Training in progress, step 2250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f759f407b1897a80281dc7418f8b9856395bc3d571214488014c389b60bc84f7
+oid sha256:9efa5a507b1e2d13741d6dd8d920f108bb4ba17026ae4bb85a703fca7207dad8
 size 29034840

trainer_log.jsonl

@@ -482,3 +482,14 @@
 {"current_steps": 2195, "total_steps": 3882, "loss": 0.2622, "lr": 4.335227249874484e-05, "epoch": 1.1303116147308783, "percentage": 56.54, "elapsed_time": "11:10:15", "remaining_time": "8:35:08", "throughput": 638.24, "total_tokens": 25667128}
 {"current_steps": 2200, "total_steps": 3882, "loss": 0.3184, "lr": 4.314120639837619e-05, "epoch": 1.1328869430852433, "percentage": 56.67, "elapsed_time": "11:11:44", "remaining_time": "8:33:34", "throughput": 638.28, "total_tokens": 25725560}
 {"current_steps": 2200, "total_steps": 3882, "eval_loss": 0.24919146299362183, "epoch": 1.1328869430852433, "percentage": 56.67, "elapsed_time": "11:12:03", "remaining_time": "8:33:49", "throughput": 637.98, "total_tokens": 25725560}
+{"current_steps": 2205, "total_steps": 3882, "loss": 0.3121, "lr": 4.2930264789752974e-05, "epoch": 1.1354622714396085, "percentage": 56.8, "elapsed_time": "11:13:37", "remaining_time": "8:32:19", "throughput": 637.94, "total_tokens": 25784048}
+{"current_steps": 2210, "total_steps": 3882, "loss": 0.2448, "lr": 4.271945150160815e-05, "epoch": 1.1380375997939738, "percentage": 56.93, "elapsed_time": "11:15:06", "remaining_time": "8:30:45", "throughput": 637.99, "total_tokens": 25842512}
+{"current_steps": 2215, "total_steps": 3882, "loss": 0.3141, "lr": 4.250877036034552e-05, "epoch": 1.140612928148339, "percentage": 57.06, "elapsed_time": "11:16:34", "remaining_time": "8:29:11", "throughput": 638.04, "total_tokens": 25900992}
+{"current_steps": 2220, "total_steps": 3882, "loss": 0.2589, "lr": 4.2298225189970424e-05, "epoch": 1.143188256502704, "percentage": 57.19, "elapsed_time": "11:18:03", "remaining_time": "8:27:37", "throughput": 638.09, "total_tokens": 25959448}
+{"current_steps": 2225, "total_steps": 3882, "loss": 0.3071, "lr": 4.2087819812020155e-05, "epoch": 1.1457635848570693, "percentage": 57.32, "elapsed_time": "11:19:30", "remaining_time": "8:26:02", "throughput": 638.16, "total_tokens": 26017936}
+{"current_steps": 2230, "total_steps": 3882, "loss": 0.1913, "lr": 4.1877558045494735e-05, "epoch": 1.1483389132114346, "percentage": 57.44, "elapsed_time": "11:20:58", "remaining_time": "8:24:28", "throughput": 638.22, "total_tokens": 26076440}
+{"current_steps": 2235, "total_steps": 3882, "loss": 0.1998, "lr": 4.166744370678748e-05, "epoch": 1.1509142415657996, "percentage": 57.57, "elapsed_time": "11:22:24", "remaining_time": "8:22:52", "throughput": 638.29, "total_tokens": 26134896}
+{"current_steps": 2240, "total_steps": 3882, "loss": 0.2382, "lr": 4.1457480609615866e-05, "epoch": 1.1534895699201648, "percentage": 57.7, "elapsed_time": "11:23:53", "remaining_time": "8:21:19", "throughput": 638.33, "total_tokens": 26193368}
+{"current_steps": 2245, "total_steps": 3882, "loss": 0.231, "lr": 4.124767256495217e-05, "epoch": 1.15606489827453, "percentage": 57.83, "elapsed_time": "11:25:26", "remaining_time": "8:19:48", "throughput": 638.32, "total_tokens": 26251848}
+{"current_steps": 2250, "total_steps": 3882, "loss": 0.273, "lr": 4.1038023380954415e-05, "epoch": 1.158640226628895, "percentage": 57.96, "elapsed_time": "11:26:59", "remaining_time": "8:18:18", "throughput": 638.29, "total_tokens": 26310336}
+{"current_steps": 2250, "total_steps": 3882, "eval_loss": 0.22014015913009644, "epoch": 1.158640226628895, "percentage": 57.96, "elapsed_time": "11:27:20", "remaining_time": "8:18:32", "throughput": 637.98, "total_tokens": 26310336}