| pico-decoder-tiny-dolma20M-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_0/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_1000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_1000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_1000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_1000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_1000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_10000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_10000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_10000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_10000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_10000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_11000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_11000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_11000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_11000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_11000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_12000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_12000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_12000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_12000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_12000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_13000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_13000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_13000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_13000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_13000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_14000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_14000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_14000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_14000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_14000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_15000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_15000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_15000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_15000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_15000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_16000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_16000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_16000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_16000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_16000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_17000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_17000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_17000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_17000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_17000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_18000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_18000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_18000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_18000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_18000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_19000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_19000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_19000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_19000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_19000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_2000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_20000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_20000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_20000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_20000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_20000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_21000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_21000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_21000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_21000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_21000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_22000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_22000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_22000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_22000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_22000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_23000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_23000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_23000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_23000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_23000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_24000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_24000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_24000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_24000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_24000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_25000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_25000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_25000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_25000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_25000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_26000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_26000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_26000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_26000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_26000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_27000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_27000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_27000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_27000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_27000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_28000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_28000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_28000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_28000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_28000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_29000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_29000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_29000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_29000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_29000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_3000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_3000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_3000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_3000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_3000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_30000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_30000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_30000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_30000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_30000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_31000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_31000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_31000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_31000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_31000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_32000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_32000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_32000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_32000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_32000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_33000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_33000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_33000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_33000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_33000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_34000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_34000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_34000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_34000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_34000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_35000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_35000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_35000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_35000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_35000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_36000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_36000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_36000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_36000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_36000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_37000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_37000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_37000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_37000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_37000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_38000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_38000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_38000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_38000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_38000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_39000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_39000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_39000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_39000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_39000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_4000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_40000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_40000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_40000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_40000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_40000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_41000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_41000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_41000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_41000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_41000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_42000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_42000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_42000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_42000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_42000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_43000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_43000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_43000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_43000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_43000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_44000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_44000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_44000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_44000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_44000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_45000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_45000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_45000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_45000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_45000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_46000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_46000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_46000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_46000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_46000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_47000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_47000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_47000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_47000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_47000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_48000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_48000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_48000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_48000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_48000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_49000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_49000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_49000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_49000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_49000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_5000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_5000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_5000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_5000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_5000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_50000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_50000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_50000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_50000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_50000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_51000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_51000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_51000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_51000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_51000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_52000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_52000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_52000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_52000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_52000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_53000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_53000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_53000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_53000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_53000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_54000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_54000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_54000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_54000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_54000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_55000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_55000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_55000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_55000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_55000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_56000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_56000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_56000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_56000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_56000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_57000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_57000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_57000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_57000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_57000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_58000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_58000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_58000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_58000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_58000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_59000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_59000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_59000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_59000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_59000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_6000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_60000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_60000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_60000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_60000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_60000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_61000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_61000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_61000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_61000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_61000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_62000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_62000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_62000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_62000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_62000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_63000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_63000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_63000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_63000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_63000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_64000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_64000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_64000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_64000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_64000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_65000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_65000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_65000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_65000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_65000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_66000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_66000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_66000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_66000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_66000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_67000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_67000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_67000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_67000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_67000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_68000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_68000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_68000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_68000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_68000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_69000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_69000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_69000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_69000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_69000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_7000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_7000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_7000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_7000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_7000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_70000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_70000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_70000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_70000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_70000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_71000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_71000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_71000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_71000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_71000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_72000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_72000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_72000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_72000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_72000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_73000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_73000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_73000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_73000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_73000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_74000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_74000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_74000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_74000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_74000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_75000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_75000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_75000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_75000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_75000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_76000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_76000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_76000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_76000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_76000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_77000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_77000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_77000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_77000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_77000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_78000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_78000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_78000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_78000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_78000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_79000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_79000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_79000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_79000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_79000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_8000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_80000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_80000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_80000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_80000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_80000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_81000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_81000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_81000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_81000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_81000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_82000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_82000