Upload folder using huggingface_hub

config.json

@@ -0,0 +1,43 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Nomove",
+    "1": "participation management",
+    "2": "PressReasoning",
+    "3": "PressAccuracy",
+    "4": "Uptake (Restating or revoicing)"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "Nomove": 0,
+    "PressAccuracy": 3,
+    "PressReasoning": 2,
+    "Uptake (Restating or revoicing)": 4,
+    "participation management": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac304968e4505914406f0e683f046c1a0a8f16f8512408e97b73935f235d67c
+size 1421507660

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694463e9ee07c81ba81cbc05b22ba22f93a94348a788e9691f7e78da071ea16a
+size 2843253758

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec38223b4e1bacb29bb096764307e58cf77809d88d73eb235262daaa76831a57
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab067424c5f7dc2022d597dda27e0f3a7afb728861479487bc1c0cef42a639db
+size 1465

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_global_step": 2088,
+  "best_metric": 0.8285096878151668,
+  "best_model_checkpoint": "./robertalarge_multiclass/checkpoint-2088",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 38.4963493347168,
+      "learning_rate": 1.996168582375479e-05,
+      "loss": 0.7634037061669361,
+      "step": 522
+    },
+    {
+      "epoch": 1.0,
+      "eval_Nomove_f1": 0.8534048976853404,
+      "eval_Nomove_precision": 0.8588791357191087,
+      "eval_Nomove_recall": 0.848,
+      "eval_Nomove_support": 3000,
+      "eval_PressAccuracy_f1": 0.875776397515528,
+      "eval_PressAccuracy_precision": 0.8788469029996104,
+      "eval_PressAccuracy_recall": 0.8727272727272727,
+      "eval_PressAccuracy_support": 2585,
+      "eval_PressReasoning_f1": 0.7333333333333333,
+      "eval_PressReasoning_precision": 0.6212624584717608,
+      "eval_PressReasoning_recall": 0.8947368421052632,
+      "eval_PressReasoning_support": 209,
+      "eval_Uptake (Restating or revoicing)_f1": 0.597979797979798,
+      "eval_Uptake (Restating or revoicing)_precision": 0.5025466893039049,
+      "eval_Uptake (Restating or revoicing)_recall": 0.7381546134663342,
+      "eval_Uptake (Restating or revoicing)_support": 401,
+      "eval_accuracy": 0.8313151900251768,
+      "eval_loss": 0.5038919448852539,
+      "eval_macro_f1": 0.7744391016253172,
+      "eval_macro_precision": 0.7441072454154222,
+      "eval_macro_recall": 0.8245914064239864,
+      "eval_mcc": 0.7642954946246379,
+      "eval_participation management_f1": 0.811701081612586,
+      "eval_participation management_precision": 0.8590010405827263,
+      "eval_participation management_recall": 0.7693383038210625,
+      "eval_participation management_support": 2146,
+      "eval_runtime": 7.1557,
+      "eval_samples_per_second": 1165.647,
+      "eval_steps_per_second": 18.307,
+      "eval_weighted_f1": 0.8343200776202896,
+      "eval_weighted_precision": 0.8420139024976997,
+      "eval_weighted_recall": 0.8313151900251768,
+      "step": 522
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.410867214202881,
+      "learning_rate": 1.7782034908471692e-05,
+      "loss": 0.4319716997987009,
+      "step": 1044
+    },
+    {
+      "epoch": 2.0,
+      "eval_Nomove_f1": 0.8761967646087818,
+      "eval_Nomove_precision": 0.8678875081752779,
+      "eval_Nomove_recall": 0.8846666666666667,
+      "eval_Nomove_support": 3000,
+      "eval_PressAccuracy_f1": 0.8749497386409328,
+      "eval_PressAccuracy_precision": 0.9108413562159899,
+      "eval_PressAccuracy_recall": 0.8417794970986461,
+      "eval_PressAccuracy_support": 2585,
+      "eval_PressReasoning_f1": 0.7859078590785908,
+      "eval_PressReasoning_precision": 0.90625,
+      "eval_PressReasoning_recall": 0.69377990430622,
+      "eval_PressReasoning_support": 209,
+      "eval_Uptake (Restating or revoicing)_f1": 0.6924101198402132,
+      "eval_Uptake (Restating or revoicing)_precision": 0.7428571428571429,
+      "eval_Uptake (Restating or revoicing)_recall": 0.6483790523690773,
+      "eval_Uptake (Restating or revoicing)_support": 401,
+      "eval_accuracy": 0.8515765495743916,
+      "eval_loss": 0.4433172047138214,
+      "eval_macro_f1": 0.8108377087957347,
+      "eval_macro_precision": 0.8422786108456553,
+      "eval_macro_recall": 0.7878123568001445,
+      "eval_mcc": 0.7898141732587503,
+      "eval_participation management_f1": 0.8247240618101546,
+      "eval_participation management_precision": 0.7835570469798657,
