Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84586103a211c06663bd404e55c4d764d0a39628f772147e29017239dc0ff834
+oid sha256:ed912ae9f29651ceebc41713ab5b91988158a52f69ac82baf6102389d31521a7
 size 29034840

trainer_log.jsonl

@@ -196,3 +196,14 @@
 {"current_steps": 895, "total_steps": 3400, "loss": 0.0337, "lr": 8.807551449590846e-05, "epoch": 0.4609837754313675, "percentage": 26.32, "elapsed_time": "4:25:36", "remaining_time": "12:23:24", "throughput": 560.71, "total_tokens": 8935680}
 {"current_steps": 900, "total_steps": 3400, "loss": 0.0063, "lr": 8.791746176467907e-05, "epoch": 0.4635591037857327, "percentage": 26.47, "elapsed_time": "4:27:02", "remaining_time": "12:21:46", "throughput": 560.81, "total_tokens": 8985600}
 {"current_steps": 900, "total_steps": 3400, "eval_loss": 0.010749292559921741, "epoch": 0.4635591037857327, "percentage": 26.47, "elapsed_time": "4:27:21", "remaining_time": "12:22:40", "throughput": 560.14, "total_tokens": 8985600}
+{"current_steps": 905, "total_steps": 3400, "loss": 0.0318, "lr": 8.775851227988656e-05, "epoch": 0.46613443214009787, "percentage": 26.62, "elapsed_time": "4:28:53", "remaining_time": "12:21:17", "throughput": 560.05, "total_tokens": 9035520}
+{"current_steps": 910, "total_steps": 3400, "loss": 0.0635, "lr": 8.759866980070963e-05, "epoch": 0.46870976049446306, "percentage": 26.76, "elapsed_time": "4:30:19", "remaining_time": "12:19:40", "throughput": 560.16, "total_tokens": 9085440}
+{"current_steps": 915, "total_steps": 3400, "loss": 0.0035, "lr": 8.743793810744654e-05, "epoch": 0.47128508884882825, "percentage": 26.91, "elapsed_time": "4:31:45", "remaining_time": "12:18:03", "throughput": 560.26, "total_tokens": 9135360}
+{"current_steps": 920, "total_steps": 3400, "loss": 0.0047, "lr": 8.727632100142551e-05, "epoch": 0.4738604172031934, "percentage": 27.06, "elapsed_time": "4:33:11", "remaining_time": "12:16:25", "throughput": 560.37, "total_tokens": 9185280}
+{"current_steps": 925, "total_steps": 3400, "loss": 0.0194, "lr": 8.711382230491493e-05, "epoch": 0.4764357455575586, "percentage": 27.21, "elapsed_time": "4:34:37", "remaining_time": "12:14:48", "throughput": 560.47, "total_tokens": 9235200}
+{"current_steps": 930, "total_steps": 3400, "loss": 0.0234, "lr": 8.695044586103296e-05, "epoch": 0.47901107391192377, "percentage": 27.35, "elapsed_time": "4:36:03", "remaining_time": "12:13:11", "throughput": 560.58, "total_tokens": 9285120}
+{"current_steps": 935, "total_steps": 3400, "loss": 0.0253, "lr": 8.678619553365659e-05, "epoch": 0.48158640226628896, "percentage": 27.5, "elapsed_time": "4:37:29", "remaining_time": "12:11:34", "throughput": 560.67, "total_tokens": 9335040}
+{"current_steps": 940, "total_steps": 3400, "loss": 0.0191, "lr": 8.662107520733027e-05, "epoch": 0.48416173062065415, "percentage": 27.65, "elapsed_time": "4:38:55", "remaining_time": "12:09:56", "throughput": 560.79, "total_tokens": 9384960}
+{"current_steps": 945, "total_steps": 3400, "loss": 0.0469, "lr": 8.64550887871741e-05, "epoch": 0.4867370589750193, "percentage": 27.79, "elapsed_time": "4:40:21", "remaining_time": "12:08:19", "throughput": 560.9, "total_tokens": 9434880}
+{"current_steps": 950, "total_steps": 3400, "loss": 0.0415, "lr": 8.628824019879137e-05, "epoch": 0.4893123873293845, "percentage": 27.94, "elapsed_time": "4:41:47", "remaining_time": "12:06:43", "throughput": 560.99, "total_tokens": 9484800}
+{"current_steps": 950, "total_steps": 3400, "eval_loss": 0.007216573692858219, "epoch": 0.4893123873293845, "percentage": 27.94, "elapsed_time": "4:42:06", "remaining_time": "12:07:32", "throughput": 560.35, "total_tokens": 9484800}