Upload Qwen2.5-Coder-1.5B-LoRA-Deep_training_logs.json
Browse files
Qwen2.5-Coder-1.5B-LoRA-Deep_training_logs.json
ADDED
|
@@ -0,0 +1,1168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss":1.2008,
|
| 4 |
+
"grad_norm":0.3822754323,
|
| 5 |
+
"learning_rate":0.0001407407,
|
| 6 |
+
"entropy":1.0346003115,
|
| 7 |
+
"num_tokens":322124.0,
|
| 8 |
+
"mean_token_accuracy":0.7109046429,
|
| 9 |
+
"epoch":0.0673400673,
|
| 10 |
+
"step":20,
|
| 11 |
+
"eval_loss":null,
|
| 12 |
+
"eval_runtime":null,
|
| 13 |
+
"eval_samples_per_second":null,
|
| 14 |
+
"eval_steps_per_second":null,
|
| 15 |
+
"eval_entropy":null,
|
| 16 |
+
"eval_num_tokens":null,
|
| 17 |
+
"eval_mean_token_accuracy":null,
|
| 18 |
+
"train_runtime":null,
|
| 19 |
+
"train_samples_per_second":null,
|
| 20 |
+
"train_steps_per_second":null,
|
| 21 |
+
"total_flos":null,
|
| 22 |
+
"train_loss":null
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"loss":0.9385,
|
| 26 |
+
"grad_norm":0.2103841156,
|
| 27 |
+
"learning_rate":0.0001999048,
|
| 28 |
+
"entropy":0.9494877957,
|
| 29 |
+
"num_tokens":642995.0,
|
| 30 |
+
"mean_token_accuracy":0.7539383888,
|
| 31 |
+
"epoch":0.1346801347,
|
| 32 |
+
"step":40,
|
| 33 |
+
"eval_loss":null,
|
| 34 |
+
"eval_runtime":null,
|
| 35 |
+
"eval_samples_per_second":null,
|
| 36 |
+
"eval_steps_per_second":null,
|
| 37 |
+
"eval_entropy":null,
|
| 38 |
+
"eval_num_tokens":null,
|
| 39 |
+
"eval_mean_token_accuracy":null,
|
| 40 |
+
"train_runtime":null,
|
| 41 |
+
"train_samples_per_second":null,
|
| 42 |
+
"train_steps_per_second":null,
|
| 43 |
+
"total_flos":null,
|
| 44 |
+
"train_loss":null
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"loss":0.915,
|
| 48 |
+
"grad_norm":0.206428811,
|
| 49 |
+
"learning_rate":0.0001993238,
|
| 50 |
+
"entropy":0.9191693425,
|
| 51 |
+
"num_tokens":966396.0,
|
| 52 |
+
"mean_token_accuracy":0.7584572025,
|
| 53 |
+
"epoch":0.202020202,
|
| 54 |
+
"step":60,
|
| 55 |
+
"eval_loss":null,
|
| 56 |
+
"eval_runtime":null,
|
| 57 |
+
"eval_samples_per_second":null,
|
| 58 |
+
"eval_steps_per_second":null,
|
| 59 |
+
"eval_entropy":null,
|
| 60 |
+
"eval_num_tokens":null,
|
| 61 |
+
"eval_mean_token_accuracy":null,
|
| 62 |
+
"train_runtime":null,
|
| 63 |
+
"train_samples_per_second":null,
|
| 64 |
+
"train_steps_per_second":null,
|
| 65 |
+
"total_flos":null,
|
| 66 |
+
"train_loss":null
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"loss":0.8441,
|
| 70 |
+
"grad_norm":0.3027354181,
|
| 71 |
+
"learning_rate":0.0001982178,
|
| 72 |
+
"entropy":0.8431956261,
|
| 73 |
+
"num_tokens":1287058.0,
|
| 74 |
+
"mean_token_accuracy":0.7713396206,
|
| 75 |
+
"epoch":0.2693602694,
|
| 76 |
+
"step":80,
|
| 77 |
+
"eval_loss":null,
|
| 78 |
+
"eval_runtime":null,
|
| 79 |
+
"eval_samples_per_second":null,
|
| 80 |
+
"eval_steps_per_second":null,
|
| 81 |
+
"eval_entropy":null,
|
| 82 |
+
"eval_num_tokens":null,
|
| 83 |
+
"eval_mean_token_accuracy":null,
|
| 84 |
+
"train_runtime":null,
|
| 85 |
+
"train_samples_per_second":null,
|
| 86 |
+
"train_steps_per_second":null,
|
| 87 |
+
"total_flos":null,
|
| 88 |
+
"train_loss":null
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"loss":0.8408,
|
| 92 |
+
"grad_norm":0.2982031703,
|
| 93 |
+
"learning_rate":0.0001965926,
|
| 94 |
+
"entropy":0.8472392239,
|
| 95 |
+
"num_tokens":1607723.0,
|
| 96 |
+
"mean_token_accuracy":0.7738652974,
|
| 97 |
+
"epoch":0.3367003367,
|
| 98 |
+
"step":100,
|
| 99 |
+
"eval_loss":null,
|
| 100 |
+
"eval_runtime":null,
|
| 101 |
+
"eval_samples_per_second":null,
|
| 102 |
+
"eval_steps_per_second":null,
|
| 103 |
+
"eval_entropy":null,
|
| 104 |
+
"eval_num_tokens":null,
|
| 105 |
+
"eval_mean_token_accuracy":null,
|
| 106 |
+
"train_runtime":null,
|
| 107 |
+
"train_samples_per_second":null,
|
| 108 |
+
"train_steps_per_second":null,
|
| 109 |
+
"total_flos":null,
|
| 110 |
+
"train_loss":null
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"loss":null,
|
| 114 |
+
"grad_norm":null,
|
| 115 |
+
"learning_rate":null,
|
| 116 |
+
"entropy":null,
|
| 117 |
+
"num_tokens":null,
|
| 118 |
+
"mean_token_accuracy":null,
|
| 119 |
+
"epoch":0.3367003367,
|
| 120 |
+
"step":100,
|
| 121 |
+
"eval_loss":0.8332510591,
|
| 122 |
+
"eval_runtime":10.3382,
|
| 123 |
+
"eval_samples_per_second":24.182,
|
| 124 |
+
"eval_steps_per_second":3.095,
|
| 125 |
+
"eval_entropy":0.8475092333,
|
| 126 |
+
"eval_num_tokens":1607723.0,
|
| 127 |
+
"eval_mean_token_accuracy":0.7752955835,
|
| 128 |
+
"train_runtime":null,
|
| 129 |
+
"train_samples_per_second":null,
|
| 130 |
+
"train_steps_per_second":null,
|
| 131 |
+
"total_flos":null,
|
| 132 |
+
"train_loss":null
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"loss":0.8262,
|
| 136 |
+
"grad_norm":0.2738818824,
|
| 137 |
+
"learning_rate":0.0001944568,
|
| 138 |
+
"entropy":0.8286631659,
|
| 139 |
+
"num_tokens":1928620.0,
|
| 140 |
+
"mean_token_accuracy":0.7755305201,
|
| 141 |
+
"epoch":0.404040404,
|
| 142 |
+
"step":120,
|
| 143 |
+
"eval_loss":null,
|
| 144 |
+
"eval_runtime":null,
|
| 145 |
+
"eval_samples_per_second":null,
|
| 146 |
+
"eval_steps_per_second":null,
