Upload 12 files

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "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": "4.24.0",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a92384149e3b3db84cc68a2ecb8bee5473fc5edf6fcfa7f6ecf7e442ad9de25
+size 535945733

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd72e589d53b20d06c8bb9c8f9d21b9566daae3753c01f3a7c71ae36e17bac6e
+size 267978033

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb89f514aa45eba5ac1c32d4c9c7d6fd0853985a8150bb976770d61706d6f2b6
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2de9749828adacdf103bf6e9592702bb7067a2c1df27dd62ab38c1eb8c070f
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97b16eeb19dcb7344a37e3169ae38c1e934c53295d4964f1c9fc1ddcc0b430e
+size 627

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.9504950495049505,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6674917491749177e-05,
+      "loss": 1.9722,
+      "step": 403
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.093264102935791,
+      "eval_runtime": 1.5252,
+      "eval_samples_per_second": 1433.916,
+      "eval_steps_per_second": 45.24,
+      "step": 404
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3349834983498351e-05,
+      "loss": 1.9372,
+      "step": 806
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.9881993532180786,
+      "eval_runtime": 1.5777,
+      "eval_samples_per_second": 1386.229,
+      "eval_steps_per_second": 43.736,
+      "step": 808
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.0024752475247525e-05,
+      "loss": 1.9278,
+      "step": 1209
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.013523578643799,
+      "eval_runtime": 1.6453,
+      "eval_samples_per_second": 1329.222,
+      "eval_steps_per_second": 41.937,
+      "step": 1212
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 6.6996699669967e-06,
+      "loss": 1.9295,
+      "step": 1612
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9506467580795288,
+      "eval_runtime": 1.7203,
+      "eval_samples_per_second": 1271.257,
+      "eval_steps_per_second": 40.108,
+      "step": 1616
+    }
+  ],
+  "max_steps": 2424,
+  "num_train_epochs": 6,
+  "total_flos": 2119255202506752.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7efc5c7798f11c5249802c91663242723545f1f56670d2df1d1a3fdb1a40f1
+size 3451