Training in progress, step 25

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f523e66f79d9c1e9203e537ed453fc1bb131244fd23dd558925a6876b523ecf9
+oid sha256:1d5af0cff5fc1605dcb6d70cdb035216d6e30b8a0c9b02bff722d4c59ba18c47
 size 1656903768

logging.jsonl

@@ -24,3 +24,9 @@
 {"eval_loss": 0.93264651, "eval_token_acc": 0.77342953, "eval_runtime": 22.0341, "eval_samples_per_second": 0.953, "eval_steps_per_second": 0.136, "epoch": 0.07633588, "global_step/max_steps": "20/786", "percentage": "2.54%", "elapsed_time": "11m 15s", "remaining_time": "7h 10m 58s"}
 {"loss": 1.03133607, "token_acc": 0.75963771, "grad_norm": 10.5853401, "learning_rate": 3.67e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029077, "epoch": 0.08015267, "global_step/max_steps": "21/786", "percentage": "2.67%", "elapsed_time": "11m 55s", "remaining_time": "7h 14m 15s"}
 {"loss": 0.90063345, "token_acc": 0.79555237, "grad_norm": 4.18292453, "learning_rate": 3.85e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029268, "epoch": 0.08396947, "global_step/max_steps": "22/786", "percentage": "2.80%", "elapsed_time": "12m 24s", "remaining_time": "7h 11m 1s"}
+{"loss": 1.25162315, "token_acc": 0.74662669, "grad_norm": 6.2844299, "learning_rate": 4.02e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029426, "epoch": 0.08778626, "global_step/max_steps": "23/786", "percentage": "2.93%", "elapsed_time": "12m 54s", "remaining_time": "7h 8m 17s"}
+{"loss": 0.91385037, "token_acc": 0.79717587, "grad_norm": 14.13236802, "learning_rate": 4.2e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029573, "epoch": 0.09160305, "global_step/max_steps": "24/786", "percentage": "3.05%", "elapsed_time": "13m 24s", "remaining_time": "7h 5m 45s"}
+{"loss": 0.80503768, "token_acc": 0.75471698, "grad_norm": 0.57895672, "learning_rate": 4.37e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029711, "epoch": 0.09541985, "global_step/max_steps": "25/786", "percentage": "3.18%", "elapsed_time": "13m 54s", "remaining_time": "7h 3m 21s"}
+{"eval_loss": 0.92728376, "eval_token_acc": 0.77350508, "eval_runtime": 22.14, "eval_samples_per_second": 0.949, "eval_steps_per_second": 0.136, "epoch": 0.09541985, "global_step/max_steps": "25/786", "percentage": "3.18%", "elapsed_time": "14m 16s", "remaining_time": "7h 14m 35s"}
+{"loss": 0.91751623, "token_acc": 0.77953335, "grad_norm": 125.80540284, "learning_rate": 4.55e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.02879, "epoch": 0.09923664, "global_step/max_steps": "26/786", "percentage": "3.31%", "elapsed_time": "14m 56s", "remaining_time": "7h 16m 34s"}
+{"loss": 0.80560565, "token_acc": 0.76595745, "grad_norm": 0.16683542, "learning_rate": 4.73e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029367, "epoch": 0.10305344, "global_step/max_steps": "27/786", "percentage": "3.44%", "elapsed_time": "15m 12s", "remaining_time": "7h 7m 29s"}