Training in progress, step 2050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef369bc6f133f918883659e41b1f1d54da5fade97c7980c94f475d0370c1ee7c
+oid sha256:106639657de8130d1e743113412b2f3457d62959f493921313086761b4423ed9
 size 29034840

trainer_log.jsonl

@@ -442,3 +442,14 @@
 {"current_steps": 1995, "total_steps": 3400, "loss": 0.3406, "lr": 3.985825419216207e-05, "epoch": 0.5137780066958537, "percentage": 58.68, "elapsed_time": "7:12:47", "remaining_time": "5:04:48", "throughput": 806.71, "total_tokens": 20948448}
 {"current_steps": 2000, "total_steps": 3400, "loss": 0.3814, "lr": 3.962027225552807e-05, "epoch": 0.5150656708730363, "percentage": 58.82, "elapsed_time": "7:14:15", "remaining_time": "5:03:58", "throughput": 806.05, "total_tokens": 21002032}
 {"current_steps": 2000, "total_steps": 3400, "eval_loss": 0.5097677707672119, "epoch": 0.5150656708730363, "percentage": 58.82, "elapsed_time": "7:14:53", "remaining_time": "5:04:25", "throughput": 804.87, "total_tokens": 21002032}
+{"current_steps": 2005, "total_steps": 3400, "loss": 0.3312, "lr": 3.938253580098613e-05, "epoch": 0.5163533350502189, "percentage": 58.97, "elapsed_time": "7:16:26", "remaining_time": "5:03:39", "throughput": 804.02, "total_tokens": 21054264}
+{"current_steps": 2010, "total_steps": 3400, "loss": 0.2914, "lr": 3.914505045103845e-05, "epoch": 0.5176409992274015, "percentage": 59.12, "elapsed_time": "7:17:53", "remaining_time": "5:02:49", "throughput": 803.36, "total_tokens": 21106872}
+{"current_steps": 2015, "total_steps": 3400, "loss": 0.3414, "lr": 3.8907821822248605e-05, "epoch": 0.5189286634045841, "percentage": 59.26, "elapsed_time": "7:19:20", "remaining_time": "5:01:58", "throughput": 802.71, "total_tokens": 21159976}
+{"current_steps": 2020, "total_steps": 3400, "loss": 0.3701, "lr": 3.867085552510864e-05, "epoch": 0.5202163275817667, "percentage": 59.41, "elapsed_time": "7:20:48", "remaining_time": "5:01:08", "throughput": 802.02, "total_tokens": 21211920}
+{"current_steps": 2025, "total_steps": 3400, "loss": 0.3867, "lr": 3.843415716390644e-05, "epoch": 0.5215039917589492, "percentage": 59.56, "elapsed_time": "7:22:15", "remaining_time": "5:00:18", "throughput": 801.37, "total_tokens": 21265128}
+{"current_steps": 2030, "total_steps": 3400, "loss": 0.3515, "lr": 3.819773233659314e-05, "epoch": 0.5227916559361319, "percentage": 59.71, "elapsed_time": "7:23:43", "remaining_time": "4:59:27", "throughput": 800.71, "total_tokens": 21317592}
+{"current_steps": 2035, "total_steps": 3400, "loss": 0.3359, "lr": 3.7961586634650767e-05, "epoch": 0.5240793201133145, "percentage": 59.85, "elapsed_time": "7:25:10", "remaining_time": "4:58:36", "throughput": 800.09, "total_tokens": 21370976}
+{"current_steps": 2040, "total_steps": 3400, "loss": 0.3265, "lr": 3.772572564296005e-05, "epoch": 0.525366984290497, "percentage": 60.0, "elapsed_time": "7:26:37", "remaining_time": "4:57:45", "throughput": 799.47, "total_tokens": 21424056}
+{"current_steps": 2045, "total_steps": 3400, "loss": 0.3738, "lr": 3.749015493966817e-05, "epoch": 0.5266546484676796, "percentage": 60.15, "elapsed_time": "7:28:05", "remaining_time": "4:56:53", "throughput": 798.81, "total_tokens": 21476248}
+{"current_steps": 2050, "total_steps": 3400, "loss": 0.3389, "lr": 3.7254880096057073e-05, "epoch": 0.5279423126448622, "percentage": 60.29, "elapsed_time": "7:29:31", "remaining_time": "4:56:01", "throughput": 798.15, "total_tokens": 21527496}
+{"current_steps": 2050, "total_steps": 3400, "eval_loss": 0.4327767789363861, "epoch": 0.5279423126448622, "percentage": 60.29, "elapsed_time": "7:30:09", "remaining_time": "4:56:27", "throughput": 797.02, "total_tokens": 21527496}