Upload 11 files

checkpoint-3500/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google-bert/bert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "text-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af47c3e07dd872351b2b10f88edf04a9d9a89756e433338ac78136f915382b35
+size 1334372264

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c129beadf427c4b5bc43300e34c34e313f70a2368b961091cc561bc079ab7aa1
+size 2668968429

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6168c26716678c2d4a45820b88518e2498326769f8e3f095ef3c85b6149075ef
+size 13990

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e20eb2864b781c90082eb04f949cb35ca3ee4e1fcc452e1f5a469a1e865c4a
+size 1064

checkpoint-3500/special_tokens_map.json

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

checkpoint-3500/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": false,
+  "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]"
+}

checkpoint-3500/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.5,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 28.593961715698242,
+      "learning_rate": 1.8e-05,
+      "loss": 0.5987,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 28.91183090209961,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4193,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 14.28818130493164,
+      "learning_rate": 1.4e-05,
+      "loss": 0.327,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3224489390850067,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3122,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 197.5911102294922,
+      "learning_rate": 1e-05,
+      "loss": 0.1583,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19191676378250122,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1589,
+      "step": 3000
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.06239569932222366,
+      "learning_rate": 6e-06,
+      "loss": 0.0558,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6523519543296000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69eab8e307e3bfb72f9e64a0fa56858572083aec0cec6effaa7b5e35bab892d
+size 4920