Upload folder using huggingface_hub

training_checkpoints/checkpoint-2240/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "positive",
+    "1": "negative",
+    "2": "neutral",
+    "3": "rel_by_party"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 1,
+    "neutral": 2,
+    "positive": 0,
+    "rel_by_party": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

training_checkpoints/checkpoint-2240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a733b907baa3c5979066307e8a7c132f4b43af0e0b94876c0f38a5c7fa3d45
+size 498618976

training_checkpoints/checkpoint-2240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511a9c944cc0e987832155e07d27b033c45fc048c73c80a5a35a51ad3d78a4e1
+size 997357818

training_checkpoints/checkpoint-2240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b41d5201173f74a09dd4e94487c63588152ed3fee40bd082b0fabe56a66a5ee
+size 14244

training_checkpoints/checkpoint-2240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d277c1ab697db13bd148f26bc1be59258cd34fcc8f4d3ee7b156c1294f09768
+size 1064

training_checkpoints/checkpoint-2240/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-2240/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-2240/trainer_state.json

@@ -0,0 +1,269 @@
+{
+  "best_metric": 0.6264265498194235,
+  "best_model_checkpoint": "case-analysis-roberta-base/checkpoint-2016",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7527839643652561,
+      "eval_f1_macro": 0.5389063030773956,
+      "eval_f1_micro": 0.7527839643652561,
+      "eval_f1_weighted": 0.7300520074128541,
+      "eval_loss": 0.8771109580993652,
+      "eval_macro_fpr": 0.13144039552419665,
+      "eval_macro_sensitivity": 0.5401895401895401,
+      "eval_macro_specificity": 0.8833499134100214,
+      "eval_precision": 0.7119932520850578,
+      "eval_precision_macro": 0.5403637213518124,
+      "eval_recall": 0.7527839643652561,
+      "eval_recall_macro": 0.5401895401895401,
+      "eval_runtime": 6.9264,
+      "eval_samples_per_second": 64.825,
+      "eval_steps_per_second": 8.229,
+      "eval_weighted_fpr": 0.09866666666666667,
+      "eval_weighted_sensitivity": 0.7527839643652561,
+      "eval_weighted_specificity": 0.7806156892748298,
+      "step": 224
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7728285077951003,
+      "eval_f1_macro": 0.5712387529890991,
+      "eval_f1_micro": 0.7728285077951002,
+      "eval_f1_weighted": 0.7555182045354769,
+      "eval_loss": 0.7935857176780701,
+      "eval_macro_fpr": 0.10804320901264429,
+      "eval_macro_sensitivity": 0.59374376286141,
+      "eval_macro_specificity": 0.9046495531497725,
+      "eval_precision": 0.7420199260104934,
+      "eval_precision_macro": 0.5529178338001868,
+      "eval_recall": 0.7728285077951003,
+      "eval_recall_macro": 0.59374376286141,
+      "eval_runtime": 33.5269,
+      "eval_samples_per_second": 13.392,
+      "eval_steps_per_second": 1.7,
+      "eval_weighted_fpr": 0.08923884514435695,
+      "eval_weighted_sensitivity": 0.7728285077951003,
+      "eval_weighted_specificity": 0.8457697048039892,
+      "step": 448
+    },
+    {
+      "epoch": 2.232142857142857,
+      "grad_norm": 10.557605743408203,
+      "learning_rate": 4.631696428571429e-05,
+      "loss": 0.8855,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7305122494432071,
+      "eval_f1_macro": 0.5313357935186093,
+      "eval_f1_micro": 0.730512249443207,
+      "eval_f1_weighted": 0.7208063173961943,
+      "eval_loss": 0.8126917481422424,
+      "eval_macro_fpr": 0.1288106780460812,
+      "eval_macro_sensitivity": 0.5599513761278467,
+      "eval_macro_specificity": 0.8878517309481255,
