Training in progress, step 3400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8815c16681432a11b5ac188380ad3a07078a835a470d216013977c67742fdcc
+oid sha256:2e3dd7488301b3ff8268dcffb6f575eefe718b69eb21c58090d96141890a4fd7
 size 18516456

trainer_log.jsonl

@@ -739,3 +739,15 @@
 {"current_steps": 3345, "total_steps": 3400, "loss": 0.3147, "lr": 7.152477799867719e-08, "epoch": 1.7226371362348698, "percentage": 98.38, "elapsed_time": "12:23:05", "remaining_time": "0:12:13", "throughput": 877.35, "total_tokens": 39117416}
 {"current_steps": 3350, "total_steps": 3400, "loss": 0.2674, "lr": 5.911383342556143e-08, "epoch": 1.725212464589235, "percentage": 98.53, "elapsed_time": "12:24:10", "remaining_time": "0:11:06", "throughput": 877.38, "total_tokens": 39175888}
 {"current_steps": 3350, "total_steps": 3400, "eval_loss": 0.8666485548019409, "epoch": 1.725212464589235, "percentage": 98.53, "elapsed_time": "12:24:26", "remaining_time": "0:11:06", "throughput": 877.07, "total_tokens": 39175888}
+{"current_steps": 3355, "total_steps": 3400, "loss": 0.2565, "lr": 4.788399817602929e-08, "epoch": 1.7277877929436003, "percentage": 98.68, "elapsed_time": "12:25:36", "remaining_time": "0:10:00", "throughput": 877.01, "total_tokens": 39234336}
+{"current_steps": 3360, "total_steps": 3400, "loss": 0.2762, "lr": 3.7835537837338506e-08, "epoch": 1.7303631212979655, "percentage": 98.82, "elapsed_time": "12:26:41", "remaining_time": "0:08:53", "throughput": 877.04, "total_tokens": 39292800}
+{"current_steps": 3365, "total_steps": 3400, "loss": 0.2196, "lr": 2.8968690057051828e-08, "epoch": 1.7329384496523308, "percentage": 98.97, "elapsed_time": "12:27:48", "remaining_time": "0:07:46", "throughput": 877.03, "total_tokens": 39351272}
+{"current_steps": 3370, "total_steps": 3400, "loss": 0.2482, "lr": 2.128366453743591e-08, "epoch": 1.7355137780066958, "percentage": 99.12, "elapsed_time": "12:28:53", "remaining_time": "0:06:40", "throughput": 877.07, "total_tokens": 39409736}
+{"current_steps": 3375, "total_steps": 3400, "loss": 0.2778, "lr": 1.4780643030476438e-08, "epoch": 1.738089106361061, "percentage": 99.26, "elapsed_time": "12:29:58", "remaining_time": "0:05:33", "throughput": 877.1, "total_tokens": 39468176}
+{"current_steps": 3380, "total_steps": 3400, "loss": 0.2048, "lr": 9.459779333587104e-09, "epoch": 1.740664434715426, "percentage": 99.41, "elapsed_time": "12:31:01", "remaining_time": "0:04:26", "throughput": 877.17, "total_tokens": 39526688}
+{"current_steps": 3385, "total_steps": 3400, "loss": 0.2296, "lr": 5.3211992859791835e-09, "epoch": 1.7432397630697913, "percentage": 99.56, "elapsed_time": "12:32:05", "remaining_time": "0:03:19", "throughput": 877.23, "total_tokens": 39585152}
+{"current_steps": 3390, "total_steps": 3400, "loss": 0.2713, "lr": 2.3650007656805806e-09, "epoch": 1.7458150914241566, "percentage": 99.71, "elapsed_time": "12:33:08", "remaining_time": "0:02:13", "throughput": 877.29, "total_tokens": 39643640}
+{"current_steps": 3395, "total_steps": 3400, "loss": 0.2964, "lr": 5.912536872321184e-10, "epoch": 1.7483904197785218, "percentage": 99.85, "elapsed_time": "12:34:12", "remaining_time": "0:01:06", "throughput": 877.35, "total_tokens": 39702144}
+{"current_steps": 3400, "total_steps": 3400, "loss": 0.1797, "lr": 0.0, "epoch": 1.750965748132887, "percentage": 100.0, "elapsed_time": "12:35:16", "remaining_time": "0:00:00", "throughput": 877.4, "total_tokens": 39760664}
+{"current_steps": 3400, "total_steps": 3400, "eval_loss": 0.8603056073188782, "epoch": 1.750965748132887, "percentage": 100.0, "elapsed_time": "12:35:32", "remaining_time": "0:00:00", "throughput": 877.09, "total_tokens": 39760664}
+{"current_steps": 3400, "total_steps": 3400, "epoch": 1.750965748132887, "percentage": 100.0, "elapsed_time": "12:35:37", "remaining_time": "0:00:00", "throughput": 877.0, "total_tokens": 39760664}