Upload 11 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "../PetBERT/pretrained",
+  "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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06348d10d1c4685e9f181b2f418c579e49f7ef83edcfc87ac5bebe11a028c97f
+size 437958648

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e21d7105cb4aefd32e7d1b62b67ee1bc2ece06d08603b5af087caace2bd5ca
+size 876038394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea10853d0c9d4d785280af92874d13aabf463bb214a99906acdd703f296b1e92
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac7308230a0ab4797d8216ea4301fd15a41a697ad8b9d77b330a6d53f0bdb99
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.9956709956709957,
+  "best_model_checkpoint": "dead_alive_classifier/models/checkpoint-96",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7878787878787878,
+      "eval_f1": 0.7878787878787878,
+      "eval_loss": 0.5285314321517944,
+      "eval_precision": 0.7878787878787878,
+      "eval_recall": 0.7878787878787878,
+      "eval_runtime": 1.1267,
+      "eval_samples_per_second": 205.029,
+      "eval_steps_per_second": 13.314,
+      "step": 32
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.974025974025974,
+      "eval_f1": 0.974025974025974,
+      "eval_loss": 0.2521773874759674,
+      "eval_precision": 0.974025974025974,
+      "eval_recall": 0.974025974025974,
+      "eval_runtime": 1.1532,
+      "eval_samples_per_second": 200.307,
+      "eval_steps_per_second": 13.007,
+      "step": 64
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9956709956709957,
+      "eval_f1": 0.9956709956709957,
+      "eval_loss": 0.037678323686122894,
+      "eval_precision": 0.9956709956709957,
+      "eval_recall": 0.9956709956709957,
+      "eval_runtime": 1.1364,
+      "eval_samples_per_second": 203.277,
+      "eval_steps_per_second": 13.2,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 395069471843520.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4420b20bb4cb311e24eaad54030b60004875fd332d5125d96281f72264169d54
+size 4984