Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -835,3 +835,5 @@
|
|
| 835 |
{"step": 16700, "tokens": 8755609600, "loss": 2.7993846893310548, "tokens_per_second": 992658.8444407133, "lr": 0.0015, "gradient_norm": 0.12987804412841797, "benchmark": false}
|
| 836 |
{"step": 16720, "tokens": 8766095360, "loss": 2.7786354064941405, "tokens_per_second": 930222.1736913013, "lr": 0.0015, "gradient_norm": 0.13684336841106415, "benchmark": false}
|
| 837 |
{"step": 16740, "tokens": 8776581120, "loss": 2.769214630126953, "tokens_per_second": 975331.3139433127, "lr": 0.0015, "gradient_norm": 0.1365191489458084, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 835 |
{"step": 16700, "tokens": 8755609600, "loss": 2.7993846893310548, "tokens_per_second": 992658.8444407133, "lr": 0.0015, "gradient_norm": 0.12987804412841797, "benchmark": false}
|
| 836 |
{"step": 16720, "tokens": 8766095360, "loss": 2.7786354064941405, "tokens_per_second": 930222.1736913013, "lr": 0.0015, "gradient_norm": 0.13684336841106415, "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}
|