Training in progress, step 150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acda72bb812aacf6b5ce45f87c28678a6f2e73c7b48f2258dd8d59ca2f5bf1aa
+oid sha256:2d6cd128d7c617876ad46ba2cf72bcffc9405810c45769e1284c0504c35ae59f
 size 29034840

trainer_log.jsonl

@@ -20,3 +20,14 @@
 {"current_steps": 95, "total_steps": 3882, "loss": 0.8996, "lr": 4.871794871794872e-05, "epoch": 0.04893123873293845, "percentage": 2.45, "elapsed_time": "0:30:31", "remaining_time": "20:17:00", "throughput": 606.61, "total_tokens": 1111176}
 {"current_steps": 100, "total_steps": 3882, "loss": 0.9024, "lr": 5.128205128205128e-05, "epoch": 0.05150656708730363, "percentage": 2.58, "elapsed_time": "0:32:01", "remaining_time": "20:10:52", "throughput": 608.88, "total_tokens": 1169664}
 {"current_steps": 100, "total_steps": 3882, "eval_loss": 0.911374032497406, "epoch": 0.05150656708730363, "percentage": 2.58, "elapsed_time": "0:32:20", "remaining_time": "20:23:12", "throughput": 602.74, "total_tokens": 1169664}
+{"current_steps": 105, "total_steps": 3882, "loss": 0.9142, "lr": 5.384615384615385e-05, "epoch": 0.05408189544166881, "percentage": 2.7, "elapsed_time": "0:33:57", "remaining_time": "20:21:47", "throughput": 602.63, "total_tokens": 1228112}
+{"current_steps": 110, "total_steps": 3882, "loss": 0.9054, "lr": 5.6410256410256414e-05, "epoch": 0.056657223796033995, "percentage": 2.83, "elapsed_time": "0:35:26", "remaining_time": "20:15:28", "throughput": 604.96, "total_tokens": 1286608}
+{"current_steps": 115, "total_steps": 3882, "loss": 0.8997, "lr": 5.897435897435898e-05, "epoch": 0.05923255215039917, "percentage": 2.96, "elapsed_time": "0:36:56", "remaining_time": "20:10:10", "throughput": 606.8, "total_tokens": 1345072}
+{"current_steps": 120, "total_steps": 3882, "loss": 0.8988, "lr": 6.153846153846155e-05, "epoch": 0.06180788050476436, "percentage": 3.09, "elapsed_time": "0:38:25", "remaining_time": "20:04:43", "throughput": 608.73, "total_tokens": 1403544}
+{"current_steps": 125, "total_steps": 3882, "loss": 0.9087, "lr": 6.410256410256412e-05, "epoch": 0.06438320885912954, "percentage": 3.22, "elapsed_time": "0:39:56", "remaining_time": "20:00:26", "throughput": 610.09, "total_tokens": 1462024}
+{"current_steps": 130, "total_steps": 3882, "loss": 0.8961, "lr": 6.666666666666667e-05, "epoch": 0.06695853721349472, "percentage": 3.35, "elapsed_time": "0:41:25", "remaining_time": "19:55:28", "throughput": 611.82, "total_tokens": 1520528}
+{"current_steps": 135, "total_steps": 3882, "loss": 0.903, "lr": 6.923076923076924e-05, "epoch": 0.0695338655678599, "percentage": 3.48, "elapsed_time": "0:42:56", "remaining_time": "19:51:42", "throughput": 612.94, "total_tokens": 1579024}
+{"current_steps": 140, "total_steps": 3882, "loss": 0.899, "lr": 7.17948717948718e-05, "epoch": 0.07210919392222509, "percentage": 3.61, "elapsed_time": "0:44:25", "remaining_time": "19:47:14", "throughput": 614.42, "total_tokens": 1637504}
+{"current_steps": 145, "total_steps": 3882, "loss": 0.9071, "lr": 7.435897435897436e-05, "epoch": 0.07468452227659027, "percentage": 3.74, "elapsed_time": "0:45:55", "remaining_time": "19:43:28", "throughput": 615.57, "total_tokens": 1696024}
+{"current_steps": 150, "total_steps": 3882, "loss": 0.9045, "lr": 7.692307692307693e-05, "epoch": 0.07725985063095545, "percentage": 3.86, "elapsed_time": "0:47:24", "remaining_time": "19:39:19", "throughput": 616.91, "total_tokens": 1754512}
+{"current_steps": 150, "total_steps": 3882, "eval_loss": 0.8934853076934814, "epoch": 0.07725985063095545, "percentage": 3.86, "elapsed_time": "0:47:43", "remaining_time": "19:47:33", "throughput": 612.63, "total_tokens": 1754512}