Training in progress, step 98

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0caf7d49bd00a93fe035a0db720213e39888b49b84e8608e35b3d1dae37802
+oid sha256:0b168451f253d8a40945334cc54a561c548f18973756464948704cb5c3556a04
 size 2819582528

trainer_log.jsonl

@@ -30,3 +30,13 @@
 {"current_steps": 90, "total_steps": 125, "loss": 0.337, "lr": 1.1699198087116589e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:02:55", "remaining_time": "0:01:08", "throughput": 203.97, "total_tokens": 35776}
 {"current_steps": 91, "total_steps": 125, "eval_loss": 0.35710158944129944, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:02:56", "remaining_time": "0:01:05", "throughput": 204.78, "total_tokens": 36128}
 {"current_steps": 95, "total_steps": 125, "loss": 0.4315, "lr": 8.870700411447816e-06, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:03:05", "remaining_time": "0:00:58", "throughput": 201.87, "total_tokens": 37472}
+{"current_steps": 98, "total_steps": 125, "eval_loss": 0.3520326614379883, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "0:03:06", "remaining_time": "0:00:51", "throughput": 206.43, "total_tokens": 38592}
+{"current_steps": 100, "total_steps": 125, "loss": 0.38, "lr": 6.358945877920861e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:03:25", "remaining_time": "0:00:51", "throughput": 191.58, "total_tokens": 39328}
+{"current_steps": 105, "total_steps": 125, "loss": 0.371, "lr": 4.213259692436367e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:03:26", "remaining_time": "0:00:39", "throughput": 200.3, "total_tokens": 41280}
+{"current_steps": 105, "total_steps": 125, "eval_loss": 0.34758228063583374, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:03:26", "remaining_time": "0:00:39", "throughput": 199.52, "total_tokens": 41280}
+{"current_steps": 110, "total_steps": 125, "loss": 0.364, "lr": 2.475778302439524e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:03:38", "remaining_time": "0:00:29", "throughput": 199.22, "total_tokens": 43552}
+{"current_steps": 112, "total_steps": 125, "eval_loss": 0.34589245915412903, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:03:39", "remaining_time": "0:00:25", "throughput": 200.95, "total_tokens": 44160}
+{"current_steps": 115, "total_steps": 125, "loss": 0.3554, "lr": 1.180621931927592e-06, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:03:47", "remaining_time": "0:00:19", "throughput": 198.32, "total_tokens": 45216}
+{"current_steps": 119, "total_steps": 125, "eval_loss": 0.3492301404476166, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "0:03:49", "remaining_time": "0:00:11", "throughput": 204.57, "total_tokens": 46944}
+{"current_steps": 120, "total_steps": 125, "loss": 0.3494, "lr": 3.5322453704410286e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:03:56", "remaining_time": "0:00:09", "throughput": 200.16, "total_tokens": 47360}
+{"current_steps": 125, "total_steps": 125, "loss": 0.3588, "lr": 9.834340423678368e-09, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:57", "remaining_time": "0:00:00", "throughput": 207.81, "total_tokens": 49376}