Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618ddb5842b77a277ba2fb75499d245929924ad35e8899db3bc116e2707491d1
+oid sha256:bbb88cd2ad49a28dfd1cc411e4818df1e3111793a50f870549a2cf9e7bc00e62
 size 18516456

trainer_log.jsonl

@@ -178,3 +178,14 @@
 {"current_steps": 795, "total_steps": 3400, "loss": 0.8986, "lr": 9.104265246026415e-05, "epoch": 0.40947720834406387, "percentage": 23.38, "elapsed_time": "3:04:33", "remaining_time": "10:04:45", "throughput": 839.7, "total_tokens": 9298528}
 {"current_steps": 800, "total_steps": 3400, "loss": 0.8881, "lr": 9.090329093371666e-05, "epoch": 0.41205253669842906, "percentage": 23.53, "elapsed_time": "3:05:37", "remaining_time": "10:03:16", "throughput": 840.14, "total_tokens": 9357016}
 {"current_steps": 800, "total_steps": 3400, "eval_loss": 0.8973079919815063, "epoch": 0.41205253669842906, "percentage": 23.53, "elapsed_time": "3:05:53", "remaining_time": "10:04:09", "throughput": 838.92, "total_tokens": 9357016}
+{"current_steps": 805, "total_steps": 3400, "loss": 0.8798, "lr": 9.076296203830579e-05, "epoch": 0.41462786505279425, "percentage": 23.68, "elapsed_time": "3:07:02", "remaining_time": "10:02:55", "throughput": 839.0, "total_tokens": 9415480}
+{"current_steps": 810, "total_steps": 3400, "loss": 0.9104, "lr": 9.062166909283062e-05, "epoch": 0.4172031934071594, "percentage": 23.82, "elapsed_time": "3:08:05", "remaining_time": "10:01:26", "throughput": 839.45, "total_tokens": 9473928}
+{"current_steps": 815, "total_steps": 3400, "loss": 0.9007, "lr": 9.047941543889014e-05, "epoch": 0.4197785217615246, "percentage": 23.97, "elapsed_time": "3:09:09", "remaining_time": "9:59:58", "throughput": 839.88, "total_tokens": 9532408}
+{"current_steps": 820, "total_steps": 3400, "loss": 0.8974, "lr": 9.033620444080428e-05, "epoch": 0.4223538501158898, "percentage": 24.12, "elapsed_time": "3:10:13", "remaining_time": "9:58:30", "throughput": 840.31, "total_tokens": 9590920}
+{"current_steps": 825, "total_steps": 3400, "loss": 0.8992, "lr": 9.019203948553422e-05, "epoch": 0.42492917847025496, "percentage": 24.26, "elapsed_time": "3:11:17", "remaining_time": "9:57:02", "throughput": 840.75, "total_tokens": 9649400}
+{"current_steps": 830, "total_steps": 3400, "loss": 0.8991, "lr": 9.004692398260244e-05, "epoch": 0.42750450682462016, "percentage": 24.41, "elapsed_time": "3:12:20", "remaining_time": "9:55:35", "throughput": 841.17, "total_tokens": 9707888}
+{"current_steps": 835, "total_steps": 3400, "loss": 0.8964, "lr": 8.9900861364012e-05, "epoch": 0.43007983517898535, "percentage": 24.56, "elapsed_time": "3:13:24", "remaining_time": "9:54:07", "throughput": 841.59, "total_tokens": 9766384}
+{"current_steps": 840, "total_steps": 3400, "loss": 0.8723, "lr": 8.975385508416532e-05, "epoch": 0.4326551635333505, "percentage": 24.71, "elapsed_time": "3:14:28", "remaining_time": "9:52:41", "throughput": 841.99, "total_tokens": 9824896}
+{"current_steps": 845, "total_steps": 3400, "loss": 0.874, "lr": 8.960590861978265e-05, "epoch": 0.4352304918877157, "percentage": 24.85, "elapsed_time": "3:15:32", "remaining_time": "9:51:15", "throughput": 842.39, "total_tokens": 9883408}
+{"current_steps": 850, "total_steps": 3400, "loss": 0.9035, "lr": 8.945702546981969e-05, "epoch": 0.43780582024208087, "percentage": 25.0, "elapsed_time": "3:16:36", "remaining_time": "9:49:49", "throughput": 842.79, "total_tokens": 9941896}
+{"current_steps": 850, "total_steps": 3400, "eval_loss": 0.8779178261756897, "epoch": 0.43780582024208087, "percentage": 25.0, "elapsed_time": "3:16:52", "remaining_time": "9:50:37", "throughput": 841.64, "total_tokens": 9941896}