Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5f3724b5d59ea4e0a9371b33e20124137112f04ac962fd4bc5e834b083db05
+oid sha256:b80d0303f147dcd83f97c68d1de338e51e85f076089eb9eec3b8eff422c8bc34
 size 18516456

trainer_log.jsonl

@@ -156,3 +156,14 @@
 {"current_steps": 695, "total_steps": 3400, "loss": 0.8986, "lr": 9.362182973536569e-05, "epoch": 0.35797064125676026, "percentage": 20.44, "elapsed_time": "2:42:32", "remaining_time": "10:32:38", "throughput": 833.49, "total_tokens": 8128816}
 {"current_steps": 700, "total_steps": 3400, "loss": 0.8972, "lr": 9.35024767453647e-05, "epoch": 0.3605459696111254, "percentage": 20.59, "elapsed_time": "2:43:36", "remaining_time": "10:31:04", "throughput": 834.03, "total_tokens": 8187320}
 {"current_steps": 700, "total_steps": 3400, "eval_loss": 0.9028835892677307, "epoch": 0.3605459696111254, "percentage": 20.59, "elapsed_time": "2:43:52", "remaining_time": "10:32:06", "throughput": 832.66, "total_tokens": 8187320}
+{"current_steps": 705, "total_steps": 3400, "loss": 0.8998, "lr": 9.338209491537257e-05, "epoch": 0.3631212979654906, "percentage": 20.74, "elapsed_time": "2:45:01", "remaining_time": "10:30:51", "throughput": 832.76, "total_tokens": 8245776}
+{"current_steps": 710, "total_steps": 3400, "loss": 0.8999, "lr": 9.326068709243727e-05, "epoch": 0.3656966263198558, "percentage": 20.88, "elapsed_time": "2:46:05", "remaining_time": "10:29:16", "throughput": 833.31, "total_tokens": 8304280}
+{"current_steps": 715, "total_steps": 3400, "loss": 0.8983, "lr": 9.313825614787177e-05, "epoch": 0.36827195467422097, "percentage": 21.03, "elapsed_time": "2:47:09", "remaining_time": "10:27:41", "throughput": 833.84, "total_tokens": 8362728}
+{"current_steps": 720, "total_steps": 3400, "loss": 0.892, "lr": 9.301480497718593e-05, "epoch": 0.37084728302858616, "percentage": 21.18, "elapsed_time": "2:48:12", "remaining_time": "10:26:08", "throughput": 834.37, "total_tokens": 8421224}
+{"current_steps": 725, "total_steps": 3400, "loss": 0.9034, "lr": 9.289033650001817e-05, "epoch": 0.37342261138295135, "percentage": 21.32, "elapsed_time": "2:49:16", "remaining_time": "10:24:35", "throughput": 834.87, "total_tokens": 8479720}
+{"current_steps": 730, "total_steps": 3400, "loss": 0.895, "lr": 9.276485366006634e-05, "epoch": 0.3759979397373165, "percentage": 21.47, "elapsed_time": "2:50:20", "remaining_time": "10:23:02", "throughput": 835.38, "total_tokens": 8538192}
+{"current_steps": 735, "total_steps": 3400, "loss": 0.8973, "lr": 9.263835942501807e-05, "epoch": 0.3785732680916817, "percentage": 21.62, "elapsed_time": "2:51:24", "remaining_time": "10:21:29", "throughput": 835.9, "total_tokens": 8596664}
+{"current_steps": 740, "total_steps": 3400, "loss": 0.8972, "lr": 9.251085678648072e-05, "epoch": 0.3811485964460469, "percentage": 21.76, "elapsed_time": "2:52:28", "remaining_time": "10:19:58", "throughput": 836.38, "total_tokens": 8655128}
+{"current_steps": 745, "total_steps": 3400, "loss": 0.8987, "lr": 9.238234875991046e-05, "epoch": 0.38372392480041206, "percentage": 21.91, "elapsed_time": "2:53:31", "remaining_time": "10:18:25", "throughput": 836.89, "total_tokens": 8713624}
+{"current_steps": 750, "total_steps": 3400, "loss": 0.9005, "lr": 9.225283838454111e-05, "epoch": 0.38629925315477726, "percentage": 22.06, "elapsed_time": "2:54:36", "remaining_time": "10:16:57", "throughput": 837.3, "total_tokens": 8772104}
+{"current_steps": 750, "total_steps": 3400, "eval_loss": 0.8981761336326599, "epoch": 0.38629925315477726, "percentage": 22.06, "elapsed_time": "2:54:52", "remaining_time": "10:17:54", "throughput": 836.02, "total_tokens": 8772104}