+      "eval_precision": 0.7320572933103704,
+      "eval_precision_macro": 0.5335863697705803,
+      "eval_recall": 0.7305122494432071,
+      "eval_recall_macro": 0.5599513761278467,
+      "eval_runtime": 35.5026,
+      "eval_samples_per_second": 12.647,
+      "eval_steps_per_second": 1.606,
+      "eval_weighted_fpr": 0.10950226244343891,
+      "eval_weighted_sensitivity": 0.7305122494432071,
+      "eval_weighted_specificity": 0.8208946743492954,
+      "step": 672
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.779510022271715,
+      "eval_f1_macro": 0.5605264699901076,
+      "eval_f1_micro": 0.779510022271715,
+      "eval_f1_weighted": 0.756140232373208,
+      "eval_loss": 1.0185617208480835,
+      "eval_macro_fpr": 0.11840141313918778,
+      "eval_macro_sensitivity": 0.565439197792139,
+      "eval_macro_specificity": 0.8949862362922303,
+      "eval_precision": 0.7503024658142448,
+      "eval_precision_macro": 0.5721560130010834,
+      "eval_recall": 0.779510022271715,
+      "eval_recall_macro": 0.565439197792139,
+      "eval_runtime": 42.1679,
+      "eval_samples_per_second": 10.648,
+      "eval_steps_per_second": 1.352,
+      "eval_weighted_fpr": 0.08616187989556136,
+      "eval_weighted_sensitivity": 0.779510022271715,
+      "eval_weighted_specificity": 0.800434922897206,
+      "step": 896
+    },
+    {
+      "epoch": 4.464285714285714,
+      "grad_norm": 4.521566867828369,
+      "learning_rate": 4.260416666666667e-05,
+      "loss": 0.5551,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8084632516703786,
+      "eval_f1_macro": 0.5892045454545454,
+      "eval_f1_micro": 0.8084632516703786,
+      "eval_f1_weighted": 0.7866926503340758,
+      "eval_loss": 0.7591320276260376,
+      "eval_macro_fpr": 0.09875084526504571,
+      "eval_macro_sensitivity": 0.5962627065568242,
+      "eval_macro_specificity": 0.91148202322346,
+      "eval_precision": 0.7673786757699211,
+      "eval_precision_macro": 0.583308107932168,
+      "eval_recall": 0.8084632516703786,
+      "eval_recall_macro": 0.5962627065568242,
+      "eval_runtime": 42.7116,
+      "eval_samples_per_second": 10.512,
+      "eval_steps_per_second": 1.335,
+      "eval_weighted_fpr": 0.07319148936170213,
+      "eval_weighted_sensitivity": 0.8084632516703786,
+      "eval_weighted_specificity": 0.8374648412234613,
+      "step": 1120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8173719376391982,
+      "eval_f1_macro": 0.603048355342882,
+      "eval_f1_micro": 0.8173719376391981,
+      "eval_f1_weighted": 0.7967392787416411,
+      "eval_loss": 0.9521613717079163,
+      "eval_macro_fpr": 0.09667046583838863,
+      "eval_macro_sensitivity": 0.5987868120221062,
+      "eval_macro_specificity": 0.9117780208671373,
+      "eval_precision": 0.7816269250029019,
+      "eval_precision_macro": 0.6116760996647348,
+      "eval_recall": 0.8173719376391982,
+      "eval_recall_macro": 0.5987868120221062,
+      "eval_runtime": 40.3104,
+      "eval_samples_per_second": 11.139,
+      "eval_steps_per_second": 1.414,
+      "eval_weighted_fpr": 0.06931530008453085,
+      "eval_weighted_sensitivity": 0.8173719376391982,
+      "eval_weighted_specificity": 0.8297401458293509,
+      "step": 1344
+    },
+    {
+      "epoch": 6.696428571428571,
+      "grad_norm": 0.38720017671585083,
+      "learning_rate": 3.888392857142857e-05,
+      "loss": 0.386,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7706013363028953,
+      "eval_f1_macro": 0.5781817655906514,
+      "eval_f1_micro": 0.7706013363028953,
+      "eval_f1_weighted": 0.7656335044104077,
+      "eval_loss": 1.0569394826889038,
+      "eval_macro_fpr": 0.10894725594931005,
