Training in progress, step 77

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7ee799c4d3c27ed7d566c982e345b115a5583eb3f85e50039a867d62084083
+oid sha256:bbe9d9c30652400ef1b49aeb93488a93c15a099e0898f60995186fb2ef0a39a0
 size 2819582528

trainer_log.jsonl

@@ -22,3 +22,15 @@
 {"current_steps": 65, "total_steps": 125, "loss": 0.4013, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:01:48", "remaining_time": "0:01:40", "throughput": 240.47, "total_tokens": 26112}
 {"current_steps": 70, "total_steps": 125, "loss": 0.3242, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:49", "remaining_time": "0:01:25", "throughput": 256.58, "total_tokens": 28064}
 {"current_steps": 70, "total_steps": 125, "eval_loss": 0.37164703011512756, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:50", "remaining_time": "0:01:26", "throughput": 254.81, "total_tokens": 28064}
+{"current_steps": 75, "total_steps": 125, "loss": 0.3963, "lr": 2.1505241511612522e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:02:00", "remaining_time": "0:01:20", "throughput": 248.35, "total_tokens": 29824}
+{"current_steps": 77, "total_steps": 125, "eval_loss": 0.3748786747455597, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:02:01", "remaining_time": "0:01:15", "throughput": 253.82, "total_tokens": 30720}
+{"current_steps": 80, "total_steps": 125, "loss": 0.3946, "lr": 1.8079112214378768e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:02:17", "remaining_time": "0:01:17", "throughput": 232.48, "total_tokens": 31904}
+{"current_steps": 84, "total_steps": 125, "eval_loss": 0.3603578209877014, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:02:18", "remaining_time": "0:01:07", "throughput": 241.67, "total_tokens": 33504}
+{"current_steps": 85, "total_steps": 125, "loss": 0.3496, "lr": 1.4788893576600099e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:02:27", "remaining_time": "0:01:09", "throughput": 230.5, "total_tokens": 33984}
+{"current_steps": 90, "total_steps": 125, "loss": 0.337, "lr": 1.1699198087116589e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:02:28", "remaining_time": "0:00:57", "throughput": 241.34, "total_tokens": 35776}
+{"current_steps": 91, "total_steps": 125, "eval_loss": 0.35710158944129944, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:02:28", "remaining_time": "0:00:55", "throughput": 242.48, "total_tokens": 36128}
+{"current_steps": 95, "total_steps": 125, "loss": 0.4315, "lr": 8.870700411447816e-06, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:02:36", "remaining_time": "0:00:49", "throughput": 239.38, "total_tokens": 37472}
+{"current_steps": 98, "total_steps": 125, "eval_loss": 0.3520326614379883, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "0:02:37", "remaining_time": "0:00:43", "throughput": 244.54, "total_tokens": 38592}
+{"current_steps": 100, "total_steps": 125, "loss": 0.38, "lr": 6.358945877920861e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:02:46", "remaining_time": "0:00:41", "throughput": 235.57, "total_tokens": 39328}
+{"current_steps": 105, "total_steps": 125, "loss": 0.371, "lr": 4.213259692436367e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:47", "remaining_time": "0:00:31", "throughput": 246.21, "total_tokens": 41280}
+{"current_steps": 105, "total_steps": 125, "eval_loss": 0.34758228063583374, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:48", "remaining_time": "0:00:32", "throughput": 245.11, "total_tokens": 41280}