Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3d3749c1bd6d89c5172acc406cbf998cb265de2f8a059883bd34374666967b
+oid sha256:9c25a3efd75d542958c5e34b7273f618978b6b36bd238438b10b03a0bfabd174
 size 18516456

trainer_log.jsonl

@@ -200,3 +200,14 @@
 {"current_steps": 895, "total_steps": 3400, "loss": 0.8989, "lr": 8.807551449590846e-05, "epoch": 0.4609837754313675, "percentage": 26.32, "elapsed_time": "3:26:25", "remaining_time": "9:37:44", "throughput": 845.22, "total_tokens": 10468240}
 {"current_steps": 900, "total_steps": 3400, "loss": 0.8961, "lr": 8.791746176467907e-05, "epoch": 0.4635591037857327, "percentage": 26.47, "elapsed_time": "3:27:28", "remaining_time": "9:36:18", "throughput": 845.63, "total_tokens": 10526712}
 {"current_steps": 900, "total_steps": 3400, "eval_loss": 0.891426146030426, "epoch": 0.4635591037857327, "percentage": 26.47, "elapsed_time": "3:27:44", "remaining_time": "9:37:03", "throughput": 844.54, "total_tokens": 10526712}
+{"current_steps": 905, "total_steps": 3400, "loss": 0.8955, "lr": 8.775851227988656e-05, "epoch": 0.46613443214009787, "percentage": 26.62, "elapsed_time": "3:28:52", "remaining_time": "9:35:50", "throughput": 844.63, "total_tokens": 10585232}
+{"current_steps": 910, "total_steps": 3400, "loss": 0.8951, "lr": 8.759866980070963e-05, "epoch": 0.46870976049446306, "percentage": 26.76, "elapsed_time": "3:29:55", "remaining_time": "9:34:23", "throughput": 845.06, "total_tokens": 10643728}
+{"current_steps": 915, "total_steps": 3400, "loss": 0.8951, "lr": 8.743793810744654e-05, "epoch": 0.47128508884882825, "percentage": 26.91, "elapsed_time": "3:30:58", "remaining_time": "9:32:58", "throughput": 845.46, "total_tokens": 10702240}
+{"current_steps": 920, "total_steps": 3400, "loss": 0.9066, "lr": 8.727632100142551e-05, "epoch": 0.4738604172031934, "percentage": 27.06, "elapsed_time": "3:32:01", "remaining_time": "9:31:32", "throughput": 845.87, "total_tokens": 10760656}
+{"current_steps": 925, "total_steps": 3400, "loss": 0.8953, "lr": 8.711382230491493e-05, "epoch": 0.4764357455575586, "percentage": 27.21, "elapsed_time": "3:33:04", "remaining_time": "9:30:06", "throughput": 846.28, "total_tokens": 10819128}
+{"current_steps": 930, "total_steps": 3400, "loss": 0.8961, "lr": 8.695044586103296e-05, "epoch": 0.47901107391192377, "percentage": 27.35, "elapsed_time": "3:34:06", "remaining_time": "9:28:40", "throughput": 846.71, "total_tokens": 10877600}
+{"current_steps": 935, "total_steps": 3400, "loss": 0.8965, "lr": 8.678619553365659e-05, "epoch": 0.48158640226628896, "percentage": 27.5, "elapsed_time": "3:35:10", "remaining_time": "9:27:15", "throughput": 847.09, "total_tokens": 10936088}
+{"current_steps": 940, "total_steps": 3400, "loss": 0.9018, "lr": 8.662107520733027e-05, "epoch": 0.48416173062065415, "percentage": 27.65, "elapsed_time": "3:36:12", "remaining_time": "9:25:50", "throughput": 847.5, "total_tokens": 10994560}
+{"current_steps": 945, "total_steps": 3400, "loss": 0.8944, "lr": 8.64550887871741e-05, "epoch": 0.4867370589750193, "percentage": 27.79, "elapsed_time": "3:37:16", "remaining_time": "9:24:26", "throughput": 847.88, "total_tokens": 11053016}
+{"current_steps": 950, "total_steps": 3400, "loss": 0.8852, "lr": 8.628824019879137e-05, "epoch": 0.4893123873293845, "percentage": 27.94, "elapsed_time": "3:38:18", "remaining_time": "9:23:01", "throughput": 848.29, "total_tokens": 11111520}
+{"current_steps": 950, "total_steps": 3400, "eval_loss": 0.8915690183639526, "epoch": 0.4893123873293845, "percentage": 27.94, "elapsed_time": "3:38:35", "remaining_time": "9:23:43", "throughput": 847.23, "total_tokens": 11111520}