Upload folder using huggingface_hub

all_runs/checkpoint-1120/added_tokens.json

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

all_runs/checkpoint-1120/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
+}

all_runs/checkpoint-1120/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cf3cd7d40235337bb018df172211a6db8d4c24219c88f1cf56b863fca8f9bd
+size 263153912

all_runs/checkpoint-1120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91735e8a702fdc76bf72c71a50431395bab39ece2b243d6a8eec0841aab84933
+size 526369978

all_runs/checkpoint-1120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2cfb0c31d46640a923adf7896113b452a5c7b1598fdeb259bfc7cffb33d113
+size 14244

all_runs/checkpoint-1120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc72debd89cf987f645165b85aacd28e6c9fb02087f12ec8a85ab200479cd04
+size 1064

all_runs/checkpoint-1120/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]"
+}

all_runs/checkpoint-1120/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]"
+}

all_runs/checkpoint-1120/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 0.6301119928151375,
+  "best_model_checkpoint": "case-analysis-distilbert-base-cased/checkpoint-896",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7661469933184856,
+      "eval_f1_macro": 0.5270352134866867,
+      "eval_f1_micro": 0.7661469933184856,
+      "eval_f1_weighted": 0.7333313004442764,
+      "eval_loss": 0.7000867128372192,
+      "eval_macro_fpr": 0.1330263157894737,
+      "eval_macro_sensitivity": 0.5137440725676019,
+      "eval_macro_specificity": 0.8818942592408516,
+      "eval_precision": 0.7310834070149471,
+      "eval_precision_macro": 0.5790641299401408,
+      "eval_recall": 0.7661469933184856,
+      "eval_recall_macro": 0.5137440725676019,
+      "eval_runtime": 5.4998,
+      "eval_samples_per_second": 81.639,
+      "eval_steps_per_second": 10.364,
+      "eval_weighted_fpr": 0.09234828496042216,
+      "eval_weighted_sensitivity": 0.7661469933184856,
+      "eval_weighted_specificity": 0.761430043644921,
+      "step": 224
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7750556792873051,
+      "eval_f1_macro": 0.5486718521990608,
+      "eval_f1_micro": 0.775055679287305,
+      "eval_f1_weighted": 0.7492575717498114,
+      "eval_loss": 0.7387592792510986,
+      "eval_macro_fpr": 0.12078200823200373,
+      "eval_macro_sensitivity": 0.5464266787796199,
+      "eval_macro_specificity": 0.8914743027952345,
+      "eval_precision": 0.7315284458297402,
+      "eval_precision_macro": 0.5585311316366537,
+      "eval_recall": 0.7750556792873051,
+      "eval_recall_macro": 0.5464266787796199,
+      "eval_runtime": 23.5227,
+      "eval_samples_per_second": 19.088,
+      "eval_steps_per_second": 2.423,
+      "eval_weighted_fpr": 0.08820960698689956,
+      "eval_weighted_sensitivity": 0.7750556792873051,
+      "eval_weighted_specificity": 0.7908415318936333,
+      "step": 448
+    },
+    {
+      "epoch": 2.232142857142857,
+      "grad_norm": 22.91168785095215,
+      "learning_rate": 4.629464285714286e-05,
+      "loss": 0.7066,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8017817371937639,
+      "eval_f1_macro": 0.576677451756589,
+      "eval_f1_micro": 0.8017817371937639,
+      "eval_f1_weighted": 0.7759761601356532,
+      "eval_loss": 0.7228724956512451,
+      "eval_macro_fpr": 0.10757194512338594,
+      "eval_macro_sensitivity": 0.5707859310800487,
+      "eval_macro_specificity": 0.9026901603449184,
+      "eval_precision": 0.7604834726234316,
+      "eval_precision_macro": 0.5932281353135314,
+      "eval_recall": 0.8017817371937639,
+      "eval_recall_macro": 0.5707859310800487,
+      "eval_runtime": 17.5142,
+      "eval_samples_per_second": 25.636,
+      "eval_steps_per_second": 3.254,
+      "eval_weighted_fpr": 0.07613344739093242,
+      "eval_weighted_sensitivity": 0.8017817371937639,
+      "eval_weighted_specificity": 0.8089789041859096,
+      "step": 672
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8062360801781737,
+      "eval_f1_macro": 0.6301119928151375,
+      "eval_f1_micro": 0.8062360801781738,
+      "eval_f1_weighted": 0.7933630533945198,
+      "eval_loss": 0.8331468105316162,
+      "eval_macro_fpr": 0.10175133159747105,
+      "eval_macro_sensitivity": 0.6114882070764424,
+      "eval_macro_specificity": 0.9069973738423197,
+      "eval_precision": 0.7896315051078991,
+      "eval_precision_macro": 0.6674639062867935,
+      "eval_recall": 0.8062360801781737,
+      "eval_recall_macro": 0.6114882070764424,
+      "eval_runtime": 17.9901,
+      "eval_samples_per_second": 24.958,
+      "eval_steps_per_second": 3.168,
+      "eval_weighted_fpr": 0.0741687979539642,
+      "eval_weighted_sensitivity": 0.8062360801781737,
+      "eval_weighted_specificity": 0.8217534151911048,
+      "step": 896
+    },
+    {
+      "epoch": 4.464285714285714,
+      "grad_norm": 0.23617026209831238,
+      "learning_rate": 4.258184523809524e-05,
+      "loss": 0.3654,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7683741648106904,
+      "eval_f1_macro": 0.5896043825978781,
+      "eval_f1_micro": 0.7683741648106904,
+      "eval_f1_weighted": 0.7610828501277613,
+      "eval_loss": 1.2299734354019165,
+      "eval_macro_fpr": 0.10662840460883276,
+      "eval_macro_sensitivity": 0.6130556645262528,
+      "eval_macro_specificity": 0.9056447032260023,
+      "eval_precision": 0.7698582566254396,
+      "eval_precision_macro": 0.6085394130060126,
+      "eval_recall": 0.7683741648106904,
+      "eval_recall_macro": 0.6130556645262528,
+      "eval_runtime": 19.5517,
+      "eval_samples_per_second": 22.965,
+      "eval_steps_per_second": 2.915,
+      "eval_weighted_fpr": 0.0913081650570676,
+      "eval_weighted_sensitivity": 0.7683741648106904,
+      "eval_weighted_specificity": 0.8542046480933186,
+      "step": 1120
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 1186950225592320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

all_runs/checkpoint-1120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3168244efe16c0aeafe631cea29ca8c9c2bbb665a169c0d40c2e4d22eaca40d9
+size 5048