Upload folder using huggingface_hub

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2e7eb7215f53fd9019e80b0b3a9f6f88c4be5cad91c8fba21bfff29b927a67
+size 327657928

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_config.json

@@ -0,0 +1,33 @@
+{
+  "teacher_model": "gpt2-large",
+  "student_model": "distilgpt2",
+  "tokenizer_model": "gpt2",
+  "batch_size": 4,
+  "max_length": 256,
+  "num_epochs": 1,
+  "learning_rate": 5e-05,
+  "distillation_alpha": 0.7,
+  "student_lm_beta": 0.3,
+  "dataset_file": "/home/jayanthram.k/Distillation/clean_dataset_with_no_outliers.csv",
+  "train_samples": 43572,
+  "val_samples": 4842,
+  "eval_samples": 100,
+  "best_validation_loss": 2.3524647863515638,
+  "evaluation_metrics": {
+    "rouge1_teacher_student_before": 0.32189833105454313,
+    "rouge2_teacher_student_before": 0.07253675599508494,
+    "rougeL_teacher_student_before": 0.19562937213425652,
+    "cosine_similarity_teacher_student_before": 0.44240760803222656,
+    "rouge1_teacher_student_after": 0.3346180933711459,
+    "rouge2_teacher_student_after": 0.08527329173516719,
+    "rougeL_teacher_student_after": 0.20919089238473532,
+    "cosine_similarity_teacher_student_after": 0.5256437659263611,
+    "rouge1_student_before_student_after": 0.3137800181943293,
+    "rouge2_student_before_student_after": 0.07712439299277635,
+    "rougeL_student_before_student_after": 0.18683832802096778,
+    "cosine_similarity_student_before_student_after": 0.4463849663734436,
+    "avg_teacher_time": 1.2837520718574524,
+    "avg_student_before_time": 0.4636122870445252,
+    "avg_student_after_time": 0.46685707569122314
+  }
+}