Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -531,3 +531,5 @@
|
|
| 531 |
{"step": 10620, "tokens": 5567938560, "loss": 2.830562210083008, "tokens_per_second": 980664.4530554473, "lr": 0.0015, "gradient_norm": 0.08211514353752136, "benchmark": false}
|
| 532 |
{"step": 10640, "tokens": 5578424320, "loss": 2.814869689941406, "tokens_per_second": 985124.8025264748, "lr": 0.0015, "gradient_norm": 0.08745996654033661, "benchmark": false}
|
| 533 |
{"step": 10660, "tokens": 5588910080, "loss": 2.798888397216797, "tokens_per_second": 987502.2586735309, "lr": 0.0015, "gradient_norm": 0.09800267219543457, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 531 |
{"step": 10620, "tokens": 5567938560, "loss": 2.830562210083008, "tokens_per_second": 980664.4530554473, "lr": 0.0015, "gradient_norm": 0.08211514353752136, "benchmark": false}
|
| 532 |
{"step": 10640, "tokens": 5578424320, "loss": 2.814869689941406, "tokens_per_second": 985124.8025264748, "lr": 0.0015, "gradient_norm": 0.08745996654033661, "benchmark": false}
|
| 533 |
{"step": 10660, "tokens": 5588910080, "loss": 2.798888397216797, "tokens_per_second": 987502.2586735309, "lr": 0.0015, "gradient_norm": 0.09800267219543457, "benchmark": false}
|
| 534 |
+
{"step": 10680, "tokens": 5599395840, "loss": 2.848857116699219, "tokens_per_second": 983825.3047975254, "lr": 0.0015, "gradient_norm": 0.09263648092746735, "benchmark": false}
|
| 535 |
+
{"step": 10700, "tokens": 5609881600, "loss": 2.8285358428955076, "tokens_per_second": 987688.8515747183, "lr": 0.0015, "gradient_norm": 0.08248348534107208, "benchmark": false}
|