Training in progress, step 20

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be94cd510bdedcc178334ba545ff7f140b03d4078136c60121d6282b1d1cff45
+oid sha256:c684f8e54c141d7cc7e79a04eaa39aed12110ddeeb91ddd2f9c74d559f9b96de
 size 369699136

logging.jsonl

@@ -9,3 +9,15 @@
 {"loss": 0.35201401, "token_acc": 0.89277345, "grad_norm": 0.55272579, "learning_rate": 8.57e-06, "memory(GiB)": 118.09, "train_speed(iter/s)": 0.024923, "epoch": 0.66055046, "global_step/max_steps": "9/39", "percentage": "23.08%", "elapsed_time": "5m 55s", "remaining_time": "19m 44s"}
 {"loss": 0.37256077, "token_acc": 0.89065348, "grad_norm": 0.80991906, "learning_rate": 8.29e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.023943, "epoch": 0.73394495, "global_step/max_steps": "10/39", "percentage": "25.64%", "elapsed_time": "6m 51s", "remaining_time": "19m 54s"}
 {"eval_loss": 0.41130996, "eval_token_acc": 0.87739136, "eval_runtime": 5.218, "eval_samples_per_second": 4.983, "eval_steps_per_second": 0.767, "epoch": 0.73394495, "global_step/max_steps": "10/39", "percentage": "25.64%", "elapsed_time": "6m 57s", "remaining_time": "20m 9s"}
+{"loss": 0.35977143, "token_acc": 0.88861149, "grad_norm": 0.57512236, "learning_rate": 8e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.023641, "epoch": 0.80733945, "global_step/max_steps": "11/39", "percentage": "28.21%", "elapsed_time": "7m 39s", "remaining_time": "19m 29s"}
+{"loss": 0.36949402, "token_acc": 0.87775763, "grad_norm": 0.58909482, "learning_rate": 7.71e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.024089, "epoch": 0.88073394, "global_step/max_steps": "12/39", "percentage": "30.77%", "elapsed_time": "8m 12s", "remaining_time": "18m 27s"}
+{"loss": 0.36182559, "token_acc": 0.87552214, "grad_norm": 0.49760887, "learning_rate": 7.43e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.024233, "epoch": 0.95412844, "global_step/max_steps": "13/39", "percentage": "33.33%", "elapsed_time": "8m 50s", "remaining_time": "17m 41s"}
+{"loss": 0.32656509, "token_acc": 0.89063243, "grad_norm": 0.49760887, "learning_rate": 7.14e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.025057, "epoch": 1.0, "global_step/max_steps": "14/39", "percentage": "35.90%", "elapsed_time": "9m 12s", "remaining_time": "16m 27s"}
+{"loss": 0.32920551, "token_acc": 0.9056304, "grad_norm": 0.76211411, "learning_rate": 6.86e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.025341, "epoch": 1.0733945, "global_step/max_steps": "15/39", "percentage": "38.46%", "elapsed_time": "9m 46s", "remaining_time": "15m 37s"}
+{"loss": 0.34082595, "token_acc": 0.89531699, "grad_norm": 0.45711133, "learning_rate": 6.57e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.024678, "epoch": 1.14678899, "global_step/max_steps": "16/39", "percentage": "41.03%", "elapsed_time": "10m 42s", "remaining_time": "15m 23s"}
+{"loss": 0.32011092, "token_acc": 0.89625612, "grad_norm": 0.44868213, "learning_rate": 6.29e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.024795, "epoch": 1.22018349, "global_step/max_steps": "17/39", "percentage": "43.59%", "elapsed_time": "11m 19s", "remaining_time": "14m 39s"}
+{"loss": 0.31977218, "token_acc": 0.90087736, "grad_norm": 0.39648461, "learning_rate": 6e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.025069, "epoch": 1.29357798, "global_step/max_steps": "18/39", "percentage": "46.15%", "elapsed_time": "11m 52s", "remaining_time": "13m 50s"}
+{"loss": 0.32391137, "token_acc": 0.8824309, "grad_norm": 0.39456472, "learning_rate": 5.71e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.025161, "epoch": 1.36697248, "global_step/max_steps": "19/39", "percentage": "48.72%", "elapsed_time": "12m 29s", "remaining_time": "13m 8s"}
+{"loss": 0.30489415, "token_acc": 0.91398474, "grad_norm": 0.44964269, "learning_rate": 5.43e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.025319, "epoch": 1.44036697, "global_step/max_steps": "20/39", "percentage": "51.28%", "elapsed_time": "13m 4s", "remaining_time": "12m 24s"}
+{"eval_loss": 0.35035759, "eval_token_acc": 0.89060129, "eval_runtime": 5.2217, "eval_samples_per_second": 4.979, "eval_steps_per_second": 0.766, "epoch": 1.44036697, "global_step/max_steps": "20/39", "percentage": "51.28%", "elapsed_time": "13m 9s", "remaining_time": "12m 29s"}
+{"loss": 0.32621384, "token_acc": 0.9063342, "grad_norm": 0.3818258, "learning_rate": 5.14e-06, "memory(GiB)": 131.04, "train_speed(iter/s)": 0.02509, "epoch": 1.51376147, "global_step/max_steps": "21/39", "percentage": "53.85%", "elapsed_time": "13m 51s", "remaining_time": "11m 52s"}

runs/events.out.tfevents.1743272706.notebook-67532d59-da58-11ef-a92b-d22a634ff48d-0.273350.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0a7672f995088369cf3fc1f1bc28547955abe9723402ed5b66539f6a394156
-size 10951
+oid sha256:5944fe5bb3ce1339616183e860d82529a891b364596c4ddf0d2ab159993d4191
+size 15049