Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -837,3 +837,5 @@
|
|
| 837 |
{"step": 16740, "tokens": 8776581120, "loss": 2.769214630126953, "tokens_per_second": 975331.3139433127, "lr": 0.0015, "gradient_norm": 0.1365191489458084, "benchmark": false}
|
| 838 |
{"step": 16760, "tokens": 8787066880, "loss": 2.735025405883789, "tokens_per_second": 987606.3200698326, "lr": 0.0015, "gradient_norm": 0.12653587758541107, "benchmark": false}
|
| 839 |
{"step": 16780, "tokens": 8797552640, "loss": 2.7759571075439453, "tokens_per_second": 977447.2956762247, "lr": 0.0015, "gradient_norm": 0.1501408964395523, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 837 |
{"step": 16740, "tokens": 8776581120, "loss": 2.769214630126953, "tokens_per_second": 975331.3139433127, "lr": 0.0015, "gradient_norm": 0.1365191489458084, "benchmark": false}
|
| 838 |
{"step": 16760, "tokens": 8787066880, "loss": 2.735025405883789, "tokens_per_second": 987606.3200698326, "lr": 0.0015, "gradient_norm": 0.12653587758541107, "benchmark": false}
|
| 839 |
{"step": 16780, "tokens": 8797552640, "loss": 2.7759571075439453, "tokens_per_second": 977447.2956762247, "lr": 0.0015, "gradient_norm": 0.1501408964395523, "benchmark": false}
|
| 840 |
+
{"step": 16800, "tokens": 8808038400, "loss": 2.755018424987793, "tokens_per_second": 981215.6592058687, "lr": 0.0015, "gradient_norm": 0.14391691982746124, "benchmark": false}
|
| 841 |
+
{"step": 16820, "tokens": 8818524160, "loss": 2.788979148864746, "tokens_per_second": 983531.0711602477, "lr": 0.0015, "gradient_norm": 0.14247770607471466, "benchmark": false}
|