Training in progress, step 1750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40488b690d3cbb62aef973e623da597fed2f1f503eac48f0d6e9e0140377208a
+oid sha256:95cb389d8c3bb8b023cd12cb33d7b6158b8a28b87779d6ac67f1897a141b861b
 size 29034840

trainer_log.jsonl

@@ -376,3 +376,14 @@
 {"current_steps": 1695, "total_steps": 3400, "loss": 0.4374, "lr": 5.4371244313677225e-05, "epoch": 0.4365181560648983, "percentage": 49.85, "elapsed_time": "5:40:50", "remaining_time": "5:42:50", "throughput": 870.12, "total_tokens": 17793968}
 {"current_steps": 1700, "total_steps": 3400, "loss": 0.3796, "lr": 5.4128967273616625e-05, "epoch": 0.43780582024208087, "percentage": 50.0, "elapsed_time": "5:42:16", "remaining_time": "5:42:16", "throughput": 868.97, "total_tokens": 17845600}
 {"current_steps": 1700, "total_steps": 3400, "eval_loss": 0.4555380642414093, "epoch": 0.43780582024208087, "percentage": 50.0, "elapsed_time": "5:42:54", "remaining_time": "5:42:54", "throughput": 867.36, "total_tokens": 17845600}
+{"current_steps": 1705, "total_steps": 3400, "loss": 0.4066, "lr": 5.388659258287102e-05, "epoch": 0.43909348441926344, "percentage": 50.15, "elapsed_time": "5:44:27", "remaining_time": "5:42:26", "throughput": 865.98, "total_tokens": 17897920}
+{"current_steps": 1710, "total_steps": 3400, "loss": 0.3599, "lr": 5.364412597363759e-05, "epoch": 0.44038114859644606, "percentage": 50.29, "elapsed_time": "5:45:59", "remaining_time": "5:41:57", "throughput": 864.69, "total_tokens": 17950920}
+{"current_steps": 1715, "total_steps": 3400, "loss": 0.3681, "lr": 5.3401573180287426e-05, "epoch": 0.4416688127736286, "percentage": 50.44, "elapsed_time": "5:47:32", "remaining_time": "5:41:27", "throughput": 863.38, "total_tokens": 18003280}
+{"current_steps": 1720, "total_steps": 3400, "loss": 0.4005, "lr": 5.315893993922986e-05, "epoch": 0.44295647695081125, "percentage": 50.59, "elapsed_time": "5:49:01", "remaining_time": "5:40:54", "throughput": 862.21, "total_tokens": 18056296}
+{"current_steps": 1725, "total_steps": 3400, "loss": 0.3513, "lr": 5.29162319887768e-05, "epoch": 0.4442441411279938, "percentage": 50.74, "elapsed_time": "5:50:30", "remaining_time": "5:40:21", "throughput": 861.06, "total_tokens": 18108904}
+{"current_steps": 1730, "total_steps": 3400, "loss": 0.373, "lr": 5.26734550690071e-05, "epoch": 0.4455318053051764, "percentage": 50.88, "elapsed_time": "5:51:59", "remaining_time": "5:39:46", "throughput": 859.91, "total_tokens": 18160696}
+{"current_steps": 1735, "total_steps": 3400, "loss": 0.4246, "lr": 5.243061492163073e-05, "epoch": 0.446819469482359, "percentage": 51.03, "elapsed_time": "5:53:29", "remaining_time": "5:39:13", "throughput": 858.77, "total_tokens": 18213760}
+{"current_steps": 1740, "total_steps": 3400, "loss": 0.3703, "lr": 5.2187717289852955e-05, "epoch": 0.4481071336595416, "percentage": 51.18, "elapsed_time": "5:54:57", "remaining_time": "5:38:37", "throughput": 857.7, "total_tokens": 18266424}
+{"current_steps": 1745, "total_steps": 3400, "loss": 0.3763, "lr": 5.1944767918238624e-05, "epoch": 0.4493947978367242, "percentage": 51.32, "elapsed_time": "5:56:24", "remaining_time": "5:38:01", "throughput": 856.63, "total_tokens": 18318984}
+{"current_steps": 1750, "total_steps": 3400, "loss": 0.3767, "lr": 5.170177255257618e-05, "epoch": 0.45068246201390677, "percentage": 51.47, "elapsed_time": "5:57:52", "remaining_time": "5:37:25", "throughput": 855.59, "total_tokens": 18371928}
+{"current_steps": 1750, "total_steps": 3400, "eval_loss": 0.4234265685081482, "epoch": 0.45068246201390677, "percentage": 51.47, "elapsed_time": "5:58:31", "remaining_time": "5:38:01", "throughput": 854.07, "total_tokens": 18371928}