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 +1530 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: google/long-t5-tglobal-xl
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: longt5_xl_sfd_memsum_30
|
| 8 |
results: []
|
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# longt5_xl_sfd_memsum_30
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 5.1322
|
| 19 |
|
|
|
|
| 3 |
base_model: google/long-t5-tglobal-xl
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- learn3r/summ_screen_memsum_oracle
|
| 8 |
model-index:
|
| 9 |
- name: longt5_xl_sfd_memsum_30
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# longt5_xl_sfd_memsum_30
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the learn3r/summ_screen_memsum_oracle dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 5.1322
|
| 21 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.22,
|
| 3 |
+
"eval_loss": 5.132218360900879,
|
| 4 |
+
"eval_runtime": 14.2345,
|
| 5 |
+
"eval_samples": 338,
|
| 6 |
+
"eval_samples_per_second": 23.745,
|
| 7 |
+
"eval_steps_per_second": 3.021,
|
| 8 |
+
"train_loss": 0.5600467140298514,
|
| 9 |
+
"train_runtime": 18789.4517,
|
| 10 |
+
"train_samples": 3673,
|
| 11 |
+
"train_samples_per_second": 5.864,
|
| 12 |
+
"train_steps_per_second": 0.022
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.22,
|
| 3 |
+
"eval_loss": 5.132218360900879,
|
| 4 |
+
"eval_runtime": 14.2345,
|
| 5 |
+
"eval_samples": 338,
|
| 6 |
+
"eval_samples_per_second": 23.745,
|
| 7 |
+
"eval_steps_per_second": 3.021
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.22,
|
| 3 |
+
"train_loss": 0.5600467140298514,
|
| 4 |
+
"train_runtime": 18789.4517,
|
| 5 |
+
"train_samples": 3673,
|
| 6 |
+
"train_samples_per_second": 5.864,
|
| 7 |
+
"train_steps_per_second": 0.022
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1530 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.255647659301758,
|
| 3 |
+
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_sfd_memsum_30/checkpoint-43",
|
| 4 |
+
"epoch": 29.217391304347824,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 420,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14,
|
| 13 |
+
"learning_rate": 0.001,
|
| 14 |
+
"loss": 3.2355,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.28,
|
| 19 |
+
"learning_rate": 0.001,
|
| 20 |
+
"loss": 3.0785,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.42,
|
| 25 |
+
"learning_rate": 0.001,
|
| 26 |
+
"loss": 3.0423,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.56,
|
| 31 |
+
"learning_rate": 0.001,
|
| 32 |
+
"loss": 2.9059,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.7,
|
| 37 |
+
"learning_rate": 0.001,
|
| 38 |
+
"loss": 2.777,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.83,
|
| 43 |
+
"learning_rate": 0.001,
|
| 44 |
+
"loss": 2.6848,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.97,
|
| 49 |
+
"learning_rate": 0.001,
|
| 50 |
+
"loss": 2.6697,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.97,
|
| 55 |
+
"eval_loss": 2.4168484210968018,
|
| 56 |
+
"eval_runtime": 14.3646,
|
| 57 |
+
"eval_samples_per_second": 23.53,
|
| 58 |
+
"eval_steps_per_second": 2.993,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.11,
|
| 63 |
+
"learning_rate": 0.001,
|
| 64 |
+
"loss": 2.4413,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.25,
|
| 69 |
+
"learning_rate": 0.001,
|
| 70 |
+
"loss": 2.3287,
|
| 71 |
+
"step": 18
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.39,
|
| 75 |
+
"learning_rate": 0.001,
|
| 76 |
+
"loss": 2.3054,
|
| 77 |
+
"step": 20
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.53,
|
| 81 |
+
"learning_rate": 0.001,
|
| 82 |
+
"loss": 2.3458,
|
| 83 |
+
"step": 22
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.67,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"loss": 2.3942,
|
| 89 |
+
"step": 24
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.81,
|
| 93 |
+
"learning_rate": 0.001,
|
| 94 |
+
"loss": 2.3186,
|
| 95 |
+
"step": 26
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.95,
|
| 99 |
+
"learning_rate": 0.001,
|
| 100 |
+
"loss": 2.2272,
|
| 101 |
+
"step": 28
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.95,
|
| 105 |
+
"eval_loss": 2.264381170272827,
|
| 106 |
+
"eval_runtime": 14.3433,
|
| 107 |
+
"eval_samples_per_second": 23.565,
|
| 108 |
+
"eval_steps_per_second": 2.998,
|
| 109 |
+
"step": 28
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.09,
|
| 113 |
+
"learning_rate": 0.001,
|
| 114 |
+
"loss": 2.0385,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.23,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"loss": 1.9493,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.37,
|
| 125 |
+
"learning_rate": 0.001,
|
| 126 |
+
"loss": 1.9811,
|
| 127 |
+
"step": 34
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.5,
|
| 131 |
+
"learning_rate": 0.001,
|
| 132 |
+
"loss": 1.9783,
|
| 133 |
+
"step": 36
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.64,
|
| 137 |
+
"learning_rate": 0.001,
|
| 138 |
+
"loss": 1.9534,
|
| 139 |
+
"step": 38
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.78,
