loss": 0.41005730628967285,
-      "eval_runtime": 1.5429,
-      "eval_samples_per_second": 1055.797,
-      "eval_steps_per_second": 66.109,
+      "eval_accuracy": 0.7808471454880295,
+      "eval_loss": 0.4515644609928131,
+      "eval_runtime": 1.6125,
+      "eval_samples_per_second": 1010.242,
+      "eval_steps_per_second": 63.256,
       "step": 367
     },
     {
       "epoch": 1.3623978201634879,
-      "grad_norm": 9.666861534118652,
-      "learning_rate": 1.831949194907621e-05,
-      "loss": 0.5034,
+      "grad_norm": 3.5979933738708496,
+      "learning_rate": 2.9911866451614284e-06,
+      "loss": 0.5208,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.861878453038674,
-      "eval_loss": 0.5616857409477234,
-      "eval_runtime": 1.528,
-      "eval_samples_per_second": 1066.087,
-      "eval_steps_per_second": 66.753,
+      "eval_accuracy": 0.8066298342541437,
+      "eval_loss": 0.448224276304245,
+      "eval_runtime": 1.6212,
+      "eval_samples_per_second": 1004.815,
+      "eval_steps_per_second": 62.917,
       "step": 734
     },
     {
       "epoch": 2.7247956403269757,
-      "grad_norm": 0.05537036433815956,
-      "learning_rate": 1.1458259009347293e-05,
-      "loss": 0.3057,
+      "grad_norm": 4.29625940322876,
+      "learning_rate": 5.026786209006726e-07,
+      "loss": 0.325,
       "step": 1000
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8575813382443217,
-      "eval_loss": 0.6872314810752869,
-      "eval_runtime": 1.521,
-      "eval_samples_per_second": 1070.983,
-      "eval_steps_per_second": 67.06,
+      "eval_accuracy": 0.8256599140577041,
+      "eval_loss": 0.4320577085018158,
+      "eval_runtime": 1.678,
+      "eval_samples_per_second": 970.776,
+      "eval_steps_per_second": 60.785,
       "step": 1101
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1835,
+  "max_steps": 1101,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -62,18 +62,18 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81016621722120.0,
+  "total_flos": 90217286439240.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.518072488880513e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 5.479694669422184e-06,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 4,
-    "seed": 4
+    "seed": 23
   }
 }

run-2/checkpoint-1101/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3af0b514cbeb65fed5983531cf5e1fc2aae93ff3c4176583420eb7605bc7fb0
+oid sha256:ebd0369de99427537c423d0dcd390a5465d1461d045302bfffcb8614bb9235cc
 size 5176

run-2/checkpoint-734/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "AIMH/mental-bert-base-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -23,5 +23,5 @@
   "transformers_version": "4.42.4",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 28996
 }

run-2/checkpoint-734/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16836ad2bed7e1c06c29ab9c278ea0801ebece4460836e1f4a03eeb6dcadf70b
-size 437958648
+oid sha256:22de66c13813794a8111aa89a923c1d57e9437dbd057535fe4d3bbc6ce22b39f
+size 433270768

run-2/checkpoint-734/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2951dc23e785ac921ccd98c3cfea9770023d11ffb4c2af318f973dd2610a452
-size 876038394
+oid sha256:6140149df5f589df3e3669009c769099a8006618fa3a6e91c1a1b4891cd5abb7
+size 866662650

run-2/checkpoint-734/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b878d34a0236f2e6d5b32621550cff1a52197ba912466b784bfa5f7f8b32056f
+oid sha256:9c39c2ac1c613684f4984d47e60b07a0f89176826248f03f52a9539dd84aa196
 size 14244

run-2/checkpoint-734/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ddbeda33f6d7c4029fa8fca87e9c1c94c8a03667a2ebe8e9ab9c63b2250fb03
+oid sha256:c3ab0ad8872c70c5a562dd2d5915ea3f7511b921e537935b427e8eb886434452
 size 1064

run-2/checkpoint-734/special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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-2/checkpoint-734/tokenizer_config.json

