Training in progress, step 20

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e9024c4970631d5c118c9f68cb0d8735391c7831e22b21daa8f955a179d71d
+oid sha256:2f3a788d462da9ac77f0e10867222c39d5d75adff0237b5117255c605e7a79e1
 size 1656903768

logging.jsonl

@@ -4,3 +4,9 @@
 {"loss": 14.58541107, "token_acc": 0.84268516, "grad_norm": 0.21005033, "learning_rate": 4.288e-05, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.003989, "epoch": 1.73282443, "global_step/max_steps": "14/24", "percentage": "58.33%", "elapsed_time": "58m 14s", "remaining_time": "41m 36s"}
 {"loss": 14.47380066, "token_acc": 0.85444938, "grad_norm": 0.21881856, "learning_rate": 3.591e-05, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.003445, "epoch": 1.85496183, "global_step/max_steps": "15/24", "percentage": "62.50%", "elapsed_time": "1h 12m 19s", "remaining_time": "43m 23s"}
 {"eval_loss": 0.45699596, "eval_token_acc": 0.85895063, "eval_runtime": 21.4898, "eval_samples_per_second": 0.977, "eval_steps_per_second": 0.14, "epoch": 1.85496183, "global_step/max_steps": "15/24", "percentage": "62.50%", "elapsed_time": "1h 12m 41s", "remaining_time": "43m 36s"}
+{"loss": 14.06553078, "token_acc": 0.86124204, "grad_norm": 0.20159593, "learning_rate": 2.923e-05, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.003033, "epoch": 1.97709924, "global_step/max_steps": "16/24", "percentage": "66.67%", "elapsed_time": "1h 27m 40s", "remaining_time": "43m 50s"}
+{"loss": 16.11391258, "token_acc": 0.86498041, "grad_norm": 0.20615543, "learning_rate": 2.297e-05, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.00269, "epoch": 2.1221374, "global_step/max_steps": "17/24", "percentage": "70.83%", "elapsed_time": "1h 45m 5s", "remaining_time": "43m 16s"}
+{"loss": 14.20277405, "token_acc": 0.85234303, "grad_norm": 0.21431336, "learning_rate": 1.726e-05, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.002511, "epoch": 2.24427481, "global_step/max_steps": "18/24", "percentage": "75.00%", "elapsed_time": "1h 59m 12s", "remaining_time": "39m 44s"}
+{"loss": 13.74881935, "token_acc": 0.87061663, "grad_norm": 0.25552696, "learning_rate": 1.221e-05, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.002367, "epoch": 2.36641221, "global_step/max_steps": "19/24", "percentage": "79.17%", "elapsed_time": "2h 13m 32s", "remaining_time": "35m 8s"}
+{"loss": 13.37627411, "token_acc": 0.86427258, "grad_norm": 0.18122235, "learning_rate": 7.94e-06, "memory(GiB)": 90.55, "train_speed(iter/s)": 0.002256, "epoch": 2.48854962, "global_step/max_steps": "20/24", "percentage": "83.33%", "elapsed_time": "2h 27m 29s", "remaining_time": "29m 29s"}
+{"eval_loss": 0.44094244, "eval_token_acc": 0.86080157, "eval_runtime": 21.4644, "eval_samples_per_second": 0.978, "eval_steps_per_second": 0.14, "epoch": 2.48854962, "global_step/max_steps": "20/24", "percentage": "83.33%", "elapsed_time": "2h 27m 51s", "remaining_time": "29m 34s"}