Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -328,3 +328,5 @@
|
|
| 328 |
{"step": 6560, "tokens": 3439329280, "loss": 2.8744361877441404, "tokens_per_second": 811605.0280486693, "lr": 0.0015, "gradient_norm": 0.0776929259300232, "benchmark": false}
|
| 329 |
{"step": 6580, "tokens": 3449815040, "loss": 2.8729530334472657, "tokens_per_second": 988722.7496293134, "lr": 0.0015, "gradient_norm": 0.07295847684144974, "benchmark": false}
|
| 330 |
{"step": 6600, "tokens": 3460300800, "loss": 2.87994327545166, "tokens_per_second": 985837.3399777771, "lr": 0.0015, "gradient_norm": 0.08181548863649368, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 328 |
{"step": 6560, "tokens": 3439329280, "loss": 2.8744361877441404, "tokens_per_second": 811605.0280486693, "lr": 0.0015, "gradient_norm": 0.0776929259300232, "benchmark": false}
|
| 329 |
{"step": 6580, "tokens": 3449815040, "loss": 2.8729530334472657, "tokens_per_second": 988722.7496293134, "lr": 0.0015, "gradient_norm": 0.07295847684144974, "benchmark": false}
|
| 330 |
{"step": 6600, "tokens": 3460300800, "loss": 2.87994327545166, "tokens_per_second": 985837.3399777771, "lr": 0.0015, "gradient_norm": 0.08181548863649368, "benchmark": false}
|
| 331 |
+
{"step": 6620, "tokens": 3470786560, "loss": 2.9264673233032226, "tokens_per_second": 938610.7678174136, "lr": 0.0015, "gradient_norm": 0.07315581291913986, "benchmark": false}
|
| 332 |
+
{"step": 6640, "tokens": 3481272320, "loss": 2.88464298248291, "tokens_per_second": 968048.0186126189, "lr": 0.0015, "gradient_norm": 0.07335823774337769, "benchmark": false}
|