Training in progress, step 20

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6b8f98e0ec3c00dfc204b273de316c3cea080180e208920ee5a00ff81d7864
+oid sha256:f523e66f79d9c1e9203e537ed453fc1bb131244fd23dd558925a6876b523ecf9
 size 1656903768

logging.jsonl

@@ -17,3 +17,10 @@
 {"loss": 0.83453828, "token_acc": 0.76897133, "grad_norm": 0.14502233, "learning_rate": 2.62e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.030603, "epoch": 0.05725191, "global_step/max_steps": "15/786", "percentage": "1.91%", "elapsed_time": "8m 3s", "remaining_time": "6h 53m 55s"}
 {"eval_loss": 0.89954847, "eval_token_acc": 0.77380728, "eval_runtime": 22.059, "eval_samples_per_second": 0.952, "eval_steps_per_second": 0.136, "epoch": 0.05725191, "global_step/max_steps": "15/786", "percentage": "1.91%", "elapsed_time": "8m 25s", "remaining_time": "7h 12m 49s"}
 {"loss": 0.99048138, "token_acc": 0.70949721, "grad_norm": 2.69842438, "learning_rate": 2.8e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029029, "epoch": 0.0610687, "global_step/max_steps": "16/786", "percentage": "2.04%", "elapsed_time": "9m 4s", "remaining_time": "7h 16m 29s"}
+{"loss": 0.98029929, "token_acc": 0.63352827, "grad_norm": 2.74421964, "learning_rate": 2.97e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029253, "epoch": 0.0648855, "global_step/max_steps": "17/786", "percentage": "2.16%", "elapsed_time": "9m 34s", "remaining_time": "7h 12m 52s"}
+{"loss": 1.27479923, "token_acc": 0.73897059, "grad_norm": 2.36793428, "learning_rate": 3.15e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029456, "epoch": 0.06870229, "global_step/max_steps": "18/786", "percentage": "2.29%", "elapsed_time": "10m 4s", "remaining_time": "7h 9m 35s"}
+{"loss": 0.79431921, "token_acc": 0.74406332, "grad_norm": 0.40841569, "learning_rate": 3.32e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.030149, "epoch": 0.07251908, "global_step/max_steps": "19/786", "percentage": "2.42%", "elapsed_time": "10m 23s", "remaining_time": "6h 59m 18s"}
+{"loss": 0.72544003, "token_acc": 0.76136364, "grad_norm": 8.14447521, "learning_rate": 3.5e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.030299, "epoch": 0.07633588, "global_step/max_steps": "20/786", "percentage": "2.54%", "elapsed_time": "10m 53s", "remaining_time": "6h 56m 54s"}
+{"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"}