Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168cc62ce0f9bc823e9f05cfca486c4f8b12cfdb3adf1b70687137fa417f7b65
+oid sha256:e67d46cdc279c111f3d8b6cd0c68158fe4239ea365a1c2b31f1709a759de013a
 size 29034840

trainer_log.jsonl

@@ -130,3 +130,14 @@
 {"current_steps": 595, "total_steps": 3882, "loss": 0.8269, "lr": 9.712389159977307e-05, "epoch": 0.3064640741694566, "percentage": 15.33, "elapsed_time": "3:04:24", "remaining_time": "16:58:45", "throughput": 628.95, "total_tokens": 6959128}
 {"current_steps": 600, "total_steps": 3882, "loss": 0.7997, "lr": 9.705225883648121e-05, "epoch": 0.3090394025238218, "percentage": 15.46, "elapsed_time": "3:05:54", "remaining_time": "16:56:56", "throughput": 629.11, "total_tokens": 7017576}
 {"current_steps": 600, "total_steps": 3882, "eval_loss": 0.787663459777832, "epoch": 0.3090394025238218, "percentage": 15.46, "elapsed_time": "3:06:14", "remaining_time": "16:58:44", "throughput": 628.0, "total_tokens": 7017576}
+{"current_steps": 605, "total_steps": 3882, "loss": 0.8925, "lr": 9.697977204284973e-05, "epoch": 0.311614730878187, "percentage": 15.58, "elapsed_time": "3:07:48", "remaining_time": "16:57:17", "throughput": 627.94, "total_tokens": 7076032}
+{"current_steps": 610, "total_steps": 3882, "loss": 0.8159, "lr": 9.690643253456297e-05, "epoch": 0.31419005923255217, "percentage": 15.71, "elapsed_time": "3:09:18", "remaining_time": "16:55:24", "throughput": 628.15, "total_tokens": 7134536}
+{"current_steps": 615, "total_steps": 3882, "loss": 0.826, "lr": 9.683224164278264e-05, "epoch": 0.31676538758691736, "percentage": 15.84, "elapsed_time": "3:10:46", "remaining_time": "16:53:28", "throughput": 628.38, "total_tokens": 7193032}
+{"current_steps": 620, "total_steps": 3882, "loss": 0.8187, "lr": 9.675720071412365e-05, "epoch": 0.3193407159412825, "percentage": 15.97, "elapsed_time": "3:12:18", "remaining_time": "16:51:46", "throughput": 628.48, "total_tokens": 7251568}
+{"current_steps": 625, "total_steps": 3882, "loss": 0.8524, "lr": 9.66813111106296e-05, "epoch": 0.3219160442956477, "percentage": 16.1, "elapsed_time": "3:13:47", "remaining_time": "16:49:51", "throughput": 628.7, "total_tokens": 7310072}
+{"current_steps": 630, "total_steps": 3882, "loss": 0.7966, "lr": 9.660457420974819e-05, "epoch": 0.3244913726500129, "percentage": 16.23, "elapsed_time": "3:15:15", "remaining_time": "16:47:55", "throughput": 628.95, "total_tokens": 7368560}
+{"current_steps": 635, "total_steps": 3882, "loss": 0.799, "lr": 9.652699140430608e-05, "epoch": 0.32706670100437807, "percentage": 16.36, "elapsed_time": "3:16:45", "remaining_time": "16:46:03", "throughput": 629.14, "total_tokens": 7427040}
+{"current_steps": 640, "total_steps": 3882, "loss": 0.8477, "lr": 9.644856410248369e-05, "epoch": 0.32964202935874326, "percentage": 16.49, "elapsed_time": "3:18:13", "remaining_time": "16:44:09", "throughput": 629.37, "total_tokens": 7485552}
+{"current_steps": 645, "total_steps": 3882, "loss": 0.7867, "lr": 9.636929372778963e-05, "epoch": 0.3322173577131084, "percentage": 16.62, "elapsed_time": "3:19:43", "remaining_time": "16:42:18", "throughput": 629.56, "total_tokens": 7544040}
+{"current_steps": 650, "total_steps": 3882, "loss": 0.8367, "lr": 9.628918171903485e-05, "epoch": 0.3347926860674736, "percentage": 16.74, "elapsed_time": "3:21:11", "remaining_time": "16:40:22", "throughput": 629.8, "total_tokens": 7602512}
+{"current_steps": 650, "total_steps": 3882, "eval_loss": 0.7940558791160583, "epoch": 0.3347926860674736, "percentage": 16.74, "elapsed_time": "3:21:31", "remaining_time": "16:42:00", "throughput": 628.77, "total_tokens": 7602512}