Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "single_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd72eadf9cf0f24c84968230db8bc1da4866528846dc74596a9eec81761c434b
+size 1740308548

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23eca4789ab4c68566cb65690da1eb83bf921ee2917efd24c24631279036ba6
+size 3480848833

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334ae11874731457170db4dfced126af9a9d3c6be13b2644f4611dfc829bca16
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f10b8187258404f2b8c9bd84b3734d289fd66db218ff910deeee1f2e7c0d53
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6faad1c0ee47d1761c3d28813552f4dce1f74ae72df2841a52eaabdade7a6e
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3c06f2b0933c07d086ecbafa324dbd096ee3035d511f97f783fda00a4bcd1e
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a659f929d5bef48b1dac5c4f52f4cb8ede9a61128b45e715ca3a9eb47ecfce
+size 1465

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_global_step": 1470,
+  "best_metric": 0.8774819661990341,
+  "best_model_checkpoint": "evaluation_results/student_run_20250723_144346/checkpoint-1470",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1470,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8571598666454993,
+      "eval_f1_fix": 0.9995735277013144,
+      "eval_f1_issue": 0.8336147671809581,
+      "eval_f1_macro": 0.8689133107206232,
+      "eval_f1_symptom": 0.773551637279597,
+      "eval_f1_weighted": 0.8591167612530499,
+      "eval_loss": 0.2723788321018219,
+      "eval_precision_fix": 0.9991474190048054,
+      "eval_precision_issue": 0.9030722197163333,
+      "eval_precision_macro": 0.8675605064388172,
+      "eval_precision_symptom": 0.7004618805953128,
+      "eval_recall_fix": 1.0,
+      "eval_recall_issue": 0.7740785290832546,
+      "eval_recall_macro": 0.879250015682372,
+      "eval_recall_symptom": 0.8636715179638613,
+      "eval_runtime": 18.9953,
+      "eval_samples_per_second": 2652.87,
+      "eval_steps_per_second": 3.317,
+      "step": 294
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 1.3646109104156494,
+      "learning_rate": 8.302721088435374e-06,
+      "loss": 0.329,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8634108588664867,
+      "eval_f1_fix": 0.9996510410608351,
+      "eval_f1_issue": 0.8428649735063036,
+      "eval_f1_macro": 0.8740543037652156,
+      "eval_f1_symptom": 0.7796468967285078,
+      "eval_f1_weighted": 0.8651299856279673,
+      "eval_loss": 0.268380343914032,
+      "eval_precision_fix": 0.9993023255813953,
+      "eval_precision_issue": 0.8998341948697942,
+      "eval_precision_macro": 0.871791140476155,
+      "eval_precision_symptom": 0.7162369009772754,
+      "eval_recall_fix": 1.0,
+      "eval_recall_issue": 0.7926797834865539,
+      "eval_recall_macro": 0.8826849600536515,
+      "eval_recall_symptom": 0.8553750966744006,
+      "eval_runtime": 18.9955,
+      "eval_samples_per_second": 2652.837,
+      "eval_steps_per_second": 3.317,
+      "step": 588
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8558699793618034,
+      "eval_f1_fix": 0.9998061038507775,
+      "eval_f1_issue": 0.8292579704692937,
+      "eval_f1_macro": 0.8684898113127071,
+      "eval_f1_symptom": 0.7764053596180502,
+      "eval_f1_weighted": 0.8579691409583291,
+      "eval_loss": 0.2672291696071625,
+      "eval_precision_fix": 0.9996122828784119,
+      "eval_precision_issue": 0.9159135763997092,
+      "eval_precision_macro": 0.8688013508195644,
+      "eval_precision_symptom": 0.6908781931805723,
+      "eval_recall_fix": 1.0,
+      "eval_recall_issue": 0.7575822665177421,
+      "eval_recall_macro": 0.8812274151417152,
+      "eval_recall_symptom": 0.8860999789074036,
+      "eval_runtime": 18.9615,
+      "eval_samples_per_second": 2657.598,
+      "eval_steps_per_second": 3.323,
+      "step": 882
+    },
+    {
+      "epoch": 3.4013605442176873,
+      "grad_norm": 0.9915511012077332,
+      "learning_rate": 6.6020408163265315e-06,
+      "loss": 0.2619,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8678956977297984,
+      "eval_f1_fix": 0.9998448770650741,
+      "eval_f1_issue": 0.8510438343290595,
+      "eval_f1_macro": 0.8771228228486488,
+      "eval_f1_symptom": 0.7804797571518131,
+      "eval_f1_weighted": 0.8691927740857269,
+      "eval_loss": 0.2652249336242676,
+      "eval_precision_fix": 0.9996898022489337,
+      "eval_precision_issue": 0.8881053565590996,
+      "eval_precision_macro": 0.8743740639614609,
+      "eval_precision_symptom": 0.7353270330763492,
+      "eval_recall_fix": 1.0,
+      "eval_recall_issue": 0.816951628146748,
+      "eval_recall_macro": 0.8828306969258993,
+      "eval_recall_symptom": 0.8315404626309498,
+      "eval_runtime": 18.9531,
+      "eval_samples_per_second": 2658.775,
+      "eval_steps_per_second": 3.324,
+      "step": 1176
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8690069852357517,
+      "eval_f1_fix": 0.9997673336435552,
+      "eval_f1_issue": 0.8539430291494212,
+      "eval_f1_macro": 0.8774819661990341,
+      "eval_f1_symptom": 0.7787355358041255,
+      "eval_f1_weighted": 0.8700198852254597,
+      "eval_loss": 0.26798591017723083,
+      "eval_precision_fix": 0.9995347755291928,
+      "eval_precision_issue": 0.880746929644341,
+      "eval_precision_macro": 0.8749433971922725,
+      "eval_precision_symptom": 0.7445484864032837,
+      "eval_recall_fix": 1.0,
+      "eval_recall_issue": 0.8287223988315148,
+      "eval_recall_macro": 0.8816451915578204,
+      "eval_recall_symptom": 0.8162131758419462,
+      "eval_runtime": 18.9943,
+      "eval_samples_per_second": 2653.007,
+      "eval_steps_per_second": 3.317,
+      "step": 1470
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2940,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.415587132761702e+16,
+  "train_batch_size": 200,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e04e7c6cd8b7cabaa2e567850d37ef7eb7d0dcde87c644beb279706b404e55
+size 5841