|
| 143 |
+
"learning_rate": 0.001,
|
| 144 |
+
"loss": 1.9822,
|
| 145 |
+
"step": 40
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.92,
|
| 149 |
+
"learning_rate": 0.001,
|
| 150 |
+
"loss": 1.9024,
|
| 151 |
+
"step": 42
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.99,
|
| 155 |
+
"eval_loss": 2.255647659301758,
|
| 156 |
+
"eval_runtime": 14.349,
|
| 157 |
+
"eval_samples_per_second": 23.556,
|
| 158 |
+
"eval_steps_per_second": 2.997,
|
| 159 |
+
"step": 43
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.06,
|
| 163 |
+
"learning_rate": 0.001,
|
| 164 |
+
"loss": 1.7788,
|
| 165 |
+
"step": 44
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.2,
|
| 169 |
+
"learning_rate": 0.001,
|
| 170 |
+
"loss": 1.6545,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.34,
|
| 175 |
+
"learning_rate": 0.001,
|
| 176 |
+
"loss": 1.633,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.48,
|
| 181 |
+
"learning_rate": 0.001,
|
| 182 |
+
"loss": 1.6763,
|
| 183 |
+
"step": 50
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.62,
|
| 187 |
+
"learning_rate": 0.001,
|
| 188 |
+
"loss": 1.6571,
|
| 189 |
+
"step": 52
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.76,
|
| 193 |
+
"learning_rate": 0.001,
|
| 194 |
+
"loss": 1.6333,
|
| 195 |
+
"step": 54
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.9,
|
| 199 |
+
"learning_rate": 0.001,
|
| 200 |
+
"loss": 1.6554,
|
| 201 |
+
"step": 56
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.97,
|
| 205 |
+
"eval_loss": 2.4007155895233154,
|
| 206 |
+
"eval_runtime": 14.3209,
|
| 207 |
+
"eval_samples_per_second": 23.602,
|
| 208 |
+
"eval_steps_per_second": 3.003,
|
| 209 |
+
"step": 57
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.03,
|
| 213 |
+
"learning_rate": 0.001,
|
| 214 |
+
"loss": 1.5927,
|
| 215 |
+
"step": 58
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.17,
|
| 219 |
+
"learning_rate": 0.001,
|
| 220 |
+
"loss": 1.3606,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.31,
|
| 225 |
+
"learning_rate": 0.001,
|
| 226 |
+
"loss": 1.3576,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.45,
|
| 231 |
+
"learning_rate": 0.001,
|
| 232 |
+
"loss": 1.4079,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 4.59,
|
| 237 |
+
"learning_rate": 0.001,
|
| 238 |
+
"loss": 1.4133,
|
| 239 |
+
"step": 66
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.73,
|
| 243 |
+
"learning_rate": 0.001,
|
| 244 |
+
"loss": 1.3712,
|
| 245 |
+
"step": 68
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 4.87,
|
| 249 |
+
"learning_rate": 0.001,
|
| 250 |
+
"loss": 1.3619,
|
| 251 |
+
"step": 70
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 4.94,
|
| 255 |
+
"eval_loss": 2.423330545425415,
|
| 256 |
+
"eval_runtime": 14.334,
|
| 257 |
+
"eval_samples_per_second": 23.58,
|
| 258 |
+
"eval_steps_per_second": 3.0,
|
| 259 |
+
"step": 71
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.01,
|
| 263 |
+
"learning_rate": 0.001,
|
| 264 |
+
"loss": 1.3071,
|
| 265 |
+
"step": 72
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 5.15,
|
| 269 |
+
"learning_rate": 0.001,
|
| 270 |
+
"loss": 1.0472,
|
| 271 |
+
"step": 74
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.29,
|
| 275 |
+
"learning_rate": 0.001,
|
| 276 |
+
"loss": 1.1038,
|
| 277 |
+
"step": 76
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 5.43,
|
| 281 |
+
"learning_rate": 0.001,
|
| 282 |
+
"loss": 1.1355,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.57,
|
| 287 |
+
"learning_rate": 0.001,
|
| 288 |
+
"loss": 1.1239,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.7,
|
| 293 |
+
"learning_rate": 0.001,
|
| 294 |
+
"loss": 1.1464,
|
| 295 |
+
"step": 82
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.84,
|
| 299 |
+
"learning_rate": 0.001,
|
| 300 |
+
"loss": 1.1564,
|
| 301 |
+
"step": 84
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.98,
|
| 305 |
+
"learning_rate": 0.001,
|
| 306 |
+
"loss": 1.1577,
|
| 307 |
+
"step": 86
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.98,
|
| 311 |
+
"eval_loss": 2.679687976837158,
|
| 312 |
+
"eval_runtime": 14.3396,
|
| 313 |
+
"eval_samples_per_second": 23.571,
|
| 314 |
+
"eval_steps_per_second": 2.999,
|
| 315 |
+
"step": 86
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.12,
|
| 319 |
+
"learning_rate": 0.001,
|
| 320 |
+
"loss": 0.9042,
|
| 321 |
+
"step": 88
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.26,
|
| 325 |
+
"learning_rate": 0.001,
|
| 326 |
+
"loss": 0.882,
|
| 327 |
+
"step": 90
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.4,
|
| 331 |
+
"learning_rate": 0.001,
|
| 332 |
+
"loss": 0.9122,
|
| 333 |
+
"step": 92
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.54,
|
| 337 |
+
"learning_rate": 0.001,
|
| 338 |
+
"loss": 0.8572,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.68,
|
| 343 |
+
"learning_rate": 0.001,
|
| 344 |
+
"loss": 0.8929,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 6.82,
|
| 349 |
+
"learning_rate": 0.001,
|
| 350 |
+
"loss": 0.9316,
|
| 351 |
+
"step": 98
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.96,
