Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175bc5f89c8f6b787367a8eb9255faf97634bd8adbbde950558027de0248e7d6
+oid sha256:fadc71a72125e03f5838a56bfadbd4602fa066c074a14f472a32a55cecf283e9
 size 433270768

run-0/checkpoint-184/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-0/checkpoint-184/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d780d4eb4eff39c58a31e4cc92b78ce056d97979b82a986aa19d49fde363c2
-size 437958648
+oid sha256:14904497aeb819b35d389d767bd0c2c6b738e61c74d9ebfe2eb359d91304867c
+size 433270768

run-0/checkpoint-184/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be659275284b3e9ca21af0864bd22c47f08afcac7176e8e6f44e391a0170581
-size 876038394
+oid sha256:1eb42b00c35b39a9288c94317e38da50c7ea7e66ac7186ca8c4fc93dfa9f87fb
+size 866662650

run-0/checkpoint-184/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d5d2b8d0718c79ee4699b73ff0682a9e37c6f09d1a4da7b4ae29c6d429e201
+oid sha256:21786abe7db04770ad5fe11a75ea383e2f20db4c48e1cbb97b29eadf57919021
 size 14244

run-0/checkpoint-184/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de06c0ad0e071418fb192e5c3b5b4e02bcf46d28f92c12fdb4d14eda8dbf0dd2
+oid sha256:739a5b91b27dc1034e9137a0f663fb583b541201a408f6780cc84acebe277005
 size 1064

run-0/checkpoint-184/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-0/checkpoint-184/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-0/checkpoint-184/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7925107427869859,
+  "best_metric": 0.7826887661141805,
   "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-184",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7925107427869859,
-      "eval_loss": 0.46051156520843506,
-      "eval_runtime": 1.5937,
-      "eval_samples_per_second": 1022.13,
-      "eval_steps_per_second": 64.001,
+      "eval_accuracy": 0.7826887661141805,
+      "eval_loss": 0.45181456208229065,
+      "eval_runtime": 1.6866,
+      "eval_samples_per_second": 965.826,
+      "eval_steps_per_second": 60.475,
       "step": 184
     }
   ],
   "logging_steps": 500,
-  "max_steps": 920,
+  "max_steps": 736,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -39,9 +39,9 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.555774125514245e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0817235137868972e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 8,
-    "seed": 16
+    "seed": 5
   }
 }

run-0/checkpoint-184/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+oid sha256:3dca1282896774eec430907d299b265f87badfd78ce3fae95cf77e64c477252a
 size 5176

run-0/checkpoint-368/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-0/checkpoint-368/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d493c7dff9a026dff5037d7f0a1eaaaf0ee5102c2f38c1ef9bb514751f0995e3
-size 437958648
+oid sha256:67dce7fb2d4f83c465a3416c279e5500cd2ccda1de19b58a50b8e6c17d9b0db6
+size 433270768

run-0/checkpoint-368/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82ce2e2b7cacb020cc47c11cf1560360b0c47260e27b73cdc7191af30a7b99a
-size 876038394
+oid sha256:fdb1489ea5df01528b5cb3af607ccea72ca7367b151cc3ea8f4d14d34ce27a5a
+size 866662650

run-0/checkpoint-368/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70af5e045d7cbe28964e239267861b2225b9d1ab64934c6b89ff05eb83cfc5ad
+oid sha256:5adc7e0b9329c5c2b8f270a5ad77762ef51cec651ab2b69c5e93b6fdcc032b71
 size 14244

run-0/checkpoint-368/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89c60f2ca7a16ed042b9965f9f5d84676cac03e58bd2e44bfd3736fd632c3af
+oid sha256:66623be9c7e826a500123eb24f5d98d30dbadb581c225227dafd683bbb302ab0
 size 1064

run-0/checkpoint-368/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-0/checkpoint-368/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-0/checkpoint-368/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8465316144874155,
+  "best_metric": 0.8238182934315531,
   "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-368",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7925107427869859,
-      "eval_loss": 0.46051156520843506,
-      "eval_runtime": 1.5937,
-      "eval_samples_per_second": 1022.13,
-      "eval_steps_per_second": 64.001,
+      "eval_accuracy": 0.7826887661141805,
+      "eval_loss": 0.45181456208229065,
+      "eval_runtime": 1.6866,
+      "eval_samples_per_second": 965.826,
+      "eval_steps_per_second": 60.475,
       "step": 184
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8465316144874155,
-      "eval_loss": 0.43229982256889343,
-      "eval_runtime": 1.6666,
-      "eval_samples_per_second": 977.463,
-      "eval_steps_per_second": 61.204,
+      "eval_accuracy": 0.8238182934315531,
+      "eval_loss": 0.38157492876052856,
+      "eval_runtime": 1.6313,
+      "eval_samples_per_second": 998.618,
+      "eval_steps_per_second": 62.529,
       "step": 368
     }
   ],
   "logging_steps": 500,
-  "max_steps": 920,
+  "max_steps": 736,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -48,9 +48,9 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.555774125514245e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0817235137868972e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 8,
-    "seed": 16
+    "seed": 5
   }
 }

