Upload fine-tuned DistilBERT model

config.json

@@ -0,0 +1,23 @@
+{
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767d7ceaa9caa5b8642b36dca7262e8e1a0f37b6ee059845eb69f99f2472ce1e
+size 265470032

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab285f9078e4087598fb56ca656eb2317548bf80d4f49c9367d672339ad0ec6e
+size 531000890

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec8b423ccab49984b88d6bcdfe532bea50471e2aced4d88c8fdd5e753f214e2
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec44327f49491e5473192836016ac321a25139cb05a44f6389303544ffac1e9
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1358292fc8093e9f2fe9936c61149d76ab0510f46cb46ae4469fee7ed1b04c12
+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
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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 +1,90 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 399.72727272727275,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 49.72727272727273,
+      "grad_norm": 8.328217506408691,
+      "learning_rate": 8.775e-06,
+      "loss": 1.8952,
+      "step": 100
+    },
+    {
+      "epoch": 99.72727272727273,
+      "grad_norm": 4.615832805633545,
+      "learning_rate": 7.525e-06,
+      "loss": 0.4619,
+      "step": 200
+    },
+    {
+      "epoch": 149.72727272727272,
+      "grad_norm": 2.132920503616333,
+      "learning_rate": 6.275e-06,
+      "loss": 0.0905,
+      "step": 300
+    },
+    {
+      "epoch": 199.72727272727272,
+      "grad_norm": 0.5747965574264526,
+      "learning_rate": 5.025e-06,
+      "loss": 0.0256,
+      "step": 400
+    },
+    {
+      "epoch": 249.72727272727272,
+      "grad_norm": 0.17656728625297546,
+      "learning_rate": 3.7750000000000003e-06,
+      "loss": 0.013,
+      "step": 500
+    },
+    {
+      "epoch": 299.72727272727275,
+      "grad_norm": 0.22439385950565338,
+      "learning_rate": 2.5250000000000004e-06,
+      "loss": 0.0083,
+      "step": 600
+    },
+    {
+      "epoch": 349.72727272727275,
+      "grad_norm": 0.07200386375188828,
+      "learning_rate": 1.275e-06,
+      "loss": 0.0059,
+      "step": 700
+    },
+    {
+      "epoch": 399.72727272727275,
+      "grad_norm": 1.7082760334014893,
+      "learning_rate": 2.5000000000000002e-08,
+      "loss": 0.0035,
+      "step": 800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 400,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8774662198149120.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc40349e88b0d2894730579ef480b89246e996c112a8f7e31426ae635745537
+size 5304