|
| 355 |
+
"learning_rate": 0.001,
|
| 356 |
+
"loss": 0.9584,
|
| 357 |
+
"step": 100
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 6.96,
|
| 361 |
+
"eval_loss": 2.8448543548583984,
|
| 362 |
+
"eval_runtime": 14.3357,
|
| 363 |
+
"eval_samples_per_second": 23.578,
|
| 364 |
+
"eval_steps_per_second": 3.0,
|
| 365 |
+
"step": 100
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.1,
|
| 369 |
+
"learning_rate": 0.001,
|
| 370 |
+
"loss": 0.7378,
|
| 371 |
+
"step": 102
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 7.23,
|
| 375 |
+
"learning_rate": 0.001,
|
| 376 |
+
"loss": 0.7519,
|
| 377 |
+
"step": 104
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 7.37,
|
| 381 |
+
"learning_rate": 0.001,
|
| 382 |
+
"loss": 0.6793,
|
| 383 |
+
"step": 106
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 7.51,
|
| 387 |
+
"learning_rate": 0.001,
|
| 388 |
+
"loss": 0.7177,
|
| 389 |
+
"step": 108
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.65,
|
| 393 |
+
"learning_rate": 0.001,
|
| 394 |
+
"loss": 0.7523,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.79,
|
| 399 |
+
"learning_rate": 0.001,
|
| 400 |
+
"loss": 0.7479,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.93,
|
| 405 |
+
"learning_rate": 0.001,
|
| 406 |
+
"loss": 0.7197,
|
| 407 |
+
"step": 114
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 8.0,
|
| 411 |
+
"eval_loss": 3.025547504425049,
|
| 412 |
+
"eval_runtime": 14.3269,
|
| 413 |
+
"eval_samples_per_second": 23.592,
|
| 414 |
+
"eval_steps_per_second": 3.001,
|
| 415 |
+
"step": 115
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 8.07,
|
| 419 |
+
"learning_rate": 0.001,
|
| 420 |
+
"loss": 0.6231,
|
| 421 |
+
"step": 116
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 8.21,
|
| 425 |
+
"learning_rate": 0.001,
|
| 426 |
+
"loss": 0.5361,
|
| 427 |
+
"step": 118
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 8.35,
|
| 431 |
+
"learning_rate": 0.001,
|
| 432 |
+
"loss": 0.5926,
|
| 433 |
+
"step": 120
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 8.49,
|
| 437 |
+
"learning_rate": 0.001,
|
| 438 |
+
"loss": 0.5732,
|
| 439 |
+
"step": 122
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 8.63,
|
| 443 |
+
"learning_rate": 0.001,
|
| 444 |
+
"loss": 0.6658,
|
| 445 |
+
"step": 124
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 8.77,
|
| 449 |
+
"learning_rate": 0.001,
|
| 450 |
+
"loss": 0.803,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 8.9,
|
| 455 |
+
"learning_rate": 0.001,
|
| 456 |
+
"loss": 0.5756,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 8.97,
|
| 461 |
+
"eval_loss": 3.146686553955078,
|
| 462 |
+
"eval_runtime": 14.3236,
|
| 463 |
+
"eval_samples_per_second": 23.597,
|
| 464 |
+
"eval_steps_per_second": 3.002,
|
| 465 |
+
"step": 129
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.04,
|
| 469 |
+
"learning_rate": 0.001,
|
| 470 |
+
"loss": 0.5221,
|
| 471 |
+
"step": 130
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.18,
|
| 475 |
+
"learning_rate": 0.001,
|
| 476 |
+
"loss": 0.4466,
|
| 477 |
+
"step": 132
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.32,
|
| 481 |
+
"learning_rate": 0.001,
|
| 482 |
+
"loss": 0.4909,
|
| 483 |
+
"step": 134
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.46,
|
| 487 |
+
"learning_rate": 0.001,
|
| 488 |
+
"loss": 0.4707,
|
| 489 |
+
"step": 136
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.6,
|
| 493 |
+
"learning_rate": 0.001,
|
| 494 |
+
"loss": 0.4588,
|
| 495 |
+
"step": 138
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 9.74,
|
| 499 |
+
"learning_rate": 0.001,
|
| 500 |
+
"loss": 0.4693,
|
| 501 |
+
"step": 140
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.88,
|
| 505 |
+
"learning_rate": 0.001,
|
| 506 |
+
"loss": 0.485,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 9.95,
|
| 511 |
+
"eval_loss": 3.2976272106170654,
|
| 512 |
+
"eval_runtime": 14.3283,
|
| 513 |
+
"eval_samples_per_second": 23.59,
|
| 514 |
+
"eval_steps_per_second": 3.001,
|
| 515 |
+
"step": 143
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 10.02,
|
| 519 |
+
"learning_rate": 0.001,
|
| 520 |
+
"loss": 0.4447,
|
| 521 |
+
"step": 144
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 10.16,
|
| 525 |
+
"learning_rate": 0.001,
|
| 526 |
+
"loss": 0.3447,
|
| 527 |
+
"step": 146
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 10.3,
|
| 531 |
+
"learning_rate": 0.001,
|
| 532 |
+
"loss": 0.3563,
|
| 533 |
+
"step": 148
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 10.43,
|
| 537 |
+
"learning_rate": 0.001,
|
| 538 |
+
"loss": 0.3578,
|
| 539 |
+
"step": 150
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 10.57,
|
| 543 |
+
"learning_rate": 0.001,
|
| 544 |
+
"loss": 0.3623,
|
| 545 |
+
"step": 152
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 10.71,
|
| 549 |
+
"learning_rate": 0.001,
|
| 550 |
+
"loss": 0.383,
|
| 551 |
+
"step": 154
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 10.85,
|
| 555 |
+
"learning_rate": 0.001,
|
| 556 |
+
"loss": 0.3717,
|
| 557 |
+
"step": 156
