Training in progress, step 1200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7aab0cd9c4fe95e67375a76eb37d59d1f473e5a6c3091db1f696fc3d335f8c
+oid sha256:c47d2eda2744bde9c36de097c0d54ac6bcafb93bcd134cf6cefce20795772fe5
 size 29034840

trainer_log.jsonl

@@ -251,3 +251,14 @@
 {"current_steps": 1145, "total_steps": 3882, "loss": 0.5472, "lr": 8.449413858127487e-05, "epoch": 0.5897501931496266, "percentage": 29.5, "elapsed_time": "5:51:17", "remaining_time": "13:59:44", "throughput": 635.37, "total_tokens": 13392280}
 {"current_steps": 1150, "total_steps": 3882, "loss": 0.5228, "lr": 8.433961761999796e-05, "epoch": 0.5923255215039918, "percentage": 29.62, "elapsed_time": "5:52:45", "remaining_time": "13:58:03", "throughput": 635.49, "total_tokens": 13450720}
 {"current_steps": 1150, "total_steps": 3882, "eval_loss": 0.6229755282402039, "epoch": 0.5923255215039918, "percentage": 29.62, "elapsed_time": "5:53:05", "remaining_time": "13:58:49", "throughput": 634.91, "total_tokens": 13450720}
+{"current_steps": 1155, "total_steps": 3882, "loss": 0.5654, "lr": 8.418447337142254e-05, "epoch": 0.5949008498583569, "percentage": 29.75, "elapsed_time": "5:54:37", "remaining_time": "13:57:18", "throughput": 634.89, "total_tokens": 13509200}
+{"current_steps": 1160, "total_steps": 3882, "loss": 0.5074, "lr": 8.402870865152172e-05, "epoch": 0.5974761782127221, "percentage": 29.88, "elapsed_time": "5:56:06", "remaining_time": "13:55:38", "throughput": 634.99, "total_tokens": 13567656}
+{"current_steps": 1165, "total_steps": 3882, "loss": 0.6436, "lr": 8.387232628753056e-05, "epoch": 0.6000515065670873, "percentage": 30.01, "elapsed_time": "5:57:34", "remaining_time": "13:53:55", "throughput": 635.12, "total_tokens": 13626136}
+{"current_steps": 1170, "total_steps": 3882, "loss": 0.55, "lr": 8.371532911789482e-05, "epoch": 0.6026268349214525, "percentage": 30.14, "elapsed_time": "5:59:02", "remaining_time": "13:52:14", "throughput": 635.24, "total_tokens": 13684608}
+{"current_steps": 1175, "total_steps": 3882, "loss": 0.5399, "lr": 8.355771999221937e-05, "epoch": 0.6052021632758177, "percentage": 30.27, "elapsed_time": "6:00:29", "remaining_time": "13:50:30", "throughput": 635.38, "total_tokens": 13743080}
+{"current_steps": 1180, "total_steps": 3882, "loss": 0.5402, "lr": 8.339950177121647e-05, "epoch": 0.6077774916301828, "percentage": 30.4, "elapsed_time": "6:01:58", "remaining_time": "13:48:50", "throughput": 635.49, "total_tokens": 13801552}
+{"current_steps": 1185, "total_steps": 3882, "loss": 0.5559, "lr": 8.324067732665393e-05, "epoch": 0.610352819984548, "percentage": 30.53, "elapsed_time": "6:03:25", "remaining_time": "13:47:08", "throughput": 635.62, "total_tokens": 13860064}
+{"current_steps": 1190, "total_steps": 3882, "loss": 0.5619, "lr": 8.308124954130289e-05, "epoch": 0.6129281483389132, "percentage": 30.65, "elapsed_time": "6:04:52", "remaining_time": "13:45:25", "throughput": 635.76, "total_tokens": 13918552}
+{"current_steps": 1195, "total_steps": 3882, "loss": 0.5933, "lr": 8.292122130888558e-05, "epoch": 0.6155034766932784, "percentage": 30.78, "elapsed_time": "6:06:21", "remaining_time": "13:43:45", "throughput": 635.87, "total_tokens": 13977056}
+{"current_steps": 1200, "total_steps": 3882, "loss": 0.5078, "lr": 8.276059553402265e-05, "epoch": 0.6180788050476436, "percentage": 30.91, "elapsed_time": "6:07:48", "remaining_time": "13:42:03", "throughput": 636.0, "total_tokens": 14035544}
+{"current_steps": 1200, "total_steps": 3882, "eval_loss": 0.6184359192848206, "epoch": 0.6180788050476436, "percentage": 30.91, "elapsed_time": "6:08:07", "remaining_time": "13:42:46", "throughput": 635.44, "total_tokens": 14035544}