|
| 147 |
+
"eval_entropy":null,
|
| 148 |
+
"eval_num_tokens":null,
|
| 149 |
+
"eval_mean_token_accuracy":null,
|
| 150 |
+
"train_runtime":null,
|
| 151 |
+
"train_samples_per_second":null,
|
| 152 |
+
"train_steps_per_second":null,
|
| 153 |
+
"total_flos":null,
|
| 154 |
+
"train_loss":null
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"loss":0.8089,
|
| 158 |
+
"grad_norm":0.2727711201,
|
| 159 |
+
"learning_rate":0.0001918216,
|
| 160 |
+
"entropy":0.8132541452,
|
| 161 |
+
"num_tokens":2249401.0,
|
| 162 |
+
"mean_token_accuracy":0.779610493,
|
| 163 |
+
"epoch":0.4713804714,
|
| 164 |
+
"step":140,
|
| 165 |
+
"eval_loss":null,
|
| 166 |
+
"eval_runtime":null,
|
| 167 |
+
"eval_samples_per_second":null,
|
| 168 |
+
"eval_steps_per_second":null,
|
| 169 |
+
"eval_entropy":null,
|
| 170 |
+
"eval_num_tokens":null,
|
| 171 |
+
"eval_mean_token_accuracy":null,
|
| 172 |
+
"train_runtime":null,
|
| 173 |
+
"train_samples_per_second":null,
|
| 174 |
+
"train_steps_per_second":null,
|
| 175 |
+
"total_flos":null,
|
| 176 |
+
"train_loss":null
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"loss":0.7815,
|
| 180 |
+
"grad_norm":0.253259182,
|
| 181 |
+
"learning_rate":0.0001887011,
|
| 182 |
+
"entropy":0.7838059939,
|
| 183 |
+
"num_tokens":2571041.0,
|
| 184 |
+
"mean_token_accuracy":0.785765557,
|
| 185 |
+
"epoch":0.5387205387,
|
| 186 |
+
"step":160,
|
| 187 |
+
"eval_loss":null,
|
| 188 |
+
"eval_runtime":null,
|
| 189 |
+
"eval_samples_per_second":null,
|
| 190 |
+
"eval_steps_per_second":null,
|
| 191 |
+
"eval_entropy":null,
|
| 192 |
+
"eval_num_tokens":null,
|
| 193 |
+
"eval_mean_token_accuracy":null,
|
| 194 |
+
"train_runtime":null,
|
| 195 |
+
"train_samples_per_second":null,
|
| 196 |
+
"train_steps_per_second":null,
|
| 197 |
+
"total_flos":null,
|
| 198 |
+
"train_loss":null
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"loss":0.763,
|
| 202 |
+
"grad_norm":0.2851669788,
|
| 203 |
+
"learning_rate":0.0001851117,
|
| 204 |
+
"entropy":0.7674662221,
|
| 205 |
+
"num_tokens":2890814.0,
|
| 206 |
+
"mean_token_accuracy":0.7893050611,
|
| 207 |
+
"epoch":0.6060606061,
|
| 208 |
+
"step":180,
|
| 209 |
+
"eval_loss":null,
|
| 210 |
+
"eval_runtime":null,
|
| 211 |
+
"eval_samples_per_second":null,
|
| 212 |
+
"eval_steps_per_second":null,
|
| 213 |
+
"eval_entropy":null,
|
| 214 |
+
"eval_num_tokens":null,
|
| 215 |
+
"eval_mean_token_accuracy":null,
|
| 216 |
+
"train_runtime":null,
|
| 217 |
+
"train_samples_per_second":null,
|
| 218 |
+
"train_steps_per_second":null,
|
| 219 |
+
"total_flos":null,
|
| 220 |
+
"train_loss":null
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"loss":0.7434,
|
| 224 |
+
"grad_norm":0.2782152891,
|
| 225 |
+
"learning_rate":0.0001810723,
|
| 226 |
+
"entropy":0.7478979569,
|
| 227 |
+
"num_tokens":3212811.0,
|
| 228 |
+
"mean_token_accuracy":0.7946783796,
|
| 229 |
+
"epoch":0.6734006734,
|
| 230 |
+
"step":200,
|
| 231 |
+
"eval_loss":null,
|
| 232 |
+
"eval_runtime":null,
|
| 233 |
+
"eval_samples_per_second":null,
|
| 234 |
+
"eval_steps_per_second":null,
|
| 235 |
+
"eval_entropy":null,
|
| 236 |
+
"eval_num_tokens":null,
|
| 237 |
+
"eval_mean_token_accuracy":null,
|
| 238 |
+
"train_runtime":null,
|
| 239 |
+
"train_samples_per_second":null,
|
| 240 |
+
"train_steps_per_second":null,
|
| 241 |
+
"total_flos":null,
|
| 242 |
+
"train_loss":null
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"loss":null,
|
| 246 |
+
"grad_norm":null,
|
| 247 |
+
"learning_rate":null,
|
| 248 |
+
"entropy":null,
|
| 249 |
+
"num_tokens":null,
|
| 250 |
+
"mean_token_accuracy":null,
|
| 251 |
+
"epoch":0.6734006734,
|
| 252 |
+
"step":200,
|
| 253 |
+
"eval_loss":0.7540781498,
|
| 254 |
+
"eval_runtime":10.3368,
|
| 255 |
+
"eval_samples_per_second":24.185,
|
| 256 |
+
"eval_steps_per_second":3.096,
|
| 257 |
+
"eval_entropy":0.7548957299,
|
| 258 |
+
"eval_num_tokens":3212811.0,
|
| 259 |
+
"eval_mean_token_accuracy":0.7921991255,
|
| 260 |
+
"train_runtime":null,
|
| 261 |
+
"train_samples_per_second":null,
|
| 262 |
+
"train_steps_per_second":null,
|
| 263 |
+
"total_flos":null,
|
| 264 |
+
"train_loss":null
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"loss":0.718,
|
| 268 |
+
"grad_norm":0.2911323905,
|
| 269 |
+
"learning_rate":0.0001766044,
|
| 270 |
+
"entropy":0.7216884721,
|
| 271 |
+
"num_tokens":3534962.0,
|
| 272 |
+
"mean_token_accuracy":0.8007057041,
|
| 273 |
+
"epoch":0.7407407407,
|
| 274 |
+
"step":220,
|
| 275 |
+
"eval_loss":null,
|
| 276 |
+
"eval_runtime":null,
|
| 277 |
+
"eval_samples_per_second":null,
|
| 278 |
+
"eval_steps_per_second":null,
|
| 279 |
+
"eval_entropy":null,
|
| 280 |
+
"eval_num_tokens":null,
|
| 281 |
+
"eval_mean_token_accuracy":null,
|
| 282 |
+
"train_runtime":null,
|
| 283 |
+
"train_samples_per_second":null,
|
| 284 |
+
"train_steps_per_second":null,
|
| 285 |
+
"total_flos":null,
|
| 286 |
+
"train_loss":null
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"loss":0.7015,
|
| 290 |
+
"grad_norm":0.3469219804,
|
| 291 |
+
"learning_rate":0.0001717316,
|
| 292 |
+
"entropy":0.7073224507,
|
| 293 |
+
