Training in progress, step 128

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47b82aa2abc24774e65bf3c840b73254af400c018b54a4b74076c10b7aa50f1
+oid sha256:f80a7bc4478514fc43b45340abbcbdc55ece8273b526f2861e622e00eaec86ef
 size 4969539560

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3948e1712d66e4846b20e1f82e841d2b592341e95b95f7284d25901e27823131
+oid sha256:ba52b61c5ccddc47cf4dc6c884fd2e506b81bcd29dba3aab266c2a249a913285
 size 1912795688

trainer_log.jsonl

@@ -611,3 +611,20 @@
 {"current_steps": 127, "total_steps": 400, "loss": 0.7756, "lr": 8.791091657286267e-08, "epoch": 31.87272727272727, "percentage": 31.75, "elapsed_time": "0:15:08", "remaining_time": "0:32:31"}
 {"current_steps": 128, "total_steps": 400, "loss": 0.6471, "lr": 8.764184669555293e-08, "epoch": 32.0, "percentage": 32.0, "elapsed_time": "0:15:10", "remaining_time": "0:32:15"}
 {"current_steps": 128, "total_steps": 400, "eval_loss": 0.7097088694572449, "epoch": 32.0, "percentage": 32.0, "elapsed_time": "0:15:11", "remaining_time": "0:32:17"}
+{"current_steps": 129, "total_steps": 400, "loss": 0.7418, "lr": 8.737029101523929e-08, "epoch": 32.29090909090909, "percentage": 32.25, "elapsed_time": "0:15:43", "remaining_time": "0:33:01"}
+{"current_steps": 130, "total_steps": 400, "loss": 0.7407, "lr": 8.709627021193817e-08, "epoch": 32.58181818181818, "percentage": 32.5, "elapsed_time": "0:15:50", "remaining_time": "0:32:53"}
+{"current_steps": 131, "total_steps": 400, "loss": 0.7486, "lr": 8.681980515339464e-08, "epoch": 32.872727272727275, "percentage": 32.75, "elapsed_time": "0:15:56", "remaining_time": "0:32:44"}
+{"current_steps": 132, "total_steps": 400, "loss": 0.7381, "lr": 8.65409168934933e-08, "epoch": 33.0, "percentage": 33.0, "elapsed_time": "0:16:00", "remaining_time": "0:32:29"}
+{"current_steps": 133, "total_steps": 400, "loss": 0.8277, "lr": 8.625962667065488e-08, "epoch": 33.29090909090909, "percentage": 33.25, "elapsed_time": "0:16:07", "remaining_time": "0:32:22"}
+{"current_steps": 134, "total_steps": 400, "loss": 0.7345, "lr": 8.597595590621892e-08, "epoch": 33.58181818181818, "percentage": 33.5, "elapsed_time": "0:16:14", "remaining_time": "0:32:15"}
+{"current_steps": 135, "total_steps": 400, "loss": 0.6949, "lr": 8.568992620281244e-08, "epoch": 33.872727272727275, "percentage": 33.75, "elapsed_time": "0:16:21", "remaining_time": "0:32:06"}
+{"current_steps": 136, "total_steps": 400, "loss": 0.6427, "lr": 8.540155934270471e-08, "epoch": 34.0, "percentage": 34.0, "elapsed_time": "0:16:24", "remaining_time": "0:31:50"}
+{"current_steps": 137, "total_steps": 400, "loss": 0.7113, "lr": 8.511087728614862e-08, "epoch": 34.29090909090909, "percentage": 34.25, "elapsed_time": "0:16:31", "remaining_time": "0:31:42"}
+{"current_steps": 138, "total_steps": 400, "loss": 0.7422, "lr": 8.481790216970819e-08, "epoch": 34.58181818181818, "percentage": 34.5, "elapsed_time": "0:16:37", "remaining_time": "0:31:34"}
+{"current_steps": 139, "total_steps": 400, "loss": 0.7829, "lr": 8.452265630457283e-08, "epoch": 34.872727272727275, "percentage": 34.75, "elapsed_time": "0:16:44", "remaining_time": "0:31:26"}
+{"current_steps": 140, "total_steps": 400, "loss": 0.718, "lr": 8.422516217485826e-08, "epoch": 35.0, "percentage": 35.0, "elapsed_time": "0:16:47", "remaining_time": "0:31:11"}
+{"current_steps": 141, "total_steps": 400, "loss": 0.7046, "lr": 8.392544243589427e-08, "epoch": 35.29090909090909, "percentage": 35.25, "elapsed_time": "0:16:55", "remaining_time": "0:31:05"}
+{"current_steps": 142, "total_steps": 400, "loss": 0.7685, "lr": 8.362351991249938e-08, "epoch": 35.58181818181818, "percentage": 35.5, "elapsed_time": "0:17:02", "remaining_time": "0:30:57"}
+{"current_steps": 143, "total_steps": 400, "loss": 0.6774, "lr": 8.331941759724268e-08, "epoch": 35.872727272727275, "percentage": 35.75, "elapsed_time": "0:17:08", "remaining_time": "0:30:49"}
+{"current_steps": 144, "total_steps": 400, "loss": 0.9019, "lr": 8.301315864869288e-08, "epoch": 36.0, "percentage": 36.0, "elapsed_time": "0:17:11", "remaining_time": "0:30:34"}
+{"current_steps": 144, "total_steps": 400, "eval_loss": 0.7050113677978516, "epoch": 36.0, "percentage": 36.0, "elapsed_time": "0:17:12", "remaining_time": "0:30:35"}