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 10.99,
|
| 561 |
+
"learning_rate": 0.001,
|
| 562 |
+
"loss": 0.4027,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 10.99,
|
| 567 |
+
"eval_loss": 3.8110954761505127,
|
| 568 |
+
"eval_runtime": 14.3426,
|
| 569 |
+
"eval_samples_per_second": 23.566,
|
| 570 |
+
"eval_steps_per_second": 2.998,
|
| 571 |
+
"step": 158
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 11.13,
|
| 575 |
+
"learning_rate": 0.001,
|
| 576 |
+
"loss": 0.2821,
|
| 577 |
+
"step": 160
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 11.27,
|
| 581 |
+
"learning_rate": 0.001,
|
| 582 |
+
"loss": 0.2735,
|
| 583 |
+
"step": 162
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 11.41,
|
| 587 |
+
"learning_rate": 0.001,
|
| 588 |
+
"loss": 0.3073,
|
| 589 |
+
"step": 164
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 11.55,
|
| 593 |
+
"learning_rate": 0.001,
|
| 594 |
+
"loss": 0.3386,
|
| 595 |
+
"step": 166
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 11.69,
|
| 599 |
+
"learning_rate": 0.001,
|
| 600 |
+
"loss": 0.3426,
|
| 601 |
+
"step": 168
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 11.83,
|
| 605 |
+
"learning_rate": 0.001,
|
| 606 |
+
"loss": 0.3111,
|
| 607 |
+
"step": 170
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 11.97,
|
| 611 |
+
"learning_rate": 0.001,
|
| 612 |
+
"loss": 0.2938,
|
| 613 |
+
"step": 172
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 11.97,
|
| 617 |
+
"eval_loss": 3.7330400943756104,
|
| 618 |
+
"eval_runtime": 14.3561,
|
| 619 |
+
"eval_samples_per_second": 23.544,
|
| 620 |
+
"eval_steps_per_second": 2.995,
|
| 621 |
+
"step": 172
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.1,
|
| 625 |
+
"learning_rate": 0.001,
|
| 626 |
+
"loss": 0.2443,
|
| 627 |
+
"step": 174
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 12.24,
|
| 631 |
+
"learning_rate": 0.001,
|
| 632 |
+
"loss": 0.2312,
|
| 633 |
+
"step": 176
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 12.38,
|
| 637 |
+
"learning_rate": 0.001,
|
| 638 |
+
"loss": 0.2253,
|
| 639 |
+
"step": 178
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.52,
|
| 643 |
+
"learning_rate": 0.001,
|
| 644 |
+
"loss": 0.243,
|
| 645 |
+
"step": 180
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 12.66,
|
| 649 |
+
"learning_rate": 0.001,
|
| 650 |
+
"loss": 0.2582,
|
| 651 |
+
"step": 182
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 12.8,
|
| 655 |
+
"learning_rate": 0.001,
|
| 656 |
+
"loss": 0.2449,
|
| 657 |
+
"step": 184
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 12.94,
|
| 661 |
+
"learning_rate": 0.001,
|
| 662 |
+
"loss": 0.2665,
|
| 663 |
+
"step": 186
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 12.94,
|
| 667 |
+
"eval_loss": 4.141729831695557,
|
| 668 |
+
"eval_runtime": 14.3523,
|
| 669 |
+
"eval_samples_per_second": 23.55,
|
| 670 |
+
"eval_steps_per_second": 2.996,
|
| 671 |
+
"step": 186
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 13.08,
|
| 675 |
+
"learning_rate": 0.001,
|
| 676 |
+
"loss": 0.2176,
|
| 677 |
+
"step": 188
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 13.22,
|
| 681 |
+
"learning_rate": 0.001,
|
| 682 |
+
"loss": 0.1728,
|
| 683 |
+
"step": 190
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 13.36,
|
| 687 |
+
"learning_rate": 0.001,
|
| 688 |
+
"loss": 0.1807,
|
| 689 |
+
"step": 192
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 13.5,
|
| 693 |
+
"learning_rate": 0.001,
|
| 694 |
+
"loss": 0.2002,
|
| 695 |
+
"step": 194
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 13.63,
|
| 699 |
+
"learning_rate": 0.001,
|
| 700 |
+
"loss": 0.1975,
|
| 701 |
+
"step": 196
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 13.77,
|
| 705 |
+
"learning_rate": 0.001,
|
| 706 |
+
"loss": 0.1973,
|
| 707 |
+
"step": 198
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 13.91,
|
| 711 |
+
"learning_rate": 0.001,
|
| 712 |
+
"loss": 0.2019,
|
| 713 |
+
"step": 200
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 13.98,
|
| 717 |
+
"eval_loss": 4.03155517578125,
|
| 718 |
+
"eval_runtime": 14.3514,
|
| 719 |
+
"eval_samples_per_second": 23.552,
|
| 720 |
+
"eval_steps_per_second": 2.996,
|
| 721 |
+
"step": 201
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 14.05,
|
| 725 |
+
"learning_rate": 0.001,
|
| 726 |
+
"loss": 0.19,
|
| 727 |
+
"step": 202
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 14.19,
|
| 731 |
+
"learning_rate": 0.001,
|
| 732 |
+
"loss": 0.1599,
|
| 733 |
+
"step": 204
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 14.33,
|
| 737 |
+
"learning_rate": 0.001,
|
| 738 |
+
"loss": 0.1647,
|
| 739 |
+
"step": 206
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 14.47,
|
| 743 |
+
"learning_rate": 0.001,
|
| 744 |
+
"loss": 0.1506,
|
| 745 |
+
"step": 208
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 14.61,
|
| 749 |
+
"learning_rate": 0.001,
|
| 750 |
+
"loss": 0.1551,
|
| 751 |
+
"step": 210
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 14.75,
|
| 755 |
+
"learning_rate": 0.001,
|
| 756 |
+
"loss": 0.1628,
|
