Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc88a9133bd30e9f761aeca11737097aa2bc75e291ca7a8f1b1b21cc4ee3a5a
+oid sha256:61fe60cd6a5c594c616d66be0bb1d9dea2f9d3063cedfcf69a99a1e90689b1b0
 size 29034840

trainer_log.jsonl

@@ -156,3 +156,14 @@
 {"current_steps": 695, "total_steps": 3400, "loss": 0.5351, "lr": 9.362182973536569e-05, "epoch": 0.17898532062838013, "percentage": 20.44, "elapsed_time": "0:31:00", "remaining_time": "2:00:42", "throughput": 3920.82, "total_tokens": 7295568}
 {"current_steps": 700, "total_steps": 3400, "loss": 0.5014, "lr": 9.35024767453647e-05, "epoch": 0.1802729848055627, "percentage": 20.59, "elapsed_time": "0:32:28", "remaining_time": "2:05:16", "throughput": 3770.1, "total_tokens": 7347040}
 {"current_steps": 700, "total_steps": 3400, "eval_loss": 0.5440100431442261, "epoch": 0.1802729848055627, "percentage": 20.59, "elapsed_time": "0:33:07", "remaining_time": "2:07:47", "throughput": 3695.91, "total_tokens": 7347040}
+{"current_steps": 705, "total_steps": 3400, "loss": 0.543, "lr": 9.338209491537257e-05, "epoch": 0.1815606489827453, "percentage": 20.74, "elapsed_time": "0:34:43", "remaining_time": "2:12:44", "throughput": 3551.6, "total_tokens": 7399584}
+{"current_steps": 710, "total_steps": 3400, "loss": 0.4995, "lr": 9.326068709243727e-05, "epoch": 0.1828483131599279, "percentage": 20.88, "elapsed_time": "0:36:11", "remaining_time": "2:17:07", "throughput": 3432.24, "total_tokens": 7452928}
+{"current_steps": 715, "total_steps": 3400, "loss": 0.5109, "lr": 9.313825614787177e-05, "epoch": 0.18413597733711048, "percentage": 21.03, "elapsed_time": "0:37:39", "remaining_time": "2:21:26", "throughput": 3321.05, "total_tokens": 7505112}
+{"current_steps": 720, "total_steps": 3400, "loss": 0.4932, "lr": 9.301480497718593e-05, "epoch": 0.18542364151429308, "percentage": 21.18, "elapsed_time": "0:39:07", "remaining_time": "2:25:37", "throughput": 3219.44, "total_tokens": 7557608}
+{"current_steps": 725, "total_steps": 3400, "loss": 0.5573, "lr": 9.289033650001817e-05, "epoch": 0.18671130569147568, "percentage": 21.32, "elapsed_time": "0:40:36", "remaining_time": "2:29:51", "throughput": 3122.82, "total_tokens": 7610048}
+{"current_steps": 730, "total_steps": 3400, "loss": 0.5305, "lr": 9.276485366006634e-05, "epoch": 0.18799896986865824, "percentage": 21.47, "elapsed_time": "0:42:04", "remaining_time": "2:33:54", "throughput": 3034.8, "total_tokens": 7662056}
+{"current_steps": 735, "total_steps": 3400, "loss": 0.5369, "lr": 9.263835942501807e-05, "epoch": 0.18928663404584084, "percentage": 21.62, "elapsed_time": "0:43:34", "remaining_time": "2:37:58", "throughput": 2950.71, "total_tokens": 7713656}
+{"current_steps": 740, "total_steps": 3400, "loss": 0.5397, "lr": 9.251085678648072e-05, "epoch": 0.19057429822302344, "percentage": 21.76, "elapsed_time": "0:45:02", "remaining_time": "2:41:54", "throughput": 2873.57, "total_tokens": 7765992}
+{"current_steps": 745, "total_steps": 3400, "loss": 0.5116, "lr": 9.238234875991046e-05, "epoch": 0.19186196240020603, "percentage": 21.91, "elapsed_time": "0:46:31", "remaining_time": "2:45:49", "throughput": 2800.48, "total_tokens": 7818448}
+{"current_steps": 750, "total_steps": 3400, "loss": 0.541, "lr": 9.225283838454111e-05, "epoch": 0.19314962657738863, "percentage": 22.06, "elapsed_time": "0:47:59", "remaining_time": "2:49:34", "throughput": 2733.14, "total_tokens": 7870520}
+{"current_steps": 750, "total_steps": 3400, "eval_loss": 0.5273815989494324, "epoch": 0.19314962657738863, "percentage": 22.06, "elapsed_time": "0:48:38", "remaining_time": "2:51:53", "throughput": 2696.45, "total_tokens": 7870520}