Training in progress, step 1050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec35e19707d55e085c42f2fc7f96384949ae1c2b6909dea425372d9568c8a7a
+oid sha256:9ec2597cb66cc8bf7c12cf0511653b2a0fba5900300120225835d32ef88d42ca
 size 29034840

trainer_log.jsonl

@@ -218,3 +218,14 @@
 {"current_steps": 995, "total_steps": 3882, "loss": 0.6508, "lr": 8.882644638028646e-05, "epoch": 0.5124903425186711, "percentage": 25.63, "elapsed_time": "5:06:03", "remaining_time": "14:48:01", "throughput": 633.74, "total_tokens": 11637712}
 {"current_steps": 1000, "total_steps": 3882, "loss": 0.5971, "lr": 8.869187556431046e-05, "epoch": 0.5150656708730363, "percentage": 25.76, "elapsed_time": "5:07:31", "remaining_time": "14:46:17", "throughput": 633.88, "total_tokens": 11696200}
 {"current_steps": 1000, "total_steps": 3882, "eval_loss": 0.7078786492347717, "epoch": 0.5150656708730363, "percentage": 25.76, "elapsed_time": "5:07:51", "remaining_time": "14:47:14", "throughput": 633.21, "total_tokens": 11696200}
+{"current_steps": 1005, "total_steps": 3882, "loss": 0.6959, "lr": 8.855660246460895e-05, "epoch": 0.5176409992274015, "percentage": 25.89, "elapsed_time": "5:09:25", "remaining_time": "14:45:47", "throughput": 633.15, "total_tokens": 11754720}
+{"current_steps": 1010, "total_steps": 3882, "loss": 0.6918, "lr": 8.842062953648023e-05, "epoch": 0.5202163275817667, "percentage": 26.02, "elapsed_time": "5:10:53", "remaining_time": "14:44:02", "throughput": 633.3, "total_tokens": 11813216}
+{"current_steps": 1015, "total_steps": 3882, "loss": 0.7269, "lr": 8.828395924792497e-05, "epoch": 0.5227916559361319, "percentage": 26.15, "elapsed_time": "5:12:21", "remaining_time": "14:42:19", "throughput": 633.43, "total_tokens": 11871712}
+{"current_steps": 1020, "total_steps": 3882, "loss": 0.7026, "lr": 8.814659407960141e-05, "epoch": 0.525366984290497, "percentage": 26.28, "elapsed_time": "5:13:49", "remaining_time": "14:40:33", "throughput": 633.58, "total_tokens": 11930200}
+{"current_steps": 1025, "total_steps": 3882, "loss": 0.6467, "lr": 8.800853652478028e-05, "epoch": 0.5279423126448622, "percentage": 26.4, "elapsed_time": "5:15:18", "remaining_time": "14:38:52", "throughput": 633.7, "total_tokens": 11988704}
+{"current_steps": 1030, "total_steps": 3882, "loss": 0.6155, "lr": 8.786978908929966e-05, "epoch": 0.5305176409992274, "percentage": 26.53, "elapsed_time": "5:16:46", "remaining_time": "14:37:07", "throughput": 633.85, "total_tokens": 12047176}
+{"current_steps": 1035, "total_steps": 3882, "loss": 0.7849, "lr": 8.773035429151937e-05, "epoch": 0.5330929693535926, "percentage": 26.66, "elapsed_time": "5:18:15", "remaining_time": "14:35:25", "throughput": 633.97, "total_tokens": 12105680}
+{"current_steps": 1040, "total_steps": 3882, "loss": 0.6341, "lr": 8.759023466227538e-05, "epoch": 0.5356682977079578, "percentage": 26.79, "elapsed_time": "5:19:42", "remaining_time": "14:33:39", "throughput": 634.13, "total_tokens": 12164208}
+{"current_steps": 1045, "total_steps": 3882, "loss": 0.7189, "lr": 8.744943274483376e-05, "epoch": 0.5382436260623229, "percentage": 26.92, "elapsed_time": "5:21:11", "remaining_time": "14:32:00", "throughput": 634.22, "total_tokens": 12222672}
+{"current_steps": 1050, "total_steps": 3882, "loss": 0.6914, "lr": 8.730795109484461e-05, "epoch": 0.5408189544166881, "percentage": 27.05, "elapsed_time": "5:22:39", "remaining_time": "14:30:14", "throughput": 634.37, "total_tokens": 12281072}
+{"current_steps": 1050, "total_steps": 3882, "eval_loss": 0.6824291348457336, "epoch": 0.5408189544166881, "percentage": 27.05, "elapsed_time": "5:22:59", "remaining_time": "14:31:08", "throughput": 633.73, "total_tokens": 12281072}