Training in progress, step 2700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c3a246645edf5ddfde12f7e3a3985714315a8a332a960d7d8036f942d6495e
+oid sha256:2b583b602b9e38c1b3b50b506d83107d06e11e7b44aab1de71c95fee8b4886d2
 size 29034840

trainer_log.jsonl

@@ -584,3 +584,14 @@
 {"current_steps": 2645, "total_steps": 3400, "loss": 0.3084, "lr": 1.2886177695085078e-05, "epoch": 0.6811743497295906, "percentage": 77.79, "elapsed_time": "0:30:03", "remaining_time": "0:08:34", "throughput": 15399.14, "total_tokens": 27775400}
 {"current_steps": 2650, "total_steps": 3400, "loss": 0.324, "lr": 1.2723678998574512e-05, "epoch": 0.6824620139067731, "percentage": 77.94, "elapsed_time": "0:31:29", "remaining_time": "0:08:54", "throughput": 14730.09, "total_tokens": 27827480}
 {"current_steps": 2650, "total_steps": 3400, "eval_loss": 0.5079630613327026, "epoch": 0.6824620139067731, "percentage": 77.94, "elapsed_time": "0:32:06", "remaining_time": "0:09:05", "throughput": 14441.68, "total_tokens": 27827480}
+{"current_steps": 2655, "total_steps": 3400, "loss": 0.3189, "lr": 1.2562061892553473e-05, "epoch": 0.6837496780839557, "percentage": 78.09, "elapsed_time": "0:33:40", "remaining_time": "0:09:27", "throughput": 13795.27, "total_tokens": 27879064}
+{"current_steps": 2660, "total_steps": 3400, "loss": 0.2458, "lr": 1.2401330199290367e-05, "epoch": 0.6850373422611383, "percentage": 78.24, "elapsed_time": "0:35:07", "remaining_time": "0:09:46", "throughput": 13254.02, "total_tokens": 27931864}
+{"current_steps": 2665, "total_steps": 3400, "loss": 0.3055, "lr": 1.224148772011346e-05, "epoch": 0.6863250064383208, "percentage": 78.38, "elapsed_time": "0:36:34", "remaining_time": "0:10:05", "throughput": 12749.47, "total_tokens": 27984408}
+{"current_steps": 2670, "total_steps": 3400, "loss": 0.2993, "lr": 1.2082538235320929e-05, "epoch": 0.6876126706155035, "percentage": 78.53, "elapsed_time": "0:38:01", "remaining_time": "0:10:23", "throughput": 12289.04, "total_tokens": 28037368}
+{"current_steps": 2675, "total_steps": 3400, "loss": 0.3572, "lr": 1.1924485504091565e-05, "epoch": 0.6889003347926861, "percentage": 78.68, "elapsed_time": "0:39:28", "remaining_time": "0:10:42", "throughput": 11858.72, "total_tokens": 28090768}
+{"current_steps": 2680, "total_steps": 3400, "loss": 0.4043, "lr": 1.1767333264395736e-05, "epoch": 0.6901879989698687, "percentage": 78.82, "elapsed_time": "0:40:54", "remaining_time": "0:10:59", "throughput": 11464.2, "total_tokens": 28142432}
+{"current_steps": 2685, "total_steps": 3400, "loss": 0.3288, "lr": 1.1611085232907132e-05, "epoch": 0.6914756631470512, "percentage": 78.97, "elapsed_time": "0:42:22", "remaining_time": "0:11:17", "throughput": 11087.75, "total_tokens": 28194896}
+{"current_steps": 2690, "total_steps": 3400, "loss": 0.3491, "lr": 1.14557451049147e-05, "epoch": 0.6927633273242338, "percentage": 79.12, "elapsed_time": "0:43:49", "remaining_time": "0:11:33", "throughput": 10744.36, "total_tokens": 28247264}
+{"current_steps": 2695, "total_steps": 3400, "loss": 0.2881, "lr": 1.1301316554235397e-05, "epoch": 0.6940509915014165, "percentage": 79.26, "elapsed_time": "0:45:16", "remaining_time": "0:11:50", "throughput": 10416.26, "total_tokens": 28299864}
+{"current_steps": 2700, "total_steps": 3400, "loss": 0.3076, "lr": 1.114780323312724e-05, "epoch": 0.695338655678599, "percentage": 79.41, "elapsed_time": "0:46:42", "remaining_time": "0:12:06", "throughput": 10115.15, "total_tokens": 28352368}
+{"current_steps": 2700, "total_steps": 3400, "eval_loss": 0.4338160753250122, "epoch": 0.695338655678599, "percentage": 79.41, "elapsed_time": "0:47:21", "remaining_time": "0:12:16", "throughput": 9977.7, "total_tokens": 28352368}