Training in progress, step 2600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4309cbe22308fad27e8b5e7c85714a164b3e5d38d0b75c9561151c809911db4b
+oid sha256:822e6dcdbe992039c470c7d5345a56c4a6d718bf3296adb52b926cfb46d4ab8e
 size 29034840

trainer_log.jsonl

@@ -553,3 +553,14 @@
 {"current_steps": 2545, "total_steps": 3882, "loss": 0.2503, "lr": 2.9084908969240664e-05, "epoch": 1.310584599536441, "percentage": 65.56, "elapsed_time": "12:58:30", "remaining_time": "6:48:59", "throughput": 637.12, "total_tokens": 29760376}
 {"current_steps": 2550, "total_steps": 3882, "loss": 0.2192, "lr": 2.8891613196868816e-05, "epoch": 1.3131599278908062, "percentage": 65.69, "elapsed_time": "12:59:59", "remaining_time": "6:47:25", "throughput": 637.16, "total_tokens": 29818856}
 {"current_steps": 2550, "total_steps": 3882, "eval_loss": 0.24317465722560883, "epoch": 1.3131599278908062, "percentage": 65.69, "elapsed_time": "13:00:19", "remaining_time": "6:47:36", "throughput": 636.89, "total_tokens": 29818856}
+{"current_steps": 2555, "total_steps": 3882, "loss": 0.2231, "lr": 2.8698700556002178e-05, "epoch": 1.3157352562451712, "percentage": 65.82, "elapsed_time": "13:01:52", "remaining_time": "6:46:05", "throughput": 636.87, "total_tokens": 29877288}
+{"current_steps": 2560, "total_steps": 3882, "loss": 0.3007, "lr": 2.8506174548135695e-05, "epoch": 1.3183105845995364, "percentage": 65.95, "elapsed_time": "13:03:21", "remaining_time": "6:44:31", "throughput": 636.91, "total_tokens": 29935776}
+{"current_steps": 2565, "total_steps": 3882, "loss": 0.1895, "lr": 2.8314038667746732e-05, "epoch": 1.3208859129539017, "percentage": 66.07, "elapsed_time": "13:04:50", "remaining_time": "6:42:58", "throughput": 636.95, "total_tokens": 29994232}
+{"current_steps": 2570, "total_steps": 3882, "loss": 0.2728, "lr": 2.81222964022315e-05, "epoch": 1.3234612413082667, "percentage": 66.2, "elapsed_time": "13:06:18", "remaining_time": "6:41:24", "throughput": 637.0, "total_tokens": 30052760}
+{"current_steps": 2575, "total_steps": 3882, "loss": 0.2827, "lr": 2.793095123184193e-05, "epoch": 1.326036569662632, "percentage": 66.33, "elapsed_time": "13:07:47", "remaining_time": "6:39:51", "throughput": 637.04, "total_tokens": 30111200}
+{"current_steps": 2580, "total_steps": 3882, "loss": 0.2191, "lr": 2.77400066296223e-05, "epoch": 1.3286118980169972, "percentage": 66.46, "elapsed_time": "13:09:15", "remaining_time": "6:38:18", "throughput": 637.09, "total_tokens": 30169680}
+{"current_steps": 2585, "total_steps": 3882, "loss": 0.2317, "lr": 2.7549466061346386e-05, "epoch": 1.3311872263713624, "percentage": 66.59, "elapsed_time": "13:10:43", "remaining_time": "6:36:44", "throughput": 637.14, "total_tokens": 30228176}
+{"current_steps": 2590, "total_steps": 3882, "loss": 0.2293, "lr": 2.7359332985454443e-05, "epoch": 1.3337625547257275, "percentage": 66.72, "elapsed_time": "13:12:12", "remaining_time": "6:35:11", "throughput": 637.18, "total_tokens": 30286656}
+{"current_steps": 2595, "total_steps": 3882, "loss": 0.1903, "lr": 2.716961085299049e-05, "epoch": 1.3363378830800927, "percentage": 66.85, "elapsed_time": "13:13:41", "remaining_time": "6:33:37", "throughput": 637.22, "total_tokens": 30345160}
+{"current_steps": 2600, "total_steps": 3882, "loss": 0.224, "lr": 2.698030310753958e-05, "epoch": 1.338913211434458, "percentage": 66.98, "elapsed_time": "13:15:10", "remaining_time": "6:32:04", "throughput": 637.25, "total_tokens": 30403640}
+{"current_steps": 2600, "total_steps": 3882, "eval_loss": 0.20262545347213745, "epoch": 1.338913211434458, "percentage": 66.98, "elapsed_time": "13:15:29", "remaining_time": "6:32:14", "throughput": 636.99, "total_tokens": 30403640}