Training in progress, step 2650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:273fcf9e0b0197d44caacef12013e816c21f5d50361370148cdbf9380973f3f1
+oid sha256:827ad766e3a13984fdb182a9e1ff3663479a4a48e1ebea8bd0fa17625232d440
 size 18516456

trainer_log.jsonl

@@ -574,3 +574,14 @@
 {"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}
+{"current_steps": 2605, "total_steps": 3400, "loss": 0.3037, "lr": 1.4217439014387251e-05, "epoch": 1.341488539788823, "percentage": 76.62, "elapsed_time": "9:39:44", "remaining_time": "2:56:55", "throughput": 875.74, "total_tokens": 30462128}
+{"current_steps": 2610, "total_steps": 3400, "loss": 0.2905, "lr": 1.404802767838176e-05, "epoch": 1.3440638681431882, "percentage": 76.76, "elapsed_time": "9:40:48", "remaining_time": "2:55:47", "throughput": 875.81, "total_tokens": 30520616}
+{"current_steps": 2615, "total_steps": 3400, "loss": 0.317, "lr": 1.3879466611824199e-05, "epoch": 1.3466391964975535, "percentage": 76.91, "elapsed_time": "9:41:51", "remaining_time": "2:54:40", "throughput": 875.89, "total_tokens": 30579024}
+{"current_steps": 2620, "total_steps": 3400, "loss": 0.2794, "lr": 1.371175980120864e-05, "epoch": 1.3492145248519187, "percentage": 77.06, "elapsed_time": "9:42:55", "remaining_time": "2:53:32", "throughput": 875.96, "total_tokens": 30637464}
+{"current_steps": 2625, "total_steps": 3400, "loss": 0.3056, "lr": 1.3544911212825906e-05, "epoch": 1.3517898532062838, "percentage": 77.21, "elapsed_time": "9:43:59", "remaining_time": "2:52:25", "throughput": 876.03, "total_tokens": 30695936}
+{"current_steps": 2630, "total_steps": 3400, "loss": 0.2712, "lr": 1.337892479266974e-05, "epoch": 1.354365181560649, "percentage": 77.35, "elapsed_time": "9:45:03", "remaining_time": "2:51:17", "throughput": 876.11, "total_tokens": 30754408}
+{"current_steps": 2635, "total_steps": 3400, "loss": 0.2615, "lr": 1.3213804466343421e-05, "epoch": 1.356940509915014, "percentage": 77.5, "elapsed_time": "9:46:06", "remaining_time": "2:50:09", "throughput": 876.2, "total_tokens": 30812848}
+{"current_steps": 2640, "total_steps": 3400, "loss": 0.2661, "lr": 1.3049554138967051e-05, "epoch": 1.3595158382693793, "percentage": 77.65, "elapsed_time": "9:47:09", "remaining_time": "2:49:01", "throughput": 876.28, "total_tokens": 30871344}
+{"current_steps": 2645, "total_steps": 3400, "loss": 0.3272, "lr": 1.2886177695085078e-05, "epoch": 1.3620911666237445, "percentage": 77.79, "elapsed_time": "9:48:12", "remaining_time": "2:47:54", "throughput": 876.38, "total_tokens": 30929824}
+{"current_steps": 2650, "total_steps": 3400, "loss": 0.2962, "lr": 1.2723678998574512e-05, "epoch": 1.3646664949781098, "percentage": 77.94, "elapsed_time": "9:49:16", "remaining_time": "2:46:46", "throughput": 876.46, "total_tokens": 30988344}
+{"current_steps": 2650, "total_steps": 3400, "eval_loss": 0.7657458186149597, "epoch": 1.3646664949781098, "percentage": 77.94, "elapsed_time": "9:49:32", "remaining_time": "2:46:51", "throughput": 876.06, "total_tokens": 30988344}