Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:704ef4bcd8ea60bbc53294ab7df6ba3b1e6831e8ce251571ce2b56c4a1de6259
+oid sha256:3acc66ee228a8fbaec1ea30a8cc721d05dae8b55d25d5c9b87dff31e5fa8b625
 size 437958648

run-3/checkpoint-184/config.json

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

run-3/checkpoint-184/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390b87a07ea0f9d6a4d87537c546b85c20c7024933ff57eb2812b09c2682daad
-size 433270768
+oid sha256:b5dd2efb9eeb705ea8b16b5da79358c1da34cf3a2882fd7eb9b8c9c9d434e92f
+size 437958648

run-3/checkpoint-184/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b24fdf61dfde76f8c765621c48bb88cb407a2f76018dfe8bc773783315b77ed8
-size 866662650
+oid sha256:24c2b27b2223fd37b2fa33684f10cc9d3177ca08579859056399040a6095f444
+size 876038394

run-3/checkpoint-184/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681ec4e61374fa9e2aab11d316c063600df1f5046025c108beada34b2dff2d47
-size 14244
+oid sha256:077a14d29ff2d9c856ffdd614b5eef79bea88d73063d9977a539a6dc593de297
+size 14308

run-3/checkpoint-184/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd64a2b79ba8923b1e6ed89d8956bba3c4abe9090f3931e4252c9fb7fcfdce95
+oid sha256:e904389b286fdd080046e19448f588d09db351c91af423321259880cd786278e
 size 1064

run-3/checkpoint-184/special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "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
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

run-3/checkpoint-184/tokenizer_config.json

@@ -43,17 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "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

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8465316144874155,
+  "best_metric": 0.7796193984039288,
   "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-3/checkpoint-184",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 184,
   "is_hyper_param_search": true,
@@ -10,16 +10,25 @@
   "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,
+      "eval_accuracy": 0.7630448127685697,
+      "eval_loss": 0.46627277135849,
+      "eval_runtime": 1.4592,
+      "eval_samples_per_second": 1116.36,
+      "eval_steps_per_second": 69.901,
+      "step": 92
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7796193984039288,
+      "eval_loss": 0.4434141218662262,
+      "eval_runtime": 1.5862,
+      "eval_samples_per_second": 1026.96,
+      "eval_steps_per_second": 64.303,
       "step": 184
     }
   ],
   "logging_steps": 500,
-  "max_steps": 368,
+  "max_steps": 184,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
@@ -30,18 +39,18 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
   "total_flos": 0,
-  "train_batch_size": 8,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 9.899372834750846e-05,
+    "learning_rate": 2.159233393188895e-05,
     "num_train_epochs": 2,
-    "per_device_train_batch_size": 8,
-    "seed": 35
+    "per_device_train_batch_size": 16,
+    "seed": 21
   }
 }

run-3/checkpoint-184/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e46e8eb76ff9978b97b6569c3ac0be7c5dc09979dbba62178dbf785d19e67c
+oid sha256:d0791269d577f31b2938387964641e880ef29f7b001df66e39e8233adc4c9474
 size 5176

run-4/checkpoint-23/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "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": 30522
+}

run-4/checkpoint-23/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acc66ee228a8fbaec1ea30a8cc721d05dae8b55d25d5c9b87dff31e5fa8b625
+size 437958648

run-4/checkpoint-23/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a961d86fd5c541e3200b35dded450f82e4d2cba58a2359dfe098b3c027759450
+size 876038394

run-4/checkpoint-23/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b5374b258a782a1c42464a3d348e037829ea94a82bd72abab9d1afc627506d
+size 14244

run-4/checkpoint-23/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77d79df43f49cd96a21a5d961fa56ca220a3195e3ffc35d77697df9dac9e4eb
+size 1064

run-4/checkpoint-23/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-23/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-23/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.5979128299570289,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-23",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 23,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5979128299570289,
+      "eval_loss": 0.678537905216217,
+      "eval_runtime": 1.4893,
+      "eval_samples_per_second": 1093.811,
+      "eval_steps_per_second": 68.489,
+      "step": 23
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 69,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9236721941091785e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 12
+  }
+}

run-4/checkpoint-23/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e5d749933754adfcd491676d87575b65895093b05afc38cb0180cdd1806f56
+size 5176

runs/Aug02_03-09-56_8953887c6028/events.out.tfevents.1722568629.8953887c6028.1235.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5cbcb06b43be72942d3502453a7046f18942f5900b2f60325164d701b9cde4
+size 6223

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0791269d577f31b2938387964641e880ef29f7b001df66e39e8233adc4c9474
+oid sha256:20e5d749933754adfcd491676d87575b65895093b05afc38cb0180cdd1806f56
 size 5176