Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -185,3 +185,5 @@
|
|
| 185 |
{"step": 3700, "tokens": 1939865600, "loss": 3.0230899810791017, "tokens_per_second": 978109.1165907453, "lr": 0.0015, "gradient_norm": 0.12378263473510742, "benchmark": false}
|
| 186 |
{"step": 3720, "tokens": 1950351360, "loss": 3.0241472244262697, "tokens_per_second": 977217.3536437268, "lr": 0.0015, "gradient_norm": 0.12801679968833923, "benchmark": false}
|
| 187 |
{"step": 3740, "tokens": 1960837120, "loss": 3.0166873931884766, "tokens_per_second": 971262.3224394342, "lr": 0.0015, "gradient_norm": 0.12122127413749695, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 185 |
{"step": 3700, "tokens": 1939865600, "loss": 3.0230899810791017, "tokens_per_second": 978109.1165907453, "lr": 0.0015, "gradient_norm": 0.12378263473510742, "benchmark": false}
|
| 186 |
{"step": 3720, "tokens": 1950351360, "loss": 3.0241472244262697, "tokens_per_second": 977217.3536437268, "lr": 0.0015, "gradient_norm": 0.12801679968833923, "benchmark": false}
|
| 187 |
{"step": 3740, "tokens": 1960837120, "loss": 3.0166873931884766, "tokens_per_second": 971262.3224394342, "lr": 0.0015, "gradient_norm": 0.12122127413749695, "benchmark": false}
|
| 188 |
+
{"step": 3760, "tokens": 1971322880, "loss": 3.0079349517822265, "tokens_per_second": 978814.4046884076, "lr": 0.0015, "gradient_norm": 0.10893643647432327, "benchmark": false}
|
| 189 |
+
{"step": 3780, "tokens": 1981808640, "loss": 2.9906312942504885, "tokens_per_second": 975213.4421708274, "lr": 0.0015, "gradient_norm": 0.1239536926150322, "benchmark": false}
|