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_82000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_82000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_82000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_83000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_83000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_83000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_83000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_83000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_84000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_84000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_84000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_84000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_84000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_85000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_85000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_85000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_85000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_85000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_86000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_86000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_86000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_86000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_86000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_87000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_87000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_87000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_87000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_87000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_88000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_88000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_88000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_88000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_88000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_89000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_89000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_89000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_89000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_89000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_9000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_9000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_9000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_9000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_9000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_90000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_90000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_90000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_90000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_90000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_91000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_91000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_91000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_91000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_91000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_92000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_92000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_92000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_92000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_92000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_93000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_93000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_93000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_93000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_93000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_94000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_94000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_94000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_94000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_94000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_95000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_95000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_95000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_95000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma20M-v1/checkpoints/step_95000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| 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_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_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_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_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_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-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_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_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-dolma250M-v1/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_0/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_0/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_0/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_10000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_10000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_10000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_10000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_10000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_100000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_100000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_12000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_12000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_12000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_12000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_12000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_14000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_14000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_14000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_14000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_14000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_16000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_16000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_16000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_16000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_16000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_18000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_18000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_18000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_18000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_18000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_2000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_2000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_2000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_2000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_2000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_20000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_20000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_20000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_20000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_20000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_22000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_22000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_22000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_22000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_22000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_24000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_24000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_24000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_24000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_24000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_26000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_26000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_26000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_26000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_26000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_28000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_28000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_28000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_28000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_28000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_30000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_30000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_30000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_30000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_30000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_32000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_32000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_32000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_32000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_32000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_34000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_34000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_34000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_34000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_34000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_36000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_36000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_36000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_36000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_36000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_38000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_38000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_38000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_38000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_38000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_4000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_4000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_4000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_4000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_4000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_40000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_40000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_40000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_40000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_40000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_42000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_42000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_42000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_42000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_42000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_44000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_44000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_44000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_44000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_44000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_46000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_46000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_46000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_46000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_46000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_48000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_48000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_48000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_48000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_48000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_50000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_50000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_50000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_50000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_50000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_52000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_52000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_52000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_52000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_52000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_54000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_54000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_54000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_54000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_54000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_56000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_56000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_56000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_56000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_56000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_58000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_58000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_58000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_58000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_58000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_6000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_6000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_6000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_6000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_6000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_60000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_60000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_60000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_60000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_60000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_62000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_62000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_62000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_62000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_62000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_64000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_64000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_64000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_64000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_64000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_66000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_66000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_66000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_66000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_66000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_68000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_68000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_68000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_68000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_68000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_70000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_70000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_70000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_70000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_70000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_72000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_72000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_72000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_72000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_72000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_74000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_74000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_74000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_74000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_74000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_76000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_76000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_76000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_76000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_76000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_78000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_78000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_78000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_78000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_78000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_8000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_8000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_8000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_8000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_8000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_80000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_80000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_80000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_80000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_80000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_82000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_82000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_82000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_82000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_82000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_84000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_84000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_84000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_84000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_84000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_86000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_86000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_86000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_86000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_86000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_88000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_88000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_88000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_88000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_88000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_90000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_90000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_90000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_90000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_90000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_92000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_92000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_92000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_92000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_92000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_94000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_94000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_94000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_94000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_94000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_96000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_96000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_96000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_96000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_96000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_98000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_98000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_98000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_98000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_98000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_100000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_100000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_100000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_102000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_102000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_102000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_102000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_102000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_104000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_104000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_104000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_104000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_104000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_106000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_106000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_106000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_106000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_106000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_108000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_108000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_108000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_108000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_108000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_110000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_110000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_110000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_110000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_110000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_112000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_112000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_112000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_112000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_112000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_114000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_114000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_114000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_114000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_114000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_116000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_116000/learning_dynamics/train_data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_116000/learning_dynamics/train_gradients.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_116000/learning_dynamics/train_weights.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_116000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_118000/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| pico-decoder-tiny-dolma250M-v1/checkpoints/step_118000/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| tiny-dolma205M-v2/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| tiny-dolma205M-v2/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text | |
| tiny-dolma205M-v3/checkpoints/step_0/fabric_state/checkpoint.pt filter=lfs diff=lfs merge=lfs -text | |
| tiny-dolma205M-v3/checkpoints/step_0/model.safetensors filter=lfs diff=lfs merge=lfs -text | |