Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -11,3 +11,5 @@
|
|
| 11 |
{"step": 220, "tokens": 115343360, "loss": 6.25281867980957, "tokens_per_second": 1011047.7764669958, "lr": 0.000165, "gradient_norm": 2.103592872619629, "benchmark": false}
|
| 12 |
{"step": 240, "tokens": 125829120, "loss": 6.059990692138672, "tokens_per_second": 1014516.1725319899, "lr": 0.00017999999999999998, "gradient_norm": 2.0833327770233154, "benchmark": false}
|
| 13 |
{"step": 260, "tokens": 136314880, "loss": 5.868567276000976, "tokens_per_second": 970291.6904213858, "lr": 0.00019500000000000002, "gradient_norm": 1.8735260963439941, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 11 |
{"step": 220, "tokens": 115343360, "loss": 6.25281867980957, "tokens_per_second": 1011047.7764669958, "lr": 0.000165, "gradient_norm": 2.103592872619629, "benchmark": false}
|
| 12 |
{"step": 240, "tokens": 125829120, "loss": 6.059990692138672, "tokens_per_second": 1014516.1725319899, "lr": 0.00017999999999999998, "gradient_norm": 2.0833327770233154, "benchmark": false}
|
| 13 |
{"step": 260, "tokens": 136314880, "loss": 5.868567276000976, "tokens_per_second": 970291.6904213858, "lr": 0.00019500000000000002, "gradient_norm": 1.8735260963439941, "benchmark": false}
|
| 14 |
+
{"step": 280, "tokens": 146800640, "loss": 5.708786392211914, "tokens_per_second": 1013524.8939050153, "lr": 0.00021000000000000004, "gradient_norm": 2.135854482650757, "benchmark": false}
|
| 15 |
+
{"step": 300, "tokens": 157286400, "loss": 5.5515869140625, "tokens_per_second": 1017056.3127177466, "lr": 0.000225, "gradient_norm": 2.5311148166656494, "benchmark": false}
|