run-0/checkpoint-368/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+oid sha256:3dca1282896774eec430907d299b265f87badfd78ce3fae95cf77e64c477252a
 size 5176

run-0/checkpoint-552/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-0/checkpoint-552/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b77bbb7e1df0dc5a48f8a406a7b0e1145391ec84fae6e1e6a8795ce73c58ed
-size 437958648
+oid sha256:e738066ddf5b3e7a73d4c63cc786c746ebd7f322a2aff63827136cbd74c3e6c2
+size 433270768

run-0/checkpoint-552/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62312ef3c09a91483ac2d197c8f5f20839ba487621389b2d93c6b6d0e752061a
-size 876038394
+oid sha256:83868c36b9e545a70e142df07b372f02fc3d7531617e33a0bb98a18ba09bc14a
+size 866662650

run-0/checkpoint-552/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619620f0cd63f475f31cadad465dc60d440a2f8b2a371d893b1ed395348c6899
+oid sha256:d4c47e551cb0fb04f7a3b0097cb93ad2b69429e684a5a15bb1645ad0a8680b9f
 size 14244

run-0/checkpoint-552/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a32d9e6a3ae75c5f3bdf9d23aa7eb9cb5d2269791dcef101e28b852644e9d0
+oid sha256:ca67c1719e7ecdf02147ca37365edb98f6fef1d7cfba46ebb4d7610ff244fccf
 size 1064

run-0/checkpoint-552/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-0/checkpoint-552/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-0/checkpoint-552/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.8465316144874155,
-  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-368",
+  "best_metric": 0.8520564763658687,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-552",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 552,
@@ -10,43 +10,43 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7925107427869859,
-      "eval_loss": 0.46051156520843506,
-      "eval_runtime": 1.5937,
-      "eval_samples_per_second": 1022.13,
-      "eval_steps_per_second": 64.001,
+      "eval_accuracy": 0.7826887661141805,
+      "eval_loss": 0.45181456208229065,
+      "eval_runtime": 1.6866,
+      "eval_samples_per_second": 965.826,
+      "eval_steps_per_second": 60.475,
       "step": 184
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8465316144874155,
-      "eval_loss": 0.43229982256889343,
-      "eval_runtime": 1.6666,
-      "eval_samples_per_second": 977.463,
-      "eval_steps_per_second": 61.204,
+      "eval_accuracy": 0.8238182934315531,
+      "eval_loss": 0.38157492876052856,
+      "eval_runtime": 1.6313,
+      "eval_samples_per_second": 998.618,
+      "eval_steps_per_second": 62.529,
       "step": 368
     },
     {
       "epoch": 2.717391304347826,
-      "grad_norm": 0.23171758651733398,
-      "learning_rate": 7.102447094738944e-06,
-      "loss": 0.3446,
+      "grad_norm": 19.13737678527832,
+      "learning_rate": 3.4685699626862464e-06,
+      "loss": 0.3706,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8397790055248618,
-      "eval_loss": 0.6237844824790955,
-      "eval_runtime": 1.5569,
-      "eval_samples_per_second": 1046.301,
-      "eval_steps_per_second": 65.514,
+      "eval_accuracy": 0.8520564763658687,
+      "eval_loss": 0.3886027932167053,
+      "eval_runtime": 1.6798,
+      "eval_samples_per_second": 969.762,
+      "eval_steps_per_second": 60.722,
       "step": 552
     }
   ],
   "logging_steps": 500,
-  "max_steps": 920,
+  "max_steps": 736,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -60,13 +60,13 @@
       "attributes": {}
     }
   },
-  "total_flos": 91478369505360.0,
+  "total_flos": 104085089056320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.555774125514245e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0817235137868972e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 8,
-    "seed": 16
+    "seed": 5
   }
 }

run-0/checkpoint-552/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+oid sha256:3dca1282896774eec430907d299b265f87badfd78ce3fae95cf77e64c477252a
 size 5176

run-0/checkpoint-736/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-0/checkpoint-736/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b086d7f0cad5d7ac8b3ca97fb34babdfe6f393964f3cf519bcc614dcd789220
-size 437958648
+oid sha256:e60433460a3a14f30b3b9c6d8745fcaae38ebb6f550d28d5a9f4eebf6a415624
+size 433270768

run-0/checkpoint-736/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f4600d613016d067c04f992f485e9f11515625ca4ade292f7428ecd1b6cb54d
-size 876038394
+oid sha256:c1a7a2a6fa9214a6c6b5e6cdec516e37af1f2b0fdef678ac40c185adf1901b39
+size 866662650

