End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+benchmarks.shelve.dat filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,158 @@
+---
+base_model: gpt2
+datasets:
+- wikimedia/wikipedia
+library_name: Distily
+license: mit
+tags:
+- bitnet
+- 1.58b
+- generated_from_trainer
+model-index:
+- name: distily_multi_attn_experiment_ortho
+  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**: 124,439,808
+- **Data Type (dtype)**: torch.bfloat16
+- **Model Size**: 0.24 GB
+
+
+# Benchmark Metrics Comparison
+
+| Metric | attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal, attn_weight=25.0 | teacher |
+| :--- | :--- | :--- |
+| ai2_arc (acc) | 0.305 | 0.354 |
+| ai2_arc (acc_norm) | 0.302 | 0.339 |
+| arc_challenge (acc) | 0.173 | 0.188 |
+| arc_challenge (acc_norm) | 0.223 | 0.222 |
+| arc_easy (acc) | 0.37 | 0.436 |
+| arc_easy (acc_norm) | 0.34 | 0.396 |
+| boolq (acc) | 0.387 | 0.51 |
+| cola (mcc) | 0.044 | 0.01 |
+| glue (acc) | 0.412 | 0.403 |
+| glue (f1) | 0.451 | 0.529 |
+| glue (mcc) | 0.044 | 0.01 |
+| hellaswag (acc) | 0.315 | 0.343 |
+| hellaswag (acc_norm) | 0.344 | 0.393 |
+| mnli (acc) | 0.338 | 0.338 |
+| mnli_mismatch (acc) | 0.351 | 0.346 |
+| mrpc (acc) | 0.353 | 0.515 |
+| mrpc (f1) | 0.143 | 0.631 |
+| qnli (acc) | 0.497 | 0.491 |
+| qqp (acc) | 0.406 | 0.367 |
+| qqp (f1) | 0.501 | 0.512 |
+| rte (acc) | 0.549 | 0.516 |
+| sst2 (acc) | 0.545 | 0.511 |
+| wikitext (bits_per_byte) | 1.127 | 0.98 |
+| wikitext (byte_perplexity) | 2.184 | 1.973 |
+| wikitext (word_perplexity) | 65.25 | 37.82 |
+| wnli (acc) | 0.451 | 0.451 |
+
+# Resource Usage Comparison
+
+- VRAM Use: 7.7830 GB
+
+# Distillation (Teacher -> Student) Architecture Difference:
+
+- **Architecture**: `GPT2LMHeadModel` -> `GPT2LMHeadModel`
+- **Total Parameters**: 124,439,808 -> 124,439,808
+- **Data Type (dtype)**: torch.bfloat16 -> torch.bfloat16
+- **Model Size**: 0.24 GB -> 0.24 GB
+
+<details>
+<summary>Module Diff Details</summary>
+
+```diff
+
+```
+
+</details>
+<br/>
+
+# Train Dataset
+Trained on 145,724,804 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+
+- Num Samples: `247,500`
+- Subset: `20231101.en`
+- Split: `train`
+
+
+# Training Objective
+
+```
+DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=25.0, loss_fn=raw_mse, layer_mapper=layer-2))
+```
+
+# Hyperparameters
+The following hyperparameters were used during training:
+
+<details>
+<summary>Expand</summary>
+
+- learning_rate: `0.0001`
+- train_batch_size: `4`
+- eval_batch_size: `8`
+- seed: `42`
+- optimizer: `Adam with betas=(0.9,0.999) and epsilon=1e-08`
+- lr_scheduler_type: `cosine_with_min_lr`
+- lr_scheduler_warmup_ratio: `0.5`
+- num_epochs: `1.0`
+- distillation_objective: `DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=25.0, loss_fn=raw_mse, layer_mapper=layer-2))`
+- train_embeddings: `True`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f0d1223cb50>`
+- student_model_name_or_path: `None`
+- student_config_name_or_path: `None`
+- student_model_config: `None`
+- reinitialize_weights: `None`
+- copy_teacher_modules: `[('lm_head', False)]`
+- student_model_as_bitnet: `True`
+- student_model_compile: `False`
+- dropout: `None`
+- teacher_model_name_or_path: `gpt2`
+- teacher_load_in_8bit: `False`
+- teacher_load_in_4bit: `False`
+- teacher_model_compile: `False`
+- dataset_uri: `wikimedia/wikipedia`
+- dataset_subset: `20231101.en`
+- dataset_split: `train`
+- dataset_column_name: `text`
+- dataset_sample_size: `250000`
+- dataset_test_size: `0.01`
+- gradient_accumulation_steps: `1`
+- weight_decay: `0.0`
+- max_grad_norm: `1.0`
+- warmup_ratio: `0.5`
+- warmup_steps: `0`
+- gradient_checkpointing: `True`
+
+</details>
+<br/>
+
+
+# Framework Versions
+- Distily 0.3.0
+- Transformers 4.44.0
+- Pytorch 2.3.0
+- Datasets 2.21.0

benchmarks.shelve.bak

@@ -0,0 +1,2 @@
+'teacher', (0, 26029753)
+'attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal, attn_weight=25.0', (26030080, 26029753)

benchmarks.shelve.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08da2c1102a7b8635c1aac31997fbdc32e594beca1614e4a38096dec1f9bf07
+size 52059833

benchmarks.shelve.dir

@@ -0,0 +1,2 @@
+'teacher', (0, 26029753)
+'attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal, attn_weight=25.0', (26030080, 26029753)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.44.0"
+}

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1023,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50256,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,