Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -129,3 +129,5 @@
|
|
| 129 |
{"step": 2580, "tokens": 1352663040, "loss": 3.124241065979004, "tokens_per_second": 930455.2500459759, "lr": 0.0015, "gradient_norm": 0.24497447907924652, "benchmark": false}
|
| 130 |
{"step": 2600, "tokens": 1363148800, "loss": 3.1559934616088867, "tokens_per_second": 989359.9285415264, "lr": 0.0015, "gradient_norm": 0.2681301236152649, "benchmark": false}
|
| 131 |
{"step": 2620, "tokens": 1373634560, "loss": 3.120655632019043, "tokens_per_second": 988014.3404262743, "lr": 0.0015, "gradient_norm": 0.22039465606212616, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 129 |
{"step": 2580, "tokens": 1352663040, "loss": 3.124241065979004, "tokens_per_second": 930455.2500459759, "lr": 0.0015, "gradient_norm": 0.24497447907924652, "benchmark": false}
|
| 130 |
{"step": 2600, "tokens": 1363148800, "loss": 3.1559934616088867, "tokens_per_second": 989359.9285415264, "lr": 0.0015, "gradient_norm": 0.2681301236152649, "benchmark": false}
|
| 131 |
{"step": 2620, "tokens": 1373634560, "loss": 3.120655632019043, "tokens_per_second": 988014.3404262743, "lr": 0.0015, "gradient_norm": 0.22039465606212616, "benchmark": false}
|
| 132 |
+
{"step": 2640, "tokens": 1384120320, "loss": 3.119555854797363, "tokens_per_second": 989281.896508611, "lr": 0.0015, "gradient_norm": 0.22109156847000122, "benchmark": false}
|
| 133 |
+
{"step": 2660, "tokens": 1394606080, "loss": 3.1065670013427735, "tokens_per_second": 960148.7382511444, "lr": 0.0015, "gradient_norm": 0.3518049716949463, "benchmark": false}
|