Training in progress, step 24

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e767a2aa978c9100da0250167dfecd8f04a1fd8d5bdeb7313dc6d3ba41666c0
+oid sha256:5ef18e7f7d2f69dd0ae4a583d263a84aa237a7fd1bb2e073284b47221c681376
 size 1656903768

logging.jsonl

@@ -16,3 +16,9 @@
 {"loss": 19.1674099, "token_acc": 0.81255735, "grad_norm": 0.07065283, "learning_rate": 1.221e-05, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001627, "epoch": 2.24427481, "global_step/max_steps": "19/24", "percentage": "79.17%", "elapsed_time": "3h 14m 26s", "remaining_time": "51m 10s"}
 {"loss": 18.75621605, "token_acc": 0.83829445, "grad_norm": 0.07214139, "learning_rate": 7.94e-06, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001595, "epoch": 2.36641221, "global_step/max_steps": "20/24", "percentage": "83.33%", "elapsed_time": "3h 28m 43s", "remaining_time": "41m 44s"}
 {"eval_loss": 0.59709889, "eval_token_acc": 0.82612473, "eval_runtime": 21.3202, "eval_samples_per_second": 0.985, "eval_steps_per_second": 0.141, "epoch": 2.36641221, "global_step/max_steps": "20/24", "percentage": "83.33%", "elapsed_time": "3h 29m 4s", "remaining_time": "41m 48s"}
+{"loss": 18.29937744, "token_acc": 0.82519542, "grad_norm": 0.06567915, "learning_rate": 4.52e-06, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001567, "epoch": 2.48854962, "global_step/max_steps": "21/24", "percentage": "87.50%", "elapsed_time": "3h 43m 9s", "remaining_time": "31m 52s"}
+{"loss": 18.23294449, "token_acc": 0.83060083, "grad_norm": 0.06983872, "learning_rate": 2.03e-06, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.00154, "epoch": 2.61068702, "global_step/max_steps": "22/24", "percentage": "91.67%", "elapsed_time": "3h 57m 52s", "remaining_time": "21m 37s"}
+{"loss": 18.95943832, "token_acc": 0.82205675, "grad_norm": 0.07328164, "learning_rate": 5.1e-07, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001518, "epoch": 2.73282443, "global_step/max_steps": "23/24", "percentage": "95.83%", "elapsed_time": "4h 12m 18s", "remaining_time": "10m 58s"}
+{"loss": 19.01360703, "token_acc": 0.82943965, "grad_norm": 0.08025298, "learning_rate": 0.0, "memory(GiB)": 96.08, "train_speed(iter/s)": 0.001501, "epoch": 2.85496183, "global_step/max_steps": "24/24", "percentage": "100.00%", "elapsed_time": "4h 26m 17s", "remaining_time": "0s"}
+{"eval_loss": 0.59335285, "eval_token_acc": 0.8263136, "eval_runtime": 21.3278, "eval_samples_per_second": 0.985, "eval_steps_per_second": 0.141, "epoch": 2.85496183, "global_step/max_steps": "24/24", "percentage": "100.00%", "elapsed_time": "4h 26m 38s", "remaining_time": "0s"}
+{"train_runtime": 16013.4271, "train_samples_per_second": 0.392, "train_steps_per_second": 0.001, "total_flos": 5980870452183040.0, "train_loss": 15.74809513, "epoch": 2.85496183, "global_step/max_steps": "24/24", "percentage": "100.00%", "elapsed_time": "4h 26m 49s", "remaining_time": "0s"}