Training in progress, step 1550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0263e90dbe014ac70c526fa71d2fd7a1bebb2c4fe954d285088a83f154c10e0
+oid sha256:f1764f403b39c14f233fd2d6443f410cab81d66e3cc9f1d476e6e55a6642ff67
 size 29034840

trainer_log.jsonl

@@ -332,3 +332,14 @@
 {"current_steps": 1495, "total_steps": 3400, "loss": 0.4489, "lr": 6.391686172908506e-05, "epoch": 0.38501158897759463, "percentage": 43.97, "elapsed_time": "4:39:16", "remaining_time": "5:55:51", "throughput": 936.55, "total_tokens": 15693120}
 {"current_steps": 1500, "total_steps": 3400, "loss": 0.4338, "lr": 6.368314950360415e-05, "epoch": 0.38629925315477726, "percentage": 44.12, "elapsed_time": "4:40:42", "remaining_time": "5:55:34", "throughput": 934.81, "total_tokens": 15744848}
 {"current_steps": 1500, "total_steps": 3400, "eval_loss": 0.45475366711616516, "epoch": 0.38629925315477726, "percentage": 44.12, "elapsed_time": "4:41:21", "remaining_time": "5:56:22", "throughput": 932.68, "total_tokens": 15744848}
+{"current_steps": 1505, "total_steps": 3400, "loss": 0.4558, "lr": 6.344911366961934e-05, "epoch": 0.3875869173319598, "percentage": 44.26, "elapsed_time": "4:42:55", "remaining_time": "5:56:14", "throughput": 930.61, "total_tokens": 15797632}
+{"current_steps": 1510, "total_steps": 3400, "loss": 0.4518, "lr": 6.321475976211266e-05, "epoch": 0.3888745815091424, "percentage": 44.41, "elapsed_time": "4:44:22", "remaining_time": "5:55:56", "throughput": 928.95, "total_tokens": 15850040}
+{"current_steps": 1515, "total_steps": 3400, "loss": 0.4092, "lr": 6.298009332358856e-05, "epoch": 0.390162245686325, "percentage": 44.56, "elapsed_time": "4:45:50", "remaining_time": "5:55:39", "throughput": 927.21, "total_tokens": 15902496}
+{"current_steps": 1520, "total_steps": 3400, "loss": 0.478, "lr": 6.274511990394294e-05, "epoch": 0.3914499098635076, "percentage": 44.71, "elapsed_time": "4:47:17", "remaining_time": "5:55:20", "throughput": 925.59, "total_tokens": 15954936}
+{"current_steps": 1525, "total_steps": 3400, "loss": 0.4294, "lr": 6.250984506033183e-05, "epoch": 0.3927375740406902, "percentage": 44.85, "elapsed_time": "4:48:45", "remaining_time": "5:55:01", "throughput": 923.94, "total_tokens": 16007624}
+{"current_steps": 1530, "total_steps": 3400, "loss": 0.3846, "lr": 6.227427435703997e-05, "epoch": 0.3940252382178728, "percentage": 45.0, "elapsed_time": "4:50:14", "remaining_time": "5:54:44", "throughput": 922.17, "total_tokens": 16059440}
+{"current_steps": 1535, "total_steps": 3400, "loss": 0.4372, "lr": 6.203841336534924e-05, "epoch": 0.39531290239505534, "percentage": 45.15, "elapsed_time": "4:51:44", "remaining_time": "5:54:27", "throughput": 920.42, "total_tokens": 16111136}
+{"current_steps": 1540, "total_steps": 3400, "loss": 0.484, "lr": 6.180226766340688e-05, "epoch": 0.39660056657223797, "percentage": 45.29, "elapsed_time": "4:53:13", "remaining_time": "5:54:09", "throughput": 918.74, "total_tokens": 16163976}
+{"current_steps": 1545, "total_steps": 3400, "loss": 0.3965, "lr": 6.156584283609359e-05, "epoch": 0.39788823074942054, "percentage": 45.44, "elapsed_time": "4:54:43", "remaining_time": "5:53:51", "throughput": 917.09, "total_tokens": 16217192}
+{"current_steps": 1550, "total_steps": 3400, "loss": 0.3872, "lr": 6.132914447489137e-05, "epoch": 0.39917589492660316, "percentage": 45.59, "elapsed_time": "4:56:11", "remaining_time": "5:53:30", "throughput": 915.52, "total_tokens": 16269896}
+{"current_steps": 1550, "total_steps": 3400, "eval_loss": 0.4416767656803131, "epoch": 0.39917589492660316, "percentage": 45.59, "elapsed_time": "4:56:49", "remaining_time": "5:54:16", "throughput": 913.54, "total_tokens": 16269896}