Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81846ac02e033886bed1edec96d0da70d2a41c811163f600e741ff029d3c0d0
+oid sha256:886e83225731329ec8fecf2885b7ea9c6656cc91593fafb84eb477c2dda182a4
 size 29034840

trainer_log.jsonl

@@ -65,3 +65,14 @@
 {"current_steps": 295, "total_steps": 6770, "loss": 0.6885, "lr": 8.702064896755162e-05, "epoch": 0.08714918759231906, "percentage": 4.36, "elapsed_time": "1:29:17", "remaining_time": "1 day, 8:39:53", "throughput": 570.19, "total_tokens": 3054808}
 {"current_steps": 300, "total_steps": 6770, "loss": 0.78, "lr": 8.849557522123895e-05, "epoch": 0.08862629246676514, "percentage": 4.43, "elapsed_time": "1:30:43", "remaining_time": "1 day, 8:36:32", "throughput": 570.84, "total_tokens": 3107200}
 {"current_steps": 300, "total_steps": 6770, "eval_loss": 0.8194220662117004, "epoch": 0.08862629246676514, "percentage": 4.43, "elapsed_time": "1:31:02", "remaining_time": "1 day, 8:43:25", "throughput": 568.83, "total_tokens": 3107200}
+{"current_steps": 305, "total_steps": 6770, "loss": 0.7394, "lr": 8.997050147492626e-05, "epoch": 0.09010339734121123, "percentage": 4.51, "elapsed_time": "1:32:35", "remaining_time": "1 day, 8:42:43", "throughput": 568.54, "total_tokens": 3158648}
+{"current_steps": 310, "total_steps": 6770, "loss": 0.7371, "lr": 9.144542772861357e-05, "epoch": 0.0915805022156573, "percentage": 4.58, "elapsed_time": "1:34:01", "remaining_time": "1 day, 8:39:19", "throughput": 569.11, "total_tokens": 3210560}
+{"current_steps": 315, "total_steps": 6770, "loss": 0.7622, "lr": 9.29203539823009e-05, "epoch": 0.0930576070901034, "percentage": 4.65, "elapsed_time": "1:35:29", "remaining_time": "1 day, 8:36:39", "throughput": 569.67, "total_tokens": 3263664}
+{"current_steps": 320, "total_steps": 6770, "loss": 0.7214, "lr": 9.43952802359882e-05, "epoch": 0.09453471196454949, "percentage": 4.73, "elapsed_time": "1:36:54", "remaining_time": "1 day, 8:33:24", "throughput": 570.18, "total_tokens": 3315520}
+{"current_steps": 325, "total_steps": 6770, "loss": 0.7078, "lr": 9.587020648967551e-05, "epoch": 0.09601181683899557, "percentage": 4.8, "elapsed_time": "1:38:22", "remaining_time": "1 day, 8:30:46", "throughput": 570.64, "total_tokens": 3368088}
+{"current_steps": 330, "total_steps": 6770, "loss": 0.6852, "lr": 9.734513274336283e-05, "epoch": 0.09748892171344166, "percentage": 4.87, "elapsed_time": "1:39:48", "remaining_time": "1 day, 8:27:38", "throughput": 571.16, "total_tokens": 3420176}
+{"current_steps": 335, "total_steps": 6770, "loss": 0.7557, "lr": 9.882005899705014e-05, "epoch": 0.09896602658788774, "percentage": 4.95, "elapsed_time": "1:41:15", "remaining_time": "1 day, 8:25:11", "throughput": 571.3, "total_tokens": 3471184}
+{"current_steps": 340, "total_steps": 6770, "loss": 0.6709, "lr": 9.99999940340072e-05, "epoch": 0.10044313146233383, "percentage": 5.02, "elapsed_time": "1:42:41", "remaining_time": "1 day, 8:22:10", "throughput": 571.75, "total_tokens": 3523008}
+{"current_steps": 345, "total_steps": 6770, "loss": 0.7252, "lr": 9.999978522440803e-05, "epoch": 0.1019202363367799, "percentage": 5.1, "elapsed_time": "1:44:08", "remaining_time": "1 day, 8:19:27", "throughput": 571.96, "total_tokens": 3573880}
+{"current_steps": 350, "total_steps": 6770, "loss": 0.6602, "lr": 9.999927811659165e-05, "epoch": 0.103397341211226, "percentage": 5.17, "elapsed_time": "1:45:35", "remaining_time": "1 day, 8:16:42", "throughput": 572.33, "total_tokens": 3625752}
+{"current_steps": 350, "total_steps": 6770, "eval_loss": 0.7663387656211853, "epoch": 0.103397341211226, "percentage": 5.17, "elapsed_time": "1:45:54", "remaining_time": "1 day, 8:22:34", "throughput": 570.6, "total_tokens": 3625752}