Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -1196,3 +1196,5 @@
|
|
| 1196 |
{"step": 23920, "tokens": 12540968960, "loss": 2.7601694107055663, "tokens_per_second": 975348.6145191451, "lr": 0.0015, "gradient_norm": 0.16925016045570374, "benchmark": false}
|
| 1197 |
{"step": 23940, "tokens": 12551454720, "loss": 2.691547393798828, "tokens_per_second": 975890.01228013, "lr": 0.0015, "gradient_norm": 0.15195700526237488, "benchmark": false}
|
| 1198 |
{"step": 23960, "tokens": 12561940480, "loss": 2.7447614669799805, "tokens_per_second": 997427.3005360373, "lr": 0.0015, "gradient_norm": 0.15338551998138428, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 1196 |
{"step": 23920, "tokens": 12540968960, "loss": 2.7601694107055663, "tokens_per_second": 975348.6145191451, "lr": 0.0015, "gradient_norm": 0.16925016045570374, "benchmark": false}
|
| 1197 |
{"step": 23940, "tokens": 12551454720, "loss": 2.691547393798828, "tokens_per_second": 975890.01228013, "lr": 0.0015, "gradient_norm": 0.15195700526237488, "benchmark": false}
|
| 1198 |
{"step": 23960, "tokens": 12561940480, "loss": 2.7447614669799805, "tokens_per_second": 997427.3005360373, "lr": 0.0015, "gradient_norm": 0.15338551998138428, "benchmark": false}
|
| 1199 |
+
{"step": 23980, "tokens": 12572426240, "loss": 2.7036411285400392, "tokens_per_second": 741396.487194083, "lr": 0.0015, "gradient_norm": 0.1688719540834427, "benchmark": false}
|
| 1200 |
+
{"step": 24000, "tokens": 12582912000, "loss": 2.718919372558594, "tokens_per_second": 982995.1583360904, "lr": 0.0015, "gradient_norm": 0.16046124696731567, "benchmark": false}
|