Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e3913cdb218f4940e97110368dad2d1faea4555e2d3be9b765ca062f909214
+oid sha256:cd4297aebfd94c1c658683f162b7ca02f1eea775fe99c7ee88c2ef914c2ac511
 size 25200088

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.2461, "accuracy": 0.925000011920929, "learning_rate": 2.290805391669212e-06, "epoch": 0.6789858186506231, "percentage": 52.67, "elapsed_time": "1:43:39", "remaining_time": "1:33:09", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 0.2483, "accuracy": 0.925000011920929, "learning_rate": 2.238678841830867e-06, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:44:51", "remaining_time": "1:31:45", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.24035032093524933, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:45:17", "remaining_time": "1:32:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.2647, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.6961753330468414, "percentage": 54.0, "elapsed_time": "1:46:36", "remaining_time": "1:30:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 0.1888, "accuracy": 0.8999999761581421, "learning_rate": 2.134792428593971e-06, "epoch": 0.7047700902449506, "percentage": 54.67, "elapsed_time": "1:47:52", "remaining_time": "1:29:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.2141, "accuracy": 0.949999988079071, "learning_rate": 2.0830781332097446e-06, "epoch": 0.7133648474430597, "percentage": 55.33, "elapsed_time": "1:49:06", "remaining_time": "1:28:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.1953, "accuracy": 0.949999988079071, "learning_rate": 2.031546713535688e-06, "epoch": 0.7219596046411689, "percentage": 56.0, "elapsed_time": "1:50:14", "remaining_time": "1:26:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "loss": 0.2395, "accuracy": 0.8999999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:51:31", "remaining_time": "1:25:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2363433688879013, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:51:56", "remaining_time": "1:25:36", "throughput": "0.00", "total_tokens": 0}