Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d780d4eb4eff39c58a31e4cc92b78ce056d97979b82a986aa19d49fde363c2
+oid sha256:1b086d7f0cad5d7ac8b3ca97fb34babdfe6f393964f3cf519bcc614dcd789220
 size 437958648

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d493c7dff9a026dff5037d7f0a1eaaaf0ee5102c2f38c1ef9bb514751f0995e3
+size 437958648

run-0/checkpoint-368/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82ce2e2b7cacb020cc47c11cf1560360b0c47260e27b73cdc7191af30a7b99a
+size 876038394

run-0/checkpoint-368/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70af5e045d7cbe28964e239267861b2225b9d1ab64934c6b89ff05eb83cfc5ad
+size 14244

run-0/checkpoint-368/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89c60f2ca7a16ed042b9965f9f5d84676cac03e58bd2e44bfd3736fd632c3af
+size 1064

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

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8465316144874155,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/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": 0.7925107427869859,
+      "eval_loss": 0.46051156520843506,
+      "eval_runtime": 1.5937,
+      "eval_samples_per_second": 1022.13,
+      "eval_steps_per_second": 64.001,
+      "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,
+      "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": 1.555774125514245e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-368/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+size 5176

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b77bbb7e1df0dc5a48f8a406a7b0e1145391ec84fae6e1e6a8795ce73c58ed
+size 437958648

run-0/checkpoint-552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62312ef3c09a91483ac2d197c8f5f20839ba487621389b2d93c6b6d0e752061a
+size 876038394

run-0/checkpoint-552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619620f0cd63f475f31cadad465dc60d440a2f8b2a371d893b1ed395348c6899
+size 14244

run-0/checkpoint-552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a32d9e6a3ae75c5f3bdf9d23aa7eb9cb5d2269791dcef101e28b852644e9d0
+size 1064

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

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.8465316144874155,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-368",
+  "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": 0.7925107427869859,
+      "eval_loss": 0.46051156520843506,
+      "eval_runtime": 1.5937,
+      "eval_samples_per_second": 1022.13,
+      "eval_steps_per_second": 64.001,
+      "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,
+      "step": 368
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 0.23171758651733398,
+      "learning_rate": 7.102447094738944e-06,
+      "loss": 0.3446,
+      "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,
+      "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": 91478369505360.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.555774125514245e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+size 5176

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b086d7f0cad5d7ac8b3ca97fb34babdfe6f393964f3cf519bcc614dcd789220
+size 437958648

run-0/checkpoint-736/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4600d613016d067c04f992f485e9f11515625ca4ade292f7428ecd1b6cb54d
+size 876038394

run-0/checkpoint-736/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a274b481f3952e1a88154b4b298f31bc77d8c11b2f34c327c4293901cfb8947
+size 14244

run-0/checkpoint-736/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046271b35351f5d36bebed49e5d44c0ca13b08fc5cc09925b2e0d79afa927909
+size 1064

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

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.8594229588704727,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/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": 0.7925107427869859,
+      "eval_loss": 0.46051156520843506,
+      "eval_runtime": 1.5937,
+      "eval_samples_per_second": 1022.13,
+      "eval_steps_per_second": 64.001,
+      "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,
+      "step": 368
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 0.23171758651733398,
+      "learning_rate": 7.102447094738944e-06,
+      "loss": 0.3446,
+      "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,
+      "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,
+      "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": 91478369505360.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.555774125514245e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-736/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efee40aa6ef16f75d0bab59bc4883188b1ff229c2801a9c84957d4b3eadd3426
+size 5176

runs/Jul31_19-18-04_20e4e50bc3c6/events.out.tfevents.1722453492.20e4e50bc3c6.1187.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93513ff9c5eebf84bac3dd8c9bfe7c3d7c140a8f40826bac5eb60c106bf017a
-size 5248
+oid sha256:9c29cc803de37264d7a8715e700c1dec1b733f452899249b08affcba0697f785
+size 7105