Training in progress, step 144

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80a7bc4478514fc43b45340abbcbdc55ece8273b526f2861e622e00eaec86ef
+oid sha256:47ff32476ecc21d56bff8791c9c19cc9356ce3dd7fcc8242010e48d55c769041
 size 4969539560

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba52b61c5ccddc47cf4dc6c884fd2e506b81bcd29dba3aab266c2a249a913285
+oid sha256:78bfd1c19c7ea6b2dab65d32007db116ce032d73875b76b9a0b25bc3b2426bf7
 size 1912795688

trainer_log.jsonl

@@ -628,3 +628,20 @@
 {"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"}
+{"current_steps": 145, "total_steps": 400, "loss": 0.7921, "lr": 8.270476638965461e-08, "epoch": 36.29090909090909, "percentage": 36.25, "elapsed_time": "0:17:43", "remaining_time": "0:31:10"}
+{"current_steps": 146, "total_steps": 400, "loss": 0.6827, "lr": 8.239426430539243e-08, "epoch": 36.58181818181818, "percentage": 36.5, "elapsed_time": "0:17:50", "remaining_time": "0:31:03"}
+{"current_steps": 147, "total_steps": 400, "loss": 0.7774, "lr": 8.208167604184218e-08, "epoch": 36.872727272727275, "percentage": 36.75, "elapsed_time": "0:17:57", "remaining_time": "0:30:55"}
+{"current_steps": 148, "total_steps": 400, "loss": 0.6709, "lr": 8.176702540381035e-08, "epoch": 37.0, "percentage": 37.0, "elapsed_time": "0:18:00", "remaining_time": "0:30:40"}
+{"current_steps": 149, "total_steps": 400, "loss": 0.7302, "lr": 8.145033635316129e-08, "epoch": 37.29090909090909, "percentage": 37.25, "elapsed_time": "0:18:07", "remaining_time": "0:30:32"}
+{"current_steps": 150, "total_steps": 400, "loss": 0.7301, "lr": 8.113163300699229e-08, "epoch": 37.58181818181818, "percentage": 37.5, "elapsed_time": "0:18:14", "remaining_time": "0:30:23"}
+{"current_steps": 151, "total_steps": 400, "loss": 0.7223, "lr": 8.081093963579708e-08, "epoch": 37.872727272727275, "percentage": 37.75, "elapsed_time": "0:18:22", "remaining_time": "0:30:17"}
+{"current_steps": 152, "total_steps": 400, "loss": 0.7989, "lr": 8.048828066161747e-08, "epoch": 38.0, "percentage": 38.0, "elapsed_time": "0:18:25", "remaining_time": "0:30:02"}
+{"current_steps": 153, "total_steps": 400, "loss": 0.6768, "lr": 8.016368065618359e-08, "epoch": 38.29090909090909, "percentage": 38.25, "elapsed_time": "0:18:31", "remaining_time": "0:29:55"}
+{"current_steps": 154, "total_steps": 400, "loss": 0.7454, "lr": 7.983716433904262e-08, "epoch": 38.58181818181818, "percentage": 38.5, "elapsed_time": "0:18:38", "remaining_time": "0:29:47"}
+{"current_steps": 155, "total_steps": 400, "loss": 0.7511, "lr": 7.950875657567622e-08, "epoch": 38.872727272727275, "percentage": 38.75, "elapsed_time": "0:18:46", "remaining_time": "0:29:40"}
+{"current_steps": 156, "total_steps": 400, "loss": 0.8113, "lr": 7.917848237560708e-08, "epoch": 39.0, "percentage": 39.0, "elapsed_time": "0:18:48", "remaining_time": "0:29:25"}
+{"current_steps": 157, "total_steps": 400, "loss": 0.7076, "lr": 7.884636689049422e-08, "epoch": 39.29090909090909, "percentage": 39.25, "elapsed_time": "0:18:55", "remaining_time": "0:29:17"}
+{"current_steps": 158, "total_steps": 400, "loss": 0.7437, "lr": 7.851243541221769e-08, "epoch": 39.58181818181818, "percentage": 39.5, "elapsed_time": "0:19:02", "remaining_time": "0:29:10"}
+{"current_steps": 159, "total_steps": 400, "loss": 0.7404, "lr": 7.817671337095244e-08, "epoch": 39.872727272727275, "percentage": 39.75, "elapsed_time": "0:19:09", "remaining_time": "0:29:02"}
+{"current_steps": 160, "total_steps": 400, "loss": 0.7328, "lr": 7.78392263332317e-08, "epoch": 40.0, "percentage": 40.0, "elapsed_time": "0:19:12", "remaining_time": "0:28:49"}
+{"current_steps": 160, "total_steps": 400, "eval_loss": 0.7006868124008179, "epoch": 40.0, "percentage": 40.0, "elapsed_time": "0:19:13", "remaining_time": "0:28:50"}