Upload folder using huggingface_hub

training_checkpoints/checkpoint-672/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 28996
+}

training_checkpoints/checkpoint-672/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "positive",
+    "1": "negative",
+    "2": "neutral",
+    "3": "rel_by_party"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "negative": 1,
+    "neutral": 2,
+    "positive": 0,
+    "rel_by_party": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 28996,
+  "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": "4.40.2",
+  "vocab_size": 28997
+}

training_checkpoints/checkpoint-672/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccda723584e3f87851c6d4fa0f6803e6221bdeb3c0c197f068753d04dde2a2e
+size 263153912

training_checkpoints/checkpoint-672/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2e3f894ac3f2bbcddf38637802cc895b46d7a1caf11b92cddc570828fa5cfb
+size 526369978

training_checkpoints/checkpoint-672/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90decba5b405fec1de685e8fa134fd69a6cc12166bed5535226eb5cec761252e
+size 14244

training_checkpoints/checkpoint-672/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9a3f98e11364f5e565bedc0bb8b71f97fbe5f7fd840035411aad27e961fa46
+size 1064

training_checkpoints/checkpoint-672/special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

training_checkpoints/checkpoint-672/tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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
+    },
+    "28996": {
+      "content": "<pad>",
+      "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]"
+}

training_checkpoints/checkpoint-672/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.6006365232660228,
+  "best_model_checkpoint": "case-analysis-distilbert-base-cased/checkpoint-448",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 672,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7683741648106904,
+      "eval_f1_macro": 0.5345911091709411,
+      "eval_f1_micro": 0.7683741648106904,
+      "eval_f1_weighted": 0.7419347573003691,
+      "eval_loss": 0.6746780872344971,
+      "eval_macro_fpr": 0.12600030005040652,
+      "eval_macro_sensitivity": 0.5319427525309879,
+      "eval_macro_specificity": 0.8890561890350515,
+      "eval_precision": 0.723734857424959,
+      "eval_precision_macro": 0.5435421823199279,
+      "eval_recall": 0.7683741648106904,
+      "eval_recall_macro": 0.5319427525309879,
+      "eval_runtime": 5.5739,
+      "eval_samples_per_second": 80.554,
+      "eval_steps_per_second": 10.226,
+      "eval_weighted_fpr": 0.0913081650570676,
+      "eval_weighted_sensitivity": 0.7683741648106904,
+      "eval_weighted_specificity": 0.7878505913295152,
+      "step": 224
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8151447661469933,
+      "eval_f1_macro": 0.6006365232660228,
+      "eval_f1_micro": 0.8151447661469933,
+      "eval_f1_weighted": 0.7944989450754872,
+      "eval_loss": 0.6685805916786194,
+      "eval_macro_fpr": 0.09260504201680672,
+      "eval_macro_sensitivity": 0.6135692606280841,
+      "eval_macro_specificity": 0.9160924396038365,
+      "eval_precision": 0.775170081701242,
+      "eval_precision_macro": 0.5885022601098201,
+      "eval_recall": 0.8151447661469933,
+      "eval_recall_macro": 0.6135692606280841,
+      "eval_runtime": 22.918,
+      "eval_samples_per_second": 19.592,
+      "eval_steps_per_second": 2.487,
+      "eval_weighted_fpr": 0.07027942421676546,
+      "eval_weighted_sensitivity": 0.8151447661469933,
+      "eval_weighted_specificity": 0.8492249922683526,
+      "step": 448
+    },
+    {
+      "epoch": 2.232142857142857,
+      "grad_norm": 15.72251033782959,
+      "learning_rate": 4.6302083333333335e-05,
+      "loss": 0.6982,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8106904231625836,
+      "eval_f1_macro": 0.5965678894021851,
+      "eval_f1_micro": 0.8106904231625834,
+      "eval_f1_weighted": 0.789500666861841,
+      "eval_loss": 0.7899503111839294,
+      "eval_macro_fpr": 0.09825302902225978,
+      "eval_macro_sensitivity": 0.6052493478964067,
+      "eval_macro_specificity": 0.910687377505773,
+      "eval_precision": 0.7758060756348297,
+      "eval_precision_macro": 0.5947486579771227,
+      "eval_recall": 0.8106904231625836,
+      "eval_recall_macro": 0.6052493478964067,
+      "eval_runtime": 22.9183,
+      "eval_samples_per_second": 19.591,
+      "eval_steps_per_second": 2.487,
+      "eval_weighted_fpr": 0.07221750212404418,
+      "eval_weighted_sensitivity": 0.8106904231625836,
+      "eval_weighted_specificity": 0.8320590868605084,
+      "step": 672
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 712170135355392.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-672/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69a367f465c21d14de763eeb210a4f6dfdc2d5d36a7fd05f0a714a904e7ac23
+size 5048