Upload folder using huggingface_hub

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35cdd2ef13a9452bbc36b963a7fa4ae1c8adc6dbbb0903d837a133e9d041038e
+size 1740304440

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d46329e34f4dee8bafa2e791b4f9672a70b59baaced43685f6f95bce4be70b
+size 3480840641

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd72f92feb53e84a26bcfb4914f8c5f37fe8e27c0d6233855819fd95270ed70
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e218b878c3f990decf02bd12f688b6e3253ec09d4838575116756e5574e8cde3
+size 1465

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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": 512,
+  "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 +1,108 @@
+{
+  "best_global_step": 1365,
+  "best_metric": 0.8920863309352518,
+  "best_model_checkpoint": "evaluation_results/student_run_20250630_205323/checkpoint-1365",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1365,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8878048780487805,
+      "eval_f1": 0.8570026178010471,
+      "eval_loss": 0.2749616503715515,
+      "eval_precision": 0.9056016597510373,
+      "eval_recall": 0.8133540372670808,
+      "eval_runtime": 99.4939,
+      "eval_samples_per_second": 78.296,
+      "eval_steps_per_second": 9.79,
+      "step": 273
+    },
+    {
+      "epoch": 1.8315018315018317,
+      "grad_norm": 2.6613881587982178,
+      "learning_rate": 8.172161172161172e-06,
+      "loss": 0.2475,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9003851091142491,
+      "eval_f1": 0.8750402576489533,
+      "eval_loss": 0.2577052414417267,
+      "eval_precision": 0.908695652173913,
+      "eval_recall": 0.8437888198757764,
+      "eval_runtime": 105.9957,
+      "eval_samples_per_second": 73.494,
+      "eval_steps_per_second": 9.189,
+      "step": 546
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.902824133504493,
+      "eval_f1": 0.885320405999091,
+      "eval_loss": 0.2662721276283264,
+      "eval_precision": 0.8642413487133984,
+      "eval_recall": 0.9074534161490683,
+      "eval_runtime": 110.1943,
+      "eval_samples_per_second": 70.693,
+      "eval_steps_per_second": 8.839,
+      "step": 819
+    },
+    {
+      "epoch": 3.663003663003663,
+      "grad_norm": 2.496551990509033,
+      "learning_rate": 6.340659340659341e-06,
+      "loss": 0.1213,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9061617458279846,
+      "eval_f1": 0.8839498333068742,
+      "eval_loss": 0.2616208493709564,
+      "eval_precision": 0.9041896719714193,
+      "eval_recall": 0.8645962732919255,
+      "eval_runtime": 103.6645,
+      "eval_samples_per_second": 75.146,
+      "eval_steps_per_second": 9.396,
+      "step": 1092
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9114249037227214,
+      "eval_f1": 0.8920863309352518,
+      "eval_loss": 0.29260820150375366,
+      "eval_precision": 0.8985507246376812,
+      "eval_recall": 0.8857142857142857,
+      "eval_runtime": 109.3416,
+      "eval_samples_per_second": 71.245,
+      "eval_steps_per_second": 8.908,
+      "step": 1365
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "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": 3.168704518472448e+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 sha256:6394defc3ecb337d9b9b5220dfd42d079c49a0e5f9044344eaf2b164b819e3c1
+size 5777