Commit
•
7e10397
1
Parent(s):
6da856d
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jun15_15-05-22_labgpu/events.out.tfevents.1655307432.labgpu.19883.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +67 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_combined_score": 0.8754223466068438,
|
| 4 |
+
"eval_loss": 0.5347728133201599,
|
| 5 |
+
"eval_pearson": 0.8773310199946579,
|
| 6 |
+
"eval_runtime": 7.8565,
|
| 7 |
+
"eval_samples": 1500,
|
| 8 |
+
"eval_samples_per_second": 190.925,
|
| 9 |
+
"eval_spearmanr": 0.8735136732190296,
|
| 10 |
+
"eval_steps_per_second": 23.929,
|
| 11 |
+
"train_loss": 11197704656.541739,
|
| 12 |
+
"train_runtime": 1310.0328,
|
| 13 |
+
"train_samples": 5749,
|
| 14 |
+
"train_samples_per_second": 43.884,
|
| 15 |
+
"train_steps_per_second": 2.748
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_combined_score": 0.8754223466068438,
|
| 4 |
+
"eval_loss": 0.5347728133201599,
|
| 5 |
+
"eval_pearson": 0.8773310199946579,
|
| 6 |
+
"eval_runtime": 7.8565,
|
| 7 |
+
"eval_samples": 1500,
|
| 8 |
+
"eval_samples_per_second": 190.925,
|
| 9 |
+
"eval_spearmanr": 0.8735136732190296,
|
| 10 |
+
"eval_steps_per_second": 23.929
|
| 11 |
+
}
|
runs/Jun15_15-05-22_labgpu/events.out.tfevents.1655307432.labgpu.19883.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90973647a943db39278a039b298685cfe8eca959d280238f0692f4c7798f46e1
|
| 3 |
+
size 473
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 11197704656.541739,
|
| 4 |
+
"train_runtime": 1310.0328,
|
| 5 |
+
"train_samples": 5749,
|
| 6 |
+
"train_samples_per_second": 43.884,
|
| 7 |
+
"train_steps_per_second": 2.748
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 3600,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.39,
|
| 12 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 13 |
+
"loss": 80623473524.736,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.78,
|
| 18 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 19 |
+
"loss": 0.9617,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 4.17,
|
| 24 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 25 |
+
"loss": 0.3908,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 5.56,
|
| 30 |
+
"learning_rate": 8.888888888888888e-06,
|
| 31 |
+
"loss": 0.3095,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 6.94,
|
| 36 |
+
"learning_rate": 6.111111111111112e-06,
|
| 37 |
+
"loss": 0.256,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 8.33,
|
| 42 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 43 |
+
"loss": 0.2181,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 9.72,
|
| 48 |
+
"learning_rate": 5.555555555555555e-07,
|
| 49 |
+
"loss": 0.1911,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 10.0,
|
| 54 |
+
"step": 3600,
|
| 55 |
+
"total_flos": 901255567357440.0,
|
| 56 |
+
"train_loss": 11197704656.541739,
|
| 57 |
+
"train_runtime": 1310.0328,
|
| 58 |
+
"train_samples_per_second": 43.884,
|
| 59 |
+
"train_steps_per_second": 2.748
|
| 60 |
+
}
|
| 61 |
+
],
|
| 62 |
+
"max_steps": 3600,
|
| 63 |
+
"num_train_epochs": 10,
|
| 64 |
+
"total_flos": 901255567357440.0,
|
| 65 |
+
"trial_name": null,
|
| 66 |
+
"trial_params": null
|
| 67 |
+
}
|