diff --git "a/.gitattributes" "b/.gitattributes"
deleted file mode 100644--- "a/.gitattributes"
+++ /dev/null
@@ -1,1506 +0,0 @@
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_0/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_10000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_10000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_10000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_10000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_12000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_12000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_12000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_12000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_12000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_14000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_14000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_14000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_14000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_14000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_16000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_16000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_16000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_16000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_16000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_18000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_18000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_18000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_18000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_18000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_2000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_20000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_20000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_20000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_20000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_20000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_22000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_22000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_22000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_22000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_22000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_24000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_24000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_24000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_24000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_24000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_26000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_26000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_26000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_26000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_26000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_28000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_28000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_28000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_28000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_28000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_30000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_30000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_30000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_30000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_30000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_32000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_32000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_32000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_32000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_32000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_34000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_34000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_34000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_34000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_34000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_36000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_36000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_36000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_36000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_36000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_38000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_38000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_38000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_38000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_38000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_4000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_40000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_40000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_40000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_40000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_40000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_42000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_42000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_42000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_42000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_42000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_44000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_44000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_44000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_44000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_44000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_46000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_46000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_46000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_46000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_46000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_6000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_8000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_48000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_48000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_48000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_48000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_48000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_50000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_50000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_50000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_50000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_50000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_52000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_52000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_52000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_52000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_52000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_54000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_54000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_54000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_54000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_54000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_56000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_56000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_56000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_56000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_56000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_58000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_58000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_58000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_58000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_58000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_60000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_60000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_60000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_60000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_60000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_62000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_62000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_62000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_62000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_62000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_64000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_64000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_64000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_64000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_64000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_66000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_66000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_66000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_66000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_66000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_68000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_68000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_68000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_68000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_68000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_0/learning_dynamics/train_activations.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_0/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_27/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v0/checkpoints/step_27/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_1000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_1000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_1000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_1000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_1755/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma-teensy-v1/checkpoints/step_1755/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_1000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_1000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_1000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_1000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_3000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_3000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_3000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_3000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_5000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_5000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_5000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_7000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_7000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_7000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_7000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_9000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_9000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_9000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v1/checkpoints/step_9000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_0/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_1000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_1000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_1000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_1000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_1000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_2000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_3000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_3000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_3000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_3000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_3000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_4000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_5000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_5000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_5000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_5000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v2/checkpoints/step_5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_10500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_11500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_12500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_13500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_14500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_1500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_15500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_16500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_17500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_18500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_19500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_20000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_20000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_3500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_4500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_5500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_6500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_7500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_8500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma29k-v3/checkpoints/step_9500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_100000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_100000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_10500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_11500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_12500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_13500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_14500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_1500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_15500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_16500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_17500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_18500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_19500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_20500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_21500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_22500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_23500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_24500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_25500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_26500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_27500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_28500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_29500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_30500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_31500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_32500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_33500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_34500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_3500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_35500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_36500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_37500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_38500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_39500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_40500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_41500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_42500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_43500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_44500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_4500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_45500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_46500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_47500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_48500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_49500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_50500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_51500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_52500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_53500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_54500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_5500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_55500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_56500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_57500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_58500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_59500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_60500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_61500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_62500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_63500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_64500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_6500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_65500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_66500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_67500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_68500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_69500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_70500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_71500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_72500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_73500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_74500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_7500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_75500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_76500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_77500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_78500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_79500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_80500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_81500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_82500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_83500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_84500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_8500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_85500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_86500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_87500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_88500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_89500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_90500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_91500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_92500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_93500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_94500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_9500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_95500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_96500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_97500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_98500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99500/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99500/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99500/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma5M-v1/checkpoints/step_99500/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_100000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_100000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_70000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_70000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_70000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_70000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_70000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_72000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_72000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_72000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_72000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_72000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_74000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_74000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_74000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_74000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_74000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_76000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_76000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_76000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_76000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_76000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_78000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_78000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_78000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_78000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_78000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_80000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_80000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_80000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_80000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_80000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_82000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_82000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_82000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_82000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_82000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_84000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_84000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_84000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_84000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_84000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_86000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_86000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_86000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_86000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_86000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_88000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_88000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_88000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_88000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_88000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_90000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_90000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_90000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_90000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_90000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_92000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_92000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_92000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_92000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_92000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_94000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_94000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_94000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_94000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_94000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_96000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_96000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_96000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_96000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_96000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_98000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_98000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_98000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_98000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-dolma10M-v1/checkpoints/step_98000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_10000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_10000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_10000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_100000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_100000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_12000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_12000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_12000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_12000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_14000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_14000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_14000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_14000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_16000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_16000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_16000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_16000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_18000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_18000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_18000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_18000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_20000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_20000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_20000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_20000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_22000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_22000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_22000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_22000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_24000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_24000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_24000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_24000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_26000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_26000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_26000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_26000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_28000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_28000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_28000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_28000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_30000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_30000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_30000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_30000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_32000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_32000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_32000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_32000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_34000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_34000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_34000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_34000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_36000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_36000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_36000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_36000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_38000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_38000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_38000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_38000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_40000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_40000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_40000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_40000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_42000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_42000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_42000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_42000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_44000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_44000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_44000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_44000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_46000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_46000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_46000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_46000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_48000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_48000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_48000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_48000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_50000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_50000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_50000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_50000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_52000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_52000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_52000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_52000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_54000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_54000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_54000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_54000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_56000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_56000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_56000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_56000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_58000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_58000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_58000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_58000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_60000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_60000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_60000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_60000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_62000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_62000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_62000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_62000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_64000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_64000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_64000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_64000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_66000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_66000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_66000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_66000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_68000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_68000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_68000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_68000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_70000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_70000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_70000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_70000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_72000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_72000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_72000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_72000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_74000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_74000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_74000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_74000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_76000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_76000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_76000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_76000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_78000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_78000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_78000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_78000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_80000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_80000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_80000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_80000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_82000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_82000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_82000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_82000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_84000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_84000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_84000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_84000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_86000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_86000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_86000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_86000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_88000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_88000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_88000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_88000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_90000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_90000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_90000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_90000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_92000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_92000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_92000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_92000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_94000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_94000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_94000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_94000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_96000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_96000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_96000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_96000/model.safetensors filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_98000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_98000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_98000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text
-pico-decoder-tiny-wikipedia_en-v1/checkpoints/step_98000/model.safetensors filter=lfs diff=lfs merge=lfs -text