Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086f56d8253ad2de065083ad9ed3e401f206ca6169266148720dc9056e97e11d
+oid sha256:9c65b6b24daabfe64ef0f6c6a0cc775ba02b62fb7a4c18bdac4a973c02aef24f
 size 29034840

trainer_log.jsonl

@@ -152,3 +152,14 @@
 {"current_steps": 695, "total_steps": 3882, "loss": 0.7311, "lr": 9.55305450518895e-05, "epoch": 0.35797064125676026, "percentage": 17.9, "elapsed_time": "3:34:56", "remaining_time": "16:25:39", "throughput": 630.3, "total_tokens": 8128816}
 {"current_steps": 700, "total_steps": 3882, "loss": 0.774, "lr": 9.544209918461642e-05, "epoch": 0.3605459696111254, "percentage": 18.03, "elapsed_time": "3:36:24", "remaining_time": "16:23:44", "throughput": 630.54, "total_tokens": 8187320}
 {"current_steps": 700, "total_steps": 3882, "eval_loss": 0.7318872809410095, "epoch": 0.3605459696111254, "percentage": 18.03, "elapsed_time": "3:36:44", "remaining_time": "16:25:14", "throughput": 629.58, "total_tokens": 8187320}
+{"current_steps": 705, "total_steps": 3882, "loss": 0.765, "lr": 9.535282851249103e-05, "epoch": 0.3631212979654906, "percentage": 18.16, "elapsed_time": "3:38:19", "remaining_time": "16:23:51", "throughput": 629.47, "total_tokens": 8245776}
+{"current_steps": 710, "total_steps": 3882, "loss": 0.7287, "lr": 9.526273465583646e-05, "epoch": 0.3656966263198558, "percentage": 18.29, "elapsed_time": "3:39:48", "remaining_time": "16:21:58", "throughput": 629.68, "total_tokens": 8304280}
+{"current_steps": 715, "total_steps": 3882, "loss": 0.758, "lr": 9.517181924991716e-05, "epoch": 0.36827195467422097, "percentage": 18.42, "elapsed_time": "3:41:17", "remaining_time": "16:20:12", "throughput": 629.83, "total_tokens": 8362728}
+{"current_steps": 720, "total_steps": 3882, "loss": 0.795, "lr": 9.508008394490926e-05, "epoch": 0.37084728302858616, "percentage": 18.55, "elapsed_time": "3:42:47", "remaining_time": "16:18:23", "throughput": 630.0, "total_tokens": 8421224}
+{"current_steps": 725, "total_steps": 3882, "loss": 0.6901, "lr": 9.498753040587066e-05, "epoch": 0.37342261138295135, "percentage": 18.68, "elapsed_time": "3:44:16", "remaining_time": "16:16:37", "throughput": 630.15, "total_tokens": 8479720}
+{"current_steps": 730, "total_steps": 3882, "loss": 0.7618, "lr": 9.48941603127107e-05, "epoch": 0.3759979397373165, "percentage": 18.8, "elapsed_time": "3:45:45", "remaining_time": "16:14:47", "throughput": 630.33, "total_tokens": 8538192}
+{"current_steps": 735, "total_steps": 3882, "loss": 0.7481, "lr": 9.479997536015977e-05, "epoch": 0.3785732680916817, "percentage": 18.93, "elapsed_time": "3:47:14", "remaining_time": "16:12:58", "throughput": 630.5, "total_tokens": 8596664}
+{"current_steps": 740, "total_steps": 3882, "loss": 0.746, "lr": 9.47049772577385e-05, "epoch": 0.3811485964460469, "percentage": 19.06, "elapsed_time": "3:48:44", "remaining_time": "16:11:11", "throughput": 630.65, "total_tokens": 8655128}
+{"current_steps": 745, "total_steps": 3882, "loss": 0.812, "lr": 9.460916772972672e-05, "epoch": 0.38372392480041206, "percentage": 19.19, "elapsed_time": "3:50:13", "remaining_time": "16:09:23", "throughput": 630.83, "total_tokens": 8713624}
+{"current_steps": 750, "total_steps": 3882, "loss": 0.6751, "lr": 9.451254851513222e-05, "epoch": 0.38629925315477726, "percentage": 19.32, "elapsed_time": "3:51:43", "remaining_time": "16:07:42", "throughput": 630.91, "total_tokens": 8772104}
+{"current_steps": 750, "total_steps": 3882, "eval_loss": 0.732211709022522, "epoch": 0.38629925315477726, "percentage": 19.32, "elapsed_time": "3:52:03", "remaining_time": "16:09:05", "throughput": 630.01, "total_tokens": 8772104}