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 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976d6997d582f4a4097562af985e64d5a0d38f5b2fa04bc4059f158a65d1d2b9
+size 531000890

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913a01d13779c7b6964bc3e6b299b19c05aad22d6605fbaf8b786e9c80a2faf9
+size 265493026

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38744eb53a83d94c2f4dd4a29a706f0abc9c54b16c58bb2b372744c92e6a0a0d
+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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 1.1202219724655151,
+  "best_model_checkpoint": "finetune_distilbert-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": 2.6968,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7570002434867303e-05,
+      "loss": 1.6023,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.635256878500122e-05,
+      "loss": 1.4278,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5135135135135138e-05,
+      "loss": 1.3395,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3917701485269055e-05,
+      "loss": 1.292,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1892027854919434,
+      "eval_runtime": 41.132,
+      "eval_samples_per_second": 256.978,
+      "eval_steps_per_second": 2.018,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.270026783540297e-05,
+      "loss": 1.1553,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.1482834185536888e-05,
+      "loss": 1.0573,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0265400535670807e-05,
+      "loss": 1.0386,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.050401753104456e-06,
+      "loss": 1.0412,
+      "step": 4500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.835402970538106e-06,
+      "loss": 1.0434,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1202219724655151,
+      "eval_runtime": 40.4003,
+      "eval_samples_per_second": 261.631,
+      "eval_steps_per_second": 2.054,
+      "step": 5476
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8214,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.7167621364554752e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2587cee033c81db09f66cefeff68bf2140bcbcdcc56875373c4de582d3f6ad
+size 4536