Upload 11 files

checkpoint-4000/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-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c276e045cfac9ac4b43ae150eed1c3b35b41bc84eb75f2f93d243c10200770e
+size 1334372264

checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd253bc3b5c72733c113223092462c545f7ee013e81a686dbc29197bf1ff49be
+size 2668979437

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e51ffcaa455ae2005b68f68d019a67417d341358b9166291e72690da9b965a8
+size 14308

checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a73398ad9a775f08098040ae4aa89fb37d161e46a958ff4dbcd0155e75a1a8
+size 1064

checkpoint-4000/special_tokens_map.json

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

checkpoint-4000/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-4000/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.001000500250125,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 17.20686149597168,
+      "learning_rate": 0.18999499749874937,
+      "loss": 26.5314,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.102985382080078,
+      "learning_rate": 0.17998999499749876,
+      "loss": 26.7788,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.944087505340576,
+      "learning_rate": 0.16998499249624813,
+      "loss": 24.8765,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.642237663269043,
+      "learning_rate": 0.15997998999499752,
+      "loss": 26.802,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 17.359766006469727,
+      "learning_rate": 0.14997498749374688,
+      "loss": 21.9876,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 18.080049514770508,
+      "learning_rate": 0.13996998499249624,
+      "loss": 23.0366,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 9.133398056030273,
+      "learning_rate": 0.12996498249124563,
+      "loss": 23.0511,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 34.05988311767578,
+      "learning_rate": 0.119959979989995,
+      "loss": 20.0652,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9995,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.981807590104269e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e6aef16acdd9251960725cb052e8d2548320f104c938cfff3d56d92ad25c58
+size 4984