-
RxT-Beta 3B A190M Interaction SFT v1.5.0
-
Epoch 0 - Val loss 3.3566
-
In progress training - batch: 31250
-
In progress training - batch: 28672
-
In progress training - batch: 24576
-
In progress training - batch: 20480
-
In progress training - batch: 16384
-
In progress training - batch: 12288
-
In progress training - batch: 8192
-
In progress training - batch: 4096
-
RxT-Beta 3B A190M Interaction SFT v1.4.0
-
Epoch 0 - Val loss 3.3440
-
In progress training - batch: 78125
-
In progress training - batch: 77824
-
In progress training - batch: 73728
-
In progress training - batch: 69632
-
In progress training - batch: 65536
-
In progress training - batch: 61440
-
In progress training - batch: 57344
-
In progress training - batch: 53248
-
In progress training - batch: 49152
-
In progress training - batch: 45056
-
In progress training - batch: 40960
-
In progress training - batch: 36864
-
In progress training - batch: 32768
-
In progress training - batch: 28672
-
In progress training - batch: 24576
-
In progress training - batch: 20480
-
In progress training - batch: 16384
-
In progress training - batch: 12288
-
In progress training - batch: 8192
-
In progress training - batch: 4096
-
In progress training - batch: 65536
-
In progress training - batch: 57344
-
In progress training - batch: 49152
-
In progress training - batch: 40960
-
In progress training - batch: 32768
-
In progress training - batch: 24576
-
In progress training - batch: 16384
-
In progress training - batch: 8192
-
Update config.json
-
Push model using huggingface_hub.
-
In progress training - batch: 40960
-
In progress training - batch: 32768
-
In progress training - batch: 24576
-
In progress training - batch: 16384
-
In progress training - batch: 8192
-
RxT-Beta 3B A190M Interaction SFT v1.1.0
-
Epoch 0 - Val loss 1.6248
-
In progress training - batch: 46875