Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -56,3 +56,5 @@
|
|
| 56 |
{"step": 1120, "tokens": 587202560, "loss": 3.4398429870605467, "tokens_per_second": 850654.6348279766, "lr": 0.0008400000000000001, "gradient_norm": 0.3153975307941437, "benchmark": false}
|
| 57 |
{"step": 1140, "tokens": 597688320, "loss": 3.4438480377197265, "tokens_per_second": 980482.9249238867, "lr": 0.000855, "gradient_norm": 0.32889819145202637, "benchmark": false}
|
| 58 |
{"step": 1160, "tokens": 608174080, "loss": 3.4141963958740233, "tokens_per_second": 950779.5897118163, "lr": 0.00087, "gradient_norm": 0.31094542145729065, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 56 |
{"step": 1120, "tokens": 587202560, "loss": 3.4398429870605467, "tokens_per_second": 850654.6348279766, "lr": 0.0008400000000000001, "gradient_norm": 0.3153975307941437, "benchmark": false}
|
| 57 |
{"step": 1140, "tokens": 597688320, "loss": 3.4438480377197265, "tokens_per_second": 980482.9249238867, "lr": 0.000855, "gradient_norm": 0.32889819145202637, "benchmark": false}
|
| 58 |
{"step": 1160, "tokens": 608174080, "loss": 3.4141963958740233, "tokens_per_second": 950779.5897118163, "lr": 0.00087, "gradient_norm": 0.31094542145729065, "benchmark": false}
|
| 59 |
+
{"step": 1180, "tokens": 618659840, "loss": 3.4345771789550783, "tokens_per_second": 991621.5290955171, "lr": 0.0008849999999999999, "gradient_norm": 0.3323631286621094, "benchmark": false}
|
| 60 |
+
{"step": 1200, "tokens": 629145600, "loss": 3.3983821868896484, "tokens_per_second": 943885.1715741617, "lr": 0.0009, "gradient_norm": 0.3000882565975189, "benchmark": false}
|