| 757 |
+
"step": 212
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 14.89,
|
| 761 |
+
"learning_rate": 0.001,
|
| 762 |
+
"loss": 0.1706,
|
| 763 |
+
"step": 214
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 14.96,
|
| 767 |
+
"eval_loss": 4.135679244995117,
|
| 768 |
+
"eval_runtime": 14.348,
|
| 769 |
+
"eval_samples_per_second": 23.557,
|
| 770 |
+
"eval_steps_per_second": 2.997,
|
| 771 |
+
"step": 215
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 15.03,
|
| 775 |
+
"learning_rate": 0.001,
|
| 776 |
+
"loss": 0.1729,
|
| 777 |
+
"step": 216
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 15.17,
|
| 781 |
+
"learning_rate": 0.001,
|
| 782 |
+
"loss": 0.1421,
|
| 783 |
+
"step": 218
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 15.3,
|
| 787 |
+
"learning_rate": 0.001,
|
| 788 |
+
"loss": 0.1398,
|
| 789 |
+
"step": 220
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 15.44,
|
| 793 |
+
"learning_rate": 0.001,
|
| 794 |
+
"loss": 0.1377,
|
| 795 |
+
"step": 222
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 15.58,
|
| 799 |
+
"learning_rate": 0.001,
|
| 800 |
+
"loss": 0.1307,
|
| 801 |
+
"step": 224
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 15.72,
|
| 805 |
+
"learning_rate": 0.001,
|
| 806 |
+
"loss": 0.1284,
|
| 807 |
+
"step": 226
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 15.86,
|
| 811 |
+
"learning_rate": 0.001,
|
| 812 |
+
"loss": 0.1384,
|
| 813 |
+
"step": 228
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 16.0,
|
| 817 |
+
"learning_rate": 0.001,
|
| 818 |
+
"loss": 0.1418,
|
| 819 |
+
"step": 230
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 16.0,
|
| 823 |
+
"eval_loss": 4.10220193862915,
|
| 824 |
+
"eval_runtime": 14.3626,
|
| 825 |
+
"eval_samples_per_second": 23.533,
|
| 826 |
+
"eval_steps_per_second": 2.994,
|
| 827 |
+
"step": 230
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 16.14,
|
| 831 |
+
"learning_rate": 0.001,
|
| 832 |
+
"loss": 0.1085,
|
| 833 |
+
"step": 232
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 16.28,
|
| 837 |
+
"learning_rate": 0.001,
|
| 838 |
+
"loss": 0.1024,
|
| 839 |
+
"step": 234
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 16.42,
|
| 843 |
+
"learning_rate": 0.001,
|
| 844 |
+
"loss": 0.1073,
|
| 845 |
+
"step": 236
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 16.56,
|
| 849 |
+
"learning_rate": 0.001,
|
| 850 |
+
"loss": 0.1075,
|
| 851 |
+
"step": 238
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 16.7,
|
| 855 |
+
"learning_rate": 0.001,
|
| 856 |
+
"loss": 0.1193,
|
| 857 |
+
"step": 240
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 16.83,
|
| 861 |
+
"learning_rate": 0.001,
|
| 862 |
+
"loss": 0.1191,
|
| 863 |
+
"step": 242
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 16.97,
|
| 867 |
+
"learning_rate": 0.001,
|
| 868 |
+
"loss": 0.1286,
|
| 869 |
+
"step": 244
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 16.97,
|
| 873 |
+
"eval_loss": 4.119844436645508,
|
| 874 |
+
"eval_runtime": 14.3458,
|
| 875 |
+
"eval_samples_per_second": 23.561,
|
| 876 |
+
"eval_steps_per_second": 2.997,
|
| 877 |
+
"step": 244
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 17.11,
|
| 881 |
+
"learning_rate": 0.001,
|
| 882 |
+
"loss": 0.1073,
|
| 883 |
+
"step": 246
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 17.25,
|
| 887 |
+
"learning_rate": 0.001,
|
| 888 |
+
"loss": 0.0944,
|
| 889 |
+
"step": 248
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 17.39,
|
| 893 |
+
"learning_rate": 0.001,
|
| 894 |
+
"loss": 0.0973,
|
| 895 |
+
"step": 250
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 17.53,
|
| 899 |
+
"learning_rate": 0.001,
|
| 900 |
+
"loss": 0.0922,
|
| 901 |
+
"step": 252
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 17.67,
|
| 905 |
+
"learning_rate": 0.001,
|
| 906 |
+
"loss": 0.0969,
|
| 907 |
+
"step": 254
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 17.81,
|
| 911 |
+
"learning_rate": 0.001,
|
| 912 |
+
"loss": 0.096,
|
| 913 |
+
"step": 256
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 17.95,
|
| 917 |
+
"learning_rate": 0.001,
|
| 918 |
+
"loss": 0.1022,
|
| 919 |
+
"step": 258
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 17.95,
|
| 923 |
+
"eval_loss": 4.186199188232422,
|
| 924 |
+
"eval_runtime": 14.357,
|
| 925 |
+
"eval_samples_per_second": 23.543,
|
| 926 |
+
"eval_steps_per_second": 2.995,
|
| 927 |
+
"step": 258
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 18.09,
|
| 931 |
+
"learning_rate": 0.001,
|
| 932 |
+
"loss": 0.0902,
|
| 933 |
+
"step": 260
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 18.23,
|
| 937 |
+
"learning_rate": 0.001,
|
| 938 |
+
"loss": 0.083,
|
| 939 |
+
"step": 262
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 18.37,
|
| 943 |
+
"learning_rate": 0.001,
|
| 944 |
+
"loss": 0.0826,
|
| 945 |
+
"step": 264
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 18.5,
|
| 949 |
+
"learning_rate": 0.001,
|
| 950 |
+
"loss": 0.0955,
|
| 951 |
+
"step": 266
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 18.64,
|
| 955 |
+
