Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6287ca2ed8e9ca31735e5d987ece6f9b430689719f525a3a04c74ff709108ab
+oid sha256:6e045152a73f87855427fb379b7010340bcb5b7bc986cabfaa3a74bd91d905f7
 size 29034840

trainer_log.jsonl

@@ -174,3 +174,14 @@
 {"current_steps": 795, "total_steps": 3400, "loss": 0.0022, "lr": 9.104265246026415e-05, "epoch": 0.40947720834406387, "percentage": 23.38, "elapsed_time": "3:56:04", "remaining_time": "12:53:34", "throughput": 560.35, "total_tokens": 7937280}
 {"current_steps": 800, "total_steps": 3400, "loss": 0.0065, "lr": 9.090329093371666e-05, "epoch": 0.41205253669842906, "percentage": 23.53, "elapsed_time": "3:57:31", "remaining_time": "12:51:57", "throughput": 560.44, "total_tokens": 7987200}
 {"current_steps": 800, "total_steps": 3400, "eval_loss": 0.006797688081860542, "epoch": 0.41205253669842906, "percentage": 23.53, "elapsed_time": "3:57:50", "remaining_time": "12:53:00", "throughput": 559.68, "total_tokens": 7987200}
+{"current_steps": 805, "total_steps": 3400, "loss": 0.0025, "lr": 9.076296203830579e-05, "epoch": 0.41462786505279425, "percentage": 23.68, "elapsed_time": "3:59:22", "remaining_time": "12:51:39", "throughput": 559.58, "total_tokens": 8037120}
+{"current_steps": 810, "total_steps": 3400, "loss": 0.0338, "lr": 9.062166909283062e-05, "epoch": 0.4172031934071594, "percentage": 23.82, "elapsed_time": "4:00:49", "remaining_time": "12:50:02", "throughput": 559.68, "total_tokens": 8087040}
+{"current_steps": 815, "total_steps": 3400, "loss": 0.0505, "lr": 9.047941543889014e-05, "epoch": 0.4197785217615246, "percentage": 23.97, "elapsed_time": "4:02:15", "remaining_time": "12:48:23", "throughput": 559.8, "total_tokens": 8136960}
+{"current_steps": 820, "total_steps": 3400, "loss": 0.0335, "lr": 9.033620444080428e-05, "epoch": 0.4223538501158898, "percentage": 24.12, "elapsed_time": "4:03:41", "remaining_time": "12:46:44", "throughput": 559.91, "total_tokens": 8186880}
+{"current_steps": 825, "total_steps": 3400, "loss": 0.0196, "lr": 9.019203948553422e-05, "epoch": 0.42492917847025496, "percentage": 24.26, "elapsed_time": "4:05:07", "remaining_time": "12:45:05", "throughput": 560.04, "total_tokens": 8236800}
+{"current_steps": 830, "total_steps": 3400, "loss": 0.018, "lr": 9.004692398260244e-05, "epoch": 0.42750450682462016, "percentage": 24.41, "elapsed_time": "4:06:34", "remaining_time": "12:43:28", "throughput": 560.13, "total_tokens": 8286720}
+{"current_steps": 835, "total_steps": 3400, "loss": 0.012, "lr": 8.9900861364012e-05, "epoch": 0.43007983517898535, "percentage": 24.56, "elapsed_time": "4:08:00", "remaining_time": "12:41:49", "throughput": 560.26, "total_tokens": 8336640}
+{"current_steps": 840, "total_steps": 3400, "loss": 0.0062, "lr": 8.975385508416532e-05, "epoch": 0.4326551635333505, "percentage": 24.71, "elapsed_time": "4:09:26", "remaining_time": "12:40:12", "throughput": 560.35, "total_tokens": 8386560}
+{"current_steps": 845, "total_steps": 3400, "loss": 0.0232, "lr": 8.960590861978265e-05, "epoch": 0.4352304918877157, "percentage": 24.85, "elapsed_time": "4:10:52", "remaining_time": "12:38:33", "throughput": 560.48, "total_tokens": 8436480}
+{"current_steps": 850, "total_steps": 3400, "loss": 0.0306, "lr": 8.945702546981969e-05, "epoch": 0.43780582024208087, "percentage": 25.0, "elapsed_time": "4:12:18", "remaining_time": "12:36:54", "throughput": 560.6, "total_tokens": 8486400}
+{"current_steps": 850, "total_steps": 3400, "eval_loss": 0.007198736071586609, "epoch": 0.43780582024208087, "percentage": 25.0, "elapsed_time": "4:12:37", "remaining_time": "12:37:53", "throughput": 559.87, "total_tokens": 8486400}