Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -657,3 +657,5 @@
|
|
| 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}
|
|
|
|
|
|
|
|
|
| 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}
|
| 660 |
+
{"step": 13200, "tokens": 6920601600, "loss": 2.7888532638549806, "tokens_per_second": 834428.6390277194, "lr": 0.0015, "gradient_norm": 0.10792775452136993, "benchmark": false}
|
| 661 |
+
{"step": 13220, "tokens": 6931087360, "loss": 2.770762634277344, "tokens_per_second": 984348.7338467747, "lr": 0.0015, "gradient_norm": 0.10894811153411865, "benchmark": false}
|