run-0/checkpoint-736/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a274b481f3952e1a88154b4b298f31bc77d8c11b2f34c327c4293901cfb8947
+oid sha256:09111e111459102080ed949ecfe5be2a91e2d04f47d7be008649634b2877c619
 size 14244

run-0/checkpoint-736/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046271b35351f5d36bebed49e5d44c0ca13b08fc5cc09925b2e0d79afa927909
+oid sha256:3663481edf83a09f6aee2aacb4de5b4a3928c23d15cb3333b5457a97c31f0986
 size 1064

run-0/checkpoint-736/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-0/checkpoint-736/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-0/checkpoint-736/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.8594229588704727,
-  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-736",
+  "best_metric": 0.8520564763658687,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-552",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 736,
@@ -10,52 +10,52 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7925107427869859,
-      "eval_loss": 0.46051156520843506,
-      "eval_runtime": 1.5937,
-      "eval_samples_per_second": 1022.13,
-      "eval_steps_per_second": 64.001,
+      "eval_accuracy": 0.7826887661141805,
+      "eval_loss": 0.45181456208229065,
+      "eval_runtime": 1.6866,
+      "eval_samples_per_second": 965.826,
+      "eval_steps_per_second": 60.475,
       "step": 184
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8465316144874155,
-      "eval_loss": 0.43229982256889343,
-      "eval_runtime": 1.6666,
-      "eval_samples_per_second": 977.463,
-      "eval_steps_per_second": 61.204,
+      "eval_accuracy": 0.8238182934315531,
+      "eval_loss": 0.38157492876052856,
+      "eval_runtime": 1.6313,
+      "eval_samples_per_second": 998.618,
+      "eval_steps_per_second": 62.529,
       "step": 368
     },
     {
       "epoch": 2.717391304347826,
-      "grad_norm": 0.23171758651733398,
-      "learning_rate": 7.102447094738944e-06,
-      "loss": 0.3446,
+      "grad_norm": 19.13737678527832,
+      "learning_rate": 3.4685699626862464e-06,
+      "loss": 0.3706,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8397790055248618,
-      "eval_loss": 0.6237844824790955,
-      "eval_runtime": 1.5569,
-      "eval_samples_per_second": 1046.301,
-      "eval_steps_per_second": 65.514,
+      "eval_accuracy": 0.8520564763658687,
+      "eval_loss": 0.3886027932167053,
+      "eval_runtime": 1.6798,
+      "eval_samples_per_second": 969.762,
+      "eval_steps_per_second": 60.722,
       "step": 552
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8594229588704727,
-      "eval_loss": 0.6028990745544434,
-      "eval_runtime": 1.5442,
-      "eval_samples_per_second": 1054.886,
-      "eval_steps_per_second": 66.052,
+      "eval_accuracy": 0.8520564763658687,
+      "eval_loss": 0.414229154586792,
+      "eval_runtime": 1.6727,
+      "eval_samples_per_second": 973.864,
+      "eval_steps_per_second": 60.979,
       "step": 736
     }
   ],
   "logging_steps": 500,
-  "max_steps": 920,
+  "max_steps": 736,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -64,18 +64,18 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 91478369505360.0,
+  "total_flos": 104085089056320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.555774125514245e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0817235137868972e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 8,
-    "seed": 16
+    "seed": 5
   }
 }

run-0/checkpoint-736/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+oid sha256:3dca1282896774eec430907d299b265f87badfd78ce3fae95cf77e64c477252a
 size 5176

run-1/checkpoint-138/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-1/checkpoint-138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ee7a111736cb9ce1ed2851f73fb0a692e984f01a4766aa252f42d325574210
-size 437958648
+oid sha256:633dbc2c8e981deacd7b99da5f5c4c9bcdb73230ab14686bda24612491410d67
+size 433270768

run-1/checkpoint-138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7774cbcb4af7c4ca85d3e09b4825debb50dd45e99f27b8b784e1efbaab1f5c5b
-size 876038394
+oid sha256:5a7aeecf2cd0e13d0bd81cb8043bdcf28d265abb9b5897a7f0b24f2a7a30ca10
+size 866662650

run-1/checkpoint-138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6fdaf5f9b5fc8b85922b753f680b87ac15b39643871824d2f8cacd706c1fff
-size 14308
+oid sha256:c4673f91a41f7ae8a78df03aba2d1037bf40dc9118a2b888b0da54d02fa0a9df
+size 14244

run-1/checkpoint-138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e9cf636587d8b361ef92837fa3e0296c9f550f08506447d9c47ff628c19a08
+oid sha256:3c752a24e0c2337854c356490b3502f10b0d4695aedf184215315bb4e0ef1e0a
 size 1064