Training in progress, step 2100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106639657de8130d1e743113412b2f3457d62959f493921313086761b4423ed9
+oid sha256:7f75c51d9ca969a9d3cbb26206d8c3751152111b430ee8f78c774b9d99426948
 size 29034840

trainer_log.jsonl

@@ -453,3 +453,14 @@
 {"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}
+{"current_steps": 2055, "total_steps": 3400, "loss": 0.3937, "lr": 3.7019906676411446e-05, "epoch": 0.5292299768220448, "percentage": 60.44, "elapsed_time": "7:31:43", "remaining_time": "4:55:39", "throughput": 796.21, "total_tokens": 21579816}
+{"current_steps": 2060, "total_steps": 3400, "loss": 0.4039, "lr": 3.678524023788735e-05, "epoch": 0.5305176409992274, "percentage": 60.59, "elapsed_time": "7:33:09", "remaining_time": "4:54:46", "throughput": 795.58, "total_tokens": 21631776}
+{"current_steps": 2065, "total_steps": 3400, "loss": 0.3501, "lr": 3.6550886330380665e-05, "epoch": 0.53180530517641, "percentage": 60.74, "elapsed_time": "7:34:38", "remaining_time": "4:53:54", "throughput": 794.91, "total_tokens": 21683608}
+{"current_steps": 2070, "total_steps": 3400, "loss": 0.3334, "lr": 3.631685049639586e-05, "epoch": 0.5330929693535926, "percentage": 60.88, "elapsed_time": "7:36:04", "remaining_time": "4:53:02", "throughput": 794.3, "total_tokens": 21735672}
+{"current_steps": 2075, "total_steps": 3400, "loss": 0.3292, "lr": 3.608313827091493e-05, "epoch": 0.5343806335307751, "percentage": 61.03, "elapsed_time": "7:37:32", "remaining_time": "4:52:09", "throughput": 793.65, "total_tokens": 21787592}
+{"current_steps": 2080, "total_steps": 3400, "loss": 0.3616, "lr": 3.5849755181266474e-05, "epoch": 0.5356682977079578, "percentage": 61.18, "elapsed_time": "7:38:58", "remaining_time": "4:51:16", "throughput": 793.08, "total_tokens": 21840448}
+{"current_steps": 2085, "total_steps": 3400, "loss": 0.3082, "lr": 3.5616706746995026e-05, "epoch": 0.5369559618851404, "percentage": 61.32, "elapsed_time": "7:40:26", "remaining_time": "4:50:23", "throughput": 792.47, "total_tokens": 21893096}
+{"current_steps": 2090, "total_steps": 3400, "loss": 0.293, "lr": 3.538399847973036e-05, "epoch": 0.5382436260623229, "percentage": 61.47, "elapsed_time": "7:41:53", "remaining_time": "4:49:30", "throughput": 791.87, "total_tokens": 21945184}
+{"current_steps": 2095, "total_steps": 3400, "loss": 0.3835, "lr": 3.515163588305735e-05, "epoch": 0.5395312902395055, "percentage": 61.62, "elapsed_time": "7:43:20", "remaining_time": "4:48:37", "throughput": 791.29, "total_tokens": 21998016}
+{"current_steps": 2100, "total_steps": 3400, "loss": 0.3983, "lr": 3.491962445238569e-05, "epoch": 0.5408189544166881, "percentage": 61.76, "elapsed_time": "7:44:47", "remaining_time": "4:47:43", "throughput": 790.68, "total_tokens": 22050376}
+{"current_steps": 2100, "total_steps": 3400, "eval_loss": 0.481829971075058, "epoch": 0.5408189544166881, "percentage": 61.76, "elapsed_time": "7:45:25", "remaining_time": "4:48:07", "throughput": 789.61, "total_tokens": 22050376}