Upload 11 files

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e234658527e68b330801030d716b73381864142071ee885be69fe06ced1dad3c
+size 267832560

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0417a0f21e4b06d8b6c44c0f38e6b814481c3fbad7c00e025d6cf155b0c3364
+size 535727290

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdaeb33cb755748c8cd40941b10c8c4f1fc6db9566fe0569853ec29ec0e93e1
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d944f5855dedd93de5810fb83351c896ba8bcf8ae6abf8ac51fb2013da8b6d
+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 +1,55 @@
+{
+  "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": false,
+  "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 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.253427505493164,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.3123,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.989475727081299,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2298,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9698,
+      "eval_loss": 0.10075412690639496,
+      "eval_runtime": 73.2779,
+      "eval_samples_per_second": 68.233,
+      "eval_steps_per_second": 4.271,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.917862892150879,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1791,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 6.352814674377441,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1424,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.428704023361206,
+      "learning_rate": 0.0,
+      "loss": 0.1345,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9774,
+      "eval_loss": 0.08082816004753113,
+      "eval_runtime": 73.6205,
+      "eval_samples_per_second": 67.916,
+      "eval_steps_per_second": 4.252,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 5239934236117440.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f87a092b5577a38bcfc591b2aa5c91c98e0d006cb50683cfc81f9bb6208e931
+size 5240