Training in progress, step 1350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f02e158d7a0ecd4f15ebd388f3f9321f3c48f48b6c240184415bff2106b4225
+oid sha256:6aef5102eef70c31f0044c654484ffa32b1a0562551889340924debb001cc356
 size 29034840

trainer_log.jsonl

@@ -284,3 +284,14 @@
 {"current_steps": 1295, "total_steps": 3882, "loss": 0.4502, "lr": 7.959911382155566e-05, "epoch": 0.667010043780582, "percentage": 33.36, "elapsed_time": "6:36:47", "remaining_time": "13:12:39", "throughput": 636.22, "total_tokens": 15146600}
 {"current_steps": 1300, "total_steps": 3882, "loss": 0.4578, "lr": 7.942716347848353e-05, "epoch": 0.6695853721349472, "percentage": 33.49, "elapsed_time": "6:38:17", "remaining_time": "13:11:03", "throughput": 636.27, "total_tokens": 15205064}
 {"current_steps": 1300, "total_steps": 3882, "eval_loss": 0.49471279978752136, "epoch": 0.6695853721349472, "percentage": 33.49, "elapsed_time": "6:38:36", "remaining_time": "13:11:42", "throughput": 635.75, "total_tokens": 15205064}
+{"current_steps": 1305, "total_steps": 3882, "loss": 0.4589, "lr": 7.925467901247996e-05, "epoch": 0.6721607004893124, "percentage": 33.62, "elapsed_time": "6:40:10", "remaining_time": "13:10:13", "throughput": 635.71, "total_tokens": 15263560}
+{"current_steps": 1310, "total_steps": 3882, "loss": 0.457, "lr": 7.908166355425475e-05, "epoch": 0.6747360288436776, "percentage": 33.75, "elapsed_time": "6:41:39", "remaining_time": "13:08:35", "throughput": 635.79, "total_tokens": 15322016}
+{"current_steps": 1315, "total_steps": 3882, "loss": 0.51, "lr": 7.890812024415555e-05, "epoch": 0.6773113571980427, "percentage": 33.87, "elapsed_time": "6:43:06", "remaining_time": "13:06:54", "throughput": 635.91, "total_tokens": 15380504}
+{"current_steps": 1320, "total_steps": 3882, "loss": 0.4994, "lr": 7.873405223211087e-05, "epoch": 0.6798866855524079, "percentage": 34.0, "elapsed_time": "6:44:35", "remaining_time": "13:05:16", "throughput": 635.99, "total_tokens": 15438944}
+{"current_steps": 1325, "total_steps": 3882, "loss": 0.4501, "lr": 7.855946267757295e-05, "epoch": 0.6824620139067731, "percentage": 34.13, "elapsed_time": "6:46:03", "remaining_time": "13:03:37", "throughput": 636.09, "total_tokens": 15497384}
+{"current_steps": 1330, "total_steps": 3882, "loss": 0.4807, "lr": 7.838435474946034e-05, "epoch": 0.6850373422611383, "percentage": 34.26, "elapsed_time": "6:47:33", "remaining_time": "13:02:00", "throughput": 636.15, "total_tokens": 15555856}
+{"current_steps": 1335, "total_steps": 3882, "loss": 0.5112, "lr": 7.820873162610044e-05, "epoch": 0.6876126706155035, "percentage": 34.39, "elapsed_time": "6:49:01", "remaining_time": "13:00:22", "throughput": 636.24, "total_tokens": 15614368}
+{"current_steps": 1340, "total_steps": 3882, "loss": 0.4825, "lr": 7.803259649517178e-05, "epoch": 0.6901879989698687, "percentage": 34.52, "elapsed_time": "6:50:30", "remaining_time": "12:58:44", "throughput": 636.31, "total_tokens": 15672864}
+{"current_steps": 1345, "total_steps": 3882, "loss": 0.5147, "lr": 7.78559525536462e-05, "epoch": 0.6927633273242338, "percentage": 34.65, "elapsed_time": "6:51:59", "remaining_time": "12:57:06", "throughput": 636.4, "total_tokens": 15731376}
+{"current_steps": 1350, "total_steps": 3882, "loss": 0.4702, "lr": 7.767880300773074e-05, "epoch": 0.695338655678599, "percentage": 34.78, "elapsed_time": "6:53:28", "remaining_time": "12:55:30", "throughput": 636.46, "total_tokens": 15789848}
+{"current_steps": 1350, "total_steps": 3882, "eval_loss": 0.5247787237167358, "epoch": 0.695338655678599, "percentage": 34.78, "elapsed_time": "6:53:48", "remaining_time": "12:56:06", "throughput": 635.96, "total_tokens": 15789848}