Commit
•
0ef60d4
1
Parent(s):
cb3cb9b
End of training
Browse files- README.md +3 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +834 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: mit
|
|
| 3 |
base_model: unicamp-dl/ptt5-base-t5-vocab
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: t5_base-qg-aap-test
|
| 8 |
results: []
|
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# t5_base-qg-aap-test
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.0278
|
| 19 |
|
|
|
|
| 3 |
base_model: unicamp-dl/ptt5-base-t5-vocab
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- tiagoblima/preprocessed-du-qg-squadv1_pt
|
| 8 |
model-index:
|
| 9 |
- name: t5_base-qg-aap-test
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# t5_base-qg-aap-test
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on the tiagoblima/preprocessed-du-qg-squadv1_pt dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.0278
|
| 21 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.027821063995361328,
|
| 4 |
+
"eval_runtime": 0.2305,
|
| 5 |
+
"eval_samples": 8,
|
| 6 |
+
"eval_samples_per_second": 34.71,
|
| 7 |
+
"eval_steps_per_second": 4.339,
|
| 8 |
+
"train_loss": 0.8787790679931641,
|
| 9 |
+
"train_runtime": 1000.0694,
|
| 10 |
+
"train_samples": 8,
|
| 11 |
+
"train_samples_per_second": 0.8,
|
| 12 |
+
"train_steps_per_second": 0.1
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.027821063995361328,
|
| 4 |
+
"eval_runtime": 0.2305,
|
| 5 |
+
"eval_samples": 8,
|
| 6 |
+
"eval_samples_per_second": 34.71,
|
| 7 |
+
"eval_steps_per_second": 4.339
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 0.8787790679931641,
|
| 4 |
+
"train_runtime": 1000.0694,
|
| 5 |
+
"train_samples": 8,
|
| 6 |
+
"train_samples_per_second": 0.8,
|
| 7 |
+
"train_steps_per_second": 0.1
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,834 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.027821063995361328,
|
| 3 |
+
"best_model_checkpoint": "/temp/t5_base-qg-aap-test/checkpoint-100",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_loss": 8.543387413024902,
|
| 14 |
+
"eval_runtime": 0.22,
|
| 15 |
+
"eval_samples_per_second": 36.371,
|
| 16 |
+
"eval_steps_per_second": 4.546,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_loss": 7.301304340362549,
|
| 22 |
+
"eval_runtime": 0.2288,
|
| 23 |
+
"eval_samples_per_second": 34.962,
|
| 24 |
+
"eval_steps_per_second": 4.37,
|
| 25 |
+
"step": 2
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 3.0,
|
| 29 |
+
"eval_loss": 6.199253559112549,
|
| 30 |
+
"eval_runtime": 0.2323,
|
| 31 |
+
"eval_samples_per_second": 34.438,
|
| 32 |
+
"eval_steps_per_second": 4.305,
|
| 33 |
+
"step": 3
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.0,
|
| 37 |
+
"eval_loss": 5.28981351852417,
|
| 38 |
+
"eval_runtime": 0.2358,
|
| 39 |
+
"eval_samples_per_second": 33.933,
|
| 40 |
+
"eval_steps_per_second": 4.242,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 5.0,
|
| 45 |
+
"eval_loss": 4.522605895996094,
|
| 46 |
+
"eval_runtime": 0.2354,
|
| 47 |
+
"eval_samples_per_second": 33.99,
|
| 48 |
+
"eval_steps_per_second": 4.249,
|
| 49 |
+
"step": 5
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 6.0,
|
| 53 |
+
"eval_loss": 3.9202158451080322,
|
| 54 |
+
"eval_runtime": 0.2368,
|
| 55 |
+
"eval_samples_per_second": 33.78,
|
| 56 |
+
"eval_steps_per_second": 4.222,
|
| 57 |
+
"step": 6
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.0,
|
