Training in progress, step 1050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3ab6d644ac3cb3a77587a21e5db04187d88cc24b3b2be9b5e4e433e0add233
+oid sha256:4499fca7257a53d1a8959e9e138764d24facbc55103cd1d2e30b092c058fc6d9
 size 29034840

trainer_log.jsonl

@@ -218,3 +218,14 @@
 {"current_steps": 995, "total_steps": 3400, "loss": 0.0058, "lr": 8.474846307659658e-05, "epoch": 0.5124903425186711, "percentage": 29.26, "elapsed_time": "4:55:05", "remaining_time": "11:53:15", "throughput": 561.07, "total_tokens": 9934080}
 {"current_steps": 1000, "total_steps": 3400, "loss": 0.0547, "lr": 8.457321315344694e-05, "epoch": 0.5150656708730363, "percentage": 29.41, "elapsed_time": "4:56:31", "remaining_time": "11:51:40", "throughput": 561.16, "total_tokens": 9984000}
 {"current_steps": 1000, "total_steps": 3400, "eval_loss": 0.0007357922149822116, "epoch": 0.5150656708730363, "percentage": 29.41, "elapsed_time": "4:56:50", "remaining_time": "11:52:26", "throughput": 560.55, "total_tokens": 9984000}
+{"current_steps": 1005, "total_steps": 3400, "loss": 0.0042, "lr": 8.439714556870704e-05, "epoch": 0.5176409992274015, "percentage": 29.56, "elapsed_time": "4:58:22", "remaining_time": "11:51:02", "throughput": 560.49, "total_tokens": 10033920}
+{"current_steps": 1010, "total_steps": 3400, "loss": 0.0419, "lr": 8.422026448640124e-05, "epoch": 0.5202163275817667, "percentage": 29.71, "elapsed_time": "4:59:48", "remaining_time": "11:49:26", "throughput": 560.57, "total_tokens": 10083840}
+{"current_steps": 1015, "total_steps": 3400, "loss": 0.0313, "lr": 8.40425740897932e-05, "epoch": 0.5227916559361319, "percentage": 29.85, "elapsed_time": "5:01:14", "remaining_time": "11:47:49", "throughput": 560.68, "total_tokens": 10133760}
+{"current_steps": 1020, "total_steps": 3400, "loss": 0.005, "lr": 8.386407858128706e-05, "epoch": 0.525366984290497, "percentage": 30.0, "elapsed_time": "5:02:40", "remaining_time": "11:46:13", "throughput": 560.77, "total_tokens": 10183680}
+{"current_steps": 1025, "total_steps": 3400, "loss": 0.0171, "lr": 8.368478218232787e-05, "epoch": 0.5279423126448622, "percentage": 30.15, "elapsed_time": "5:04:06", "remaining_time": "11:44:37", "throughput": 560.87, "total_tokens": 10233600}
+{"current_steps": 1030, "total_steps": 3400, "loss": 0.0019, "lr": 8.350468913330192e-05, "epoch": 0.5305176409992274, "percentage": 30.29, "elapsed_time": "5:05:31", "remaining_time": "11:42:59", "throughput": 560.98, "total_tokens": 10283520}
+{"current_steps": 1035, "total_steps": 3400, "loss": 0.0256, "lr": 8.33238036934364e-05, "epoch": 0.5330929693535926, "percentage": 30.44, "elapsed_time": "5:06:57", "remaining_time": "11:41:24", "throughput": 561.06, "total_tokens": 10333440}
+{"current_steps": 1040, "total_steps": 3400, "loss": 0.0019, "lr": 8.31421301406986e-05, "epoch": 0.5356682977079578, "percentage": 30.59, "elapsed_time": "5:08:23", "remaining_time": "11:39:48", "throughput": 561.15, "total_tokens": 10383360}
+{"current_steps": 1045, "total_steps": 3400, "loss": 0.018, "lr": 8.29596727716949e-05, "epoch": 0.5382436260623229, "percentage": 30.74, "elapsed_time": "5:09:50", "remaining_time": "11:38:14", "throughput": 561.23, "total_tokens": 10433280}
+{"current_steps": 1050, "total_steps": 3400, "loss": 0.0007, "lr": 8.277643590156894e-05, "epoch": 0.5408189544166881, "percentage": 30.88, "elapsed_time": "5:11:16", "remaining_time": "11:36:40", "throughput": 561.3, "total_tokens": 10483200}
+{"current_steps": 1050, "total_steps": 3400, "eval_loss": 0.05677948147058487, "epoch": 0.5408189544166881, "percentage": 30.88, "elapsed_time": "5:11:35", "remaining_time": "11:37:22", "throughput": 560.73, "total_tokens": 10483200}