Training in progress, step 176

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ecb1df8363c2f2db81259186ac302f503ac4d05b0eabed3a059aea65207669
+oid sha256:c2a90a3fb8be7c015f5d69d981f401deb0a1c7090ca756c441db00cf9f12ce9f
 size 4969539560

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c9f05193350f7ea3fcbe0327dc0f99fd76220fc04aa49af13d7fbc73db4e30
+oid sha256:9a58a8899b511d48c4f12a03907873a2e2af75be92f7e47ba879a77cc9687488
 size 1912795688

trainer_log.jsonl

@@ -662,3 +662,20 @@
 {"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"}
+{"current_steps": 177, "total_steps": 400, "loss": 0.7001, "lr": 7.185729670371604e-08, "epoch": 44.29090909090909, "percentage": 44.25, "elapsed_time": "0:21:42", "remaining_time": "0:27:21"}
+{"current_steps": 178, "total_steps": 400, "loss": 0.786, "lr": 7.149255520259337e-08, "epoch": 44.58181818181818, "percentage": 44.5, "elapsed_time": "0:21:49", "remaining_time": "0:27:13"}
+{"current_steps": 179, "total_steps": 400, "loss": 0.6767, "lr": 7.11265577295385e-08, "epoch": 44.872727272727275, "percentage": 44.75, "elapsed_time": "0:21:56", "remaining_time": "0:27:05"}
+{"current_steps": 180, "total_steps": 400, "loss": 0.7351, "lr": 7.075933215667603e-08, "epoch": 45.0, "percentage": 45.0, "elapsed_time": "0:21:59", "remaining_time": "0:26:52"}
+{"current_steps": 181, "total_steps": 400, "loss": 0.7047, "lr": 7.039090644965509e-08, "epoch": 45.29090909090909, "percentage": 45.25, "elapsed_time": "0:22:06", "remaining_time": "0:26:45"}
+{"current_steps": 182, "total_steps": 400, "loss": 0.7113, "lr": 7.002130866551968e-08, "epoch": 45.58181818181818, "percentage": 45.5, "elapsed_time": "0:22:13", "remaining_time": "0:26:37"}
+{"current_steps": 183, "total_steps": 400, "loss": 0.7255, "lr": 6.965056695057204e-08, "epoch": 45.872727272727275, "percentage": 45.75, "elapsed_time": "0:22:20", "remaining_time": "0:26:30"}
+{"current_steps": 184, "total_steps": 400, "loss": 0.7503, "lr": 6.927870953822915e-08, "epoch": 46.0, "percentage": 46.0, "elapsed_time": "0:22:23", "remaining_time": "0:26:17"}
+{"current_steps": 185, "total_steps": 400, "loss": 0.7008, "lr": 6.890576474687262e-08, "epoch": 46.29090909090909, "percentage": 46.25, "elapsed_time": "0:22:30", "remaining_time": "0:26:09"}
+{"current_steps": 186, "total_steps": 400, "loss": 0.6925, "lr": 6.853176097769228e-08, "epoch": 46.58181818181818, "percentage": 46.5, "elapsed_time": "0:22:37", "remaining_time": "0:26:01"}
+{"current_steps": 187, "total_steps": 400, "loss": 0.7409, "lr": 6.815672671252315e-08, "epoch": 46.872727272727275, "percentage": 46.75, "elapsed_time": "0:22:44", "remaining_time": "0:25:54"}
+{"current_steps": 188, "total_steps": 400, "loss": 0.702, "lr": 6.778069051167653e-08, "epoch": 47.0, "percentage": 47.0, "elapsed_time": "0:22:47", "remaining_time": "0:25:42"}
+{"current_steps": 189, "total_steps": 400, "loss": 0.7085, "lr": 6.740368101176495e-08, "epoch": 47.29090909090909, "percentage": 47.25, "elapsed_time": "0:22:54", "remaining_time": "0:25:34"}
+{"current_steps": 190, "total_steps": 400, "loss": 0.685, "lr": 6.702572692352155e-08, "epoch": 47.58181818181818, "percentage": 47.5, "elapsed_time": "0:23:01", "remaining_time": "0:25:27"}
+{"current_steps": 191, "total_steps": 400, "loss": 0.7551, "lr": 6.664685702961344e-08, "epoch": 47.872727272727275, "percentage": 47.75, "elapsed_time": "0:23:08", "remaining_time": "0:25:19"}
+{"current_steps": 192, "total_steps": 400, "loss": 0.6327, "lr": 6.626710018244986e-08, "epoch": 48.0, "percentage": 48.0, "elapsed_time": "0:23:11", "remaining_time": "0:25:07"}
+{"current_steps": 192, "total_steps": 400, "eval_loss": 0.6752312183380127, "epoch": 48.0, "percentage": 48.0, "elapsed_time": "0:23:12", "remaining_time": "0:25:08"}