Training in progress, step 2550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9c5a90f0316ee953467cae5ec9a849c3cc7b35324d075196476f5e2a6e857e
+oid sha256:05860e6926535e861ff510ad885fc4de39eb23da412202261559dc491a06bd00
 size 18516456

trainer_log.jsonl

@@ -552,3 +552,14 @@
 {"current_steps": 2495, "total_steps": 3400, "loss": 0.2854, "lr": 1.8151288651144893e-05, "epoch": 1.284831315992789, "percentage": 73.38, "elapsed_time": "9:15:19", "remaining_time": "3:21:25", "throughput": 875.63, "total_tokens": 29175496}
 {"current_steps": 2500, "total_steps": 3400, "loss": 0.3221, "lr": 1.796421964420285e-05, "epoch": 1.2874066443471541, "percentage": 73.53, "elapsed_time": "9:16:22", "remaining_time": "3:20:17", "throughput": 875.72, "total_tokens": 29233968}
 {"current_steps": 2500, "total_steps": 3400, "eval_loss": 0.7222262620925903, "epoch": 1.2874066443471541, "percentage": 73.53, "elapsed_time": "9:16:38", "remaining_time": "3:20:23", "throughput": 875.3, "total_tokens": 29233968}
+{"current_steps": 2505, "total_steps": 3400, "loss": 0.2344, "lr": 1.7777908288191176e-05, "epoch": 1.2899819727015194, "percentage": 73.68, "elapsed_time": "9:17:46", "remaining_time": "3:19:17", "throughput": 875.27, "total_tokens": 29292464}
+{"current_steps": 2510, "total_steps": 3400, "loss": 0.2727, "lr": 1.7592358989400883e-05, "epoch": 1.2925573010558846, "percentage": 73.82, "elapsed_time": "9:18:50", "remaining_time": "3:18:09", "throughput": 875.36, "total_tokens": 29350952}
+{"current_steps": 2515, "total_steps": 3400, "loss": 0.2687, "lr": 1.740757613610028e-05, "epoch": 1.2951326294102499, "percentage": 73.97, "elapsed_time": "9:19:53", "remaining_time": "3:17:01", "throughput": 875.46, "total_tokens": 29409432}
+{"current_steps": 2520, "total_steps": 3400, "loss": 0.2632, "lr": 1.7223564098431067e-05, "epoch": 1.2977079577646151, "percentage": 74.12, "elapsed_time": "9:20:56", "remaining_time": "3:15:52", "throughput": 875.56, "total_tokens": 29467880}
+{"current_steps": 2525, "total_steps": 3400, "loss": 0.3057, "lr": 1.704032722830512e-05, "epoch": 1.3002832861189801, "percentage": 74.26, "elapsed_time": "9:21:59", "remaining_time": "3:14:44", "throughput": 875.65, "total_tokens": 29526384}
+{"current_steps": 2530, "total_steps": 3400, "loss": 0.3054, "lr": 1.68578698593014e-05, "epoch": 1.3028586144733454, "percentage": 74.41, "elapsed_time": "9:23:03", "remaining_time": "3:13:37", "throughput": 875.72, "total_tokens": 29584880}
+{"current_steps": 2535, "total_steps": 3400, "loss": 0.28, "lr": 1.6676196306563613e-05, "epoch": 1.3054339428277104, "percentage": 74.56, "elapsed_time": "9:24:07", "remaining_time": "3:12:29", "throughput": 875.8, "total_tokens": 29643344}
+{"current_steps": 2540, "total_steps": 3400, "loss": 0.3169, "lr": 1.6495310866698093e-05, "epoch": 1.3080092711820757, "percentage": 74.71, "elapsed_time": "9:25:11", "remaining_time": "3:11:21", "throughput": 875.87, "total_tokens": 29701864}
+{"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}