Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbd4c2db163eed1692965995fff6a99c384f9785d5dc16340b44ab7c2b734df0
+oid sha256:3a83521c4411b458bb33d399cce26d96c4156800b9fbac089cf4b485c06b1beb
 size 18516456

trainer_log.jsonl

@@ -46,3 +46,14 @@
 {"current_steps": 195, "total_steps": 3400, "loss": 0.9028, "lr": 9.998521935696953e-05, "epoch": 0.10043780582024209, "percentage": 5.74, "elapsed_time": "0:46:38", "remaining_time": "12:46:33", "throughput": 815.05, "total_tokens": 2280800}
 {"current_steps": 200, "total_steps": 3400, "loss": 0.9053, "lr": 9.997871633546257e-05, "epoch": 0.10301313417460727, "percentage": 5.88, "elapsed_time": "0:47:45", "remaining_time": "12:44:03", "throughput": 816.44, "total_tokens": 2339304}
 {"current_steps": 200, "total_steps": 3400, "eval_loss": 0.8982028961181641, "epoch": 0.10301313417460727, "percentage": 5.88, "elapsed_time": "0:48:02", "remaining_time": "12:48:34", "throughput": 811.65, "total_tokens": 2339304}
+{"current_steps": 205, "total_steps": 3400, "loss": 0.9003, "lr": 9.997103130994296e-05, "epoch": 0.10558846252897244, "percentage": 6.03, "elapsed_time": "0:49:13", "remaining_time": "12:47:17", "throughput": 811.74, "total_tokens": 2397808}
+{"current_steps": 210, "total_steps": 3400, "loss": 0.8969, "lr": 9.996216446216267e-05, "epoch": 0.10816379088333762, "percentage": 6.18, "elapsed_time": "0:50:20", "remaining_time": "12:44:49", "throughput": 813.08, "total_tokens": 2456288}
+{"current_steps": 215, "total_steps": 3400, "loss": 0.9114, "lr": 9.995211600182397e-05, "epoch": 0.11073911923770281, "percentage": 6.32, "elapsed_time": "0:51:28", "remaining_time": "12:42:28", "throughput": 814.32, "total_tokens": 2514784}
+{"current_steps": 220, "total_steps": 3400, "loss": 0.899, "lr": 9.994088616657444e-05, "epoch": 0.11331444759206799, "percentage": 6.47, "elapsed_time": "0:52:35", "remaining_time": "12:40:13", "throughput": 815.44, "total_tokens": 2573240}
+{"current_steps": 225, "total_steps": 3400, "loss": 0.898, "lr": 9.992847522200133e-05, "epoch": 0.11588977594643317, "percentage": 6.62, "elapsed_time": "0:53:42", "remaining_time": "12:37:54", "throughput": 816.63, "total_tokens": 2631672}
+{"current_steps": 230, "total_steps": 3400, "loss": 0.9006, "lr": 9.99148834616253e-05, "epoch": 0.11846510430079835, "percentage": 6.76, "elapsed_time": "0:54:49", "remaining_time": "12:35:36", "throughput": 817.82, "total_tokens": 2690112}
+{"current_steps": 235, "total_steps": 3400, "loss": 0.8973, "lr": 9.990011120689351e-05, "epoch": 0.12104043265516354, "percentage": 6.91, "elapsed_time": "0:55:56", "remaining_time": "12:33:23", "throughput": 818.92, "total_tokens": 2748608}
+{"current_steps": 240, "total_steps": 3400, "loss": 0.8885, "lr": 9.988415880717194e-05, "epoch": 0.12361576100952872, "percentage": 7.06, "elapsed_time": "0:57:03", "remaining_time": "12:31:13", "throughput": 820.0, "total_tokens": 2807080}
+{"current_steps": 245, "total_steps": 3400, "loss": 0.9066, "lr": 9.986702663973722e-05, "epoch": 0.1261910893638939, "percentage": 7.21, "elapsed_time": "0:58:10", "remaining_time": "12:29:07", "throughput": 820.98, "total_tokens": 2865520}
+{"current_steps": 250, "total_steps": 3400, "loss": 0.9098, "lr": 9.98487151097676e-05, "epoch": 0.12876641771825909, "percentage": 7.35, "elapsed_time": "0:59:17", "remaining_time": "12:26:59", "throughput": 822.02, "total_tokens": 2924016}
+{"current_steps": 250, "total_steps": 3400, "eval_loss": 0.8956434726715088, "epoch": 0.12876641771825909, "percentage": 7.35, "elapsed_time": "0:59:34", "remaining_time": "12:30:40", "throughput": 818.0, "total_tokens": 2924016}