"learning_rate": 0.001,
|
| 956 |
+
"loss": 0.0997,
|
| 957 |
+
"step": 268
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 18.78,
|
| 961 |
+
"learning_rate": 0.001,
|
| 962 |
+
"loss": 0.1227,
|
| 963 |
+
"step": 270
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 18.92,
|
| 967 |
+
"learning_rate": 0.001,
|
| 968 |
+
"loss": 0.1122,
|
| 969 |
+
"step": 272
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 18.99,
|
| 973 |
+
"eval_loss": 4.638622760772705,
|
| 974 |
+
"eval_runtime": 14.3606,
|
| 975 |
+
"eval_samples_per_second": 23.537,
|
| 976 |
+
"eval_steps_per_second": 2.994,
|
| 977 |
+
"step": 273
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 19.06,
|
| 981 |
+
"learning_rate": 0.001,
|
| 982 |
+
"loss": 0.0904,
|
| 983 |
+
"step": 274
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 19.2,
|
| 987 |
+
"learning_rate": 0.001,
|
| 988 |
+
"loss": 0.0891,
|
| 989 |
+
"step": 276
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 19.34,
|
| 993 |
+
"learning_rate": 0.001,
|
| 994 |
+
"loss": 0.0887,
|
| 995 |
+
"step": 278
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 19.48,
|
| 999 |
+
"learning_rate": 0.001,
|
| 1000 |
+
"loss": 0.0976,
|
| 1001 |
+
"step": 280
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 19.62,
|
| 1005 |
+
"learning_rate": 0.001,
|
| 1006 |
+
"loss": 0.1121,
|
| 1007 |
+
"step": 282
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 19.76,
|
| 1011 |
+
"learning_rate": 0.001,
|
| 1012 |
+
"loss": 0.09,
|
| 1013 |
+
"step": 284
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 19.9,
|
| 1017 |
+
"learning_rate": 0.001,
|
| 1018 |
+
"loss": 0.093,
|
| 1019 |
+
"step": 286
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 19.97,
|
| 1023 |
+
"eval_loss": 4.682866096496582,
|
| 1024 |
+
"eval_runtime": 14.3499,
|
| 1025 |
+
"eval_samples_per_second": 23.554,
|
| 1026 |
+
"eval_steps_per_second": 2.997,
|
| 1027 |
+
"step": 287
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 20.03,
|
| 1031 |
+
"learning_rate": 0.001,
|
| 1032 |
+
"loss": 0.0847,
|
| 1033 |
+
"step": 288
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 20.17,
|
| 1037 |
+
"learning_rate": 0.001,
|
| 1038 |
+
"loss": 0.0754,
|
| 1039 |
+
"step": 290
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 20.31,
|
| 1043 |
+
"learning_rate": 0.001,
|
| 1044 |
+
"loss": 0.0757,
|
| 1045 |
+
"step": 292
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 20.45,
|
| 1049 |
+
"learning_rate": 0.001,
|
| 1050 |
+
"loss": 0.0688,
|
| 1051 |
+
"step": 294
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 20.59,
|
| 1055 |
+
"learning_rate": 0.001,
|
| 1056 |
+
"loss": 0.0723,
|
| 1057 |
+
"step": 296
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 20.73,
|
| 1061 |
+
"learning_rate": 0.001,
|
| 1062 |
+
"loss": 0.079,
|
| 1063 |
+
"step": 298
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 20.87,
|
| 1067 |
+
"learning_rate": 0.001,
|
| 1068 |
+
"loss": 0.0783,
|
| 1069 |
+
"step": 300
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 20.94,
|
| 1073 |
+
"eval_loss": 4.663684844970703,
|
| 1074 |
+
"eval_runtime": 14.3504,
|
| 1075 |
+
"eval_samples_per_second": 23.553,
|
| 1076 |
+
"eval_steps_per_second": 2.996,
|
| 1077 |
+
"step": 301
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 21.01,
|
| 1081 |
+
"learning_rate": 0.001,
|
| 1082 |
+
"loss": 0.0779,
|
| 1083 |
+
"step": 302
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 21.15,
|
| 1087 |
+
"learning_rate": 0.001,
|
| 1088 |
+
"loss": 0.0648,
|
| 1089 |
+
"step": 304
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 21.29,
|
| 1093 |
+
"learning_rate": 0.001,
|
| 1094 |
+
"loss": 0.0594,
|
| 1095 |
+
"step": 306
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 21.43,
|
| 1099 |
+
"learning_rate": 0.001,
|
| 1100 |
+
"loss": 0.0644,
|
| 1101 |
+
"step": 308
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 21.57,
|
| 1105 |
+
"learning_rate": 0.001,
|
| 1106 |
+
"loss": 0.0682,
|
| 1107 |
+
"step": 310
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 21.7,
|
| 1111 |
+
"learning_rate": 0.001,
|
| 1112 |
+
"loss": 0.0702,
|
| 1113 |
+
"step": 312
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 21.84,
|
| 1117 |
+
"learning_rate": 0.001,
|
| 1118 |
+
"loss": 0.0686,
|
| 1119 |
+
"step": 314
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 21.98,
|
| 1123 |
+
"learning_rate": 0.001,
|
| 1124 |
+
"loss": 0.0698,
|
| 1125 |
+
"step": 316
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 21.98,
|
| 1129 |
+
"eval_loss": 4.718987941741943,
|
| 1130 |
+
"eval_runtime": 14.3394,
|
| 1131 |
+
"eval_samples_per_second": 23.571,
|
| 1132 |
+
"eval_steps_per_second": 2.999,
|
| 1133 |
+
"step": 316
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 22.12,
|
| 1137 |
+
"learning_rate": 0.001,
|
| 1138 |
+
"loss": 0.0702,
|
| 1139 |
+
"step": 318
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 22.26,
|
| 1143 |
+
"learning_rate": 0.001,
|
| 1144 |
+
"loss": 0.0713,
|
| 1145 |
+
"step": 320
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 22.4,
|
| 1149 |
+
"learning_rate": 0.001,