+      "eval_macro_sensitivity": 0.5857963578551814,
+      "eval_macro_specificity": 0.9056966184410946,
+      "eval_precision": 0.7610212023939332,
+      "eval_precision_macro": 0.5709751150784568,
+      "eval_recall": 0.7706013363028953,
+      "eval_recall_macro": 0.5857963578551814,
+      "eval_runtime": 36.0908,
+      "eval_samples_per_second": 12.441,
+      "eval_steps_per_second": 1.579,
+      "eval_weighted_fpr": 0.09027169149868536,
+      "eval_weighted_sensitivity": 0.7706013363028953,
+      "eval_weighted_specificity": 0.852185137461483,
+      "step": 1568
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7572383073496659,
+      "eval_f1_macro": 0.6161842736352976,
+      "eval_f1_micro": 0.7572383073496659,
+      "eval_f1_weighted": 0.7715266654127986,
+      "eval_loss": 1.1956746578216553,
+      "eval_macro_fpr": 0.10518103765035827,
+      "eval_macro_sensitivity": 0.6263515234103469,
+      "eval_macro_specificity": 0.9119340321339534,
+      "eval_precision": 0.7917843915207833,
+      "eval_precision_macro": 0.6175221125829533,
+      "eval_recall": 0.7572383073496659,
+      "eval_recall_macro": 0.6263515234103469,
+      "eval_runtime": 39.6918,
+      "eval_samples_per_second": 11.312,
+      "eval_steps_per_second": 1.436,
+      "eval_weighted_fpr": 0.09654561558901682,
+      "eval_weighted_sensitivity": 0.7572383073496659,
+      "eval_weighted_specificity": 0.8904978211861475,
+      "step": 1792
+    },
+    {
+      "epoch": 8.928571428571429,
+      "grad_norm": 0.17783766984939575,
+      "learning_rate": 3.516369047619048e-05,
+      "loss": 0.2709,
+      "step": 2000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7728285077951003,
+      "eval_f1_macro": 0.6264265498194235,
+      "eval_f1_micro": 0.7728285077951002,
+      "eval_f1_weighted": 0.7773023130906183,
+      "eval_loss": 1.2091724872589111,
+      "eval_macro_fpr": 0.10207367511358464,
+      "eval_macro_sensitivity": 0.6301385419032478,
+      "eval_macro_specificity": 0.9119745284052109,
+      "eval_precision": 0.7896658353037499,
+      "eval_precision_macro": 0.6331069825924028,
+      "eval_recall": 0.7728285077951003,
+      "eval_recall_macro": 0.6301385419032478,
+      "eval_runtime": 39.549,
+      "eval_samples_per_second": 11.353,
+      "eval_steps_per_second": 1.441,
+      "eval_weighted_fpr": 0.08923884514435695,
+      "eval_weighted_sensitivity": 0.7728285077951003,
+      "eval_weighted_specificity": 0.8750696058257429,
+      "step": 2016
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7706013363028953,
+      "eval_f1_macro": 0.6072269083290167,
+      "eval_f1_micro": 0.7706013363028953,
+      "eval_f1_weighted": 0.7728190961011124,
+      "eval_loss": 1.3829654455184937,
+      "eval_macro_fpr": 0.10942591948269315,
+      "eval_macro_sensitivity": 0.6073347029229382,
+      "eval_macro_specificity": 0.9042606300967866,
+      "eval_precision": 0.7782484840467806,
+      "eval_precision_macro": 0.611192146322276,
+      "eval_recall": 0.7706013363028953,
+      "eval_recall_macro": 0.6073347029229382,
+      "eval_runtime": 36.3346,
+      "eval_samples_per_second": 12.357,
+      "eval_steps_per_second": 1.569,
+      "eval_weighted_fpr": 0.09027169149868536,
+      "eval_weighted_sensitivity": 0.7706013363028953,
+      "eval_weighted_specificity": 0.8464411840842511,
+      "step": 2240
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 4715034779320320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-2240/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8855967b7a0e1809c878c330ee1e252a00739f2113c0de07ba125067993b5258
+size 5048