| 61 |
+
"eval_loss": 3.4436142444610596,
|
| 62 |
+
"eval_runtime": 0.2346,
|
| 63 |
+
"eval_samples_per_second": 34.095,
|
| 64 |
+
"eval_steps_per_second": 4.262,
|
| 65 |
+
"step": 7
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 8.0,
|
| 69 |
+
"eval_loss": 3.0407516956329346,
|
| 70 |
+
"eval_runtime": 0.2359,
|
| 71 |
+
"eval_samples_per_second": 33.92,
|
| 72 |
+
"eval_steps_per_second": 4.24,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 9.0,
|
| 77 |
+
"eval_loss": 2.7138168811798096,
|
| 78 |
+
"eval_runtime": 0.232,
|
| 79 |
+
"eval_samples_per_second": 34.479,
|
| 80 |
+
"eval_steps_per_second": 4.31,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.0,
|
| 85 |
+
"eval_loss": 2.443582773208618,
|
| 86 |
+
"eval_runtime": 0.2358,
|
| 87 |
+
"eval_samples_per_second": 33.927,
|
| 88 |
+
"eval_steps_per_second": 4.241,
|
| 89 |
+
"step": 10
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 11.0,
|
| 93 |
+
"eval_loss": 2.2130391597747803,
|
| 94 |
+
"eval_runtime": 0.2341,
|
| 95 |
+
"eval_samples_per_second": 34.169,
|
| 96 |
+
"eval_steps_per_second": 4.271,
|
| 97 |
+
"step": 11
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 12.0,
|
| 101 |
+
"eval_loss": 2.019005060195923,
|
| 102 |
+
"eval_runtime": 0.2346,
|
| 103 |
+
"eval_samples_per_second": 34.099,
|
| 104 |
+
"eval_steps_per_second": 4.262,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.0,
|
| 109 |
+
"eval_loss": 1.8450862169265747,
|
| 110 |
+
"eval_runtime": 0.2278,
|
| 111 |
+
"eval_samples_per_second": 35.113,
|
| 112 |
+
"eval_steps_per_second": 4.389,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 14.0,
|
| 117 |
+
"eval_loss": 1.6746028661727905,
|
| 118 |
+
"eval_runtime": 0.2332,
|
| 119 |
+
"eval_samples_per_second": 34.306,
|
| 120 |
+
"eval_steps_per_second": 4.288,
|
| 121 |
+
"step": 14
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 15.0,
|
| 125 |
+
"eval_loss": 1.5047035217285156,
|
| 126 |
+
"eval_runtime": 0.2344,
|
| 127 |
+
"eval_samples_per_second": 34.13,
|
| 128 |
+
"eval_steps_per_second": 4.266,
|
| 129 |
+
"step": 15
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.0,
|
| 133 |
+
"eval_loss": 1.3376126289367676,
|
| 134 |
+
"eval_runtime": 0.235,
|
| 135 |
+
"eval_samples_per_second": 34.041,
|
| 136 |
+
"eval_steps_per_second": 4.255,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 17.0,
|
| 141 |
+
"eval_loss": 1.1800236701965332,
|
| 142 |
+
"eval_runtime": 0.234,
|
| 143 |
+
"eval_samples_per_second": 34.182,
|
| 144 |
+
"eval_steps_per_second": 4.273,
|
| 145 |
+
"step": 17
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 18.0,
|
| 149 |
+
"eval_loss": 1.043411374092102,
|
| 150 |
+
"eval_runtime": 0.2333,
|
| 151 |
+
"eval_samples_per_second": 34.295,
|
| 152 |
+
"eval_steps_per_second": 4.287,
|
| 153 |
+
"step": 18
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 19.0,
|
| 157 |
+
"eval_loss": 0.9442155361175537,
|
| 158 |
+
"eval_runtime": 0.2311,
|
| 159 |
+
"eval_samples_per_second": 34.61,
|
| 160 |
+
"eval_steps_per_second": 4.326,
|
| 161 |
+
"step": 19
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 20.0,
|
| 165 |
+
"eval_loss": 0.8739322423934937,
|
| 166 |
+
"eval_runtime": 0.2326,
|
| 167 |
+
"eval_samples_per_second": 34.388,
|
| 168 |
+
"eval_steps_per_second": 4.299,
|
| 169 |
+
"step": 20
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 21.0,
|
| 173 |
+
"eval_loss": 0.8162761926651001,
|
| 174 |
+
"eval_runtime": 0.2315,
