Upload python KD Optuna tinyBERT checkpoint

checkpoints/python/config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "Usage",
+    "1": "Parameters",
+    "2": "DevelopmentNotes",
+    "3": "Expand",
+    "4": "Summary"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "label2id": {
+    "DevelopmentNotes": 2,
+    "Expand": 3,
+    "Parameters": 1,
+    "Summary": 4,
+    "Usage": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "problem_type": "multi_label_classification",
+  "structure": [],
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoints/python/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50ac57d20c88ba7b10194c7e4218f093a31ccd6230f6e794d076f4e47dd3fae
+size 57415564

checkpoints/python/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoints/python/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/python/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8cfbe6bb7cdeb438d7ec3635776340a0429ee5fc17971aa6dc4c03a5b08c80
+size 5969

checkpoints/python/trial_config.json

@@ -0,0 +1,7 @@
+{
+  "lr": 5.438112213347008e-05,
+  "batch_size": 32,
+  "epochs": 29,
+  "temperature": 4.205525533969048,
+  "lambda_hard": 0.09480329121907696
+}

checkpoints/python/trial_metrics.json

@@ -0,0 +1,23 @@
+{
+  "eval_loss": 11.148098945617676,
+  "eval_macro_f1": 0.5715151384722987,
+  "eval_micro_f1": 0.6088328075709779,
+  "eval_macro_precision": 0.6012552083209208,
+  "eval_macro_recall": 0.560784432940894,
+  "eval_thresholds": {
+    "Usage": 0.44000000000000006,
+    "Parameters": 0.5000000000000001,
+    "DevelopmentNotes": 0.44000000000000006,
+    "Expand": 0.4,
+    "Summary": 0.4800000000000001
+  },
+  "eval_f1_Usage": 0.6703296703296703,
+  "eval_f1_Parameters": 0.7209302325581395,
+  "eval_f1_DevelopmentNotes": 0.44,
+  "eval_f1_Expand": 0.5,
+  "eval_f1_Summary": 0.5263157894736842,
+  "eval_runtime": 0.2264,
+  "eval_samples_per_second": 1280.743,
+  "eval_steps_per_second": 44.164,
+  "epoch": 29.0
+}