Upload 8 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": "AMBIG",
+    "1": "CLEAR"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "AMBIG": 0,
+    "CLEAR": 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": "4.44.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774a0270c474d563446afcd4bfd80b4b9ac5e63e455564552a98f29ab829b140
+size 267832560

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": 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 +1,114 @@
+{
+  "best_metric": 0.3527472913265228,
+  "best_model_checkpoint": "AmBig_Questions_v7/checkpoint-96",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5934579439252337,
+      "eval_loss": 0.641407310962677,
+      "eval_runtime": 0.3064,
+      "eval_samples_per_second": 698.428,
+      "eval_steps_per_second": 13.055,
+      "step": 16
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7570093457943925,
+      "eval_loss": 0.544841468334198,
+      "eval_runtime": 0.2272,
+      "eval_samples_per_second": 942.093,
+      "eval_steps_per_second": 17.609,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8271028037383178,
+      "eval_loss": 0.44836297631263733,
+      "eval_runtime": 0.1974,
+      "eval_samples_per_second": 1083.98,
+      "eval_steps_per_second": 20.261,
+      "step": 48
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8504672897196262,
+      "eval_loss": 0.37522220611572266,
+      "eval_runtime": 0.1833,
+      "eval_samples_per_second": 1167.295,
+      "eval_steps_per_second": 21.819,
+      "step": 64
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8551401869158879,
+      "eval_loss": 0.36060166358947754,
+      "eval_runtime": 0.2024,
+      "eval_samples_per_second": 1057.568,
+      "eval_steps_per_second": 19.768,
+      "step": 80
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8551401869158879,
+      "eval_loss": 0.3527472913265228,
+      "eval_runtime": 0.1689,
+      "eval_samples_per_second": 1266.975,
+      "eval_steps_per_second": 23.682,
+      "step": 96
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8598130841121495,
+      "eval_loss": 0.35737448930740356,
+      "eval_runtime": 0.1698,
+      "eval_samples_per_second": 1260.253,
+      "eval_steps_per_second": 23.556,
+      "step": 112
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8551401869158879,
+      "eval_loss": 0.3698413670063019,
+      "eval_runtime": 0.1727,
+      "eval_samples_per_second": 1239.099,
+      "eval_steps_per_second": 23.161,
+      "step": 128
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8551401869158879,
+      "eval_loss": 0.3658725619316101,
+      "eval_runtime": 0.1701,
+      "eval_samples_per_second": 1257.934,
+      "eval_steps_per_second": 23.513,
+      "step": 144
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 57683860156152.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ace7ca70efa0574bbe8160af22b3a6341c52fb4b2ca406b4d4d126afdc7dd01
+size 5176