|
| 1150 |
+
"loss": 0.0606,
|
| 1151 |
+
"step": 322
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 22.54,
|
| 1155 |
+
"learning_rate": 0.001,
|
| 1156 |
+
"loss": 0.0599,
|
| 1157 |
+
"step": 324
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 22.68,
|
| 1161 |
+
"learning_rate": 0.001,
|
| 1162 |
+
"loss": 0.0652,
|
| 1163 |
+
"step": 326
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 22.82,
|
| 1167 |
+
"learning_rate": 0.001,
|
| 1168 |
+
"loss": 0.0643,
|
| 1169 |
+
"step": 328
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 22.96,
|
| 1173 |
+
"learning_rate": 0.001,
|
| 1174 |
+
"loss": 0.0688,
|
| 1175 |
+
"step": 330
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 22.96,
|
| 1179 |
+
"eval_loss": 5.020025253295898,
|
| 1180 |
+
"eval_runtime": 14.3306,
|
| 1181 |
+
"eval_samples_per_second": 23.586,
|
| 1182 |
+
"eval_steps_per_second": 3.001,
|
| 1183 |
+
"step": 330
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 23.1,
|
| 1187 |
+
"learning_rate": 0.001,
|
| 1188 |
+
"loss": 0.0584,
|
| 1189 |
+
"step": 332
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 23.23,
|
| 1193 |
+
"learning_rate": 0.001,
|
| 1194 |
+
"loss": 0.0565,
|
| 1195 |
+
"step": 334
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 23.37,
|
| 1199 |
+
"learning_rate": 0.001,
|
| 1200 |
+
"loss": 0.0551,
|
| 1201 |
+
"step": 336
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 23.51,
|
| 1205 |
+
"learning_rate": 0.001,
|
| 1206 |
+
"loss": 0.056,
|
| 1207 |
+
"step": 338
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 23.65,
|
| 1211 |
+
"learning_rate": 0.001,
|
| 1212 |
+
"loss": 0.0585,
|
| 1213 |
+
"step": 340
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 23.79,
|
| 1217 |
+
"learning_rate": 0.001,
|
| 1218 |
+
"loss": 0.0589,
|
| 1219 |
+
"step": 342
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 23.93,
|
| 1223 |
+
"learning_rate": 0.001,
|
| 1224 |
+
"loss": 0.0633,
|
| 1225 |
+
"step": 344
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 24.0,
|
| 1229 |
+
"eval_loss": 4.757626056671143,
|
| 1230 |
+
"eval_runtime": 14.3331,
|
| 1231 |
+
"eval_samples_per_second": 23.582,
|
| 1232 |
+
"eval_steps_per_second": 3.0,
|
| 1233 |
+
"step": 345
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 24.07,
|
| 1237 |
+
"learning_rate": 0.001,
|
| 1238 |
+
"loss": 0.0617,
|
| 1239 |
+
"step": 346
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 24.21,
|
| 1243 |
+
"learning_rate": 0.001,
|
| 1244 |
+
"loss": 0.0524,
|
| 1245 |
+
"step": 348
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 24.35,
|
| 1249 |
+
"learning_rate": 0.001,
|
| 1250 |
+
"loss": 0.0506,
|
| 1251 |
+
"step": 350
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 24.49,
|
| 1255 |
+
"learning_rate": 0.001,
|
| 1256 |
+
"loss": 0.0482,
|
| 1257 |
+
"step": 352
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 24.63,
|
| 1261 |
+
"learning_rate": 0.001,
|
| 1262 |
+
"loss": 0.0543,
|
| 1263 |
+
"step": 354
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 24.77,
|
| 1267 |
+
"learning_rate": 0.001,
|
| 1268 |
+
"loss": 0.0563,
|
| 1269 |
+
"step": 356
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 24.9,
|
| 1273 |
+
"learning_rate": 0.001,
|
| 1274 |
+
"loss": 0.0609,
|
| 1275 |
+
"step": 358
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 24.97,
|
| 1279 |
+
"eval_loss": 4.7804856300354,
|
| 1280 |
+
"eval_runtime": 14.3386,
|
| 1281 |
+
"eval_samples_per_second": 23.573,
|
| 1282 |
+
"eval_steps_per_second": 2.999,
|
| 1283 |
+
"step": 359
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 25.04,
|
| 1287 |
+
"learning_rate": 0.001,
|
| 1288 |
+
"loss": 0.054,
|
| 1289 |
+
"step": 360
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 25.18,
|
| 1293 |
+
"learning_rate": 0.001,
|
| 1294 |
+
"loss": 0.0577,
|
| 1295 |
+
"step": 362
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 25.32,
|
| 1299 |
+
"learning_rate": 0.001,
|
| 1300 |
+
"loss": 0.052,
|
| 1301 |
+
"step": 364
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 25.46,
|
| 1305 |
+
"learning_rate": 0.001,
|
| 1306 |
+
"loss": 0.0472,
|
| 1307 |
+
"step": 366
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 25.6,
|
| 1311 |
+
"learning_rate": 0.001,
|
| 1312 |
+
"loss": 0.0527,
|
| 1313 |
+
"step": 368
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 25.74,
|
| 1317 |
+
"learning_rate": 0.001,
|
| 1318 |
+
"loss": 0.0516,
|
| 1319 |
+
"step": 370
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 25.88,
|
| 1323 |
+
"learning_rate": 0.001,
|
| 1324 |
+
"loss": 0.0553,
|
| 1325 |
+
"step": 372
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 25.95,
|
| 1329 |
+
"eval_loss": 4.733786582946777,
|
| 1330 |
+
"eval_runtime": 14.3354,
|
| 1331 |
+
"eval_samples_per_second": 23.578,
|
| 1332 |
+
"eval_steps_per_second": 3.0,
|
| 1333 |
+
"step": 373
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 26.02,
|
| 1337 |
+
"learning_rate": 0.001,
|
| 1338 |
+
"loss": 0.0575,
|
| 1339 |
+
"step": 374
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 26.16,
|
| 1343 |
+
"learning_rate": 0.001,
