Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9cf6e08108ec956b577d447f798865d5df7e0c5b49f1e0913c20b1325086e3
+oid sha256:4aec5cc494e807df52fdcc90d7b4001bc07af0eb0579e01f5697f6b86e18d154
 size 433270768

run-0/checkpoint-1350/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-0/checkpoint-1350/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc91495f16d1db113d8a028efdf1a820a6ad71cea388207f324e8c64d655764b
+size 433270768

run-0/checkpoint-1350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c5ccf2a078cc151b8c97fb1dbea0cd7ce20652a82bfea4e8bf976d036eb589
+size 866662650

run-0/checkpoint-1350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d6cb45686c5d32c091586e8b9ceb903a709b263206391a741ee85a8f713693
+size 14244

run-0/checkpoint-1350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7830b0d62f068e4375f246bfe8c8ee557d9e7a80e55de7b3d8fd14137548e59b
+size 1064

run-0/checkpoint-1350/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-0/checkpoint-1350/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-0/checkpoint-1350/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": 0.601,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-900",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1350,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.582,
+      "eval_loss": 0.6757144927978516,
+      "eval_runtime": 3.0923,
+      "eval_samples_per_second": 646.762,
+      "eval_steps_per_second": 40.423,
+      "step": 450
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 5.332789897918701,
+      "learning_rate": 4.4111292546040205e-06,
+      "loss": 0.6722,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.601,
+      "eval_loss": 0.6751155257225037,
+      "eval_runtime": 3.0546,
+      "eval_samples_per_second": 654.76,
+      "eval_steps_per_second": 40.923,
+      "step": 900
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 10.084617614746094,
+      "learning_rate": 2.71454107975632e-06,
+      "loss": 0.6238,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6005,
+      "eval_loss": 0.6901094317436218,
+      "eval_runtime": 3.0873,
+      "eval_samples_per_second": 647.825,
+      "eval_steps_per_second": 40.489,
+      "step": 1350
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 117711363946800.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.1077174294517206e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-0/checkpoint-1350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306a1f2e3e0a5644b71231cb5f1bf928bfa031e0dfefec97a7754c9f173d2b4d
+size 5176

run-0/checkpoint-1800/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-0/checkpoint-1800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92cba633751515439e008eb0a732cb9e893fada28c061309ee7f8af0fa0075d
+size 433270768

run-0/checkpoint-1800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734f788bc68a9810eaf2ef78470f47787355e2f9923a82b1924a7875e72bf879
+size 866662650

run-0/checkpoint-1800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f1239e0908f3bcc43e4bd63c94171792c8e1ea7eed2c7b53e0c6d7bc6bc04f
+size 14244

run-0/checkpoint-1800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e392658cc508032cd33bdf44abc531401a3212f97bca3e99260e949e8e7b8474
+size 1064

run-0/checkpoint-1800/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-0/checkpoint-1800/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-0/checkpoint-1800/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 0.6095,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-1800",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.582,
+      "eval_loss": 0.6757144927978516,
+      "eval_runtime": 3.0923,
+      "eval_samples_per_second": 646.762,
+      "eval_steps_per_second": 40.423,
+      "step": 450
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 5.332789897918701,
+      "learning_rate": 4.4111292546040205e-06,
+      "loss": 0.6722,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.601,
+      "eval_loss": 0.6751155257225037,
+      "eval_runtime": 3.0546,
+      "eval_samples_per_second": 654.76,
+      "eval_steps_per_second": 40.923,
+      "step": 900
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 10.084617614746094,
+      "learning_rate": 2.71454107975632e-06,
+      "loss": 0.6238,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6005,
+      "eval_loss": 0.6901094317436218,
+      "eval_runtime": 3.0873,
+      "eval_samples_per_second": 647.825,
+      "eval_steps_per_second": 40.489,
+      "step": 1350
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 8.786356925964355,
+      "learning_rate": 1.01795290490862e-06,
+      "loss": 0.5528,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6095,
+      "eval_loss": 0.7042331099510193,
+      "eval_runtime": 3.1133,
+      "eval_samples_per_second": 642.413,
+      "eval_steps_per_second": 40.151,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 177197073564480.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.1077174294517206e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-0/checkpoint-1800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306a1f2e3e0a5644b71231cb5f1bf928bfa031e0dfefec97a7754c9f173d2b4d
+size 5176

run-0/checkpoint-450/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9cf6e08108ec956b577d447f798865d5df7e0c5b49f1e0913c20b1325086e3
+oid sha256:4aec5cc494e807df52fdcc90d7b4001bc07af0eb0579e01f5697f6b86e18d154
 size 433270768

