Training in progress, step 50000

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: gpt2
 datasets:
-- distily/c4_multilingual_1M
+- distily/synth_gpt2_t1_seq_1M
 library_name: Distily
 license: creativeml-openrail-m
 tags:
@@ -18,7 +18,7 @@ model-index:
 
 Distilled with [Distily](https://github.com/lapp0/distily) library
 using teacher model [gpt2](https://huggingface.co/gpt2)
-on dataset [distily/c4_multilingual_1M](https://huggingface.co/datasets/distily/c4_multilingual_1M).
+on dataset [distily/synth_gpt2_t1_seq_1M](https://huggingface.co/datasets/distily/synth_gpt2_t1_seq_1M).
 
 <!-- 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.
@@ -79,12 +79,12 @@ GPT2LMHeadModel(
 # Resource Usage
 
 - Max Train VRAM Use: 15.7135 GB
-- Available VRAM: 23.6497 GB
+- Available VRAM: 23.4329 GB
 - GPUs: 
   - 1x NVIDIA GeForce RTX 4090
-- CPUs: 28
-- CPU Memory: 62.6429 GB
-- CPU Memory Bandwidth: 700 GB/s
+- CPUs: 64
+- CPU Memory: 251.7299 GB
+- CPU Memory Bandwidth: 1600 GB/s
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -115,7 +115,7 @@ GPT2LMHeadModel(
 <br/>
 
 # Train Dataset
-Trained on 448,494,678 tokens from the [distily/c4_multilingual_1M](https://huggingface.co/datasets/distily/c4_multilingual_1M) dataset.
+Trained on 681,027,436 tokens from the [distily/synth_gpt2_t1_seq_1M](https://huggingface.co/datasets/distily/synth_gpt2_t1_seq_1M) dataset.
 
 - Num Samples: `998,000`
 - Subset: `None`
@@ -172,7 +172,7 @@ The following hyperparameters were used during training:
         projector='orthogonal'
     )
 )`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f5a6ef93eb0>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7a7afdb74e80>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`
@@ -182,13 +182,13 @@ The following hyperparameters were used during training:
 - teacher_model_name_or_path: `gpt2`
 - teacher_load_in_8bit: `False`
 - teacher_load_in_4bit: `False`
-- dataset_uri: `distily/c4_multilingual_1M`
+- dataset_uri: `distily/synth_gpt2_t1_seq_1M`
 - dataset_subset: `None`
 - dataset_split: `train`
 - dataset_column_name: `text`
 - dataset_sample_size: `1000000`
 - dataset_test_size: `0.002`
-- dataset_shuffle: `False`
+- dataset_shuffle: `True`
 - dataset_shuffle_seed: `42`
 - gradient_accumulation_steps: `1`
 - weight_decay: `0.0`

logs/dataset_shuffle=True, dataset_split=train, dataset_subset=None, dataset_uri=distily_filtered_redpajama_multilingual, lr_scheduler_kwargs=None, lr_scheduler_type=constant/events.out.tfevents.1725781824.b57c76173204

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94b1a0d5f44bc2cfd1573bcc7cd2aa2f55ab658c8774fecc3290237b32014f7
-size 1436324
+oid sha256:00d05dccf8f5ba5aa4048965f2f09377dc241267ab4585f663bd9016764c0e4b
+size 1596619

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be71e4e82c538387bc593ea6422ca0f5865ebe8510d14f4faf36079bc6878314
+oid sha256:a1a292cdeff20913a9e61397f7e618e7519c47cb9bf60bbc8759459422b0bfaa
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389128090549d767e1ec04c936f05094ed97b08c4bc5a59e39a861b902387d21
-size 5496
+oid sha256:df27e837bc207577c331df3b67b7c8b3301c875f04f12f54132150840661b885
+size 5560