Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c41476452652ae73e0b62740a6ee427194d81d4bafc77daca3815d73293d6c
+size 871311930

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379f3ca672a218174225e426baaef98bf8dcff15fbe108db0fb9ee026c9efef8
+size 435640934

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3901c5e78db8dfecd4a40a0f18caca31434c760459a2305cdf1ab363e99c42
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0330d068b8825a00b6e1dd1480ff71f1a1ed86b7dd8535e7410fde199caaeb
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 1.0080007314682007,
+  "best_model_checkpoint": "finetune_bert-base-uncased/checkpoint-5476",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8787436084733382e-05,
+      "loss": 2.324,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7570002434867303e-05,
+      "loss": 1.3702,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.635500365230095e-05,
+      "loss": 1.2429,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.513757000243487e-05,
+      "loss": 1.1599,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3920136352568787e-05,
+      "loss": 1.1298,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0416048765182495,
+      "eval_runtime": 80.4387,
+      "eval_samples_per_second": 131.404,
+      "eval_steps_per_second": 1.032,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2702702702702702e-05,
+      "loss": 0.9945,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.1485269052836621e-05,
+      "loss": 0.888,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0267835402970538e-05,
+      "loss": 0.8653,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.052836620404189e-06,
+      "loss": 0.8768,
+      "step": 4500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.835402970538106e-06,
+      "loss": 0.8736,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0080007314682007,
+      "eval_runtime": 79.7471,
+      "eval_samples_per_second": 132.544,
+      "eval_steps_per_second": 1.041,
+      "step": 5476
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8214,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.4334001889975296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103a22f293326e0fa3c383fcbafab2582fb782fa66cea086f91a3f9373bcb425
+size 4536