Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c971089b0dbb7f1fd7233b86ee4eab0e4320b6c6bbffc37c6fa55466e3172a9
+oid sha256:bdc08534aac7838c266708395ae95ee206c6d0313a225f23be71ea0622c11781
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.2568, "accuracy": 0.9375, "learning_rate": 3.3221666168464584e-06, "epoch": 0.5239786856127886, "percentage": 39.33, "elapsed_time": "1:19:54", "remaining_time": "2:03:14", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.2639, "accuracy": 0.925000011920929, "learning_rate": 3.272542485937369e-06, "epoch": 0.5328596802841918, "percentage": 40.0, "elapsed_time": "1:21:11", "remaining_time": "2:01:46", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.28853774070739746, "epoch": 0.5328596802841918, "percentage": 40.0, "elapsed_time": "1:21:36", "remaining_time": "2:02:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.2816, "accuracy": 0.9125000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.5417406749555951, "percentage": 40.67, "elapsed_time": "1:22:54", "remaining_time": "2:00:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.2891, "accuracy": 0.862500011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5506216696269982, "percentage": 41.33, "elapsed_time": "1:24:11", "remaining_time": "1:59:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.2702, "accuracy": 0.925000011920929, "learning_rate": 3.121724717912138e-06, "epoch": 0.5595026642984015, "percentage": 42.0, "elapsed_time": "1:25:24", "remaining_time": "1:57:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2598, "accuracy": 0.925000011920929, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5683836589698046, "percentage": 42.67, "elapsed_time": "1:26:45", "remaining_time": "1:56:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.2453, "accuracy": 0.9375, "learning_rate": 3.019779227044398e-06, "epoch": 0.5772646536412078, "percentage": 43.33, "elapsed_time": "1:28:00", "remaining_time": "1:55:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.27302286028862, "epoch": 0.5772646536412078, "percentage": 43.33, "elapsed_time": "1:28:25", "remaining_time": "1:55:38", "throughput": "0.00", "total_tokens": 0}