Training in progress, step 2600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05860e6926535e861ff510ad885fc4de39eb23da412202261559dc491a06bd00
+oid sha256:273fcf9e0b0197d44caacef12013e816c21f5d50361370148cdbf9380973f3f1
 size 18516456

trainer_log.jsonl

@@ -563,3 +563,14 @@
 {"current_steps": 2545, "total_steps": 3400, "loss": 0.2985, "lr": 1.631521781767214e-05, "epoch": 1.310584599536441, "percentage": 74.85, "elapsed_time": "9:26:15", "remaining_time": "3:10:14", "throughput": 875.94, "total_tokens": 29760376}
 {"current_steps": 2550, "total_steps": 3400, "loss": 0.3231, "lr": 1.6135921418712956e-05, "epoch": 1.3131599278908062, "percentage": 75.0, "elapsed_time": "9:27:19", "remaining_time": "3:09:06", "throughput": 876.02, "total_tokens": 29818856}
 {"current_steps": 2550, "total_steps": 3400, "eval_loss": 0.7146337628364563, "epoch": 1.3131599278908062, "percentage": 75.0, "elapsed_time": "9:27:35", "remaining_time": "3:09:11", "throughput": 875.6, "total_tokens": 29818856}
+{"current_steps": 2555, "total_steps": 3400, "loss": 0.2689, "lr": 1.5957425910206785e-05, "epoch": 1.3157352562451712, "percentage": 75.15, "elapsed_time": "9:28:44", "remaining_time": "3:08:05", "throughput": 875.55, "total_tokens": 29877288}
+{"current_steps": 2560, "total_steps": 3400, "loss": 0.3889, "lr": 1.577973551359877e-05, "epoch": 1.3183105845995364, "percentage": 75.29, "elapsed_time": "9:29:47", "remaining_time": "3:06:57", "throughput": 875.63, "total_tokens": 29935776}
+{"current_steps": 2565, "total_steps": 3400, "loss": 0.2489, "lr": 1.560285443129296e-05, "epoch": 1.3208859129539017, "percentage": 75.44, "elapsed_time": "9:30:52", "remaining_time": "3:05:50", "throughput": 875.68, "total_tokens": 29994232}
+{"current_steps": 2570, "total_steps": 3400, "loss": 0.3016, "lr": 1.542678684655306e-05, "epoch": 1.3234612413082667, "percentage": 75.59, "elapsed_time": "9:31:56", "remaining_time": "3:04:42", "throughput": 875.76, "total_tokens": 30052760}
+{"current_steps": 2575, "total_steps": 3400, "loss": 0.3063, "lr": 1.5251536923403426e-05, "epoch": 1.326036569662632, "percentage": 75.74, "elapsed_time": "9:32:59", "remaining_time": "3:03:34", "throughput": 875.84, "total_tokens": 30111200}
+{"current_steps": 2580, "total_steps": 3400, "loss": 0.3159, "lr": 1.5077108806530581e-05, "epoch": 1.3286118980169972, "percentage": 75.88, "elapsed_time": "9:34:03", "remaining_time": "3:02:27", "throughput": 875.91, "total_tokens": 30169680}
+{"current_steps": 2585, "total_steps": 3400, "loss": 0.3752, "lr": 1.4903506621185192e-05, "epoch": 1.3311872263713624, "percentage": 76.03, "elapsed_time": "9:35:07", "remaining_time": "3:01:19", "throughput": 875.98, "total_tokens": 30228176}
+{"current_steps": 2590, "total_steps": 3400, "loss": 0.3207, "lr": 1.4730734473084568e-05, "epoch": 1.3337625547257275, "percentage": 76.18, "elapsed_time": "9:36:11", "remaining_time": "3:00:11", "throughput": 876.06, "total_tokens": 30286656}
+{"current_steps": 2595, "total_steps": 3400, "loss": 0.2928, "lr": 1.4558796448315504e-05, "epoch": 1.3363378830800927, "percentage": 76.32, "elapsed_time": "9:37:15", "remaining_time": "2:59:04", "throughput": 876.13, "total_tokens": 30345160}
+{"current_steps": 2600, "total_steps": 3400, "loss": 0.2779, "lr": 1.4387696613237612e-05, "epoch": 1.338913211434458, "percentage": 76.47, "elapsed_time": "9:38:19", "remaining_time": "2:57:56", "throughput": 876.2, "total_tokens": 30403640}
+{"current_steps": 2600, "total_steps": 3400, "eval_loss": 0.695651650428772, "epoch": 1.338913211434458, "percentage": 76.47, "elapsed_time": "9:38:35", "remaining_time": "2:58:01", "throughput": 875.79, "total_tokens": 30403640}