Initial commit

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Casual",
+    "1": "Professional",
+    "2": "Friendly",
+    "3": "Informative",
+    "4": "Serious",
+    "5": "Humorous",
+    "6": "Authoritative",
+    "7": "Intimate"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Authoritative": 6,
+    "Casual": 0,
+    "Friendly": 2,
+    "Humorous": 5,
+    "Informative": 3,
+    "Intimate": 7,
+    "Professional": 1,
+    "Serious": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": "4.41.1",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba2603cb1ce82a119714fa0592518a85a3385185a7261d8cab10bd74b745fa0
+size 263163144

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90d83ebe436c1e9fc3af81c9d5b15a0d0bc055b9ced3da6f43d4cf5d9699ea4
+size 526388410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877c4ba1599fab3df390d0a0343142677d514aefe626ab40669e03511e87bd89
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20546c36203b63b34154fbe25b8b9d9cbad79fd7ee5df0a7eb320bd929581f52
+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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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 +1,83 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 255,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8695652173913043,
+      "eval_f1": 0.8728600541101488,
+      "eval_loss": 0.6608906984329224,
+      "eval_runtime": 0.8181,
+      "eval_samples_per_second": 421.7,
+      "eval_steps_per_second": 7.334,
+      "step": 51
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9188405797101449,
+      "eval_f1": 0.9254201727996807,
+      "eval_loss": 0.282185822725296,
+      "eval_runtime": 0.8009,
+      "eval_samples_per_second": 430.79,
+      "eval_steps_per_second": 7.492,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9565217391304348,
+      "eval_f1": 0.957832432085824,
+      "eval_loss": 0.14275817573070526,
+      "eval_runtime": 0.7983,
+      "eval_samples_per_second": 432.18,
+      "eval_steps_per_second": 7.516,
+      "step": 153
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9623188405797102,
+      "eval_f1": 0.962796387059804,
+      "eval_loss": 0.11694291979074478,
+      "eval_runtime": 0.7991,
+      "eval_samples_per_second": 431.736,
+      "eval_steps_per_second": 7.508,
+      "step": 204
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9623188405797102,
+      "eval_f1": 0.9634447984007641,
+      "eval_loss": 0.1356935352087021,
+      "eval_runtime": 0.8116,
+      "eval_samples_per_second": 425.078,
+      "eval_steps_per_second": 7.393,
+      "step": 255
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 255,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 49293495228288.0,
+  "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:c2f57bb1af615bffb83e8813544684b3016f2f0ac0f36ede66238ff8c589dc87
+size 5112