Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -661,3 +661,5 @@
|
|
| 661 |
{"step": 13220, "tokens": 6931087360, "loss": 2.770762634277344, "tokens_per_second": 984348.7338467747, "lr": 0.0015, "gradient_norm": 0.10894811153411865, "benchmark": false}
|
| 662 |
{"step": 13240, "tokens": 6941573120, "loss": 2.791122627258301, "tokens_per_second": 817360.9508909244, "lr": 0.0015, "gradient_norm": 0.11274447292089462, "benchmark": false}
|
| 663 |
{"step": 13260, "tokens": 6952058880, "loss": 2.791507911682129, "tokens_per_second": 814423.3989380366, "lr": 0.0015, "gradient_norm": 0.1253562569618225, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 661 |
{"step": 13220, "tokens": 6931087360, "loss": 2.770762634277344, "tokens_per_second": 984348.7338467747, "lr": 0.0015, "gradient_norm": 0.10894811153411865, "benchmark": false}
|
| 662 |
{"step": 13240, "tokens": 6941573120, "loss": 2.791122627258301, "tokens_per_second": 817360.9508909244, "lr": 0.0015, "gradient_norm": 0.11274447292089462, "benchmark": false}
|
| 663 |
{"step": 13260, "tokens": 6952058880, "loss": 2.791507911682129, "tokens_per_second": 814423.3989380366, "lr": 0.0015, "gradient_norm": 0.1253562569618225, "benchmark": false}
|
| 664 |
+
{"step": 13280, "tokens": 6962544640, "loss": 2.787698173522949, "tokens_per_second": 993533.085928695, "lr": 0.0015, "gradient_norm": 0.10525481402873993, "benchmark": false}
|
| 665 |
+
{"step": 13300, "tokens": 6973030400, "loss": 2.776492881774902, "tokens_per_second": 991714.7701083526, "lr": 0.0015, "gradient_norm": 0.11090178042650223, "benchmark": false}
|