Training in progress, step 2150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f75c51d9ca969a9d3cbb26206d8c3751152111b430ee8f78c774b9d99426948
+oid sha256:023a38accdab689b6f8ae25c0137c8832b5274377f50198dd88dfa1030f6f9c7
 size 29034840

trainer_log.jsonl

@@ -464,3 +464,14 @@
 {"current_steps": 2095, "total_steps": 3400, "loss": 0.3835, "lr": 3.515163588305735e-05, "epoch": 0.5395312902395055, "percentage": 61.62, "elapsed_time": "7:43:20", "remaining_time": "4:48:37", "throughput": 791.29, "total_tokens": 21998016}
 {"current_steps": 2100, "total_steps": 3400, "loss": 0.3983, "lr": 3.491962445238569e-05, "epoch": 0.5408189544166881, "percentage": 61.76, "elapsed_time": "7:44:47", "remaining_time": "4:47:43", "throughput": 790.68, "total_tokens": 22050376}
 {"current_steps": 2100, "total_steps": 3400, "eval_loss": 0.481829971075058, "epoch": 0.5408189544166881, "percentage": 61.76, "elapsed_time": "7:45:25", "remaining_time": "4:48:07", "throughput": 789.61, "total_tokens": 22050376}
+{"current_steps": 2105, "total_steps": 3400, "loss": 0.4067, "lr": 3.4687969674819906e-05, "epoch": 0.5421066185938708, "percentage": 61.91, "elapsed_time": "7:46:58", "remaining_time": "4:47:17", "throughput": 788.86, "total_tokens": 22102848}
+{"current_steps": 2110, "total_steps": 3400, "loss": 0.36, "lr": 3.445667702902969e-05, "epoch": 0.5433942827710533, "percentage": 62.06, "elapsed_time": "7:48:26", "remaining_time": "4:46:23", "throughput": 788.28, "total_tokens": 22155432}
+{"current_steps": 2115, "total_steps": 3400, "loss": 0.3569, "lr": 3.4225751985120215e-05, "epoch": 0.5446819469482359, "percentage": 62.21, "elapsed_time": "7:49:53", "remaining_time": "4:45:29", "throughput": 787.67, "total_tokens": 22207528}
+{"current_steps": 2120, "total_steps": 3400, "loss": 0.3503, "lr": 3.3995200004502816e-05, "epoch": 0.5459696111254185, "percentage": 62.35, "elapsed_time": "7:51:21", "remaining_time": "4:44:35", "throughput": 787.09, "total_tokens": 22260016}
+{"current_steps": 2125, "total_steps": 3400, "loss": 0.342, "lr": 3.3765026539765834e-05, "epoch": 0.547257275302601, "percentage": 62.5, "elapsed_time": "7:52:49", "remaining_time": "4:43:41", "throughput": 786.51, "total_tokens": 22312616}
+{"current_steps": 2130, "total_steps": 3400, "loss": 0.4113, "lr": 3.3535237034545675e-05, "epoch": 0.5485449394797837, "percentage": 62.65, "elapsed_time": "7:54:16", "remaining_time": "4:42:47", "throughput": 785.92, "total_tokens": 22364776}
+{"current_steps": 2135, "total_steps": 3400, "loss": 0.311, "lr": 3.330583692339802e-05, "epoch": 0.5498326036569663, "percentage": 62.79, "elapsed_time": "7:55:43", "remaining_time": "4:41:52", "throughput": 785.37, "total_tokens": 22416944}
+{"current_steps": 2140, "total_steps": 3400, "loss": 0.358, "lr": 3.307683163166934e-05, "epoch": 0.5511202678341488, "percentage": 62.94, "elapsed_time": "7:57:11", "remaining_time": "4:40:57", "throughput": 784.77, "total_tokens": 22468960}
+{"current_steps": 2145, "total_steps": 3400, "loss": 0.378, "lr": 3.284822657536856e-05, "epoch": 0.5524079320113314, "percentage": 63.09, "elapsed_time": "7:58:37", "remaining_time": "4:40:02", "throughput": 784.24, "total_tokens": 22521624}
+{"current_steps": 2150, "total_steps": 3400, "loss": 0.3687, "lr": 3.262002716103897e-05, "epoch": 0.553695596188514, "percentage": 63.24, "elapsed_time": "8:00:05", "remaining_time": "4:39:07", "throughput": 783.66, "total_tokens": 22574104}
+{"current_steps": 2150, "total_steps": 3400, "eval_loss": 0.4504742920398712, "epoch": 0.553695596188514, "percentage": 63.24, "elapsed_time": "8:00:44", "remaining_time": "4:39:29", "throughput": 782.63, "total_tokens": 22574104}