Training in progress, step 1300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176fb1c1416e7836affe6e751cb01891a9a4235ffa9e418ece291228e7c61b72
+oid sha256:3f02e158d7a0ecd4f15ebd388f3f9321f3c48f48b6c240184415bff2106b4225
 size 29034840

trainer_log.jsonl

@@ -273,3 +273,14 @@
 {"current_steps": 1245, "total_steps": 3882, "loss": 0.5807, "lr": 8.128855873920265e-05, "epoch": 0.6412567602369302, "percentage": 32.07, "elapsed_time": "6:21:31", "remaining_time": "13:28:06", "throughput": 636.12, "total_tokens": 14561872}
 {"current_steps": 1250, "total_steps": 3882, "loss": 0.5268, "lr": 8.112211965375059e-05, "epoch": 0.6438320885912954, "percentage": 32.2, "elapsed_time": "6:23:00", "remaining_time": "13:26:27", "throughput": 636.21, "total_tokens": 14620336}
 {"current_steps": 1250, "total_steps": 3882, "eval_loss": 0.5496931672096252, "epoch": 0.6438320885912954, "percentage": 32.2, "elapsed_time": "6:23:19", "remaining_time": "13:27:08", "throughput": 635.67, "total_tokens": 14620336}
+{"current_steps": 1255, "total_steps": 3882, "loss": 0.6012, "lr": 8.095511568076548e-05, "epoch": 0.6464074169456606, "percentage": 32.33, "elapsed_time": "6:24:54", "remaining_time": "13:25:41", "throughput": 635.6, "total_tokens": 14678792}
+{"current_steps": 1260, "total_steps": 3882, "loss": 0.5358, "lr": 8.078754985148247e-05, "epoch": 0.6489827453000258, "percentage": 32.46, "elapsed_time": "6:26:23", "remaining_time": "13:24:02", "throughput": 635.69, "total_tokens": 14737272}
+{"current_steps": 1265, "total_steps": 3882, "loss": 0.4676, "lr": 8.061942520733474e-05, "epoch": 0.6515580736543909, "percentage": 32.59, "elapsed_time": "6:27:52", "remaining_time": "13:22:25", "throughput": 635.76, "total_tokens": 14795784}
+{"current_steps": 1270, "total_steps": 3882, "loss": 0.489, "lr": 8.045074479989838e-05, "epoch": 0.6541334020087561, "percentage": 32.72, "elapsed_time": "6:29:21", "remaining_time": "13:20:47", "throughput": 635.84, "total_tokens": 14854272}
+{"current_steps": 1275, "total_steps": 3882, "loss": 0.4505, "lr": 8.02815116908369e-05, "epoch": 0.6567087303631213, "percentage": 32.84, "elapsed_time": "6:30:50", "remaining_time": "13:19:10", "throughput": 635.91, "total_tokens": 14912720}
+{"current_steps": 1280, "total_steps": 3882, "loss": 0.4987, "lr": 8.011172895184579e-05, "epoch": 0.6592840587174865, "percentage": 32.97, "elapsed_time": "6:32:19", "remaining_time": "13:17:32", "throughput": 635.99, "total_tokens": 14971192}
+{"current_steps": 1285, "total_steps": 3882, "loss": 0.5156, "lr": 7.994139966459664e-05, "epoch": 0.6618593870718517, "percentage": 33.1, "elapsed_time": "6:33:49", "remaining_time": "13:15:54", "throughput": 636.06, "total_tokens": 15029656}
+{"current_steps": 1290, "total_steps": 3882, "loss": 0.5266, "lr": 7.977052692068127e-05, "epoch": 0.6644347154262168, "percentage": 33.23, "elapsed_time": "6:35:18", "remaining_time": "13:14:17", "throughput": 636.14, "total_tokens": 15088144}
+{"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}