Upload 11 files

checkpoint-9500/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-9500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c67de052274d21b94d2fd438f6cca8875ed1036f5e613216cde834a617fb23
+size 1334372264

checkpoint-9500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0aafe5f86a70fb3ecc36180491f6181aa082663e51994ca494fb13d90aa914a
+size 2668968429

checkpoint-9500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f953902c1528af93adc7fa4b80bd02b2925d9870bb6f8898ab7499fa05ef88dd
+size 13990

checkpoint-9500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49eeaf2cf1797cf760bc5fbc43645e09ca1d880bed705880505810e2b771c5b1
+size 1064

checkpoint-9500/special_tokens_map.json

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

checkpoint-9500/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-9500/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.752376188094047,
+  "eval_steps": 500,
+  "global_step": 9500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 40.72060012817383,
+      "learning_rate": 1.8999499749874938e-05,
+      "loss": 0.416,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.45640167593955994,
+      "learning_rate": 1.7998999499749875e-05,
+      "loss": 0.259,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 24.118961334228516,
+      "learning_rate": 1.6998499249624815e-05,
+      "loss": 0.2726,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 43.76200485229492,
+      "learning_rate": 1.599799899949975e-05,
+      "loss": 0.2471,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 31.93831443786621,
+      "learning_rate": 1.4997498749374688e-05,
+      "loss": 0.1518,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.02012985199689865,
+      "learning_rate": 1.3996998499249626e-05,
+      "loss": 0.1421,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.22942015528678894,
+      "learning_rate": 1.2996498249124563e-05,
+      "loss": 0.1463,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18562756478786469,
+      "learning_rate": 1.19959979989995e-05,
+      "loss": 0.1512,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.14861415326595306,
+      "learning_rate": 1.0995497748874438e-05,
+      "loss": 0.0811,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.19507120549678802,
+      "learning_rate": 9.994997498749376e-06,
+      "loss": 0.0634,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.011564640328288078,
+      "learning_rate": 8.994497248624313e-06,
+      "loss": 0.0776,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1320619136095047,
+      "learning_rate": 7.993996998499251e-06,
+      "loss": 0.0583,
+      "step": 6000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.002501310082152486,
+      "learning_rate": 6.9934967483741875e-06,
+      "loss": 0.0283,
+      "step": 6500
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.008065233938395977,
+      "learning_rate": 5.992996498249125e-06,
+      "loss": 0.0245,
+      "step": 7000
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.012150153517723083,
+      "learning_rate": 4.992496248124062e-06,
+      "loss": 0.0282,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0018927728524431586,
+      "learning_rate": 3.991995997999e-06,
+      "loss": 0.0181,
+      "step": 8000
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.00044900510692968965,
+      "learning_rate": 2.991495747873937e-06,
+      "loss": 0.0051,
+      "step": 8500
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.0030473130755126476,
+      "learning_rate": 1.9909954977488747e-06,
+      "loss": 0.0097,
+      "step": 9000
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.004492764361202717,
+      "learning_rate": 9.90495247623812e-07,
+      "loss": 0.0048,
+      "step": 9500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9995,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.7704832040505344e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-9500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2af8ef0f6a7e09f2ebe39e5b7c56b97bb0da3d67bdca473d4e30026e53d8a99
+size 4920