Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafcae20cec2616f79019b754b4d774006e4d29a7cf0dd3337ccaecf513543a7
+oid sha256:e2604e713adfd5ff8fff3e76524b74b5484d4e4df2c3ddf9459067c342c4d295
 size 29034840

trainer_log.jsonl

@@ -174,3 +174,14 @@
 {"current_steps": 795, "total_steps": 3882, "loss": 0.7314, "lr": 9.36068338730834e-05, "epoch": 0.40947720834406387, "percentage": 20.48, "elapsed_time": "4:05:26", "remaining_time": "15:53:02", "throughput": 631.42, "total_tokens": 9298528}
 {"current_steps": 800, "total_steps": 3882, "loss": 0.6911, "lr": 9.35022166553215e-05, "epoch": 0.41205253669842906, "percentage": 20.61, "elapsed_time": "4:06:55", "remaining_time": "15:51:17", "throughput": 631.56, "total_tokens": 9357016}
 {"current_steps": 800, "total_steps": 3882, "eval_loss": 0.7180347442626953, "epoch": 0.41205253669842906, "percentage": 20.61, "elapsed_time": "4:07:14", "remaining_time": "15:52:31", "throughput": 630.74, "total_tokens": 9357016}
+{"current_steps": 805, "total_steps": 3882, "loss": 0.7086, "lr": 9.339680984288799e-05, "epoch": 0.41462786505279425, "percentage": 20.74, "elapsed_time": "4:08:48", "remaining_time": "15:51:02", "throughput": 630.7, "total_tokens": 9415480}
+{"current_steps": 810, "total_steps": 3882, "loss": 0.7726, "lr": 9.329061534898783e-05, "epoch": 0.4172031934071594, "percentage": 20.87, "elapsed_time": "4:10:17", "remaining_time": "15:49:15", "throughput": 630.86, "total_tokens": 9473928}
+{"current_steps": 815, "total_steps": 3882, "loss": 0.7286, "lr": 9.318363510112296e-05, "epoch": 0.4197785217615246, "percentage": 20.99, "elapsed_time": "4:11:45", "remaining_time": "15:47:25", "throughput": 631.05, "total_tokens": 9532408}
+{"current_steps": 820, "total_steps": 3882, "loss": 0.7515, "lr": 9.307587104105729e-05, "epoch": 0.4223538501158898, "percentage": 21.12, "elapsed_time": "4:13:14", "remaining_time": "15:45:37", "throughput": 631.22, "total_tokens": 9590920}
+{"current_steps": 825, "total_steps": 3882, "loss": 0.7344, "lr": 9.296732512478139e-05, "epoch": 0.42492917847025496, "percentage": 21.25, "elapsed_time": "4:14:42", "remaining_time": "15:43:49", "throughput": 631.39, "total_tokens": 9649400}
+{"current_steps": 830, "total_steps": 3882, "loss": 0.6954, "lr": 9.285799932247714e-05, "epoch": 0.42750450682462016, "percentage": 21.38, "elapsed_time": "4:16:11", "remaining_time": "15:42:01", "throughput": 631.56, "total_tokens": 9707888}
+{"current_steps": 835, "total_steps": 3882, "loss": 0.7312, "lr": 9.274789561848183e-05, "epoch": 0.43007983517898535, "percentage": 21.51, "elapsed_time": "4:17:39", "remaining_time": "15:40:13", "throughput": 631.73, "total_tokens": 9766384}
+{"current_steps": 840, "total_steps": 3882, "loss": 0.647, "lr": 9.263701601125218e-05, "epoch": 0.4326551635333505, "percentage": 21.64, "elapsed_time": "4:19:07", "remaining_time": "15:38:24", "throughput": 631.92, "total_tokens": 9824896}
+{"current_steps": 845, "total_steps": 3882, "loss": 0.7273, "lr": 9.252536251332813e-05, "epoch": 0.4352304918877157, "percentage": 21.77, "elapsed_time": "4:20:36", "remaining_time": "15:36:40", "throughput": 632.05, "total_tokens": 9883408}
+{"current_steps": 850, "total_steps": 3882, "loss": 0.7455, "lr": 9.24129371512962e-05, "epoch": 0.43780582024208087, "percentage": 21.9, "elapsed_time": "4:22:04", "remaining_time": "15:34:49", "throughput": 632.26, "total_tokens": 9941896}
+{"current_steps": 850, "total_steps": 3882, "eval_loss": 0.7039459347724915, "epoch": 0.43780582024208087, "percentage": 21.9, "elapsed_time": "4:22:24", "remaining_time": "15:36:00", "throughput": 631.47, "total_tokens": 9941896}