Training in progress, step 150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecfa84856ef70e882b427ca9a984bd5881d4a783680e87de29428d4adcee039
+oid sha256:cda936af04db908af7c47cb3c69556d5cad1dfe8ef1330756b117267dd4e6a06
 size 40036488

trainer_log.jsonl

@@ -10,3 +10,9 @@
 {"current_steps": 90, "total_steps": 1000, "loss": 7.268, "accuracy": 0.6000000238418579, "learning_rate": 4.900734214192358e-06, "epoch": 0.0652351182386518, "percentage": 9.0, "elapsed_time": "0:11:56", "remaining_time": "2:00:41", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 100, "total_steps": 1000, "loss": 7.2544, "accuracy": 0.5874999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.07248346470961312, "percentage": 10.0, "elapsed_time": "0:13:09", "remaining_time": "1:58:25", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 100, "total_steps": 1000, "eval_loss": 0.8920583724975586, "epoch": 0.07248346470961312, "percentage": 10.0, "elapsed_time": "0:13:39", "remaining_time": "2:02:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 1000, "loss": 7.1762, "accuracy": 0.550000011920929, "learning_rate": 4.852201922385564e-06, "epoch": 0.07973181118057443, "percentage": 11.0, "elapsed_time": "0:15:07", "remaining_time": "2:02:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 120, "total_steps": 1000, "loss": 7.1442, "accuracy": 0.625, "learning_rate": 4.824441214720629e-06, "epoch": 0.08698015765153574, "percentage": 12.0, "elapsed_time": "0:16:20", "remaining_time": "1:59:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 130, "total_steps": 1000, "loss": 7.1449, "accuracy": 0.612500011920929, "learning_rate": 4.794386564209953e-06, "epoch": 0.09422850412249706, "percentage": 13.0, "elapsed_time": "0:17:32", "remaining_time": "1:57:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 140, "total_steps": 1000, "loss": 7.122, "accuracy": 0.625, "learning_rate": 4.762067631165049e-06, "epoch": 0.10147685059345837, "percentage": 14.0, "elapsed_time": "0:18:47", "remaining_time": "1:55:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 150, "total_steps": 1000, "loss": 7.1253, "accuracy": 0.6625000238418579, "learning_rate": 4.72751631047092e-06, "epoch": 0.10872519706441967, "percentage": 15.0, "elapsed_time": "0:19:59", "remaining_time": "1:53:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 150, "total_steps": 1000, "eval_loss": 0.8764163851737976, "epoch": 0.10872519706441967, "percentage": 15.0, "elapsed_time": "0:20:29", "remaining_time": "1:56:06", "throughput": "0.00", "total_tokens": 0}