|
| 175 |
+
"eval_samples_per_second": 34.559,
|
| 176 |
+
"eval_steps_per_second": 4.32,
|
| 177 |
+
"step": 21
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 22.0,
|
| 181 |
+
"eval_loss": 0.7628746628761292,
|
| 182 |
+
"eval_runtime": 0.2355,
|
| 183 |
+
"eval_samples_per_second": 33.977,
|
| 184 |
+
"eval_steps_per_second": 4.247,
|
| 185 |
+
"step": 22
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 23.0,
|
| 189 |
+
"eval_loss": 0.7117814421653748,
|
| 190 |
+
"eval_runtime": 0.2347,
|
| 191 |
+
"eval_samples_per_second": 34.092,
|
| 192 |
+
"eval_steps_per_second": 4.262,
|
| 193 |
+
"step": 23
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 24.0,
|
| 197 |
+
"eval_loss": 0.661788821220398,
|
| 198 |
+
"eval_runtime": 0.2304,
|
| 199 |
+
"eval_samples_per_second": 34.715,
|
| 200 |
+
"eval_steps_per_second": 4.339,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 25.0,
|
| 205 |
+
"eval_loss": 0.6104191541671753,
|
| 206 |
+
"eval_runtime": 0.2332,
|
| 207 |
+
"eval_samples_per_second": 34.307,
|
| 208 |
+
"eval_steps_per_second": 4.288,
|
| 209 |
+
"step": 25
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 26.0,
|
| 213 |
+
"eval_loss": 0.5596593618392944,
|
| 214 |
+
"eval_runtime": 0.2354,
|
| 215 |
+
"eval_samples_per_second": 33.987,
|
| 216 |
+
"eval_steps_per_second": 4.248,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 27.0,
|
| 221 |
+
"eval_loss": 0.5112428665161133,
|
| 222 |
+
"eval_runtime": 0.2316,
|
| 223 |
+
"eval_samples_per_second": 34.539,
|
| 224 |
+
"eval_steps_per_second": 4.317,
|
| 225 |
+
"step": 27
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 28.0,
|
| 229 |
+
"eval_loss": 0.4656863212585449,
|
| 230 |
+
"eval_runtime": 0.2358,
|
| 231 |
+
"eval_samples_per_second": 33.925,
|
| 232 |
+
"eval_steps_per_second": 4.241,
|
| 233 |
+
"step": 28
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 29.0,
|
| 237 |
+
"eval_loss": 0.4242892861366272,
|
| 238 |
+
"eval_runtime": 0.2324,
|
| 239 |
+
"eval_samples_per_second": 34.417,
|
| 240 |
+
"eval_steps_per_second": 4.302,
|
| 241 |
+
"step": 29
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 30.0,
|
| 245 |
+
"eval_loss": 0.38730064034461975,
|
| 246 |
+
"eval_runtime": 0.2361,
|
| 247 |
+
"eval_samples_per_second": 33.884,
|
| 248 |
+
"eval_steps_per_second": 4.236,
|
| 249 |
+
"step": 30
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 31.0,
|
| 253 |
+
"eval_loss": 0.3529461622238159,
|
| 254 |
+
"eval_runtime": 0.2273,
|
| 255 |
+
"eval_samples_per_second": 35.195,
|
| 256 |
+
"eval_steps_per_second": 4.399,
|
| 257 |
+
"step": 31
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 32.0,
|
| 261 |
+
"eval_loss": 0.3208673894405365,
|
| 262 |
+
"eval_runtime": 0.2312,
|
| 263 |
+
"eval_samples_per_second": 34.6,
|
| 264 |
+
"eval_steps_per_second": 4.325,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 33.0,
|
| 269 |
+
"eval_loss": 0.2917502224445343,
|
| 270 |
+
"eval_runtime": 0.2299,
|
| 271 |
+
"eval_samples_per_second": 34.802,
|
| 272 |
+
"eval_steps_per_second": 4.35,
|
| 273 |
+
"step": 33
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 34.0,
|
| 277 |
+
"eval_loss": 0.26672637462615967,
|
| 278 |
+
"eval_runtime": 0.2245,
|
| 279 |
+
"eval_samples_per_second": 35.641,
|
| 280 |
+
"eval_steps_per_second": 4.455,
|
| 281 |
+
"step": 34
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 35.0,
|
| 285 |
+
"eval_loss": 0.24361155927181244,
