Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -655,3 +655,5 @@
|
|
| 655 |
{"step": 13100, "tokens": 6868172800, "loss": 2.800714683532715, "tokens_per_second": 980305.0475917425, "lr": 0.0015, "gradient_norm": 0.12226828932762146, "benchmark": false}
|
| 656 |
{"step": 13120, "tokens": 6878658560, "loss": 2.8094324111938476, "tokens_per_second": 971826.2870966541, "lr": 0.0015, "gradient_norm": 0.1026187464594841, "benchmark": false}
|
| 657 |
{"step": 13140, "tokens": 6889144320, "loss": 2.798151969909668, "tokens_per_second": 971155.9418639137, "lr": 0.0015, "gradient_norm": 0.11680211126804352, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 655 |
{"step": 13100, "tokens": 6868172800, "loss": 2.800714683532715, "tokens_per_second": 980305.0475917425, "lr": 0.0015, "gradient_norm": 0.12226828932762146, "benchmark": false}
|
| 656 |
{"step": 13120, "tokens": 6878658560, "loss": 2.8094324111938476, "tokens_per_second": 971826.2870966541, "lr": 0.0015, "gradient_norm": 0.1026187464594841, "benchmark": false}
|
| 657 |
{"step": 13140, "tokens": 6889144320, "loss": 2.798151969909668, "tokens_per_second": 971155.9418639137, "lr": 0.0015, "gradient_norm": 0.11680211126804352, "benchmark": false}
|
| 658 |
+
{"step": 13160, "tokens": 6899630080, "loss": 2.8011507034301757, "tokens_per_second": 976161.7806016527, "lr": 0.0015, "gradient_norm": 0.11606810986995697, "benchmark": false}
|
| 659 |
+
{"step": 13180, "tokens": 6910115840, "loss": 2.7625892639160154, "tokens_per_second": 998782.8826195722, "lr": 0.0015, "gradient_norm": 0.1080118715763092, "benchmark": false}
|