Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb788f0d6ef0dec08ed5f5eb5575155c2531033fdd3222d6ffa1678d4305eab
+oid sha256:2a03e9eee1ec95bdd483369ad9faaa09779f119406744d2cbea8db7e18f4878e
 size 29034840

trainer_log.jsonl

@@ -42,3 +42,14 @@
 {"current_steps": 195, "total_steps": 3882, "loss": 0.9037, "lr": 0.0001, "epoch": 0.10043780582024209, "percentage": 5.02, "elapsed_time": "1:01:11", "remaining_time": "19:17:04", "throughput": 621.18, "total_tokens": 2280800}
 {"current_steps": 200, "total_steps": 3882, "loss": 0.904, "lr": 9.999954623308172e-05, "epoch": 0.10301313417460727, "percentage": 5.15, "elapsed_time": "1:02:41", "remaining_time": "19:14:00", "throughput": 621.98, "total_tokens": 2339304}
 {"current_steps": 200, "total_steps": 3882, "eval_loss": 0.8980139493942261, "epoch": 0.10301313417460727, "percentage": 5.15, "elapsed_time": "1:03:00", "remaining_time": "19:19:56", "throughput": 618.8, "total_tokens": 2339304}
+{"current_steps": 205, "total_steps": 3882, "loss": 0.9029, "lr": 9.999818494056303e-05, "epoch": 0.10558846252897244, "percentage": 5.28, "elapsed_time": "1:04:33", "remaining_time": "19:17:54", "throughput": 619.05, "total_tokens": 2397808}
+{"current_steps": 210, "total_steps": 3882, "loss": 0.9005, "lr": 9.99959161471523e-05, "epoch": 0.10816379088333762, "percentage": 5.41, "elapsed_time": "1:06:02", "remaining_time": "19:14:52", "throughput": 619.83, "total_tokens": 2456288}
+{"current_steps": 215, "total_steps": 3882, "loss": 0.9096, "lr": 9.99927398940297e-05, "epoch": 0.11073911923770281, "percentage": 5.54, "elapsed_time": "1:07:30", "remaining_time": "19:11:25", "throughput": 620.85, "total_tokens": 2514784}
+{"current_steps": 220, "total_steps": 3882, "loss": 0.9036, "lr": 9.998865623884635e-05, "epoch": 0.11331444759206799, "percentage": 5.67, "elapsed_time": "1:08:59", "remaining_time": "19:08:31", "throughput": 621.56, "total_tokens": 2573240}
+{"current_steps": 225, "total_steps": 3882, "loss": 0.901, "lr": 9.998366525572336e-05, "epoch": 0.11588977594643317, "percentage": 5.8, "elapsed_time": "1:10:27", "remaining_time": "19:05:14", "throughput": 622.48, "total_tokens": 2631672}
+{"current_steps": 230, "total_steps": 3882, "loss": 0.9018, "lr": 9.997776703525046e-05, "epoch": 0.11846510430079835, "percentage": 5.92, "elapsed_time": "1:11:56", "remaining_time": "19:02:26", "throughput": 623.14, "total_tokens": 2690112}
+{"current_steps": 235, "total_steps": 3882, "loss": 0.8934, "lr": 9.997096168448432e-05, "epoch": 0.12104043265516354, "percentage": 6.05, "elapsed_time": "1:13:24", "remaining_time": "18:59:11", "throughput": 624.07, "total_tokens": 2748608}
+{"current_steps": 240, "total_steps": 3882, "loss": 0.8876, "lr": 9.996324932694668e-05, "epoch": 0.12361576100952872, "percentage": 6.18, "elapsed_time": "1:14:53", "remaining_time": "18:56:31", "throughput": 624.67, "total_tokens": 2807080}
+{"current_steps": 245, "total_steps": 3882, "loss": 0.9084, "lr": 9.995463010262206e-05, "epoch": 0.1261910893638939, "percentage": 6.31, "elapsed_time": "1:16:21", "remaining_time": "18:53:29", "throughput": 625.48, "total_tokens": 2865520}
+{"current_steps": 250, "total_steps": 3882, "loss": 0.9106, "lr": 9.994510416795519e-05, "epoch": 0.12876641771825909, "percentage": 6.44, "elapsed_time": "1:17:50", "remaining_time": "18:50:56", "throughput": 626.03, "total_tokens": 2924016}
+{"current_steps": 250, "total_steps": 3882, "eval_loss": 0.8958488702774048, "epoch": 0.12876641771825909, "percentage": 6.44, "elapsed_time": "1:18:10", "remaining_time": "18:55:39", "throughput": 623.43, "total_tokens": 2924016}