|
| 286 |
+
"eval_runtime": 0.2331,
|
| 287 |
+
"eval_samples_per_second": 34.323,
|
| 288 |
+
"eval_steps_per_second": 4.29,
|
| 289 |
+
"step": 35
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 36.0,
|
| 293 |
+
"eval_loss": 0.22150522470474243,
|
| 294 |
+
"eval_runtime": 0.2314,
|
| 295 |
+
"eval_samples_per_second": 34.566,
|
| 296 |
+
"eval_steps_per_second": 4.321,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 37.0,
|
| 301 |
+
"eval_loss": 0.20035764575004578,
|
| 302 |
+
"eval_runtime": 0.2358,
|
| 303 |
+
"eval_samples_per_second": 33.929,
|
| 304 |
+
"eval_steps_per_second": 4.241,
|
| 305 |
+
"step": 37
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 38.0,
|
| 309 |
+
"eval_loss": 0.18083304166793823,
|
| 310 |
+
"eval_runtime": 0.2305,
|
| 311 |
+
"eval_samples_per_second": 34.715,
|
| 312 |
+
"eval_steps_per_second": 4.339,
|
| 313 |
+
"step": 38
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 39.0,
|
| 317 |
+
"eval_loss": 0.16373088955879211,
|
| 318 |
+
"eval_runtime": 0.2358,
|
| 319 |
+
"eval_samples_per_second": 33.933,
|
| 320 |
+
"eval_steps_per_second": 4.242,
|
| 321 |
+
"step": 39
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 40.0,
|
| 325 |
+
"eval_loss": 0.14839813113212585,
|
| 326 |
+
"eval_runtime": 0.236,
|
| 327 |
+
"eval_samples_per_second": 33.892,
|
| 328 |
+
"eval_steps_per_second": 4.236,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 41.0,
|
| 333 |
+
"eval_loss": 0.1357194185256958,
|
| 334 |
+
"eval_runtime": 0.2358,
|
| 335 |
+
"eval_samples_per_second": 33.932,
|
| 336 |
+
"eval_steps_per_second": 4.242,
|
| 337 |
+
"step": 41
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 42.0,
|
| 341 |
+
"eval_loss": 0.1251770257949829,
|
| 342 |
+
"eval_runtime": 0.2246,
|
| 343 |
+
"eval_samples_per_second": 35.621,
|
| 344 |
+
"eval_steps_per_second": 4.453,
|
| 345 |
+
"step": 42
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 43.0,
|
| 349 |
+
"eval_loss": 0.11590107530355453,
|
| 350 |
+
"eval_runtime": 0.2355,
|
| 351 |
+
"eval_samples_per_second": 33.971,
|
| 352 |
+
"eval_steps_per_second": 4.246,
|
| 353 |
+
"step": 43
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 44.0,
|
| 357 |
+
"eval_loss": 0.10785257816314697,
|
| 358 |
+
"eval_runtime": 0.2288,
|
| 359 |
+
"eval_samples_per_second": 34.96,
|
| 360 |
+
"eval_steps_per_second": 4.37,
|
| 361 |
+
"step": 44
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 45.0,
|
| 365 |
+
"eval_loss": 0.09967806190252304,
|
| 366 |
+
"eval_runtime": 0.2309,
|
| 367 |
+
"eval_samples_per_second": 34.652,
|
| 368 |
+
"eval_steps_per_second": 4.332,
|
| 369 |
+
"step": 45
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 46.0,
|
| 373 |
+
"eval_loss": 0.0922195091843605,
|
| 374 |
+
"eval_runtime": 0.2356,
|
| 375 |
+
"eval_samples_per_second": 33.952,
|
| 376 |
+
"eval_steps_per_second": 4.244,
|
| 377 |
+
"step": 46
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 47.0,
|
| 381 |
+
"eval_loss": 0.08580458164215088,
|
| 382 |
+
"eval_runtime": 0.2356,
|
| 383 |
+
"eval_samples_per_second": 33.959,
|
| 384 |
+
"eval_steps_per_second": 4.245,
|
| 385 |
+
"step": 47
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 48.0,
|
| 389 |
+
"eval_loss": 0.08024830371141434,
|
| 390 |
+
"eval_runtime": 0.2344,
|
| 391 |
+
"eval_samples_per_second": 34.129,
|
| 392 |
+
"eval_steps_per_second": 4.266,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 49.0,
|
| 397 |
