get ready for training: pretrain.sh and run_clm_flax.py

Deleted wandb direcotry

fix git lfs tracking

Saving weights and logs of step 77000

Saving weights and logs of step 70000

Saving weights and logs of step 63000

Saving weights and logs of step 56000

Saving weights and logs of step 49000

Saving weights and logs of step 42000

Saving weights and logs of step 35000

Saving weights and logs of step 28000

Saving weights and logs of step 21000

Saving weights and logs of step 14000

Saving weights and logs of step 7000

Saving weights and logs of step 49000

Saving weights and logs of step 42000

Saving weights and logs of step 35000

Saving weights and logs of step 28000

Saving weights and logs of step 21000

Saving weights and logs of step 14000

Saving weights and logs of step 7000

Saving weights and logs of step 7000

Saving weights and logs of step 3500

Saving weights and logs of step 10

Saving weights and logs of step 10

manual push

Investigate slow training issue

convert to pytorch epoch 1

Saving weights and logs of epoch 1

convert to pytorch

Saving weights and logs of epoch 8

Saving weights and logs of epoch 7

Saving weights and logs of epoch 6

Saving weights and logs of epoch 5

Saving weights and logs of epoch 4

Saving weights and logs of epoch 3

Saving weights and logs of epoch 2

Saving weights and logs of epoch 1

Saving weights and logs of epoch 5

Saving weights and logs of epoch 4

Saving weights and logs of epoch 3

Saving weights and logs of epoch 2

Saving weights and logs of epoch 1

Saving weights and logs of epoch 1

Add config.json for gpt2

Add tokenizer file for oscar dataset - unshuffled_deduplicated_pl

Add config, tokenizer and pretrain scripts

Create README.md

initial commit