Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6469efd0e0f557a18cd35ba4f70eb77371da998a85d2c741e6c6de160fc4ff06
+oid sha256:271e272f3f98dafac54eabf65fe7c941a42e4c849ca7ed4c3839a08fa408499d
 size 29034840

trainer_log.jsonl

@@ -175,3 +175,14 @@
 {"current_steps": 795, "total_steps": 6770, "loss": 0.4752, "lr": 9.876457665229097e-05, "epoch": 0.23485967503692762, "percentage": 11.74, "elapsed_time": "3:57:39", "remaining_time": "1 day, 5:46:14", "throughput": 578.49, "total_tokens": 8249232}
 {"current_steps": 800, "total_steps": 6770, "loss": 0.4239, "lr": 9.87374507221299e-05, "epoch": 0.2363367799113737, "percentage": 11.82, "elapsed_time": "3:59:07", "remaining_time": "1 day, 5:44:30", "throughput": 578.62, "total_tokens": 8301976}
 {"current_steps": 800, "total_steps": 6770, "eval_loss": 0.48219749331474304, "epoch": 0.2363367799113737, "percentage": 11.82, "elapsed_time": "3:59:26", "remaining_time": "1 day, 5:46:52", "throughput": 577.85, "total_tokens": 8301976}
+{"current_steps": 805, "total_steps": 6770, "loss": 0.4482, "lr": 9.87100340248266e-05, "epoch": 0.2378138847858198, "percentage": 11.89, "elapsed_time": "4:00:58", "remaining_time": "1 day, 5:45:39", "throughput": 577.76, "total_tokens": 8353736}
+{"current_steps": 810, "total_steps": 6770, "loss": 0.4764, "lr": 9.868232672394881e-05, "epoch": 0.23929098966026588, "percentage": 11.96, "elapsed_time": "4:02:26", "remaining_time": "1 day, 5:43:56", "throughput": 577.87, "total_tokens": 8406216}
+{"current_steps": 815, "total_steps": 6770, "loss": 0.4476, "lr": 9.8654328984798e-05, "epoch": 0.24076809453471196, "percentage": 12.04, "elapsed_time": "4:03:53", "remaining_time": "1 day, 5:42:06", "throughput": 577.96, "total_tokens": 8457752}
+{"current_steps": 820, "total_steps": 6770, "loss": 0.4295, "lr": 9.862604097440844e-05, "epoch": 0.24224519940915806, "percentage": 12.11, "elapsed_time": "4:05:21", "remaining_time": "1 day, 5:40:22", "throughput": 578.09, "total_tokens": 8510440}
+{"current_steps": 825, "total_steps": 6770, "loss": 0.5384, "lr": 9.859746286154607e-05, "epoch": 0.24372230428360414, "percentage": 12.19, "elapsed_time": "4:06:49", "remaining_time": "1 day, 5:38:34", "throughput": 578.16, "total_tokens": 8562016}
+{"current_steps": 830, "total_steps": 6770, "loss": 0.5357, "lr": 9.856859481670764e-05, "epoch": 0.24519940915805022, "percentage": 12.26, "elapsed_time": "4:08:16", "remaining_time": "1 day, 5:36:46", "throughput": 578.28, "total_tokens": 8614184}
+{"current_steps": 835, "total_steps": 6770, "loss": 0.5309, "lr": 9.853943701211963e-05, "epoch": 0.2466765140324963, "percentage": 12.33, "elapsed_time": "4:09:43", "remaining_time": "1 day, 5:34:59", "throughput": 578.4, "total_tokens": 8666528}
+{"current_steps": 840, "total_steps": 6770, "loss": 0.4949, "lr": 9.850998962173719e-05, "epoch": 0.2481536189069424, "percentage": 12.41, "elapsed_time": "4:11:10", "remaining_time": "1 day, 5:33:13", "throughput": 578.47, "total_tokens": 8718048}
+{"current_steps": 845, "total_steps": 6770, "loss": 0.4681, "lr": 9.848025282124317e-05, "epoch": 0.24963072378138848, "percentage": 12.48, "elapsed_time": "4:12:38", "remaining_time": "1 day, 5:31:28", "throughput": 578.55, "total_tokens": 8769968}
+{"current_steps": 850, "total_steps": 6770, "loss": 0.4949, "lr": 9.845022678804701e-05, "epoch": 0.2511078286558346, "percentage": 12.56, "elapsed_time": "4:14:05", "remaining_time": "1 day, 5:29:41", "throughput": 578.71, "total_tokens": 8822832}
+{"current_steps": 850, "total_steps": 6770, "eval_loss": 0.6121839880943298, "epoch": 0.2511078286558346, "percentage": 12.56, "elapsed_time": "4:14:24", "remaining_time": "1 day, 5:31:54", "throughput": 577.98, "total_tokens": 8822832}