+
"eval_loss": 0.07487977296113968,
|
| 398 |
+
"eval_runtime": 0.2357,
|
| 399 |
+
"eval_samples_per_second": 33.936,
|
| 400 |
+
"eval_steps_per_second": 4.242,
|
| 401 |
+
"step": 49
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 50.0,
|
| 405 |
+
"eval_loss": 0.07032416760921478,
|
| 406 |
+
"eval_runtime": 0.231,
|
| 407 |
+
"eval_samples_per_second": 34.629,
|
| 408 |
+
"eval_steps_per_second": 4.329,
|
| 409 |
+
"step": 50
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 51.0,
|
| 413 |
+
"eval_loss": 0.06604083627462387,
|
| 414 |
+
"eval_runtime": 0.2355,
|
| 415 |
+
"eval_samples_per_second": 33.971,
|
| 416 |
+
"eval_steps_per_second": 4.246,
|
| 417 |
+
"step": 51
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 52.0,
|
| 421 |
+
"eval_loss": 0.06256596744060516,
|
| 422 |
+
"eval_runtime": 0.2338,
|
| 423 |
+
"eval_samples_per_second": 34.216,
|
| 424 |
+
"eval_steps_per_second": 4.277,
|
| 425 |
+
"step": 52
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 53.0,
|
| 429 |
+
"eval_loss": 0.0596306137740612,
|
| 430 |
+
"eval_runtime": 0.2355,
|
| 431 |
+
"eval_samples_per_second": 33.976,
|
| 432 |
+
"eval_steps_per_second": 4.247,
|
| 433 |
+
"step": 53
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 54.0,
|
| 437 |
+
"eval_loss": 0.05728648975491524,
|
| 438 |
+
"eval_runtime": 0.2313,
|
| 439 |
+
"eval_samples_per_second": 34.582,
|
| 440 |
+
"eval_steps_per_second": 4.323,
|
| 441 |
+
"step": 54
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 55.0,
|
| 445 |
+
"eval_loss": 0.05549569055438042,
|
| 446 |
+
"eval_runtime": 0.2351,
|
| 447 |
+
"eval_samples_per_second": 34.022,
|
| 448 |
+
"eval_steps_per_second": 4.253,
|
| 449 |
+
"step": 55
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 56.0,
|
| 453 |
+
"eval_loss": 0.0538727343082428,
|
| 454 |
+
"eval_runtime": 0.2351,
|
| 455 |
+
"eval_samples_per_second": 34.035,
|
| 456 |
+
"eval_steps_per_second": 4.254,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 57.0,
|
| 461 |
+
"eval_loss": 0.05207115411758423,
|
| 462 |
+
"eval_runtime": 0.2247,
|
| 463 |
+
"eval_samples_per_second": 35.607,
|
| 464 |
+
"eval_steps_per_second": 4.451,
|
| 465 |
+
"step": 57
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 58.0,
|
| 469 |
+
"eval_loss": 0.05064238980412483,
|
| 470 |
+
"eval_runtime": 0.2241,
|
| 471 |
+
"eval_samples_per_second": 35.694,
|
| 472 |
+
"eval_steps_per_second": 4.462,
|
| 473 |
+
"step": 58
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 59.0,
|
| 477 |
+
"eval_loss": 0.0496056042611599,
|
| 478 |
+
"eval_runtime": 0.2358,
|
| 479 |
+
"eval_samples_per_second": 33.922,
|
| 480 |
+
"eval_steps_per_second": 4.24,
|
| 481 |
+
"step": 59
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 60.0,
|
| 485 |
+
"eval_loss": 0.04849918186664581,
|
| 486 |
+
"eval_runtime": 0.234,
|
| 487 |
+
"eval_samples_per_second": 34.194,
|
| 488 |
+
"eval_steps_per_second": 4.274,
|
| 489 |
+
"step": 60
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 61.0,
|
| 493 |
+
"eval_loss": 0.04720243811607361,
|
| 494 |
+
"eval_runtime": 0.2354,
|
| 495 |
+
"eval_samples_per_second": 33.992,
|
| 496 |
+
"eval_steps_per_second": 4.249,
|
| 497 |
+
"step": 61
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 62.0,
|
| 501 |
+
"eval_loss": 0.04599544033408165,
|
| 502 |
+
"eval_runtime": 0.2346,
|
| 503 |
+
"eval_samples_per_second": 34.103,
|
| 504 |
+
"eval_steps_per_second": 4.263,
|
