Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -665,3 +665,5 @@
|
|
| 665 |
{"step": 13300, "tokens": 6973030400, "loss": 2.776492881774902, "tokens_per_second": 991714.7701083526, "lr": 0.0015, "gradient_norm": 0.11090178042650223, "benchmark": false}
|
| 666 |
{"step": 13320, "tokens": 6983516160, "loss": 2.781183624267578, "tokens_per_second": 977445.8018478808, "lr": 0.0015, "gradient_norm": 0.11422978341579437, "benchmark": false}
|
| 667 |
{"step": 13340, "tokens": 6994001920, "loss": 2.77828369140625, "tokens_per_second": 984796.0072479807, "lr": 0.0015, "gradient_norm": 0.11428497731685638, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 665 |
{"step": 13300, "tokens": 6973030400, "loss": 2.776492881774902, "tokens_per_second": 991714.7701083526, "lr": 0.0015, "gradient_norm": 0.11090178042650223, "benchmark": false}
|
| 666 |
{"step": 13320, "tokens": 6983516160, "loss": 2.781183624267578, "tokens_per_second": 977445.8018478808, "lr": 0.0015, "gradient_norm": 0.11422978341579437, "benchmark": false}
|
| 667 |
{"step": 13340, "tokens": 6994001920, "loss": 2.77828369140625, "tokens_per_second": 984796.0072479807, "lr": 0.0015, "gradient_norm": 0.11428497731685638, "benchmark": false}
|
| 668 |
+
{"step": 13360, "tokens": 7004487680, "loss": 2.8044715881347657, "tokens_per_second": 987909.036007852, "lr": 0.0015, "gradient_norm": 0.1091688796877861, "benchmark": false}
|
| 669 |
+
{"step": 13380, "tokens": 7014973440, "loss": 2.8291257858276366, "tokens_per_second": 992076.2403446267, "lr": 0.0015, "gradient_norm": 0.10559467226266861, "benchmark": false}
|