"num_tokens":3855519.0,
|
| 294 |
+
"mean_token_accuracy":0.8033309393,
|
| 295 |
+
"epoch":0.8080808081,
|
| 296 |
+
"step":240,
|
| 297 |
+
"eval_loss":null,
|
| 298 |
+
"eval_runtime":null,
|
| 299 |
+
"eval_samples_per_second":null,
|
| 300 |
+
"eval_steps_per_second":null,
|
| 301 |
+
"eval_entropy":null,
|
| 302 |
+
"eval_num_tokens":null,
|
| 303 |
+
"eval_mean_token_accuracy":null,
|
| 304 |
+
"train_runtime":null,
|
| 305 |
+
"train_samples_per_second":null,
|
| 306 |
+
"train_steps_per_second":null,
|
| 307 |
+
"total_flos":null,
|
| 308 |
+
"train_loss":null
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"loss":0.7066,
|
| 312 |
+
"grad_norm":0.3413038254,
|
| 313 |
+
"learning_rate":0.0001664796,
|
| 314 |
+
"entropy":0.7131307989,
|
| 315 |
+
"num_tokens":4174694.0,
|
| 316 |
+
"mean_token_accuracy":0.8030782551,
|
| 317 |
+
"epoch":0.8754208754,
|
| 318 |
+
"step":260,
|
| 319 |
+
"eval_loss":null,
|
| 320 |
+
"eval_runtime":null,
|
| 321 |
+
"eval_samples_per_second":null,
|
| 322 |
+
"eval_steps_per_second":null,
|
| 323 |
+
"eval_entropy":null,
|
| 324 |
+
"eval_num_tokens":null,
|
| 325 |
+
"eval_mean_token_accuracy":null,
|
| 326 |
+
"train_runtime":null,
|
| 327 |
+
"train_samples_per_second":null,
|
| 328 |
+
"train_steps_per_second":null,
|
| 329 |
+
"total_flos":null,
|
| 330 |
+
"train_loss":null
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"loss":0.6725,
|
| 334 |
+
"grad_norm":0.3970124125,
|
| 335 |
+
"learning_rate":0.0001608761,
|
| 336 |
+
"entropy":0.6751278345,
|
| 337 |
+
"num_tokens":4495214.0,
|
| 338 |
+
"mean_token_accuracy":0.8109409161,
|
| 339 |
+
"epoch":0.9427609428,
|
| 340 |
+
"step":280,
|
| 341 |
+
"eval_loss":null,
|
| 342 |
+
"eval_runtime":null,
|
| 343 |
+
"eval_samples_per_second":null,
|
| 344 |
+
"eval_steps_per_second":null,
|
| 345 |
+
"eval_entropy":null,
|
| 346 |
+
"eval_num_tokens":null,
|
| 347 |
+
"eval_mean_token_accuracy":null,
|
| 348 |
+
"train_runtime":null,
|
| 349 |
+
"train_samples_per_second":null,
|
| 350 |
+
"train_steps_per_second":null,
|
| 351 |
+
"total_flos":null,
|
| 352 |
+
"train_loss":null
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"loss":0.6567,
|
| 356 |
+
"grad_norm":0.4383921921,
|
| 357 |
+
"learning_rate":0.0001549509,
|
| 358 |
+
"entropy":0.6729893133,
|
| 359 |
+
"num_tokens":4815033.0,
|
| 360 |
+
"mean_token_accuracy":0.8148056932,
|
| 361 |
+
"epoch":1.0101010101,
|
| 362 |
+
"step":300,
|
| 363 |
+
"eval_loss":null,
|
| 364 |
+
"eval_runtime":null,
|
| 365 |
+
"eval_samples_per_second":null,
|
| 366 |
+
"eval_steps_per_second":null,
|
| 367 |
+
"eval_entropy":null,
|
| 368 |
+
"eval_num_tokens":null,
|
| 369 |
+
"eval_mean_token_accuracy":null,
|
| 370 |
+
"train_runtime":null,
|
| 371 |
+
"train_samples_per_second":null,
|
| 372 |
+
"train_steps_per_second":null,
|
| 373 |
+
"total_flos":null,
|
| 374 |
+
"train_loss":null
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"loss":null,
|
| 378 |
+
"grad_norm":null,
|
| 379 |
+
"learning_rate":null,
|
| 380 |
+
"entropy":null,
|
| 381 |
+
"num_tokens":null,
|
| 382 |
+
"mean_token_accuracy":null,
|
| 383 |
+
"epoch":1.0101010101,
|
| 384 |
+
"step":300,
|
| 385 |
+
"eval_loss":0.6720606685,
|
| 386 |
+
"eval_runtime":10.367,
|
| 387 |
+
"eval_samples_per_second":24.115,
|
| 388 |
+
"eval_steps_per_second":3.087,
|
| 389 |
+
"eval_entropy":0.6333643645,
|
| 390 |
+
"eval_num_tokens":4815033.0,
|
| 391 |
+
"eval_mean_token_accuracy":0.8116748761,
|
| 392 |
+
"train_runtime":null,
|
| 393 |
+
"train_samples_per_second":null,
|
| 394 |
+
"train_steps_per_second":null,
|
| 395 |
+
"total_flos":null,
|
| 396 |
+
"train_loss":null
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"loss":0.5649,
|
| 400 |
+
"grad_norm":0.4388367832,
|
| 401 |
+
"learning_rate":0.0001487352,
|
| 402 |
+
"entropy":0.5757804383,
|
| 403 |
+
"num_tokens":5135569.0,
|
| 404 |
+
"mean_token_accuracy":0.8381757662,
|
| 405 |
+
"epoch":1.0774410774,
|
| 406 |
+
"step":320,
|
| 407 |
+
"eval_loss":null,
|
| 408 |
+
"eval_runtime":null,
|
| 409 |
+
"eval_samples_per_second":null,
|
| 410 |
+
"eval_steps_per_second":null,
|
| 411 |
+
"eval_entropy":null,
|
| 412 |
+
"eval_num_tokens":null,
|
| 413 |
+
"eval_mean_token_accuracy":null,
|
| 414 |
+
"train_runtime":null,
|
| 415 |
+
"train_samples_per_second":null,
|
| 416 |
+
"train_steps_per_second":null,
|
| 417 |
+
"total_flos":null,
|
| 418 |
+
"train_loss":null
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"loss":0.564,
|
| 422 |
+
"grad_norm":0.4527507126,
|
| 423 |
+
"learning_rate":0.0001422618,
|
| 424 |
+
"entropy":0.5801134199,
|
| 425 |
+
"num_tokens":5456292.0,
|
| 426 |
+
"mean_token_accuracy":0.8384027012,
|
| 427 |
+
"epoch":1.1447811448,
|
| 428 |
+
"step":340,
|
| 429 |
+
"eval_loss":null,
|
| 430 |
+
"eval_runtime":null,
|
| 431 |
+
"eval_samples_per_second":null,
|
| 432 |
+
"eval_steps_per_second":null,
|
| 433 |
+
"eval_entropy":null,
|
| 434 |
+
"eval_num_tokens":null,
|
| 435 |
+
"eval_mean_token_accuracy":null,
|
| 436 |
+
"train_runtime":null,
|
| 437 |
+
"train_samples_per_second":null,
|
| 438 |
+
"train_steps_per_second":null,
|
