Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fce035445e540e519e7ae9ef95d4b23834d351f5d25c8e4dcaebb5ccc00a4b3
+oid sha256:1891249c8b74a2d2d79bf2f0863e1fccb45446adc36f987e95d3f5f6a7610fd1
 size 40036488

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.6926, "accuracy": 0.987500011920929, "learning_rate": 2.290805391669212e-06, "epoch": 0.6483381206401313, "percentage": 52.67, "elapsed_time": "1:43:22", "remaining_time": "1:32:54", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 0.9249, "accuracy": 0.9624999761581421, "learning_rate": 2.238678841830867e-06, "epoch": 0.6565449322938038, "percentage": 53.33, "elapsed_time": "1:44:34", "remaining_time": "1:31:29", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.12732766568660736, "epoch": 0.6565449322938038, "percentage": 53.33, "elapsed_time": "1:45:00", "remaining_time": "1:31:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.8352, "accuracy": 0.9624999761581421, "learning_rate": 2.186666916089239e-06, "epoch": 0.6647517439474764, "percentage": 54.0, "elapsed_time": "1:46:25", "remaining_time": "1:30:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 0.7119, "accuracy": 1.0, "learning_rate": 2.134792428593971e-06, "epoch": 0.6729585556011489, "percentage": 54.67, "elapsed_time": "1:47:35", "remaining_time": "1:29:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.8678, "accuracy": 0.9750000238418579, "learning_rate": 2.0830781332097446e-06, "epoch": 0.6811653672548215, "percentage": 55.33, "elapsed_time": "1:48:46", "remaining_time": "1:27:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.7634, "accuracy": 1.0, "learning_rate": 2.031546713535688e-06, "epoch": 0.689372178908494, "percentage": 56.0, "elapsed_time": "1:49:56", "remaining_time": "1:26:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "loss": 0.9929, "accuracy": 0.987500011920929, "learning_rate": 1.9802207729556023e-06, "epoch": 0.6975789905621665, "percentage": 56.67, "elapsed_time": "1:51:08", "remaining_time": "1:24:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.11519541591405869, "epoch": 0.6975789905621665, "percentage": 56.67, "elapsed_time": "1:51:34", "remaining_time": "1:25:19", "throughput": "0.00", "total_tokens": 0}