Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a10f8004a7cf08aaf06d4a2531659d5220ecc605c4286e7c0c9fd8662977ca4
+oid sha256:e18b3b55391290fa102826a1e71aba3750b61eafc8d5a853f755688f29389482
 size 437958648

run-7/checkpoint-184/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770348fd8b1253de5a479d14ddd4bb1ce3bc917fb881aeb0c9e189cd214d6466
+oid sha256:45bb6c49c2bedd3504a185f0dce951195cf6d38bac23597772f8431210847ba9
 size 437958648

run-7/checkpoint-184/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7063058cd8d58576dd8cbe5348e8de13dfc195c4b9eacfc23d9a916dd1c4dc0b
+oid sha256:868db70dc279c5d8098672ca8d47ee7eb62bdee7cc99a04d925d482941ac4993
 size 876038394

run-7/checkpoint-184/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8bb9bde246d02b70bda4a225a6ccdb5bed7324dacfc3ed50db070926cf9c87
-size 14308
+oid sha256:00bf828b1919b530596e9a1734505951eab0a227f4a347b876f1c643c9b2b956
+size 14244

run-7/checkpoint-184/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f7bc4fa9d630ccd56f888d0b282720d75d1e8d643c566818be703b8e6de47b
+oid sha256:0fb14ba6f788273c29f871dd1124460e8da363a4500daff1fd2b44e559e3ace1
 size 1064

run-7/checkpoint-184/trainer_state.json

@@ -1,54 +1,17 @@
 {
-  "best_metric": 0.8367096378146102,
-  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-7/checkpoint-184",
-  "epoch": 4.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "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": 0.7839165131982812,
-      "eval_loss": 0.44573765993118286,
-      "eval_runtime": 1.5248,
-      "eval_samples_per_second": 1068.356,
-      "eval_steps_per_second": 66.895,
-      "step": 46
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8029465930018416,
-      "eval_loss": 0.4049816429615021,
-      "eval_runtime": 1.5307,
-      "eval_samples_per_second": 1064.206,
-      "eval_steps_per_second": 66.635,
-      "step": 92
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8305709023941068,
-      "eval_loss": 0.36977845430374146,
-      "eval_runtime": 1.5281,
-      "eval_samples_per_second": 1066.032,
-      "eval_steps_per_second": 66.75,
-      "step": 138
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8367096378146102,
-      "eval_loss": 0.38024526834487915,
-      "eval_runtime": 1.5933,
-      "eval_samples_per_second": 1022.426,
-      "eval_steps_per_second": 64.019,
-      "step": 184
-    }
-  ],
+  "log_history": [],
   "logging_steps": 500,
   "max_steps": 184,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -63,12 +26,12 @@
     }
   },
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.448709525953929e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "seed": 21
+    "learning_rate": 7.059488330688458e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 36
   }
 }

run-7/checkpoint-184/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7783b64377581c270d4bf6ae57189eb09386ad289a71203380cd72e257c9a682
+oid sha256:575bb016637d16461e5cbb2d3476fe7a1937baddcde0db5fb1c149eb0a1cf074
 size 5176

run-8/checkpoint-184/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-8/checkpoint-184/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871d64bbcfe7e3b7796e49809c2c034ee718a85d48065ba01fb33c8b128ea7b7
+size 437958648

run-8/checkpoint-184/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc2aa37c641062526fd14c9e1965c4a0cc15c4e045dff2ff279113327355038
+size 876038394

run-8/checkpoint-184/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9dbde989aabd7113299b007c70b149b3d27968de69c8cddf8b5f43b150d373
+size 14308

run-8/checkpoint-184/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0e9beb3c68ca5959fb2ff6789e58f2e43b008984b3dba67ca73c97d2362a84
+size 1064

run-8/checkpoint-184/special_tokens_map.json

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

run-8/checkpoint-184/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-8/checkpoint-184/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.8182934315531001,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-8/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": 0.8182934315531001,
+      "eval_loss": 0.39697179198265076,
+      "eval_runtime": 1.4648,
+      "eval_samples_per_second": 1112.118,
+      "eval_steps_per_second": 69.635,
+      "step": 184
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 920,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.186801881082434e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-8/checkpoint-184/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa6fdef93917d7fe7ad43bf5df2576ba9b6fddeca1ccee15cf1281a921dc8a8
+size 5176

run-8/checkpoint-368/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-8/checkpoint-368/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cf0e9c534cfe1ddf1880e1729493ea338f8433f07635eb68f746a277c26903
+size 437958648

run-8/checkpoint-368/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae84e3db447fdbacf502f50da7d22d04aed3ca1139205c4aa8f0fbeafc8d06c6
+size 876038394

run-8/checkpoint-368/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fd8b234f80eec82bdaf2cf7e7e24a728f9330e69ee3761cf99a20f53659f2f
+size 14308