| 439 |
+
"total_flos":null,
|
| 440 |
+
"train_loss":null
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"loss":0.5403,
|
| 444 |
+
"grad_norm":0.6442076564,
|
| 445 |
+
"learning_rate":0.0001355651,
|
| 446 |
+
"entropy":0.5545659784,
|
| 447 |
+
"num_tokens":5779926.0,
|
| 448 |
+
"mean_token_accuracy":0.8451263145,
|
| 449 |
+
"epoch":1.2121212121,
|
| 450 |
+
"step":360,
|
| 451 |
+
"eval_loss":null,
|
| 452 |
+
"eval_runtime":null,
|
| 453 |
+
"eval_samples_per_second":null,
|
| 454 |
+
"eval_steps_per_second":null,
|
| 455 |
+
"eval_entropy":null,
|
| 456 |
+
"eval_num_tokens":null,
|
| 457 |
+
"eval_mean_token_accuracy":null,
|
| 458 |
+
"train_runtime":null,
|
| 459 |
+
"train_samples_per_second":null,
|
| 460 |
+
"train_steps_per_second":null,
|
| 461 |
+
"total_flos":null,
|
| 462 |
+
"train_loss":null
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"loss":0.5554,
|
| 466 |
+
"grad_norm":0.5305426717,
|
| 467 |
+
"learning_rate":0.0001286803,
|
| 468 |
+
"entropy":0.5719649505,
|
| 469 |
+
"num_tokens":6100921.0,
|
| 470 |
+
"mean_token_accuracy":0.8403378457,
|
| 471 |
+
"epoch":1.2794612795,
|
| 472 |
+
"step":380,
|
| 473 |
+
"eval_loss":null,
|
| 474 |
+
"eval_runtime":null,
|
| 475 |
+
"eval_samples_per_second":null,
|
| 476 |
+
"eval_steps_per_second":null,
|
| 477 |
+
"eval_entropy":null,
|
| 478 |
+
"eval_num_tokens":null,
|
| 479 |
+
"eval_mean_token_accuracy":null,
|
| 480 |
+
"train_runtime":null,
|
| 481 |
+
"train_samples_per_second":null,
|
| 482 |
+
"train_steps_per_second":null,
|
| 483 |
+
"total_flos":null,
|
| 484 |
+
"train_loss":null
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"loss":0.5345,
|
| 488 |
+
"grad_norm":0.5867527723,
|
| 489 |
+
"learning_rate":0.000121644,
|
| 490 |
+
"entropy":0.5514425825,
|
| 491 |
+
"num_tokens":6423622.0,
|
| 492 |
+
"mean_token_accuracy":0.8455459923,
|
| 493 |
+
"epoch":1.3468013468,
|
| 494 |
+
"step":400,
|
| 495 |
+
"eval_loss":null,
|
| 496 |
+
"eval_runtime":null,
|
| 497 |
+
"eval_samples_per_second":null,
|
| 498 |
+
"eval_steps_per_second":null,
|
| 499 |
+
"eval_entropy":null,
|
| 500 |
+
"eval_num_tokens":null,
|
| 501 |
+
"eval_mean_token_accuracy":null,
|
| 502 |
+
"train_runtime":null,
|
| 503 |
+
"train_samples_per_second":null,
|
| 504 |
+
"train_steps_per_second":null,
|
| 505 |
+
"total_flos":null,
|
| 506 |
+
"train_loss":null
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"loss":null,
|
| 510 |
+
"grad_norm":null,
|
| 511 |
+
"learning_rate":null,
|
| 512 |
+
"entropy":null,
|
| 513 |
+
"num_tokens":null,
|
| 514 |
+
"mean_token_accuracy":null,
|
| 515 |
+
"epoch":1.3468013468,
|
| 516 |
+
"step":400,
|
| 517 |
+
"eval_loss":0.5978295803,
|
| 518 |
+
"eval_runtime":10.3395,
|
| 519 |
+
"eval_samples_per_second":24.179,
|
| 520 |
+
"eval_steps_per_second":3.095,
|
| 521 |
+
"eval_entropy":0.5523942402,
|
| 522 |
+
"eval_num_tokens":6423622.0,
|
| 523 |
+
"eval_mean_token_accuracy":0.8328636196,
|
| 524 |
+
"train_runtime":null,
|
| 525 |
+
"train_samples_per_second":null,
|
| 526 |
+
"train_steps_per_second":null,
|
| 527 |
+
"total_flos":null,
|
| 528 |
+
"train_loss":null
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"loss":0.5122,
|
| 532 |
+
"grad_norm":0.5380092859,
|
| 533 |
+
"learning_rate":0.0001144932,
|
| 534 |
+
"entropy":0.5361574471,
|
| 535 |
+
"num_tokens":6744569.0,
|
| 536 |
+
"mean_token_accuracy":0.8533119515,
|
| 537 |
+
"epoch":1.4141414141,
|
| 538 |
+
"step":420,
|
| 539 |
+
"eval_loss":null,
|
| 540 |
+
"eval_runtime":null,
|
| 541 |
+
"eval_samples_per_second":null,
|
| 542 |
+
"eval_steps_per_second":null,
|
| 543 |
+
"eval_entropy":null,
|
| 544 |
+
"eval_num_tokens":null,
|
| 545 |
+
"eval_mean_token_accuracy":null,
|
| 546 |
+
"train_runtime":null,
|
| 547 |
+
"train_samples_per_second":null,
|
| 548 |
+
"train_steps_per_second":null,
|
| 549 |
+
"total_flos":null,
|
| 550 |
+
"train_loss":null
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"loss":0.4923,
|
| 554 |
+
"grad_norm":0.5738714933,
|
| 555 |
+
"learning_rate":0.0001072658,
|
| 556 |
+
"entropy":0.5068911854,
|
| 557 |
+
"num_tokens":7065251.0,
|
| 558 |
+
"mean_token_accuracy":0.8583682023,
|
| 559 |
+
"epoch":1.4814814815,
|
| 560 |
+
"step":440,
|
| 561 |
+
"eval_loss":null,
|
| 562 |
+
"eval_runtime":null,
|
| 563 |
+
"eval_samples_per_second":null,
|
| 564 |
+
"eval_steps_per_second":null,
|
| 565 |
+
"eval_entropy":null,
|
| 566 |
+
"eval_num_tokens":null,
|
| 567 |
+
"eval_mean_token_accuracy":null,
|
| 568 |
+
"train_runtime":null,
|
| 569 |
+
"train_samples_per_second":null,
|
| 570 |
+
"train_steps_per_second":null,
|
| 571 |
+
"total_flos":null,
|
| 572 |
+
"train_loss":null
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"loss":0.4808,
|
| 576 |
+
"grad_norm":0.5104277134,
|
| 577 |
+
"learning_rate":0.0001,
|
| 578 |
+
"entropy":0.504258769,
|
| 579 |
+
"num_tokens":7385952.0,
|
| 580 |
+
"mean_token_accuracy":0.861315985,
|
| 581 |
+
"epoch":1.5488215488,
|
| 582 |
+
"step":460,
|
| 583 |
+
"eval_loss":null,
|
| 584 |
+
"eval_runtime":null,
|
| 585 |
+
"eval_samples_per_second":null,
|
| 586 |
+
