Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c194e4011ebc3d53bf21924236aa69f02cd3e886bdcc096049ceabfa8e037964
+oid sha256:40f0e52182147fdabf2ddf1a520d0249faf099e8bb9941553d5a51b579af5e1c
 size 29034840

trainer_log.jsonl

@@ -189,3 +189,14 @@
 {"current_steps": 845, "total_steps": 3400, "loss": 0.5046, "lr": 8.960590861978265e-05, "epoch": 0.21761524594385784, "percentage": 24.85, "elapsed_time": "1:17:51", "remaining_time": "3:55:24", "throughput": 1898.38, "total_tokens": 8867720}
 {"current_steps": 850, "total_steps": 3400, "loss": 0.5063, "lr": 8.945702546981969e-05, "epoch": 0.21890291012104043, "percentage": 25.0, "elapsed_time": "1:19:21", "remaining_time": "3:58:04", "throughput": 1873.33, "total_tokens": 8919608}
 {"current_steps": 850, "total_steps": 3400, "eval_loss": 0.5525640249252319, "epoch": 0.21890291012104043, "percentage": 25.0, "elapsed_time": "1:20:00", "remaining_time": "4:00:01", "throughput": 1858.09, "total_tokens": 8919608}
+{"current_steps": 855, "total_steps": 3400, "loss": 0.5853, "lr": 8.930720915538487e-05, "epoch": 0.22019057429822303, "percentage": 25.15, "elapsed_time": "1:21:34", "remaining_time": "4:02:50", "throughput": 1832.75, "total_tokens": 8971048}
+{"current_steps": 860, "total_steps": 3400, "loss": 0.5534, "lr": 8.915646321965614e-05, "epoch": 0.22147823847540563, "percentage": 25.29, "elapsed_time": "1:23:04", "remaining_time": "4:05:22", "throughput": 1810.11, "total_tokens": 9022936}
+{"current_steps": 865, "total_steps": 3400, "loss": 0.5623, "lr": 8.900479122779712e-05, "epoch": 0.2227659026525882, "percentage": 25.44, "elapsed_time": "1:24:32", "remaining_time": "4:07:47", "throughput": 1788.95, "total_tokens": 9075336}
+{"current_steps": 870, "total_steps": 3400, "loss": 0.5561, "lr": 8.885219676687277e-05, "epoch": 0.2240535668297708, "percentage": 25.59, "elapsed_time": "1:26:03", "remaining_time": "4:10:14", "throughput": 1767.89, "total_tokens": 9127688}
+{"current_steps": 875, "total_steps": 3400, "loss": 0.5449, "lr": 8.869868344576459e-05, "epoch": 0.22534123100695339, "percentage": 25.74, "elapsed_time": "1:27:31", "remaining_time": "4:12:34", "throughput": 1748.15, "total_tokens": 9180624}
+{"current_steps": 880, "total_steps": 3400, "loss": 0.5062, "lr": 8.854425489508532e-05, "epoch": 0.22662889518413598, "percentage": 25.88, "elapsed_time": "1:29:02", "remaining_time": "4:14:57", "throughput": 1728.37, "total_tokens": 9233176}
+{"current_steps": 885, "total_steps": 3400, "loss": 0.5033, "lr": 8.838891476709288e-05, "epoch": 0.22791655936131858, "percentage": 26.03, "elapsed_time": "1:30:30", "remaining_time": "4:17:12", "throughput": 1710.09, "total_tokens": 9286688}
+{"current_steps": 890, "total_steps": 3400, "loss": 0.4845, "lr": 8.823266673560426e-05, "epoch": 0.22920422353850115, "percentage": 26.18, "elapsed_time": "1:31:59", "remaining_time": "4:19:26", "throughput": 1692.06, "total_tokens": 9339600}
+{"current_steps": 895, "total_steps": 3400, "loss": 0.5595, "lr": 8.807551449590846e-05, "epoch": 0.23049188771568374, "percentage": 26.32, "elapsed_time": "1:33:27", "remaining_time": "4:21:34", "throughput": 1674.82, "total_tokens": 9391536}
+{"current_steps": 900, "total_steps": 3400, "loss": 0.5251, "lr": 8.791746176467907e-05, "epoch": 0.23177955189286634, "percentage": 26.47, "elapsed_time": "1:34:57", "remaining_time": "4:23:46", "throughput": 1657.48, "total_tokens": 9443616}
+{"current_steps": 900, "total_steps": 3400, "eval_loss": 0.49604204297065735, "epoch": 0.23177955189286634, "percentage": 26.47, "elapsed_time": "1:35:37", "remaining_time": "4:25:36", "throughput": 1646.06, "total_tokens": 9443616}