Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2a3600272e96e508d95cd7d0fd4b74d14a69bf837314e079cf130d77ecb3317
+oid sha256:704ef4bcd8ea60bbc53294ab7df6ba3b1e6831e8ce251571ce2b56c4a1de6259
 size 437958648

run-2/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-2/checkpoint-184/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5e42febac8d0cecb2b8123dc686cfdc81198fa76688b0f700ebeba7af5f784
+size 437958648

run-2/checkpoint-184/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e72877bf67794c6f44e0c8d92f0036ec944a3fde2b19d1002e32475cf7c57b4
+size 876038394

run-2/checkpoint-184/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bee3747225d3e87f0fbd94c197c37f9d0c5f6f2ab64ca3322e7da7d83d6c67b
+size 14244

run-2/checkpoint-184/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07be6581b5e0bb50f197e3c56d8007949fd5e0341d6b71ae3d7c23006bff2b8
+size 1064

run-2/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-2/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-2/checkpoint-184/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.7796193984039288,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-2/checkpoint-184",
+  "epoch": 2.0,
+  "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": 0.7427869858809085,
+      "eval_loss": 0.5516446232795715,
+      "eval_runtime": 1.4701,
+      "eval_samples_per_second": 1108.088,
+      "eval_steps_per_second": 69.383,
+      "step": 92
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7796193984039288,
+      "eval_loss": 0.4907834231853485,
+      "eval_runtime": 1.4672,
+      "eval_samples_per_second": 1110.289,
+      "eval_steps_per_second": 69.521,
+      "step": 184
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 276,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.70273355101153e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 34
+  }
+}

run-2/checkpoint-184/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d34981dd3fd33e65c92f70ad92eaa956bd937a111bf4e8c6a2095c5441093ef
+size 5176

run-2/checkpoint-276/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-2/checkpoint-276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf79e93c568cd0503b592b2c2f50423e191232b9a273c336f985a5d4c79414d4
+size 437958648

run-2/checkpoint-276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291c69a4fe9d9506a7cdc71793d5e736496eaf8d058b0511b39490b7cef7120a
+size 876038394

run-2/checkpoint-276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46639a69ecc73cb4861f5fc22bfea68464a07d050b572654f6767c668ad6e828
+size 14244

run-2/checkpoint-276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148bc3f911586b4ca438844075cf152c18a7d6257c781767c642167825688b5f
+size 1064

run-2/checkpoint-276/special_tokens_map.json

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

run-2/checkpoint-276/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-2/checkpoint-276/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.7888275015346838,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-2/checkpoint-276",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7427869858809085,
+      "eval_loss": 0.5516446232795715,
+      "eval_runtime": 1.4701,
+      "eval_samples_per_second": 1108.088,
+      "eval_steps_per_second": 69.383,
+      "step": 92
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7796193984039288,
+      "eval_loss": 0.4907834231853485,
+      "eval_runtime": 1.4672,
+      "eval_samples_per_second": 1110.289,
+      "eval_steps_per_second": 69.521,
+      "step": 184
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7888275015346838,
+      "eval_loss": 0.4724823236465454,
+      "eval_runtime": 1.5456,
+      "eval_samples_per_second": 1053.943,
+      "eval_steps_per_second": 65.993,
+      "step": 276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 276,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.70273355101153e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 34
+  }
+}

run-2/checkpoint-276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d34981dd3fd33e65c92f70ad92eaa956bd937a111bf4e8c6a2095c5441093ef
+size 5176

run-3/checkpoint-92/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-3/checkpoint-92/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704ef4bcd8ea60bbc53294ab7df6ba3b1e6831e8ce251571ce2b56c4a1de6259
+size 437958648

run-3/checkpoint-92/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77853a651ce5c08b430bbdf675f508b602dd636d24837f19e9e739633ad713a7
+size 876038394

run-3/checkpoint-92/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d662894e2ad3859698ff562c3b1a1eaa688be13e87a8890726f1c3a8235ffc08
+size 14308

run-3/checkpoint-92/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52de5acbb08d572db5717feb477dccdca94b4ad9641aa965aa3e617065b073cb
+size 1064

run-3/checkpoint-92/special_tokens_map.json

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

run-3/checkpoint-92/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-3/checkpoint-92/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.7630448127685697,
+  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-3/checkpoint-92",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 92,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 184,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.159233393188895e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 21
+  }
+}

run-3/checkpoint-92/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0791269d577f31b2938387964641e880ef29f7b001df66e39e8233adc4c9474
+size 5176

runs/Aug02_03-09-56_8953887c6028/events.out.tfevents.1722568498.8953887c6028.1235.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8ecd562b8bb72129fa04bf50a4ba54197a22b33c34a4cf330d9f6f245a51a4
+size 5917

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d34981dd3fd33e65c92f70ad92eaa956bd937a111bf4e8c6a2095c5441093ef
+oid sha256:d0791269d577f31b2938387964641e880ef29f7b001df66e39e8233adc4c9474
 size 5176