run-8/checkpoint-368/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4813f844974ccfd98fe8d0919aab4850c12580960134f1090fc2b6a9f0caeb
+size 1064

run-8/checkpoint-368/special_tokens_map.json

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

run-8/checkpoint-368/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-8/checkpoint-368/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8446899938612645,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-8/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": 0.8182934315531001,
+      "eval_loss": 0.39697179198265076,
+      "eval_runtime": 1.4648,
+      "eval_samples_per_second": 1112.118,
+      "eval_steps_per_second": 69.635,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8446899938612645,
+      "eval_loss": 0.4469450116157532,
+      "eval_runtime": 1.4697,
+      "eval_samples_per_second": 1108.387,
+      "eval_steps_per_second": 69.402,
+      "step": 368
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 920,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.186801881082434e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-8/checkpoint-368/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa6fdef93917d7fe7ad43bf5df2576ba9b6fddeca1ccee15cf1281a921dc8a8
+size 5176

run-8/checkpoint-552/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-8/checkpoint-552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56724db37427c14a83043f0e20fb7e3442bf5fb1d90c2ede868394566d4f57f
+size 437958648

run-8/checkpoint-552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b7451a0fed6ecc8883e0797d051d2556bef8ee15e45e4ca20fdd38d1a934d6
+size 876038394

run-8/checkpoint-552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75ff17b5cb476de53a1678bd79961ec1cc3cbc187954498c179da1bbc3bd5a9
+size 14308

run-8/checkpoint-552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb1b7053ccbd69e3471cd7f4d3d85c30ff8647ab1075c236d407056fefb245c
+size 1064

run-8/checkpoint-552/special_tokens_map.json

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

run-8/checkpoint-552/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-8/checkpoint-552/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.8496009821976673,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-8/checkpoint-552",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8182934315531001,
+      "eval_loss": 0.39697179198265076,
+      "eval_runtime": 1.4648,
+      "eval_samples_per_second": 1112.118,
+      "eval_steps_per_second": 69.635,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8446899938612645,
+      "eval_loss": 0.4469450116157532,
+      "eval_runtime": 1.4697,
+      "eval_samples_per_second": 1108.387,
+      "eval_steps_per_second": 69.402,
+      "step": 368
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 8.623266220092773,
+      "learning_rate": 3.7374530326680673e-05,
+      "loss": 0.3328,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8496009821976673,
+      "eval_loss": 0.7693418264389038,
+      "eval_runtime": 1.4817,
+      "eval_samples_per_second": 1099.419,
+      "eval_steps_per_second": 68.84,
+      "step": 552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 920,
+  "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": 166182381453960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.186801881082434e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-8/checkpoint-552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa6fdef93917d7fe7ad43bf5df2576ba9b6fddeca1ccee15cf1281a921dc8a8
+size 5176

run-8/checkpoint-736/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-8/checkpoint-736/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55634ac9308f6162f645a237065d0f0ca7c8361699fd2b0dcf72cc05e60ad73e
+size 437958648

run-8/checkpoint-736/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a579a515b4edb7d7c4c097f8e965cd7d7243e6385f6ca8aa2b7c56f70ec79a8
+size 876038394

run-8/checkpoint-736/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d36cc7e5515baf19e79ba7261a0e995224c4f7be1e0bd9deed1e937d143fb84
+size 14308

run-8/checkpoint-736/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f2ecdf0377af42389d796b25959693d160849b740ca15bc38faae2c99ff870
+size 1064

run-8/checkpoint-736/special_tokens_map.json

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

run-8/checkpoint-736/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-8/checkpoint-736/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.852670349907919,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-8/checkpoint-736",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 736,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8182934315531001,
+      "eval_loss": 0.39697179198265076,
+      "eval_runtime": 1.4648,
+      "eval_samples_per_second": 1112.118,
+      "eval_steps_per_second": 69.635,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8446899938612645,
+      "eval_loss": 0.4469450116157532,
+      "eval_runtime": 1.4697,
+      "eval_samples_per_second": 1108.387,
+      "eval_steps_per_second": 69.402,
+      "step": 368
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 8.623266220092773,
+      "learning_rate": 3.7374530326680673e-05,
+      "loss": 0.3328,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8496009821976673,
+      "eval_loss": 0.7693418264389038,
+      "eval_runtime": 1.4817,
+      "eval_samples_per_second": 1099.419,
+      "eval_steps_per_second": 68.84,
+      "step": 552
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.852670349907919,
+      "eval_loss": 0.9155253767967224,
+      "eval_runtime": 1.4898,
+      "eval_samples_per_second": 1093.449,
+      "eval_steps_per_second": 68.466,
+      "step": 736
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 920,
+  "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": 166182381453960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.186801881082434e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-8/checkpoint-736/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa6fdef93917d7fe7ad43bf5df2576ba9b6fddeca1ccee15cf1281a921dc8a8
+size 5176