Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -133,3 +133,5 @@
|
|
| 133 |
{"step": 2660, "tokens": 1394606080, "loss": 3.1065670013427735, "tokens_per_second": 960148.7382511444, "lr": 0.0015, "gradient_norm": 0.3518049716949463, "benchmark": false}
|
| 134 |
{"step": 2680, "tokens": 1405091840, "loss": 3.0817359924316405, "tokens_per_second": 986287.0883485635, "lr": 0.0015, "gradient_norm": 0.23797304928302765, "benchmark": false}
|
| 135 |
{"step": 2700, "tokens": 1415577600, "loss": 3.105073928833008, "tokens_per_second": 979995.0214306681, "lr": 0.0015, "gradient_norm": 0.24327975511550903, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 133 |
{"step": 2660, "tokens": 1394606080, "loss": 3.1065670013427735, "tokens_per_second": 960148.7382511444, "lr": 0.0015, "gradient_norm": 0.3518049716949463, "benchmark": false}
|
| 134 |
{"step": 2680, "tokens": 1405091840, "loss": 3.0817359924316405, "tokens_per_second": 986287.0883485635, "lr": 0.0015, "gradient_norm": 0.23797304928302765, "benchmark": false}
|
| 135 |
{"step": 2700, "tokens": 1415577600, "loss": 3.105073928833008, "tokens_per_second": 979995.0214306681, "lr": 0.0015, "gradient_norm": 0.24327975511550903, "benchmark": false}
|
| 136 |
+
{"step": 2720, "tokens": 1426063360, "loss": 3.1123846054077147, "tokens_per_second": 994175.0496723149, "lr": 0.0015, "gradient_norm": 0.2370196431875229, "benchmark": false}
|
| 137 |
+
{"step": 2740, "tokens": 1436549120, "loss": 3.092816162109375, "tokens_per_second": 838924.7631111884, "lr": 0.0015, "gradient_norm": 0.2178315669298172, "benchmark": false}
|