Training in progress, step 2150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24a4c37b80664a17b4612dbf43f560521041adc8bc0cc8d0182857100b9274e
+oid sha256:d1c3e74f99d6e6f70e37f4de247287b17ec6f7280a9a5e1856338be701a8ce67
 size 29034840

trainer_log.jsonl

@@ -472,3 +472,14 @@
 {"current_steps": 2095, "total_steps": 6770, "loss": 0.2475, "lr": 8.27044225452443e-05, "epoch": 0.6189069423929099, "percentage": 30.95, "elapsed_time": "2:14:29", "remaining_time": "5:00:06", "throughput": 2696.8, "total_tokens": 21760744}
 {"current_steps": 2100, "total_steps": 6770, "loss": 0.1826, "lr": 8.26119460776609e-05, "epoch": 0.620384047267356, "percentage": 31.02, "elapsed_time": "2:15:56", "remaining_time": "5:02:19", "throughput": 2674.27, "total_tokens": 21813984}
 {"current_steps": 2100, "total_steps": 6770, "eval_loss": 0.5386325716972351, "epoch": 0.620384047267356, "percentage": 31.02, "elapsed_time": "2:16:16", "remaining_time": "5:03:02", "throughput": 2667.96, "total_tokens": 21813984}
+{"current_steps": 2105, "total_steps": 6770, "loss": 0.3018, "lr": 8.251927504753426e-05, "epoch": 0.621861152141802, "percentage": 31.09, "elapsed_time": "2:17:48", "remaining_time": "5:05:23", "throughput": 2644.46, "total_tokens": 21865304}
+{"current_steps": 2110, "total_steps": 6770, "loss": 0.2725, "lr": 8.24264100077388e-05, "epoch": 0.6233382570162481, "percentage": 31.17, "elapsed_time": "2:19:15", "remaining_time": "5:07:33", "throughput": 2623.29, "total_tokens": 21918568}
+{"current_steps": 2115, "total_steps": 6770, "loss": 0.3103, "lr": 8.233335151230646e-05, "epoch": 0.6248153618906942, "percentage": 31.24, "elapsed_time": "2:20:41", "remaining_time": "5:09:39", "throughput": 2602.66, "total_tokens": 21970352}
+{"current_steps": 2120, "total_steps": 6770, "loss": 0.2868, "lr": 8.224010011642326e-05, "epoch": 0.6262924667651403, "percentage": 31.31, "elapsed_time": "2:22:08", "remaining_time": "5:11:46", "throughput": 2582.09, "total_tokens": 22021312}
+{"current_steps": 2125, "total_steps": 6770, "loss": 0.335, "lr": 8.21466563764261e-05, "epoch": 0.6277695716395865, "percentage": 31.39, "elapsed_time": "2:23:33", "remaining_time": "5:13:49", "throughput": 2562.52, "total_tokens": 22073496}
+{"current_steps": 2130, "total_steps": 6770, "loss": 0.3764, "lr": 8.205302084979937e-05, "epoch": 0.6292466765140325, "percentage": 31.46, "elapsed_time": "2:25:01", "remaining_time": "5:15:54", "throughput": 2542.68, "total_tokens": 22124088}
+{"current_steps": 2135, "total_steps": 6770, "loss": 0.2681, "lr": 8.19591940951717e-05, "epoch": 0.6307237813884786, "percentage": 31.54, "elapsed_time": "2:26:27", "remaining_time": "5:17:56", "throughput": 2523.68, "total_tokens": 22175824}
+{"current_steps": 2140, "total_steps": 6770, "loss": 0.2619, "lr": 8.186517667231259e-05, "epoch": 0.6322008862629247, "percentage": 31.61, "elapsed_time": "2:27:53", "remaining_time": "5:19:57", "throughput": 2504.99, "total_tokens": 22227376}
+{"current_steps": 2145, "total_steps": 6770, "loss": 0.2516, "lr": 8.1770969142129e-05, "epoch": 0.6336779911373708, "percentage": 31.68, "elapsed_time": "2:29:19", "remaining_time": "5:21:59", "throughput": 2486.61, "total_tokens": 22279928}
+{"current_steps": 2150, "total_steps": 6770, "loss": 0.2387, "lr": 8.167657206666217e-05, "epoch": 0.6351550960118169, "percentage": 31.76, "elapsed_time": "2:30:47", "remaining_time": "5:24:00", "throughput": 2468.41, "total_tokens": 22332144}
+{"current_steps": 2150, "total_steps": 6770, "eval_loss": 0.25809118151664734, "epoch": 0.6351550960118169, "percentage": 31.76, "elapsed_time": "2:31:06", "remaining_time": "5:24:42", "throughput": 2463.15, "total_tokens": 22332144}