Training in progress, step 110

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dde5603bdbdd49e8653f667e1d73c188659040e2f60ae7dd8f5e18a616c0bde
+oid sha256:003767a8422f0694431cc97e9ccaacad4575c669ef64e1da6fe46adcfa2a9d53
 size 3565203280

logging.jsonl

@@ -117,3 +117,8 @@
 {"loss": 0.59382796, "token_acc": 0.78, "grad_norm": 1.66870689, "learning_rate": 5.72e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.110805, "epoch": 0.05724987, "global_step/max_steps": "107/1869", "percentage": "5.72%", "elapsed_time": "15m 36s", "remaining_time": "4h 16m 55s"}
 {"loss": 0.49897149, "token_acc": 0.85014409, "grad_norm": 1.56035566, "learning_rate": 5.78e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.111209, "epoch": 0.05778491, "global_step/max_steps": "108/1869", "percentage": "5.78%", "elapsed_time": "15m 41s", "remaining_time": "4h 15m 53s"}
 {"loss": 0.5497005, "token_acc": 0.88143177, "grad_norm": 1.39917779, "learning_rate": 5.83e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.111584, "epoch": 0.05831996, "global_step/max_steps": "109/1869", "percentage": "5.83%", "elapsed_time": "15m 47s", "remaining_time": "4h 14m 56s"}
+{"loss": 0.55191898, "token_acc": 0.8778135, "grad_norm": 1.57978892, "learning_rate": 5.88e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.112422, "epoch": 0.058855, "global_step/max_steps": "110/1869", "percentage": "5.89%", "elapsed_time": "15m 48s", "remaining_time": "4h 12m 54s"}
+{"eval_loss": 0.55265617, "eval_token_acc": 0.81567564, "eval_runtime": 47.043, "eval_samples_per_second": 9.821, "eval_steps_per_second": 1.233, "epoch": 0.058855, "global_step/max_steps": "110/1869", "percentage": "5.89%", "elapsed_time": "16m 35s", "remaining_time": "4h 25m 26s"}
+{"loss": 0.51185912, "token_acc": 0.82028027, "grad_norm": 1.4405241, "learning_rate": 5.94e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.106683, "epoch": 0.05939005, "global_step/max_steps": "111/1869", "percentage": "5.94%", "elapsed_time": "16m 50s", "remaining_time": "4h 26m 51s"}
+{"loss": 0.52429932, "token_acc": 0.80310881, "grad_norm": 1.38541508, "learning_rate": 5.99e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.107074, "epoch": 0.05992509, "global_step/max_steps": "112/1869", "percentage": "5.99%", "elapsed_time": "16m 56s", "remaining_time": "4h 25m 46s"}
+{"loss": 0.52454728, "token_acc": 0.86216216, "grad_norm": 1.48425007, "learning_rate": 6.04e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.107862, "epoch": 0.06046014, "global_step/max_steps": "113/1869", "percentage": "6.05%", "elapsed_time": "16m 58s", "remaining_time": "4h 23m 41s"}