| 505 |
+
"step": 62
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 63.0,
|
| 509 |
+
"eval_loss": 0.04451025277376175,
|
| 510 |
+
"eval_runtime": 0.2405,
|
| 511 |
+
"eval_samples_per_second": 33.268,
|
| 512 |
+
"eval_steps_per_second": 4.159,
|
| 513 |
+
"step": 63
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 64.0,
|
| 517 |
+
"eval_loss": 0.04322642832994461,
|
| 518 |
+
"eval_runtime": 0.2321,
|
| 519 |
+
"eval_samples_per_second": 34.47,
|
| 520 |
+
"eval_steps_per_second": 4.309,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 65.0,
|
| 525 |
+
"eval_loss": 0.04210076108574867,
|
| 526 |
+
"eval_runtime": 0.2361,
|
| 527 |
+
"eval_samples_per_second": 33.885,
|
| 528 |
+
"eval_steps_per_second": 4.236,
|
| 529 |
+
"step": 65
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 66.0,
|
| 533 |
+
"eval_loss": 0.04086441919207573,
|
| 534 |
+
"eval_runtime": 0.2341,
|
| 535 |
+
"eval_samples_per_second": 34.177,
|
| 536 |
+
"eval_steps_per_second": 4.272,
|
| 537 |
+
"step": 66
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 67.0,
|
| 541 |
+
"eval_loss": 0.03964550420641899,
|
| 542 |
+
"eval_runtime": 0.2287,
|
| 543 |
+
"eval_samples_per_second": 34.977,
|
| 544 |
+
"eval_steps_per_second": 4.372,
|
| 545 |
+
"step": 67
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 68.0,
|
| 549 |
+
"eval_loss": 0.03853166475892067,
|
| 550 |
+
"eval_runtime": 0.2351,
|
| 551 |
+
"eval_samples_per_second": 34.031,
|
| 552 |
+
"eval_steps_per_second": 4.254,
|
| 553 |
+
"step": 68
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 69.0,
|
| 557 |
+
"eval_loss": 0.03747276961803436,
|
| 558 |
+
"eval_runtime": 0.2354,
|
| 559 |
+
"eval_samples_per_second": 33.984,
|
| 560 |
+
"eval_steps_per_second": 4.248,
|
| 561 |
+
"step": 69
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 70.0,
|
| 565 |
+
"eval_loss": 0.0365348644554615,
|
| 566 |
+
"eval_runtime": 0.2257,
|
| 567 |
+
"eval_samples_per_second": 35.448,
|
| 568 |
+
"eval_steps_per_second": 4.431,
|
| 569 |
+
"step": 70
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 71.0,
|
| 573 |
+
"eval_loss": 0.035752058029174805,
|
| 574 |
+
"eval_runtime": 0.2347,
|
| 575 |
+
"eval_samples_per_second": 34.085,
|
| 576 |
+
"eval_steps_per_second": 4.261,
|
| 577 |
+
"step": 71
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 72.0,
|
| 581 |
+
"eval_loss": 0.03502313047647476,
|
| 582 |
+
"eval_runtime": 0.2313,
|
| 583 |
+
"eval_samples_per_second": 34.586,
|
| 584 |
+
"eval_steps_per_second": 4.323,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 73.0,
|
| 589 |
+
"eval_loss": 0.03442569449543953,
|
| 590 |
+
"eval_runtime": 0.2356,
|
| 591 |
+
"eval_samples_per_second": 33.962,
|
| 592 |
+
"eval_steps_per_second": 4.245,
|
| 593 |
+
"step": 73
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 74.0,
|
| 597 |
+
"eval_loss": 0.03383530303835869,
|
| 598 |
+
"eval_runtime": 0.2258,
|
| 599 |
+
"eval_samples_per_second": 35.436,
|
| 600 |
+
"eval_steps_per_second": 4.429,
|
| 601 |
+
"step": 74
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 75.0,
|
| 605 |
+
"eval_loss": 0.0333658903837204,
|
| 606 |
+
"eval_runtime": 0.2352,
|
| 607 |
+
"eval_samples_per_second": 34.018,
|
| 608 |
+
"eval_steps_per_second": 4.252,
|
| 609 |
+
"step": 75
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 76.0,
|
| 613 |
+
"eval_loss": 0.03294898569583893,
|
| 614 |
+
"eval_runtime": 0.2302,
|
| 615 |
+
"eval_samples_per_second": 34.754,
