Upload 11 files

checkpoint-8000/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-8000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084123c3174b643466e229f3692e89656fcd31bdb19043b0184386d0e11961f8
+size 1334372264

checkpoint-8000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d14d1fb05e9993625e2dbd482cd64280e15fb932151f1bf3d382302b80bd00
+size 2668968429

checkpoint-8000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b69deff9a6c5b0f0245ab655c5b3883527671d649e63077661419d064ab09c
+size 13990

checkpoint-8000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87004e6e320dcb07363535fcf86b22f6057567f4886d7c43f330e40765f0fa6e
+size 1064

checkpoint-8000/special_tokens_map.json

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

checkpoint-8000/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-8000/trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.99800099950025,
+  "eval_steps": 500,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.5337328910827637,
+      "learning_rate": 1.900049975012494e-05,
+      "loss": 0.4281,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.992353081703186,
+      "learning_rate": 1.8000999500249876e-05,
+      "loss": 0.2656,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.4741365909576416,
+      "learning_rate": 1.7001499250374815e-05,
+      "loss": 0.263,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5607998967170715,
+      "learning_rate": 1.600199900049975e-05,
+      "loss": 0.2228,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 56.73757553100586,
+      "learning_rate": 1.500249875062469e-05,
+      "loss": 0.1552,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 10.09034252166748,
+      "learning_rate": 1.4002998500749626e-05,
+      "loss": 0.1395,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 49.66099166870117,
+      "learning_rate": 1.3003498250874565e-05,
+      "loss": 0.1396,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.33147394657135,
+      "learning_rate": 1.2003998000999502e-05,
+      "loss": 0.1468,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.00538645638152957,
+      "learning_rate": 1.100449775112444e-05,
+      "loss": 0.0595,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.2792365550994873,
+      "learning_rate": 1.0004997501249377e-05,
+      "loss": 0.0529,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.09408382326364517,
+      "learning_rate": 9.005497251374314e-06,
+      "loss": 0.0578,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.005479688756167889,
+      "learning_rate": 8.005997001499251e-06,
+      "loss": 0.0523,
+      "step": 6000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.0009208513656631112,
+      "learning_rate": 7.006496751624189e-06,
+      "loss": 0.0145,
+      "step": 6500
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.2281578779220581,
+      "learning_rate": 6.006996501749126e-06,
+      "loss": 0.0129,
+      "step": 7000
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.005618613678961992,
+      "learning_rate": 5.0074962518740634e-06,
+      "loss": 0.0162,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0017482700059190392,
+      "learning_rate": 4.0079960019990015e-06,
+      "loss": 0.0212,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10005,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.4906009173590528e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa413c015ab4e81047ee7566efb44836d3f954f40726365f4c18a1bb17ec28e
+size 4920