Training in progress, step 15

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56918846517cc0d46e50c5d931dc4f6a369bc484511c4dd39a37d0da451f8de5
+oid sha256:aba94b294b77ab1b529c8814f6c0eef6d82bac90189f0a09399acd43066b733a
 size 1656903768

logging.jsonl

@@ -4,3 +4,9 @@
 {"loss": 26.9921093, "token_acc": 0.78990856, "grad_norm": 0.10876788, "learning_rate": 7.703e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.00246, "epoch": 1.1221374, "global_step/max_steps": "9/24", "percentage": "37.50%", "elapsed_time": "1h 0m 45s", "remaining_time": "1h 41m 15s"}
 {"loss": 22.41528702, "token_acc": 0.78308229, "grad_norm": 0.1409045, "learning_rate": 7.077e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.002205, "epoch": 1.24427481, "global_step/max_steps": "10/24", "percentage": "41.67%", "elapsed_time": "1h 15m 21s", "remaining_time": "1h 45m 29s"}
 {"eval_loss": 0.6736415, "eval_token_acc": 0.81044838, "eval_runtime": 21.32, "eval_samples_per_second": 0.985, "eval_steps_per_second": 0.141, "epoch": 1.24427481, "global_step/max_steps": "10/24", "percentage": "41.67%", "elapsed_time": "1h 15m 42s", "remaining_time": "1h 45m 59s"}
+{"loss": 21.04436493, "token_acc": 0.80944369, "grad_norm": 0.10238781, "learning_rate": 6.409e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.002032, "epoch": 1.36641221, "global_step/max_steps": "11/24", "percentage": "45.83%", "elapsed_time": "1h 30m 1s", "remaining_time": "1h 46m 23s"}
+{"loss": 20.38782883, "token_acc": 0.80890374, "grad_norm": 0.10003216, "learning_rate": 5.712e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001907, "epoch": 1.48854962, "global_step/max_steps": "12/24", "percentage": "50.00%", "elapsed_time": "1h 44m 38s", "remaining_time": "1h 44m 38s"}
+{"loss": 20.67288208, "token_acc": 0.81596492, "grad_norm": 0.09609438, "learning_rate": 5e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001805, "epoch": 1.61068702, "global_step/max_steps": "13/24", "percentage": "54.17%", "elapsed_time": "1h 59m 49s", "remaining_time": "1h 41m 23s"}
+{"loss": 19.65369225, "token_acc": 0.80329641, "grad_norm": 0.08990939, "learning_rate": 4.288e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001742, "epoch": 1.73282443, "global_step/max_steps": "14/24", "percentage": "58.33%", "elapsed_time": "2h 13m 43s", "remaining_time": "1h 35m 31s"}
+{"loss": 19.39007759, "token_acc": 0.82374368, "grad_norm": 0.08934228, "learning_rate": 3.591e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.00169, "epoch": 1.85496183, "global_step/max_steps": "15/24", "percentage": "62.50%", "elapsed_time": "2h 27m 45s", "remaining_time": "1h 28m 39s"}
+{"eval_loss": 0.61527205, "eval_token_acc": 0.82136516, "eval_runtime": 21.2842, "eval_samples_per_second": 0.987, "eval_steps_per_second": 0.141, "epoch": 1.85496183, "global_step/max_steps": "15/24", "percentage": "62.50%", "elapsed_time": "2h 28m 6s", "remaining_time": "1h 28m 51s"}