Training in progress, step 160

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ff32476ecc21d56bff8791c9c19cc9356ce3dd7fcc8242010e48d55c769041
+oid sha256:d8ecb1df8363c2f2db81259186ac302f503ac4d05b0eabed3a059aea65207669
 size 4969539560

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bfd1c19c7ea6b2dab65d32007db116ce032d73875b76b9a0b25bc3b2426bf7
+oid sha256:a9c9f05193350f7ea3fcbe0327dc0f99fd76220fc04aa49af13d7fbc73db4e30
 size 1912795688

trainer_log.jsonl

@@ -645,3 +645,20 @@
 {"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"}
+{"current_steps": 161, "total_steps": 400, "loss": 0.7431, "lr": 7.75e-08, "epoch": 40.29090909090909, "percentage": 40.25, "elapsed_time": "0:19:42", "remaining_time": "0:29:16"}
+{"current_steps": 162, "total_steps": 400, "loss": 0.7585, "lr": 7.715906020465603e-08, "epoch": 40.58181818181818, "percentage": 40.5, "elapsed_time": "0:19:49", "remaining_time": "0:29:08"}
+{"current_steps": 163, "total_steps": 400, "loss": 0.7324, "lr": 7.681643291108518e-08, "epoch": 40.872727272727275, "percentage": 40.75, "elapsed_time": "0:19:56", "remaining_time": "0:28:59"}
+{"current_steps": 164, "total_steps": 400, "loss": 0.6533, "lr": 7.647214421168238e-08, "epoch": 41.0, "percentage": 41.0, "elapsed_time": "0:20:00", "remaining_time": "0:28:47"}
+{"current_steps": 165, "total_steps": 400, "loss": 0.7135, "lr": 7.612622032536508e-08, "epoch": 41.29090909090909, "percentage": 41.25, "elapsed_time": "0:20:07", "remaining_time": "0:28:39"}
+{"current_steps": 166, "total_steps": 400, "loss": 0.7597, "lr": 7.577868759557654e-08, "epoch": 41.58181818181818, "percentage": 41.5, "elapsed_time": "0:20:14", "remaining_time": "0:28:31"}
+{"current_steps": 167, "total_steps": 400, "loss": 0.7109, "lr": 7.54295724882796e-08, "epoch": 41.872727272727275, "percentage": 41.75, "elapsed_time": "0:20:20", "remaining_time": "0:28:23"}
+{"current_steps": 168, "total_steps": 400, "loss": 0.7504, "lr": 7.507890158994139e-08, "epoch": 42.0, "percentage": 42.0, "elapsed_time": "0:20:24", "remaining_time": "0:28:10"}
+{"current_steps": 169, "total_steps": 400, "loss": 0.7096, "lr": 7.472670160550848e-08, "epoch": 42.29090909090909, "percentage": 42.25, "elapsed_time": "0:20:31", "remaining_time": "0:28:03"}
+{"current_steps": 170, "total_steps": 400, "loss": 0.7692, "lr": 7.437299935637328e-08, "epoch": 42.58181818181818, "percentage": 42.5, "elapsed_time": "0:20:38", "remaining_time": "0:27:55"}
+{"current_steps": 171, "total_steps": 400, "loss": 0.7346, "lr": 7.401782177833146e-08, "epoch": 42.872727272727275, "percentage": 42.75, "elapsed_time": "0:20:44", "remaining_time": "0:27:47"}
+{"current_steps": 172, "total_steps": 400, "loss": 0.6633, "lr": 7.366119591953075e-08, "epoch": 43.0, "percentage": 43.0, "elapsed_time": "0:20:47", "remaining_time": "0:27:34"}
+{"current_steps": 173, "total_steps": 400, "loss": 0.7365, "lr": 7.3303148938411e-08, "epoch": 43.29090909090909, "percentage": 43.25, "elapsed_time": "0:20:55", "remaining_time": "0:27:27"}
+{"current_steps": 174, "total_steps": 400, "loss": 0.7511, "lr": 7.294370810163607e-08, "epoch": 43.58181818181818, "percentage": 43.5, "elapsed_time": "0:21:02", "remaining_time": "0:27:19"}
+{"current_steps": 175, "total_steps": 400, "loss": 0.6481, "lr": 7.258290078201731e-08, "epoch": 43.872727272727275, "percentage": 43.75, "elapsed_time": "0:21:08", "remaining_time": "0:27:11"}
+{"current_steps": 176, "total_steps": 400, "loss": 0.8191, "lr": 7.222075445642904e-08, "epoch": 44.0, "percentage": 44.0, "elapsed_time": "0:21:11", "remaining_time": "0:26:58"}
+{"current_steps": 176, "total_steps": 400, "eval_loss": 0.6937930583953857, "epoch": 44.0, "percentage": 44.0, "elapsed_time": "0:21:12", "remaining_time": "0:26:59"}