|
| 616 |
+
"eval_steps_per_second": 4.344,
|
| 617 |
+
"step": 76
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 77.0,
|
| 621 |
+
"eval_loss": 0.03257429972290993,
|
| 622 |
+
"eval_runtime": 0.2347,
|
| 623 |
+
"eval_samples_per_second": 34.09,
|
| 624 |
+
"eval_steps_per_second": 4.261,
|
| 625 |
+
"step": 77
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 78.0,
|
| 629 |
+
"eval_loss": 0.032144706696271896,
|
| 630 |
+
"eval_runtime": 0.2353,
|
| 631 |
+
"eval_samples_per_second": 33.996,
|
| 632 |
+
"eval_steps_per_second": 4.25,
|
| 633 |
+
"step": 78
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 79.0,
|
| 637 |
+
"eval_loss": 0.03174722567200661,
|
| 638 |
+
"eval_runtime": 0.2359,
|
| 639 |
+
"eval_samples_per_second": 33.913,
|
| 640 |
+
"eval_steps_per_second": 4.239,
|
| 641 |
+
"step": 79
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 80.0,
|
| 645 |
+
"eval_loss": 0.031351201236248016,
|
| 646 |
+
"eval_runtime": 0.2302,
|
| 647 |
+
"eval_samples_per_second": 34.75,
|
| 648 |
+
"eval_steps_per_second": 4.344,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 81.0,
|
| 653 |
+
"eval_loss": 0.03098256327211857,
|
| 654 |
+
"eval_runtime": 0.235,
|
| 655 |
+
"eval_samples_per_second": 34.037,
|
| 656 |
+
"eval_steps_per_second": 4.255,
|
| 657 |
+
"step": 81
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 82.0,
|
| 661 |
+
"eval_loss": 0.030596623197197914,
|
| 662 |
+
"eval_runtime": 0.2313,
|
| 663 |
+
"eval_samples_per_second": 34.582,
|
| 664 |
+
"eval_steps_per_second": 4.323,
|
| 665 |
+
"step": 82
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 83.0,
|
| 669 |
+
"eval_loss": 0.0302561167627573,
|
| 670 |
+
"eval_runtime": 0.2311,
|
| 671 |
+
"eval_samples_per_second": 34.612,
|
| 672 |
+
"eval_steps_per_second": 4.326,
|
| 673 |
+
"step": 83
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 84.0,
|
| 677 |
+
"eval_loss": 0.02994276024401188,
|
| 678 |
+
"eval_runtime": 0.2345,
|
| 679 |
+
"eval_samples_per_second": 34.114,
|
| 680 |
+
"eval_steps_per_second": 4.264,
|
| 681 |
+
"step": 84
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 85.0,
|
| 685 |
+
"eval_loss": 0.029655389487743378,
|
| 686 |
+
"eval_runtime": 0.2317,
|
| 687 |
+
"eval_samples_per_second": 34.52,
|
| 688 |
+
"eval_steps_per_second": 4.315,
|
| 689 |
+
"step": 85
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 86.0,
|
| 693 |
+
"eval_loss": 0.029432008042931557,
|
| 694 |
+
"eval_runtime": 0.2323,
|
| 695 |
+
"eval_samples_per_second": 34.432,
|
| 696 |
+
"eval_steps_per_second": 4.304,
|
| 697 |
+
"step": 86
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 87.0,
|
| 701 |
+
"eval_loss": 0.02922823093831539,
|
| 702 |
+
"eval_runtime": 0.2355,
|
| 703 |
+
"eval_samples_per_second": 33.969,
|
| 704 |
+
"eval_steps_per_second": 4.246,
|
| 705 |
+
"step": 87
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 88.0,
|
| 709 |
+
"eval_loss": 0.02902672439813614,
|
| 710 |
+
"eval_runtime": 0.2356,
|
| 711 |
+
"eval_samples_per_second": 33.956,
|
| 712 |
+
"eval_steps_per_second": 4.244,
|
| 713 |
+
"step": 88
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 89.0,
|
| 717 |
+
"eval_loss": 0.02884937822818756,
|
| 718 |
+
"eval_runtime": 0.2358,
|
| 719 |
+
"eval_samples_per_second": 33.922,
|
| 720 |
+
"eval_steps_per_second": 4.24,
|
| 721 |
+
"step": 89
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 90.0,
|
| 725 |
+