"eval_steps_per_second":null,
|
| 587 |
+
"eval_entropy":null,
|
| 588 |
+
"eval_num_tokens":null,
|
| 589 |
+
"eval_mean_token_accuracy":null,
|
| 590 |
+
"train_runtime":null,
|
| 591 |
+
"train_samples_per_second":null,
|
| 592 |
+
"train_steps_per_second":null,
|
| 593 |
+
"total_flos":null,
|
| 594 |
+
"train_loss":null
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"loss":0.4867,
|
| 598 |
+
"grad_norm":0.5913535357,
|
| 599 |
+
"learning_rate":0.0000927342,
|
| 600 |
+
"entropy":0.5113813952,
|
| 601 |
+
"num_tokens":7704982.0,
|
| 602 |
+
"mean_token_accuracy":0.8592018247,
|
| 603 |
+
"epoch":1.6161616162,
|
| 604 |
+
"step":480,
|
| 605 |
+
"eval_loss":null,
|
| 606 |
+
"eval_runtime":null,
|
| 607 |
+
"eval_samples_per_second":null,
|
| 608 |
+
"eval_steps_per_second":null,
|
| 609 |
+
"eval_entropy":null,
|
| 610 |
+
"eval_num_tokens":null,
|
| 611 |
+
"eval_mean_token_accuracy":null,
|
| 612 |
+
"train_runtime":null,
|
| 613 |
+
"train_samples_per_second":null,
|
| 614 |
+
"train_steps_per_second":null,
|
| 615 |
+
"total_flos":null,
|
| 616 |
+
"train_loss":null
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"loss":0.4591,
|
| 620 |
+
"grad_norm":0.5065989494,
|
| 621 |
+
"learning_rate":0.0000855068,
|
| 622 |
+
"entropy":0.4817487616,
|
| 623 |
+
"num_tokens":8026316.0,
|
| 624 |
+
"mean_token_accuracy":0.8679369375,
|
| 625 |
+
"epoch":1.6835016835,
|
| 626 |
+
"step":500,
|
| 627 |
+
"eval_loss":null,
|
| 628 |
+
"eval_runtime":null,
|
| 629 |
+
"eval_samples_per_second":null,
|
| 630 |
+
"eval_steps_per_second":null,
|
| 631 |
+
"eval_entropy":null,
|
| 632 |
+
"eval_num_tokens":null,
|
| 633 |
+
"eval_mean_token_accuracy":null,
|
| 634 |
+
"train_runtime":null,
|
| 635 |
+
"train_samples_per_second":null,
|
| 636 |
+
"train_steps_per_second":null,
|
| 637 |
+
"total_flos":null,
|
| 638 |
+
"train_loss":null
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"loss":null,
|
| 642 |
+
"grad_norm":null,
|
| 643 |
+
"learning_rate":null,
|
| 644 |
+
"entropy":null,
|
| 645 |
+
"num_tokens":null,
|
| 646 |
+
"mean_token_accuracy":null,
|
| 647 |
+
"epoch":1.6835016835,
|
| 648 |
+
"step":500,
|
| 649 |
+
"eval_loss":0.511384666,
|
| 650 |
+
"eval_runtime":10.3657,
|
| 651 |
+
"eval_samples_per_second":24.118,
|
| 652 |
+
"eval_steps_per_second":3.087,
|
| 653 |
+
"eval_entropy":0.514307227,
|
| 654 |
+
"eval_num_tokens":8026316.0,
|
| 655 |
+
"eval_mean_token_accuracy":0.8547733743,
|
| 656 |
+
"train_runtime":null,
|
| 657 |
+
"train_samples_per_second":null,
|
| 658 |
+
"train_steps_per_second":null,
|
| 659 |
+
"total_flos":null,
|
| 660 |
+
"train_loss":null
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"loss":0.4296,
|
| 664 |
+
"grad_norm":0.5839767456,
|
| 665 |
+
"learning_rate":0.000078356,
|
| 666 |
+
"entropy":0.4638194107,
|
| 667 |
+
"num_tokens":8348213.0,
|
| 668 |
+
"mean_token_accuracy":0.8757635169,
|
| 669 |
+
"epoch":1.7508417508,
|
| 670 |
+
"step":520,
|
| 671 |
+
"eval_loss":null,
|
| 672 |
+
"eval_runtime":null,
|
| 673 |
+
"eval_samples_per_second":null,
|
| 674 |
+
"eval_steps_per_second":null,
|
| 675 |
+
"eval_entropy":null,
|
| 676 |
+
"eval_num_tokens":null,
|
| 677 |
+
"eval_mean_token_accuracy":null,
|
| 678 |
+
"train_runtime":null,
|
| 679 |
+
"train_samples_per_second":null,
|
| 680 |
+
"train_steps_per_second":null,
|
| 681 |
+
"total_flos":null,
|
| 682 |
+
"train_loss":null
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"loss":0.4351,
|
| 686 |
+
"grad_norm":0.6890075207,
|
| 687 |
+
"learning_rate":0.0000713197,
|
| 688 |
+
"entropy":0.4628964256,
|
| 689 |
+
"num_tokens":8671513.0,
|
| 690 |
+
"mean_token_accuracy":0.8734818839,
|
| 691 |
+
"epoch":1.8181818182,
|
| 692 |
+
"step":540,
|
| 693 |
+
"eval_loss":null,
|
| 694 |
+
"eval_runtime":null,
|
| 695 |
+
"eval_samples_per_second":null,
|
| 696 |
+
"eval_steps_per_second":null,
|
| 697 |
+
"eval_entropy":null,
|
| 698 |
+
"eval_num_tokens":null,
|
| 699 |
+
"eval_mean_token_accuracy":null,
|
| 700 |
+
"train_runtime":null,
|
| 701 |
+
"train_samples_per_second":null,
|
| 702 |
+
"train_steps_per_second":null,
|
| 703 |
+
"total_flos":null,
|
| 704 |
+
"train_loss":null
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"loss":0.4173,
|
| 708 |
+
"grad_norm":0.5538685918,
|
| 709 |
+
"learning_rate":0.0000644349,
|
| 710 |
+
"entropy":0.4462708168,
|
| 711 |
+
"num_tokens":8990602.0,
|
| 712 |
+
"mean_token_accuracy":0.8780993037,
|
| 713 |
+
"epoch":1.8855218855,
|
| 714 |
+
"step":560,
|
| 715 |
+
"eval_loss":null,
|
| 716 |
+
"eval_runtime":null,
|
| 717 |
+
"eval_samples_per_second":null,
|
| 718 |
+
"eval_steps_per_second":null,
|
| 719 |
+
"eval_entropy":null,
|
| 720 |
+
"eval_num_tokens":null,
|
| 721 |
+
"eval_mean_token_accuracy":null,
|
| 722 |
+
"train_runtime":null,
|
| 723 |
+
"train_samples_per_second":null,
|
| 724 |
+
"train_steps_per_second":null,
|
| 725 |
+
"total_flos":null,
|
| 726 |
+
"train_loss":null
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"loss":0.4249,
|
| 730 |
+
"grad_norm":0.6900932789,
|
| 731 |
+
"learning_rate":0.0000577382,
|
| 732 |
+
"entropy":0.4559292875,
|
| 733 |