@@ -43,13 +43,17 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

run-2/checkpoint-734/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.861878453038674,
+  "best_metric": 0.8066298342541437,
   "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-2/checkpoint-734",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,34 +10,34 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8207489257213014,
-      "eval_loss": 0.41005730628967285,
-      "eval_runtime": 1.5429,
-      "eval_samples_per_second": 1055.797,
-      "eval_steps_per_second": 66.109,
+      "eval_accuracy": 0.7808471454880295,
+      "eval_loss": 0.4515644609928131,
+      "eval_runtime": 1.6125,
+      "eval_samples_per_second": 1010.242,
+      "eval_steps_per_second": 63.256,
       "step": 367
     },
     {
       "epoch": 1.3623978201634879,
-      "grad_norm": 9.666861534118652,
-      "learning_rate": 1.831949194907621e-05,
-      "loss": 0.5034,
+      "grad_norm": 3.5979933738708496,
+      "learning_rate": 2.9911866451614284e-06,
+      "loss": 0.5208,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.861878453038674,
-      "eval_loss": 0.5616857409477234,
-      "eval_runtime": 1.528,
-      "eval_samples_per_second": 1066.087,
-      "eval_steps_per_second": 66.753,
+      "eval_accuracy": 0.8066298342541437,
+      "eval_loss": 0.448224276304245,
+      "eval_runtime": 1.6212,
+      "eval_samples_per_second": 1004.815,
+      "eval_steps_per_second": 62.917,
       "step": 734
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1835,
+  "max_steps": 1101,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -51,13 +51,13 @@
       "attributes": {}
     }
   },
-  "total_flos": 40395769218240.0,
+  "total_flos": 45391795937400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.518072488880513e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 5.479694669422184e-06,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 4,
-    "seed": 4
+    "seed": 23
   }
 }

run-2/checkpoint-734/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3af0b514cbeb65fed5983531cf5e1fc2aae93ff3c4176583420eb7605bc7fb0
+oid sha256:ebd0369de99427537c423d0dcd390a5465d1461d045302bfffcb8614bb9235cc
 size 5176

run-3/checkpoint-184/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "AIMH/mental-bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-3/checkpoint-184/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390b87a07ea0f9d6a4d87537c546b85c20c7024933ff57eb2812b09c2682daad
+size 433270768

run-3/checkpoint-184/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24fdf61dfde76f8c765621c48bb88cb407a2f76018dfe8bc773783315b77ed8
+size 866662650

run-3/checkpoint-184/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681ec4e61374fa9e2aab11d316c063600df1f5046025c108beada34b2dff2d47
+size 14244

run-3/checkpoint-184/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd64a2b79ba8923b1e6ed89d8956bba3c4abe9090f3931e4252c9fb7fcfdce95
+size 1064

run-3/checkpoint-184/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-3/checkpoint-184/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-184/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.8465316144874155,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-3/checkpoint-184",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 184,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8465316144874155,
+      "eval_loss": 0.4355960190296173,
+      "eval_runtime": 1.6102,
+      "eval_samples_per_second": 1011.674,
+      "eval_steps_per_second": 63.346,
+      "step": 184
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 368,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.899372834750846e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 35
+  }
+}

run-3/checkpoint-184/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e46e8eb76ff9978b97b6569c3ac0be7c5dc09979dbba62178dbf785d19e67c
+size 5176

runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722522793.1d376fbba8fb.12065.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8a2ed30a8a9722b0d9f5f4d492153d65867329454e353ef638efc271abd324
+size 5948

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebd0369de99427537c423d0dcd390a5465d1461d045302bfffcb8614bb9235cc
+oid sha256:24e46e8eb76ff9978b97b6569c3ac0be7c5dc09979dbba62178dbf785d19e67c
 size 5176