Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -659,3 +659,5 @@
|
|
| 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}
|
|
|
|
|
|
|
|
|
| 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}
|
| 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}
|