+
"num_tokens":9310065.0,
|
| 734 |
+
"mean_token_accuracy":0.8769208066,
|
| 735 |
+
"epoch":1.9528619529,
|
| 736 |
+
"step":580,
|
| 737 |
+
"eval_loss":null,
|
| 738 |
+
"eval_runtime":null,
|
| 739 |
+
"eval_samples_per_second":null,
|
| 740 |
+
"eval_steps_per_second":null,
|
| 741 |
+
"eval_entropy":null,
|
| 742 |
+
"eval_num_tokens":null,
|
| 743 |
+
"eval_mean_token_accuracy":null,
|
| 744 |
+
"train_runtime":null,
|
| 745 |
+
"train_samples_per_second":null,
|
| 746 |
+
"train_steps_per_second":null,
|
| 747 |
+
"total_flos":null,
|
| 748 |
+
"train_loss":null
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"loss":0.3863,
|
| 752 |
+
"grad_norm":0.6177843809,
|
| 753 |
+
"learning_rate":0.0000512648,
|
| 754 |
+
"entropy":0.4270478457,
|
| 755 |
+
"num_tokens":9629281.0,
|
| 756 |
+
"mean_token_accuracy":0.8871142037,
|
| 757 |
+
"epoch":2.0202020202,
|
| 758 |
+
"step":600,
|
| 759 |
+
"eval_loss":null,
|
| 760 |
+
"eval_runtime":null,
|
| 761 |
+
"eval_samples_per_second":null,
|
| 762 |
+
"eval_steps_per_second":null,
|
| 763 |
+
"eval_entropy":null,
|
| 764 |
+
"eval_num_tokens":null,
|
| 765 |
+
"eval_mean_token_accuracy":null,
|
| 766 |
+
"train_runtime":null,
|
| 767 |
+
"train_samples_per_second":null,
|
| 768 |
+
"train_steps_per_second":null,
|
| 769 |
+
"total_flos":null,
|
| 770 |
+
"train_loss":null
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"loss":null,
|
| 774 |
+
"grad_norm":null,
|
| 775 |
+
"learning_rate":null,
|
| 776 |
+
"entropy":null,
|
| 777 |
+
"num_tokens":null,
|
| 778 |
+
"mean_token_accuracy":null,
|
| 779 |
+
"epoch":2.0202020202,
|
| 780 |
+
"step":600,
|
| 781 |
+
"eval_loss":0.4490914941,
|
| 782 |
+
"eval_runtime":10.371,
|
| 783 |
+
"eval_samples_per_second":24.106,
|
| 784 |
+
"eval_steps_per_second":3.086,
|
| 785 |
+
"eval_entropy":0.4390519308,
|
| 786 |
+
"eval_num_tokens":9629281.0,
|
| 787 |
+
"eval_mean_token_accuracy":0.8718043752,
|
| 788 |
+
"train_runtime":null,
|
| 789 |
+
"train_samples_per_second":null,
|
| 790 |
+
"train_steps_per_second":null,
|
| 791 |
+
"total_flos":null,
|
| 792 |
+
"train_loss":null
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"loss":0.3554,
|
| 796 |
+
"grad_norm":0.5899857879,
|
| 797 |
+
"learning_rate":0.0000450491,
|
| 798 |
+
"entropy":0.396466079,
|
| 799 |
+
"num_tokens":9951673.0,
|
| 800 |
+
"mean_token_accuracy":0.8959640451,
|
| 801 |
+
"epoch":2.0875420875,
|
| 802 |
+
"step":620,
|
| 803 |
+
"eval_loss":null,
|
| 804 |
+
"eval_runtime":null,
|
| 805 |
+
"eval_samples_per_second":null,
|
| 806 |
+
"eval_steps_per_second":null,
|
| 807 |
+
"eval_entropy":null,
|
| 808 |
+
"eval_num_tokens":null,
|
| 809 |
+
"eval_mean_token_accuracy":null,
|
| 810 |
+
"train_runtime":null,
|
| 811 |
+
"train_samples_per_second":null,
|
| 812 |
+
"train_steps_per_second":null,
|
| 813 |
+
"total_flos":null,
|
| 814 |
+
"train_loss":null
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"loss":0.3401,
|
| 818 |
+
"grad_norm":0.6384023428,
|
| 819 |
+
"learning_rate":0.0000391239,
|
| 820 |
+
"entropy":0.3796210378,
|
| 821 |
+
"num_tokens":10273617.0,
|
| 822 |
+
"mean_token_accuracy":0.8999493234,
|
| 823 |
+
"epoch":2.1548821549,
|
| 824 |
+
"step":640,
|
| 825 |
+
"eval_loss":null,
|
| 826 |
+
"eval_runtime":null,
|
| 827 |
+
"eval_samples_per_second":null,
|
| 828 |
+
"eval_steps_per_second":null,
|
| 829 |
+
"eval_entropy":null,
|
| 830 |
+
"eval_num_tokens":null,
|
| 831 |
+
"eval_mean_token_accuracy":null,
|
| 832 |
+
"train_runtime":null,
|
| 833 |
+
"train_samples_per_second":null,
|
| 834 |
+
"train_steps_per_second":null,
|
| 835 |
+
"total_flos":null,
|
| 836 |
+
"train_loss":null
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"loss":0.3281,
|
| 840 |
+
"grad_norm":0.6890760064,
|
| 841 |
+
"learning_rate":0.0000335204,
|
| 842 |
+
"entropy":0.3717882721,
|
| 843 |
+
"num_tokens":10594830.0,
|
| 844 |
+
"mean_token_accuracy":0.9037643224,
|
| 845 |
+
"epoch":2.2222222222,
|
| 846 |
+
"step":660,
|
| 847 |
+
"eval_loss":null,
|
| 848 |
+
"eval_runtime":null,
|
| 849 |
+
"eval_samples_per_second":null,
|
| 850 |
+
"eval_steps_per_second":null,
|
| 851 |
+
"eval_entropy":null,
|
| 852 |
+
"eval_num_tokens":null,
|
| 853 |
+
"eval_mean_token_accuracy":null,
|
| 854 |
+
"train_runtime":null,
|
| 855 |
+
"train_samples_per_second":null,
|
| 856 |
+
"train_steps_per_second":null,
|
| 857 |
+
"total_flos":null,
|
| 858 |
+
"train_loss":null
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"loss":0.32,
|
| 862 |
+
"grad_norm":0.6508978605,
|
| 863 |
+
"learning_rate":0.0000282684,
|
| 864 |
+
"entropy":0.3625029052,
|
| 865 |
+
"num_tokens":10916597.0,
|
| 866 |
+
"mean_token_accuracy":0.9063778028,
|
| 867 |
+
"epoch":2.2895622896,
|
| 868 |
+
"step":680,
|
| 869 |
+
"eval_loss":null,
|
| 870 |
+
"eval_runtime":null,
|
| 871 |
+
"eval_samples_per_second":null,
|
| 872 |
+
"eval_steps_per_second":null,
|
| 873 |
+
"eval_entropy":null,
|
| 874 |
+
"eval_num_tokens":null,
|
| 875 |
+
"eval_mean_token_accuracy":null,
|
| 876 |
+
"train_runtime":null,
|
| 877 |
+
"train_samples_per_second":null,
|
| 878 |
+
"train_steps_per_second":null,