|
| 1344 |
+
"loss": 0.0579,
|
| 1345 |
+
"step": 376
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 26.3,
|
| 1349 |
+
"learning_rate": 0.001,
|
| 1350 |
+
"loss": 0.0598,
|
| 1351 |
+
"step": 378
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 26.43,
|
| 1355 |
+
"learning_rate": 0.001,
|
| 1356 |
+
"loss": 0.0647,
|
| 1357 |
+
"step": 380
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 26.57,
|
| 1361 |
+
"learning_rate": 0.001,
|
| 1362 |
+
"loss": 0.0486,
|
| 1363 |
+
"step": 382
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 26.71,
|
| 1367 |
+
"learning_rate": 0.001,
|
| 1368 |
+
"loss": 0.0434,
|
| 1369 |
+
"step": 384
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 26.85,
|
| 1373 |
+
"learning_rate": 0.001,
|
| 1374 |
+
"loss": 0.0523,
|
| 1375 |
+
"step": 386
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 26.99,
|
| 1379 |
+
"learning_rate": 0.001,
|
| 1380 |
+
"loss": 0.0503,
|
| 1381 |
+
"step": 388
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 26.99,
|
| 1385 |
+
"eval_loss": 5.140863418579102,
|
| 1386 |
+
"eval_runtime": 14.327,
|
| 1387 |
+
"eval_samples_per_second": 23.592,
|
| 1388 |
+
"eval_steps_per_second": 3.001,
|
| 1389 |
+
"step": 388
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 27.13,
|
| 1393 |
+
"learning_rate": 0.001,
|
| 1394 |
+
"loss": 0.0393,
|
| 1395 |
+
"step": 390
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 27.27,
|
| 1399 |
+
"learning_rate": 0.001,
|
| 1400 |
+
"loss": 0.038,
|
| 1401 |
+
"step": 392
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 27.41,
|
| 1405 |
+
"learning_rate": 0.001,
|
| 1406 |
+
"loss": 0.0407,
|
| 1407 |
+
"step": 394
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 27.55,
|
| 1411 |
+
"learning_rate": 0.001,
|
| 1412 |
+
"loss": 0.0417,
|
| 1413 |
+
"step": 396
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 27.69,
|
| 1417 |
+
"learning_rate": 0.001,
|
| 1418 |
+
"loss": 0.0437,
|
| 1419 |
+
"step": 398
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 27.83,
|
| 1423 |
+
"learning_rate": 0.001,
|
| 1424 |
+
"loss": 0.0448,
|
| 1425 |
+
"step": 400
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 27.97,
|
| 1429 |
+
"learning_rate": 0.001,
|
| 1430 |
+
"loss": 0.0471,
|
| 1431 |
+
"step": 402
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 27.97,
|
| 1435 |
+
"eval_loss": 5.14629602432251,
|
| 1436 |
+
"eval_runtime": 14.3389,
|
| 1437 |
+
"eval_samples_per_second": 23.572,
|
| 1438 |
+
"eval_steps_per_second": 2.999,
|
| 1439 |
+
"step": 402
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 28.1,
|
| 1443 |
+
"learning_rate": 0.001,
|
| 1444 |
+
"loss": 0.041,
|
| 1445 |
+
"step": 404
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 28.24,
|
| 1449 |
+
"learning_rate": 0.001,
|
| 1450 |
+
"loss": 0.0391,
|
| 1451 |
+
"step": 406
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 28.38,
|
| 1455 |
+
"learning_rate": 0.001,
|
| 1456 |
+
"loss": 0.0429,
|
| 1457 |
+
"step": 408
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 28.52,
|
| 1461 |
+
"learning_rate": 0.001,
|
| 1462 |
+
"loss": 0.0472,
|
| 1463 |
+
"step": 410
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 28.66,
|
| 1467 |
+
"learning_rate": 0.001,
|
| 1468 |
+
"loss": 0.0458,
|
| 1469 |
+
"step": 412
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 28.8,
|
| 1473 |
+
"learning_rate": 0.001,
|
| 1474 |
+
"loss": 0.0451,
|
| 1475 |
+
"step": 414
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 28.94,
|
| 1479 |
+
"learning_rate": 0.001,
|
| 1480 |
+
"loss": 0.0472,
|
| 1481 |
+
"step": 416
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 28.94,
|
| 1485 |
+
"eval_loss": 5.163626194000244,
|
| 1486 |
+
"eval_runtime": 14.3465,
|
| 1487 |
+
"eval_samples_per_second": 23.56,
|
| 1488 |
+
"eval_steps_per_second": 2.997,
|
| 1489 |
+
"step": 416
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 29.08,
|
| 1493 |
+
"learning_rate": 0.001,
|
| 1494 |
+
"loss": 0.0403,
|
| 1495 |
+
"step": 418
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 29.22,
|
| 1499 |
+
"learning_rate": 0.001,
|
| 1500 |
+
"loss": 0.0376,
|
| 1501 |
+
"step": 420
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 29.22,
|
| 1505 |
+
"eval_loss": 5.132218360900879,
|
| 1506 |
+
"eval_runtime": 14.3004,
|
| 1507 |
+
"eval_samples_per_second": 23.636,
|
| 1508 |
+
"eval_steps_per_second": 3.007,
|
| 1509 |
+
"step": 420
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 29.22,
|
| 1513 |
+
"step": 420,
|
| 1514 |
+
"total_flos": 8.206795539988808e+17,
|
| 1515 |
+
"train_loss": 0.5600467140298514,
|
| 1516 |
+
"train_runtime": 18789.4517,
|
| 1517 |
+
"train_samples_per_second": 5.864,
|
| 1518 |
+
"train_steps_per_second": 0.022
|
| 1519 |
+
}
|
| 1520 |
+
],
|
| 1521 |
+
"logging_steps": 2,
|
| 1522 |
+
"max_steps": 420,
|
| 1523 |
+
"num_input_tokens_seen": 0,
|
| 1524 |
+
"num_train_epochs": 30,
|
| 1525 |
+
"save_steps": 500,
|
| 1526 |
+
"total_flos": 8.206795539988808e+17,
|
| 1527 |
+
"train_batch_size": 8,
|
| 1528 |
+
"trial_name": null,
|
| 1529 |
+
"trial_params": null
|
| 1530 |
+
}
|