Training in progress, step 3050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c6af243f589a55fa9a3c1d1d73c19fe4b53c2830aa75e5338a55fa38ab436d
+oid sha256:ddb314047f6c123f2abaf4b7b141070b2299dee4fc65b9c0ec7277494419776e
 size 18516456

trainer_log.jsonl

@@ -662,3 +662,14 @@
 {"current_steps": 2995, "total_steps": 3400, "loss": 0.2555, "lr": 3.829320579258466e-06, "epoch": 1.5423641514293074, "percentage": 88.09, "elapsed_time": "11:05:14", "remaining_time": "1:29:57", "throughput": 877.47, "total_tokens": 35023552}
 {"current_steps": 3000, "total_steps": 3400, "loss": 0.2259, "lr": 3.7365415833504725e-06, "epoch": 1.5449394797836724, "percentage": 88.24, "elapsed_time": "11:06:19", "remaining_time": "1:28:50", "throughput": 877.5, "total_tokens": 35082056}
 {"current_steps": 3000, "total_steps": 3400, "eval_loss": 0.8405727744102478, "epoch": 1.5449394797836724, "percentage": 88.24, "elapsed_time": "11:06:35", "remaining_time": "1:28:52", "throughput": 877.15, "total_tokens": 35082056}
+{"current_steps": 3005, "total_steps": 3400, "loss": 0.2157, "lr": 3.644856725057405e-06, "epoch": 1.5475148081380374, "percentage": 88.38, "elapsed_time": "11:07:45", "remaining_time": "1:27:46", "throughput": 877.08, "total_tokens": 35140568}
+{"current_steps": 3010, "total_steps": 3400, "loss": 0.2233, "lr": 3.554268172739661e-06, "epoch": 1.5500901364924027, "percentage": 88.53, "elapsed_time": "11:08:50", "remaining_time": "1:26:39", "throughput": 877.12, "total_tokens": 35199064}
+{"current_steps": 3015, "total_steps": 3400, "loss": 0.2951, "lr": 3.4647780688298826e-06, "epoch": 1.552665464846768, "percentage": 88.68, "elapsed_time": "11:09:55", "remaining_time": "1:25:32", "throughput": 877.16, "total_tokens": 35257576}
+{"current_steps": 3020, "total_steps": 3400, "loss": 0.2274, "lr": 3.376388529782215e-06, "epoch": 1.5552407932011332, "percentage": 88.82, "elapsed_time": "11:10:59", "remaining_time": "1:24:25", "throughput": 877.21, "total_tokens": 35316064}
+{"current_steps": 3025, "total_steps": 3400, "loss": 0.2479, "lr": 3.2891016460222967e-06, "epoch": 1.5578161215554984, "percentage": 88.97, "elapsed_time": "11:12:04", "remaining_time": "1:23:18", "throughput": 877.25, "total_tokens": 35374504}
+{"current_steps": 3030, "total_steps": 3400, "loss": 0.292, "lr": 3.2029194818977983e-06, "epoch": 1.5603914499098637, "percentage": 89.12, "elapsed_time": "11:13:08", "remaining_time": "1:22:11", "throughput": 877.31, "total_tokens": 35432984}
+{"current_steps": 3035, "total_steps": 3400, "loss": 0.241, "lr": 3.117844075629617e-06, "epoch": 1.5629667782642287, "percentage": 89.26, "elapsed_time": "11:14:12", "remaining_time": "1:21:05", "throughput": 877.35, "total_tokens": 35491488}
+{"current_steps": 3040, "total_steps": 3400, "loss": 0.228, "lr": 3.033877439263666e-06, "epoch": 1.5655421066185937, "percentage": 89.41, "elapsed_time": "11:15:17", "remaining_time": "1:19:58", "throughput": 877.41, "total_tokens": 35549984}
+{"current_steps": 3045, "total_steps": 3400, "loss": 0.2485, "lr": 2.951021558623274e-06, "epoch": 1.568117434972959, "percentage": 89.56, "elapsed_time": "11:16:21", "remaining_time": "1:18:51", "throughput": 877.45, "total_tokens": 35608488}
+{"current_steps": 3050, "total_steps": 3400, "loss": 0.2851, "lr": 2.869278393262226e-06, "epoch": 1.5706927633273242, "percentage": 89.71, "elapsed_time": "11:17:25", "remaining_time": "1:17:44", "throughput": 877.5, "total_tokens": 35666976}
+{"current_steps": 3050, "total_steps": 3400, "eval_loss": 0.8473746180534363, "epoch": 1.5706927633273242, "percentage": 89.71, "elapsed_time": "11:17:41", "remaining_time": "1:17:46", "throughput": 877.16, "total_tokens": 35666976}