|
| 879 |
+
"total_flos":null,
|
| 880 |
+
"train_loss":null
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"loss":0.3189,
|
| 884 |
+
"grad_norm":0.6131536961,
|
| 885 |
+
"learning_rate":0.0000233956,
|
| 886 |
+
"entropy":0.3583062481,
|
| 887 |
+
"num_tokens":11235743.0,
|
| 888 |
+
"mean_token_accuracy":0.9068948857,
|
| 889 |
+
"epoch":2.3569023569,
|
| 890 |
+
"step":700,
|
| 891 |
+
"eval_loss":null,
|
| 892 |
+
"eval_runtime":null,
|
| 893 |
+
"eval_samples_per_second":null,
|
| 894 |
+
"eval_steps_per_second":null,
|
| 895 |
+
"eval_entropy":null,
|
| 896 |
+
"eval_num_tokens":null,
|
| 897 |
+
"eval_mean_token_accuracy":null,
|
| 898 |
+
"train_runtime":null,
|
| 899 |
+
"train_samples_per_second":null,
|
| 900 |
+
"train_steps_per_second":null,
|
| 901 |
+
"total_flos":null,
|
| 902 |
+
"train_loss":null
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"loss":null,
|
| 906 |
+
"grad_norm":null,
|
| 907 |
+
"learning_rate":null,
|
| 908 |
+
"entropy":null,
|
| 909 |
+
"num_tokens":null,
|
| 910 |
+
"mean_token_accuracy":null,
|
| 911 |
+
"epoch":2.3569023569,
|
| 912 |
+
"step":700,
|
| 913 |
+
"eval_loss":0.4149619639,
|
| 914 |
+
"eval_runtime":10.3707,
|
| 915 |
+
"eval_samples_per_second":24.106,
|
| 916 |
+
"eval_steps_per_second":3.086,
|
| 917 |
+
"eval_entropy":0.4037288642,
|
| 918 |
+
"eval_num_tokens":11235743.0,
|
| 919 |
+
"eval_mean_token_accuracy":0.8824688997,
|
| 920 |
+
"train_runtime":null,
|
| 921 |
+
"train_samples_per_second":null,
|
| 922 |
+
"train_steps_per_second":null,
|
| 923 |
+
"total_flos":null,
|
| 924 |
+
"train_loss":null
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"loss":0.3248,
|
| 928 |
+
"grad_norm":0.5035169125,
|
| 929 |
+
"learning_rate":0.0000189277,
|
| 930 |
+
"entropy":0.3696210571,
|
| 931 |
+
"num_tokens":11556934.0,
|
| 932 |
+
"mean_token_accuracy":0.9046057545,
|
| 933 |
+
"epoch":2.4242424242,
|
| 934 |
+
"step":720,
|
| 935 |
+
"eval_loss":null,
|
| 936 |
+
"eval_runtime":null,
|
| 937 |
+
"eval_samples_per_second":null,
|
| 938 |
+
"eval_steps_per_second":null,
|
| 939 |
+
"eval_entropy":null,
|
| 940 |
+
"eval_num_tokens":null,
|
| 941 |
+
"eval_mean_token_accuracy":null,
|
| 942 |
+
"train_runtime":null,
|
| 943 |
+
"train_samples_per_second":null,
|
| 944 |
+
"train_steps_per_second":null,
|
| 945 |
+
"total_flos":null,
|
| 946 |
+
"train_loss":null
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"loss":0.3126,
|
| 950 |
+
"grad_norm":0.5420159698,
|
| 951 |
+
"learning_rate":0.0000148883,
|
| 952 |
+
"entropy":0.3530109294,
|
| 953 |
+
"num_tokens":11879049.0,
|
| 954 |
+
"mean_token_accuracy":0.910102234,
|
| 955 |
+
"epoch":2.4915824916,
|
| 956 |
+
"step":740,
|
| 957 |
+
"eval_loss":null,
|
| 958 |
+
"eval_runtime":null,
|
| 959 |
+
"eval_samples_per_second":null,
|
| 960 |
+
"eval_steps_per_second":null,
|
| 961 |
+
"eval_entropy":null,
|
| 962 |
+
"eval_num_tokens":null,
|
| 963 |
+
"eval_mean_token_accuracy":null,
|
| 964 |
+
"train_runtime":null,
|
| 965 |
+
"train_samples_per_second":null,
|
| 966 |
+
"train_steps_per_second":null,
|
| 967 |
+
"total_flos":null,
|
| 968 |
+
"train_loss":null
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"loss":0.3017,
|
| 972 |
+
"grad_norm":0.4808464348,
|
| 973 |
+
"learning_rate":0.0000112989,
|
| 974 |
+
"entropy":0.3429520307,
|
| 975 |
+
"num_tokens":12199559.0,
|
| 976 |
+
"mean_token_accuracy":0.9116890863,
|
| 977 |
+
"epoch":2.5589225589,
|
| 978 |
+
"step":760,
|
| 979 |
+
"eval_loss":null,
|
| 980 |
+
"eval_runtime":null,
|
| 981 |
+
"eval_samples_per_second":null,
|
| 982 |
+
"eval_steps_per_second":null,
|
| 983 |
+
"eval_entropy":null,
|
| 984 |
+
"eval_num_tokens":null,
|
| 985 |
+
"eval_mean_token_accuracy":null,
|
| 986 |
+
"train_runtime":null,
|
| 987 |
+
"train_samples_per_second":null,
|
| 988 |
+
"train_steps_per_second":null,
|
| 989 |
+
"total_flos":null,
|
| 990 |
+
"train_loss":null
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"loss":0.2944,
|
| 994 |
+
"grad_norm":0.5233286023,
|
| 995 |
+
"learning_rate":0.0000081784,
|
| 996 |
+
"entropy":0.3373699239,
|
| 997 |
+
"num_tokens":12518745.0,
|
| 998 |
+
"mean_token_accuracy":0.9141617462,
|
| 999 |
+
"epoch":2.6262626263,
|
| 1000 |
+
"step":780,
|
| 1001 |
+
"eval_loss":null,
|
| 1002 |
+
"eval_runtime":null,
|
| 1003 |
+
"eval_samples_per_second":null,
|
| 1004 |
+
"eval_steps_per_second":null,
|
| 1005 |
+
"eval_entropy":null,
|
| 1006 |
+
"eval_num_tokens":null,
|
| 1007 |
+
"eval_mean_token_accuracy":null,
|
| 1008 |
+
"train_runtime":null,
|
| 1009 |
+
"train_samples_per_second":null,
|
| 1010 |
+
"train_steps_per_second":null,
|
| 1011 |
+
"total_flos":null,
|
| 1012 |
+
"train_loss":null
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"loss":0.3132,
|
| 1016 |
+
"grad_norm":0.540781498,
|
| 1017 |
+
"learning_rate":0.0000055432,
|
| 1018 |
+
"entropy":0.3541788673,
|
| 1019 |
+
"num_tokens":12839323.0,
|
| 1020 |
+
"mean_token_accuracy":0.9097139165,
|
| 1021 |
+
"epoch":2.6936026936,
|
| 1022 |
+
"step":800,
|
| 1023 |
+
"eval_loss":null,
|
| 1024 |
+
"eval_runtime":null,
|
| 1025 |
+