+      "eval_participation management_recall": 0.8704566635601119,
+      "eval_participation management_support": 2146,
+      "eval_runtime": 7.1565,
+      "eval_samples_per_second": 1165.511,
+      "eval_steps_per_second": 18.305,
+      "eval_weighted_f1": 0.8514691770124805,
+      "eval_weighted_precision": 0.8544530412958486,
+      "eval_weighted_recall": 0.8515765495743916,
+      "step": 1044
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 15.955626487731934,
+      "learning_rate": 1.555981268624947e-05,
+      "loss": 0.33474684675077826,
+      "step": 1566
+    },
+    {
+      "epoch": 3.0,
+      "eval_Nomove_f1": 0.8818949809508034,
+      "eval_Nomove_precision": 0.8765228844254198,
+      "eval_Nomove_recall": 0.8873333333333333,
+      "eval_Nomove_support": 3000,
+      "eval_PressAccuracy_f1": 0.895219512195122,
+      "eval_PressAccuracy_precision": 0.9031496062992126,
+      "eval_PressAccuracy_recall": 0.8874274661508704,
+      "eval_PressAccuracy_support": 2585,
+      "eval_PressReasoning_f1": 0.7851851851851851,
+      "eval_PressReasoning_precision": 0.8112244897959183,
+      "eval_PressReasoning_recall": 0.7607655502392344,
+      "eval_PressReasoning_support": 209,
+      "eval_Uptake (Restating or revoicing)_f1": 0.7187079407806191,
+      "eval_Uptake (Restating or revoicing)_precision": 0.7807017543859649,
+      "eval_Uptake (Restating or revoicing)_recall": 0.6658354114713217,
+      "eval_Uptake (Restating or revoicing)_support": 401,
+      "eval_accuracy": 0.8676417695719938,
+      "eval_loss": 0.4420914053916931,
+      "eval_macro_f1": 0.8259179007665363,
+      "eval_macro_precision": 0.8409864136479698,
+      "eval_macro_recall": 0.8131521285670041,
+      "eval_mcc": 0.8119580097491912,
+      "eval_participation management_f1": 0.8485818847209515,
+      "eval_participation management_precision": 0.8333333333333334,
+      "eval_participation management_recall": 0.8643988816402609,
+      "eval_participation management_support": 2146,
+      "eval_runtime": 7.1677,
+      "eval_samples_per_second": 1163.701,
+      "eval_steps_per_second": 18.277,
+      "eval_weighted_f1": 0.867184953176441,
+      "eval_weighted_precision": 0.8674200984017715,
+      "eval_weighted_recall": 0.8676417695719938,
+      "step": 1566
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 36.6058464050293,
+      "learning_rate": 1.3337590464027246e-05,
+      "loss": 0.2601611257969648,
+      "step": 2088
+    },
+    {
+      "epoch": 4.0,
+      "eval_Nomove_f1": 0.881498224087827,
+      "eval_Nomove_precision": 0.8547276142767689,
+      "eval_Nomove_recall": 0.91,
+      "eval_Nomove_support": 3000,
+      "eval_PressAccuracy_f1": 0.8888455538221529,
+      "eval_PressAccuracy_precision": 0.8961856075501377,
+      "eval_PressAccuracy_recall": 0.8816247582205029,
+      "eval_PressAccuracy_support": 2585,
+      "eval_PressReasoning_f1": 0.8066037735849058,
+      "eval_PressReasoning_precision": 0.7953488372093023,
+      "eval_PressReasoning_recall": 0.8181818181818182,
+      "eval_PressReasoning_support": 209,
+      "eval_Uptake (Restating or revoicing)_f1": 0.7253613666228647,
+      "eval_Uptake (Restating or revoicing)_precision": 0.7666666666666667,
+      "eval_Uptake (Restating or revoicing)_recall": 0.6882793017456359,
+      "eval_Uptake (Restating or revoicing)_support": 401,
+      "eval_accuracy": 0.8644047476321784,
+      "eval_loss": 0.45752763748168945,
+      "eval_macro_f1": 0.8285096878151668,
+      "eval_macro_precision": 0.8354787959044984,
+      "eval_macro_recall": 0.8230840908206446,
+      "eval_mcc": 0.8074382310097558,
+      "eval_participation management_f1": 0.8402395209580839,
+      "eval_participation management_precision": 0.8644652538196156,
+      "eval_participation management_recall": 0.8173345759552656,
+      "eval_participation management_support": 2146,
+      "eval_runtime": 7.1558,
+      "eval_samples_per_second": 1165.633,
+      "eval_steps_per_second": 18.307,
+      "eval_weighted_f1": 0.8637770696037415,
+      "eval_weighted_precision": 0.8643599464517906,
+      "eval_weighted_recall": 0.8644047476321784,
+      "step": 2088
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5220,
+  "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": 1.1956807869597816e+16,
+  "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 sha256:2284e75e30578949fb784db96b4b1ffd5fb26daab6fcaaca58ecfc91092e52c3
+size 5201