Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -559,3 +559,5 @@
|
|
| 559 |
{"step": 11180, "tokens": 5861539840, "loss": 2.809165191650391, "tokens_per_second": 985815.5093693133, "lr": 0.0015, "gradient_norm": 0.09285029768943787, "benchmark": false}
|
| 560 |
{"step": 11200, "tokens": 5872025600, "loss": 2.811720848083496, "tokens_per_second": 979650.1506031567, "lr": 0.0015, "gradient_norm": 0.11280045658349991, "benchmark": false}
|
| 561 |
{"step": 11220, "tokens": 5882511360, "loss": 2.781954765319824, "tokens_per_second": 981459.3504546183, "lr": 0.0015, "gradient_norm": 0.09573668986558914, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 559 |
{"step": 11180, "tokens": 5861539840, "loss": 2.809165191650391, "tokens_per_second": 985815.5093693133, "lr": 0.0015, "gradient_norm": 0.09285029768943787, "benchmark": false}
|
| 560 |
{"step": 11200, "tokens": 5872025600, "loss": 2.811720848083496, "tokens_per_second": 979650.1506031567, "lr": 0.0015, "gradient_norm": 0.11280045658349991, "benchmark": false}
|
| 561 |
{"step": 11220, "tokens": 5882511360, "loss": 2.781954765319824, "tokens_per_second": 981459.3504546183, "lr": 0.0015, "gradient_norm": 0.09573668986558914, "benchmark": false}
|
| 562 |
+
{"step": 11240, "tokens": 5892997120, "loss": 2.815509033203125, "tokens_per_second": 974762.4417187519, "lr": 0.0015, "gradient_norm": 0.09371116757392883, "benchmark": false}
|
| 563 |
+
{"step": 11260, "tokens": 5903482880, "loss": 2.839525032043457, "tokens_per_second": 981038.8163443952, "lr": 0.0015, "gradient_norm": 0.0912681445479393, "benchmark": false}
|