"eval_samples_per_second":null,
|
| 1026 |
+
"eval_steps_per_second":null,
|
| 1027 |
+
"eval_entropy":null,
|
| 1028 |
+
"eval_num_tokens":null,
|
| 1029 |
+
"eval_mean_token_accuracy":null,
|
| 1030 |
+
"train_runtime":null,
|
| 1031 |
+
"train_samples_per_second":null,
|
| 1032 |
+
"train_steps_per_second":null,
|
| 1033 |
+
"total_flos":null,
|
| 1034 |
+
"train_loss":null
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"loss":null,
|
| 1038 |
+
"grad_norm":null,
|
| 1039 |
+
"learning_rate":null,
|
| 1040 |
+
"entropy":null,
|
| 1041 |
+
"num_tokens":null,
|
| 1042 |
+
"mean_token_accuracy":null,
|
| 1043 |
+
"epoch":2.6936026936,
|
| 1044 |
+
"step":800,
|
| 1045 |
+
"eval_loss":0.3966158926,
|
| 1046 |
+
"eval_runtime":10.3484,
|
| 1047 |
+
"eval_samples_per_second":24.158,
|
| 1048 |
+
"eval_steps_per_second":3.092,
|
| 1049 |
+
"eval_entropy":0.3902668599,
|
| 1050 |
+
"eval_num_tokens":12839323.0,
|
| 1051 |
+
"eval_mean_token_accuracy":0.8880477473,
|
| 1052 |
+
"train_runtime":null,
|
| 1053 |
+
"train_samples_per_second":null,
|
| 1054 |
+
"train_steps_per_second":null,
|
| 1055 |
+
"total_flos":null,
|
| 1056 |
+
"train_loss":null
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"loss":0.3082,
|
| 1060 |
+
"grad_norm":0.5258508921,
|
| 1061 |
+
"learning_rate":0.0000034074,
|
| 1062 |
+
"entropy":0.3506111713,
|
| 1063 |
+
"num_tokens":13160627.0,
|
| 1064 |
+
"mean_token_accuracy":0.9098422483,
|
| 1065 |
+
"epoch":2.7609427609,
|
| 1066 |
+
"step":820,
|
| 1067 |
+
"eval_loss":null,
|
| 1068 |
+
"eval_runtime":null,
|
| 1069 |
+
"eval_samples_per_second":null,
|
| 1070 |
+
"eval_steps_per_second":null,
|
| 1071 |
+
"eval_entropy":null,
|
| 1072 |
+
"eval_num_tokens":null,
|
| 1073 |
+
"eval_mean_token_accuracy":null,
|
| 1074 |
+
"train_runtime":null,
|
| 1075 |
+
"train_samples_per_second":null,
|
| 1076 |
+
"train_steps_per_second":null,
|
| 1077 |
+
"total_flos":null,
|
| 1078 |
+
"train_loss":null
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"loss":0.3079,
|
| 1082 |
+
"grad_norm":0.4996784031,
|
| 1083 |
+
"learning_rate":0.0000017822,
|
| 1084 |
+
"entropy":0.3474921705,
|
| 1085 |
+
"num_tokens":13481114.0,
|
| 1086 |
+
"mean_token_accuracy":0.9094100349,
|
| 1087 |
+
"epoch":2.8282828283,
|
| 1088 |
+
"step":840,
|
| 1089 |
+
"eval_loss":null,
|
| 1090 |
+
"eval_runtime":null,
|
| 1091 |
+
"eval_samples_per_second":null,
|
| 1092 |
+
"eval_steps_per_second":null,
|
| 1093 |
+
"eval_entropy":null,
|
| 1094 |
+
"eval_num_tokens":null,
|
| 1095 |
+
"eval_mean_token_accuracy":null,
|
| 1096 |
+
"train_runtime":null,
|
| 1097 |
+
"train_samples_per_second":null,
|
| 1098 |
+
"train_steps_per_second":null,
|
| 1099 |
+
"total_flos":null,
|
| 1100 |
+
"train_loss":null
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"loss":0.3092,
|
| 1104 |
+
"grad_norm":0.4853805304,
|
| 1105 |
+
"learning_rate":0.0000006762,
|
| 1106 |
+
"entropy":0.3521205258,
|
| 1107 |
+
"num_tokens":13803114.0,
|
| 1108 |
+
"mean_token_accuracy":0.9098572351,
|
| 1109 |
+
"epoch":2.8956228956,
|
| 1110 |
+
"step":860,
|
| 1111 |
+
"eval_loss":null,
|
| 1112 |
+
"eval_runtime":null,
|
| 1113 |
+
"eval_samples_per_second":null,
|
| 1114 |
+
"eval_steps_per_second":null,
|
| 1115 |
+
"eval_entropy":null,
|
| 1116 |
+
"eval_num_tokens":null,
|
| 1117 |
+
"eval_mean_token_accuracy":null,
|
| 1118 |
+
"train_runtime":null,
|
| 1119 |
+
"train_samples_per_second":null,
|
| 1120 |
+
"train_steps_per_second":null,
|
| 1121 |
+
"total_flos":null,
|
| 1122 |
+
"train_loss":null
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"loss":0.3038,
|
| 1126 |
+
"grad_norm":0.5111385584,
|
| 1127 |
+
"learning_rate":0.0000000952,
|
| 1128 |
+
"entropy":0.3490505032,
|
| 1129 |
+
"num_tokens":14125289.0,
|
| 1130 |
+
"mean_token_accuracy":0.9108231679,
|
| 1131 |
+
"epoch":2.962962963,
|
| 1132 |
+
"step":880,
|
| 1133 |
+
"eval_loss":null,
|
| 1134 |
+
"eval_runtime":null,
|
| 1135 |
+
"eval_samples_per_second":null,
|
| 1136 |
+
"eval_steps_per_second":null,
|
| 1137 |
+
"eval_entropy":null,
|
| 1138 |
+
"eval_num_tokens":null,
|
| 1139 |
+
"eval_mean_token_accuracy":null,
|
| 1140 |
+
"train_runtime":null,
|
| 1141 |
+
"train_samples_per_second":null,
|
| 1142 |
+
"train_steps_per_second":null,
|
| 1143 |
+
"total_flos":null,
|
| 1144 |
+
"train_loss":null
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"loss":null,
|
| 1148 |
+
"grad_norm":null,
|
| 1149 |
+
"learning_rate":null,
|
| 1150 |
+
"entropy":null,
|
| 1151 |
+
"num_tokens":null,
|
| 1152 |
+
"mean_token_accuracy":null,
|
| 1153 |
+
"epoch":3.0,
|
| 1154 |
+
"step":891,
|
| 1155 |
+
"eval_loss":null,
|
| 1156 |
+
"eval_runtime":null,
|
| 1157 |
+
"eval_samples_per_second":null,
|
| 1158 |
+
"eval_steps_per_second":null,
|
| 1159 |
+
"eval_entropy":null,
|
| 1160 |
+
"eval_num_tokens":null,
|
| 1161 |
+
"eval_mean_token_accuracy":null,
|
| 1162 |
+
"train_runtime":1912.4699,
|
| 1163 |
+
"train_samples_per_second":7.451,
|
| 1164 |
+
"train_steps_per_second":0.466,
|
| 1165 |
+
"total_flos":1.163395683e+17,
|
| 1166 |
+
"train_loss":0.5388089069
|
| 1167 |
+
}
|
| 1168 |
+
]
|