Training in progress, step 15

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4543dc3325c39698fbbddf9356ca7f09abd2079c5e4495fdccbbae8efd448994
+oid sha256:1e6b8f98e0ec3c00dfc204b273de316c3cea080180e208920ee5a00ff81d7864
 size 1656903768

logging.jsonl

@@ -12,3 +12,8 @@
 {"eval_loss": 0.92826158, "eval_token_acc": 0.77293847, "eval_runtime": 22.0765, "eval_samples_per_second": 0.951, "eval_steps_per_second": 0.136, "epoch": 0.03816794, "global_step/max_steps": "10/786", "percentage": "1.27%", "elapsed_time": "5m 36s", "remaining_time": "7h 15m 24s"}
 {"loss": 0.78038925, "token_acc": 0.75861374, "grad_norm": 0.60470217, "learning_rate": 1.93e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.028719, "epoch": 0.04198473, "global_step/max_steps": "11/786", "percentage": "1.40%", "elapsed_time": "6m 16s", "remaining_time": "7h 21m 34s"}
 {"loss": 1.00450289, "token_acc": 0.66912442, "grad_norm": 7.0186057, "learning_rate": 2.1e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.028992, "epoch": 0.04580153, "global_step/max_steps": "12/786", "percentage": "1.53%", "elapsed_time": "6m 46s", "remaining_time": "7h 17m 27s"}
+{"loss": 1.2894696, "token_acc": 0.818409, "grad_norm": 15.69610859, "learning_rate": 2.28e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029284, "epoch": 0.04961832, "global_step/max_steps": "13/786", "percentage": "1.65%", "elapsed_time": "7m 16s", "remaining_time": "7h 13m 2s"}
+{"loss": 0.91177201, "token_acc": 0.76051188, "grad_norm": 19.4416792, "learning_rate": 2.45e-06, "memory(GiB)": 88.62, "train_speed(iter/s)": 0.029532, "epoch": 0.05343511, "global_step/max_steps": "14/786", "percentage": "1.78%", "elapsed_time": "7m 47s", "remaining_time": "7h 9m 17s"}
+{"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"}