run-0/checkpoint-450/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa761d75654c53d130a610651c0e5810252854f51a1b9ee85fa0e6821b99816
+oid sha256:d7953ea1971895df03da6a0f26098ca912b867c5e760d15ee883e3dc7a5d1bc0
 size 866662650

run-0/checkpoint-450/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6edc5a4391b7a0bf956d9b303e80f47c2d9c175db13f6f3655c9ac11de1b1537
+oid sha256:7354178e72b62fe5640b8c83773b8cb4ba1969437018cbc9b0d2446625b4705c
 size 14244

run-0/checkpoint-450/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fc158db76c8f941e6026986d791697f9661c481151bb73e29a8fe812f9b06e
+oid sha256:84a1b222b5e7e5a3c36403b8bc5bb80655029784c4afda217dc99e49207dc555
 size 1064

run-0/checkpoint-450/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.582,
+  "best_metric": 0.5775,
   "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-450",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.582,
-      "eval_loss": 0.6757144927978516,
-      "eval_runtime": 3.0923,
-      "eval_samples_per_second": 646.762,
-      "eval_steps_per_second": 40.423,
+      "eval_accuracy": 0.5775,
+      "eval_loss": 0.6721444129943848,
+      "eval_runtime": 3.1417,
+      "eval_samples_per_second": 636.592,
+      "eval_steps_per_second": 39.787,
       "step": 450
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1800,
+  "max_steps": 450,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -30,7 +30,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -39,9 +39,9 @@
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 6.1077174294517206e-06,
-    "num_train_epochs": 4,
+    "learning_rate": 2.9756235955884987e-06,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 4,
-    "seed": 11
+    "seed": 6
   }
 }

run-0/checkpoint-450/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306a1f2e3e0a5644b71231cb5f1bf928bfa031e0dfefec97a7754c9f173d2b4d
+oid sha256:d38c6d6ebdd0f678d78aa49abbd1aaddd569cfb3e35dad0222aced730dc5d871
 size 5176

run-0/checkpoint-900/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-0/checkpoint-900/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd75bd69394940408678e4d06f2b525b7b417000d2983074aca193f5988d117
+size 433270768

run-0/checkpoint-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf663e8b0613810b5ec81318d1ffce83af56d770a074818dc2454dec0bebeb3
+size 866662650

run-0/checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34abbc9fd10ded646deee010b0618d9b4cb4145a7e0743059bff7dfcf3e14c4e
+size 14244

run-0/checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e8aed687b07f4eded2dfa48827ccca26b591efbba302aa112217b93b96e9e9
+size 1064

run-0/checkpoint-900/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-0/checkpoint-900/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-0/checkpoint-900/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.601,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-900",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.582,
+      "eval_loss": 0.6757144927978516,
+      "eval_runtime": 3.0923,
+      "eval_samples_per_second": 646.762,
+      "eval_steps_per_second": 40.423,
+      "step": 450
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 5.332789897918701,
+      "learning_rate": 4.4111292546040205e-06,
+      "loss": 0.6722,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.601,
+      "eval_loss": 0.6751155257225037,
+      "eval_runtime": 3.0546,
+      "eval_samples_per_second": 654.76,
+      "eval_steps_per_second": 40.923,
+      "step": 900
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 59639876251680.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.1077174294517206e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-0/checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306a1f2e3e0a5644b71231cb5f1bf928bfa031e0dfefec97a7754c9f173d2b4d
+size 5176

run-1/checkpoint-113/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-1/checkpoint-113/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ef512dc333e02dd50a0fbeeaa10cf86a89145edfa2bc6bbbb15e688362592bc
+size 433270768

run-1/checkpoint-113/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55d402f5cb660682f0fa717747bacc14ee39183732b604b9bb149c181501ce6
+size 866662650

run-1/checkpoint-113/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df79dd5bba777654c58009215bdcca11b3db6c3ed63fbd2ae632bd87f7802be0
+size 14308

run-1/checkpoint-113/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14a8aa7de27c23773b80f4eeba81aed83cbcd2b982f4d91b76fa456f56f643d
+size 1064

run-1/checkpoint-113/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-1/checkpoint-113/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-1/checkpoint-113/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.5945,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-113",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 113,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5945,
+      "eval_loss": 0.6746140718460083,
+      "eval_runtime": 3.0608,
+      "eval_samples_per_second": 653.432,
+      "eval_steps_per_second": 40.84,
+      "step": 113
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 565,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.117087338208196e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-1/checkpoint-113/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6cf6d62bd96276ddb153ee4c0dd1056bc0032dc430c2a812d2ddb559048838
+size 5176