"eval_loss": 0.02867262251675129,
|
| 726 |
+
"eval_runtime": 0.2321,
|
| 727 |
+
"eval_samples_per_second": 34.471,
|
| 728 |
+
"eval_steps_per_second": 4.309,
|
| 729 |
+
"step": 90
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 91.0,
|
| 733 |
+
"eval_loss": 0.02851748839020729,
|
| 734 |
+
"eval_runtime": 0.236,
|
| 735 |
+
"eval_samples_per_second": 33.898,
|
| 736 |
+
"eval_steps_per_second": 4.237,
|
| 737 |
+
"step": 91
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 92.0,
|
| 741 |
+
"eval_loss": 0.02836400270462036,
|
| 742 |
+
"eval_runtime": 0.2256,
|
| 743 |
+
"eval_samples_per_second": 35.466,
|
| 744 |
+
"eval_steps_per_second": 4.433,
|
| 745 |
+
"step": 92
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 93.0,
|
| 749 |
+
"eval_loss": 0.028240736573934555,
|
| 750 |
+
"eval_runtime": 0.2355,
|
| 751 |
+
"eval_samples_per_second": 33.963,
|
| 752 |
+
"eval_steps_per_second": 4.245,
|
| 753 |
+
"step": 93
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 94.0,
|
| 757 |
+
"eval_loss": 0.02814488857984543,
|
| 758 |
+
"eval_runtime": 0.231,
|
| 759 |
+
"eval_samples_per_second": 34.627,
|
| 760 |
+
"eval_steps_per_second": 4.328,
|
| 761 |
+
"step": 94
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 95.0,
|
| 765 |
+
"eval_loss": 0.0280709657818079,
|
| 766 |
+
"eval_runtime": 0.2356,
|
| 767 |
+
"eval_samples_per_second": 33.953,
|
| 768 |
+
"eval_steps_per_second": 4.244,
|
| 769 |
+
"step": 95
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 96.0,
|
| 773 |
+
"eval_loss": 0.02801009640097618,
|
| 774 |
+
"eval_runtime": 0.2315,
|
| 775 |
+
"eval_samples_per_second": 34.556,
|
| 776 |
+
"eval_steps_per_second": 4.319,
|
| 777 |
+
"step": 96
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 97.0,
|
| 781 |
+
"eval_loss": 0.02794581837952137,
|
| 782 |
+
"eval_runtime": 0.2362,
|
| 783 |
+
"eval_samples_per_second": 33.87,
|
| 784 |
+
"eval_steps_per_second": 4.234,
|
| 785 |
+
"step": 97
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 98.0,
|
| 789 |
+
"eval_loss": 0.027881627902388573,
|
| 790 |
+
"eval_runtime": 0.2362,
|
| 791 |
+
"eval_samples_per_second": 33.875,
|
| 792 |
+
"eval_steps_per_second": 4.234,
|
| 793 |
+
"step": 98
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 99.0,
|
| 797 |
+
"eval_loss": 0.027840854600071907,
|
| 798 |
+
"eval_runtime": 0.2356,
|
| 799 |
+
"eval_samples_per_second": 33.95,
|
| 800 |
+
"eval_steps_per_second": 4.244,
|
| 801 |
+
"step": 99
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 100.0,
|
| 805 |
+
"learning_rate": 0.0,
|
| 806 |
+
"loss": 0.8788,
|
| 807 |
+
"step": 100
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 100.0,
|
| 811 |
+
"eval_loss": 0.027821063995361328,
|
| 812 |
+
"eval_runtime": 0.2225,
|
| 813 |
+
"eval_samples_per_second": 35.947,
|
| 814 |
+
"eval_steps_per_second": 4.493,
|
| 815 |
+
"step": 100
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 100.0,
|
| 819 |
+
"step": 100,
|
| 820 |
+
"total_flos": 487166312448000.0,
|
| 821 |
+
"train_loss": 0.8787790679931641,
|
| 822 |
+
"train_runtime": 1000.0694,
|
| 823 |
+
"train_samples_per_second": 0.8,
|
| 824 |
+
"train_steps_per_second": 0.1
|
| 825 |
+
}
|
| 826 |
+
],
|
| 827 |
+
"logging_steps": 100,
|
| 828 |
+
"max_steps": 100,
|
| 829 |
+
"num_train_epochs": 100,
|
| 830 |
+
"save_steps": 500,
|
| 831 |
+
"total_flos": 487166312448000.0,
|
| 832 |
+
"trial_name": null,
|
| 833 |
+
"trial_params": null
|
| 834 |
+
}
|