End of training

README.md

@@ -0,0 +1,210 @@
+---
+base_model: gpt2
+datasets:
+- wikimedia/wikipedia
+library_name: Distily
+license: creativeml-openrail-m
+tags:
+- generated_from_trainer
+- Distily
+base_model_relation: finetune
+model-index:
+- name: distily_long_dataset_sweep
+  results: []
+---
+
+
+# Summary
+
+Distilled with [Distily](https://github.com/lapp0/distily) library
+using teacher model [gpt2](https://huggingface.co/gpt2)
+on dataset [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia).
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment.
+
+# Model description
+
+More information needed
+
+# Intended uses & limitations
+
+More information needed
+-->
+
+# Model Architecture:
+- **Architecture**: `GPT2LMHeadModel`
+- **Total Parameters**: 81,912,576
+- **Data Type (dtype)**: torch.bfloat16
+- **Model Size**: 0.16 GB
+
+<details>
+<summary>Student Model Details</summary>
+
+```
+GPT2LMHeadModel(
+  (transformer): GPT2Model(
+    (wte): Embedding(50257, 768)
+    (wpe): Embedding(1024, 768)
+    (drop): Dropout(p=0.1, inplace=False)
+    (h): ModuleList(
+      (0-5): 6 x GPT2Block(
+        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+        (attn): GPT2FlashAttention2(
+          (c_attn): Conv1D()
+          (c_proj): Conv1D()
+          (attn_dropout): Dropout(p=0.1, inplace=False)
+          (resid_dropout): Dropout(p=0.1, inplace=False)
+        )
+        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+        (mlp): GPT2MLP(
+          (c_fc): Conv1D()
+          (c_proj): Conv1D()
+          (act): NewGELUActivation()
+          (dropout): Dropout(p=0.1, inplace=False)
+        )
+      )
+    )
+    (ln_f): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+  )
+  (lm_head): Linear(in_features=768, out_features=50257, bias=False)
+)
+```
+
+</details>
+<br/>
+
+
+
+# Resource Usage
+
+- Max Train VRAM Use: 15.7146 GB
+- Available VRAM: 23.6429 GB
+- GPUs: 
+  - 1x NVIDIA GeForce RTX 4090
+- CPUs: 32
+- CPU Memory: 61.9353 GB
+- CPU Memory Bandwidth: 800 GB/s
+
+# Distillation (Teacher -> Student) Architecture Difference:
+
+- **Architecture**: `GPT2LMHeadModel` -> `GPT2LMHeadModel`
+- **Total Parameters**: 124,439,808 -> 81,912,576
+- **Data Type (dtype)**: torch.bfloat16 -> torch.bfloat16
+- **Model Size**: 0.24 GB -> 0.16 GB
+
+<details>
+<summary>Module Diff Details</summary>
+
+```diff
+--- teacher model modules
++++ student model modules
+@@ -4,7 +4,7 @@
+     (wpe): Embedding(1024, 768)
+     (drop): Dropout(p=0.1, inplace=False)
+     (h): ModuleList(
+-      (0-11): 12 x GPT2Block(
++      (0-5): 6 x GPT2Block(
+         (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+         (attn): GPT2FlashAttention2(
+           (c_attn): Conv1D()
+
+```
+
+</details>
+<br/>
+
+# Train Dataset
+Trained on 1,756,071,327 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+
+- Num Samples: `3,996,000`
+- Subset: `20231101.en`
+- Split: `train`
+
+
+# Training Objective
+
+```
+DistillationObjective(
+    logits_loss_component=LossComponent(
+        weight=1,
+        loss_fn='kl'
+    ),
+    hs_loss_component=LossComponent(
+        weight=0
+    ),
+    attn_loss_component=LossComponent(
+        weight=5.0,
+        loss_fn='raw_mse',
+        layer_mapper='layer-2',
+        norm='layernorm_teacher_only_affine',
+        projector='orthogonal'
+    )
+)
+```
+
+# Hyperparameters
+The following hyperparameters were used during training:
+
+<details>
+<summary>Expand</summary>
+
+- learning_rate: `0.0002`
+- train_batch_size: `16`
+- eval_batch_size: `8`
+- seed: `42`
+- optimizer: `Adam with betas=(0.9,0.999) and epsilon=1e-08`
+- lr_scheduler_type: `constant_with_warmup`
+- num_epochs: `1.0`
+- distillation_objective: `DistillationObjective(
+    logits_loss_component=LossComponent(
+        weight=1,
+        loss_fn='kl'
+    ),
+    hs_loss_component=LossComponent(
+        weight=0
+    ),
+    attn_loss_component=LossComponent(
+        weight=5.0,
+        loss_fn='raw_mse',
+        layer_mapper='layer-2',
+        norm='layernorm_teacher_only_affine',
+        projector='orthogonal'
+    )
+)`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7fbc60ceb9a0>`
+- student_model_name_or_path: `None`
+- student_config_name_or_path: `distilbert/distilgpt2`
+- student_model_config: `None`
+- reinitialize_weights: `None`
+- copy_teacher_modules: `[('lm_head', False)]`
+- student_model_as_bitnet: `False`
+- student_model_use_liger: `True`
+- teacher_model_name_or_path: `gpt2`
+- teacher_load_in_8bit: `False`
+- teacher_load_in_4bit: `False`
+- dataset_uri: `wikimedia/wikipedia`
+- dataset_subset: `20231101.en`
+- dataset_split: `train`
+- dataset_column_name: `text`
+- dataset_sample_size: `4000000`
+- dataset_test_size: `0.001`
+- dataset_shuffle: `False`
+- dataset_shuffle_seed: `42`
+- dataset_trust_remote_code: `False`
+- gradient_accumulation_steps: `1`
+- weight_decay: `0.0`
+- max_grad_norm: `1.0`
+- warmup_ratio: `0`
+- warmup_steps: `0`
+- gradient_checkpointing: `True`
+
+</details>
+<br/>
+
+
+# Framework Versions
+- Distily 0.5.0
+- Transformers 4.44.2
+- Pytorch 2.3.0
+- Datasets 2.21.0

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.44.2"
+}

logs/learning_rate=0.0002, lr_scheduler_type=constant_with_warmup, warmup_ratio=0/events.out.tfevents.1725867271.0b434856d812.32418.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4a5624a7fa2e300bb69dbb9ad89b1d64eda0031292349d4c5cb3d6691862c3
-size 7850056
+oid sha256:63ee9ff0b0551ad932f24bf477554554c87c939040c626d7128c2d05103c4400
+size 8002567

logs/learning_rate=0.0002, lr_scheduler_type=constant_with_warmup, warmup_ratio=0/events.out.tfevents.1725948110.0b434856d812.32418.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32cd42cfc4634c184414096fabec8612291e0fdb3e6884200f80a8d1c147589
+size 577

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1ac8808909d34b1a0402fd7bbdf760bb3320dfe22d965e5f21e6090fe9962d
+oid sha256:595ec17c9e77ee50d918b3870289ca2c639d2d0497c4294b5fcb713ec0b17d52
 size 163832792

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1023,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c3869cd08fda14fe474ce52934eabf7564d13023fb20648af8648c7ce43aa1
-size 5496
+oid sha256:fcf6dcc0cdc2a6669648caee0d06040388b822462cb8287de898a1934a78d13a
+size 5432