Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -236,3 +236,5 @@
|
|
| 236 |
{"step": 4720, "tokens": 2474639360, "loss": 2.962502670288086, "tokens_per_second": 972814.0600136536, "lr": 0.0015, "gradient_norm": 0.09654846042394638, "benchmark": false}
|
| 237 |
{"step": 4740, "tokens": 2485125120, "loss": 2.978459358215332, "tokens_per_second": 969742.2589327429, "lr": 0.0015, "gradient_norm": 0.09661349654197693, "benchmark": false}
|
| 238 |
{"step": 4760, "tokens": 2495610880, "loss": 2.9715957641601562, "tokens_per_second": 969051.8322886985, "lr": 0.0015, "gradient_norm": 0.09438515454530716, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 236 |
{"step": 4720, "tokens": 2474639360, "loss": 2.962502670288086, "tokens_per_second": 972814.0600136536, "lr": 0.0015, "gradient_norm": 0.09654846042394638, "benchmark": false}
|
| 237 |
{"step": 4740, "tokens": 2485125120, "loss": 2.978459358215332, "tokens_per_second": 969742.2589327429, "lr": 0.0015, "gradient_norm": 0.09661349654197693, "benchmark": false}
|
| 238 |
{"step": 4760, "tokens": 2495610880, "loss": 2.9715957641601562, "tokens_per_second": 969051.8322886985, "lr": 0.0015, "gradient_norm": 0.09438515454530716, "benchmark": false}
|
| 239 |
+
{"step": 4780, "tokens": 2506096640, "loss": 2.970972442626953, "tokens_per_second": 961760.1791516629, "lr": 0.0015, "gradient_norm": 0.07773580402135849, "benchmark": false}
|
| 240 |
+
{"step": 4800, "tokens": 2516582400, "loss": 2.9481992721557617, "tokens_per_second": 971270.9862248712, "lr": 0.0015, "gradient_norm": 0.11723429709672928, "benchmark": false}
|