Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390b87a07ea0f9d6a4d87537c546b85c20c7024933ff57eb2812b09c2682daad
+oid sha256:329f350b2d9a5cc17a7334cbc94c7d1dc768b91e9f888d7626d925a7819e5688
 size 433270768

run-3/checkpoint-368/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-368/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5588fd4fb5373124d89fc0a0a2f43c5fcee283e72c901e059bbc4593dd1cfe9b
+size 433270768

run-3/checkpoint-368/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37520d63ad5a3a190366b8e59d12443ef8dad72774f53e8d34be43eedd7ac4b1
+size 866662650

run-3/checkpoint-368/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27807e038333f48c5f75334b23c774e2226a803429ea032139b17354f7dbbd6f
+size 14244

run-3/checkpoint-368/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a82642831692912f76602d7f506d72509a972c1a6c2b8583ea0a9099a58ddb
+size 1064

run-3/checkpoint-368/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-368/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-368/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8667894413750767,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-3/checkpoint-368",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 368,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8667894413750767,
+      "eval_loss": 0.6534619927406311,
+      "eval_runtime": 1.6695,
+      "eval_samples_per_second": 975.744,
+      "eval_steps_per_second": 61.096,
+      "step": 368
+    }
+  ],
+  "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": true
+      },
+      "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-368/training_args.bin

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

run-4/checkpoint-367/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-4/checkpoint-367/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329f350b2d9a5cc17a7334cbc94c7d1dc768b91e9f888d7626d925a7819e5688
+size 433270768

run-4/checkpoint-367/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2c7733ee06f7c9b9603ece5450e9c545a222d558b73e24a203337007ea9082
+size 866662650

run-4/checkpoint-367/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70cdebbd53d4dce78f1e25a9c2da144f246f5473dcbc0e0c5a8add86f033082
+size 14244

run-4/checkpoint-367/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3611f9f1e1771be1797418a57ab5a10d74471eef8e4862d3019716a03279188
+size 1064

run-4/checkpoint-367/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-4/checkpoint-367/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-4/checkpoint-367/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.7120933087783916,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-367",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 367,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7120933087783916,
+      "eval_loss": 0.591880738735199,
+      "eval_runtime": 1.6836,
+      "eval_samples_per_second": 967.568,
+      "eval_steps_per_second": 60.584,
+      "step": 367
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 367,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.674212761854381e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 19
+  }
+}

run-4/checkpoint-367/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91a637f2d58ccee01a0218fa524e1aa886a44d2f6746f44066d8ae0c3a913f6
+size 5176

runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722522921.1d376fbba8fb.12065.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc91b1b61269e86194cc2fe7364ce70e3397389ab1eda62859a60268ac8ee518
+size 5625

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e46e8eb76ff9978b97b6569c3ac0be7c5dc09979dbba62178dbf785d19e67c
+oid sha256:b91a637f2d58ccee01a0218fa524e1aa886a44d2f6746f44066d8ae0c3a913f6
 size 5176