Upload 11 files

checkpoint-7000/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-7000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e88f6e03094b6a620200b3c3979bcae833dd580115f794da4e629efc6bd91c
+size 1334372264

checkpoint-7000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a60e372751b7786aba3f1e6c99102be97130b3002f6ec84509e0d63679b4c0
+size 2668979437

checkpoint-7000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8ad36d902d2022ce42c809e2011e6c819a15a996b51d400bbaac2a1971bf0a
+size 14308

checkpoint-7000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad57bec89fcf3f58fbb03d0a50462e1d9d3f2972bdff04c12a9f04fcff4a95d9
+size 1064

checkpoint-7000/special_tokens_map.json

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

checkpoint-7000/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-7000/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.501750875437719,
+  "eval_steps": 500,
+  "global_step": 7000,
+  "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
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 14.25749397277832,
+      "learning_rate": 0.10995497748874437,
+      "loss": 18.3821,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 11.474056243896484,
+      "learning_rate": 0.09994997498749375,
+      "loss": 15.509,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 17.367544174194336,
+      "learning_rate": 0.08994497248624313,
+      "loss": 16.8976,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 22.115795135498047,
+      "learning_rate": 0.0799399699849925,
+      "loss": 13.2737,
+      "step": 6000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 6.301364421844482,
+      "learning_rate": 0.06993496748374188,
+      "loss": 12.3313,
+      "step": 6500
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 12.592329978942871,
+      "learning_rate": 0.05992996498249125,
+      "loss": 10.3698,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9995,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 5.218256475818803e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7000/training_args.bin

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