Commit
•
52d9354
1
Parent(s):
59081f4
End of training
Browse files- README.md +16 -5
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +780 -0
README.md
CHANGED
|
@@ -1,13 +1,24 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
base_model: facebook/bart-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: bart-base-finetuned-xe_ey_fae
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,10 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# bart-base-finetuned-xe_ey_fae
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: facebook/bart-base
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- datasets/all_binary_and_xe_ey_fae_counterfactual
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: bart-base-finetuned-xe_ey_fae
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Masked Language Modeling
|
| 14 |
+
type: fill-mask
|
| 15 |
+
dataset:
|
| 16 |
+
name: datasets/all_binary_and_xe_ey_fae_counterfactual
|
| 17 |
+
type: datasets/all_binary_and_xe_ey_fae_counterfactual
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Accuracy
|
| 20 |
+
type: accuracy
|
| 21 |
+
value: 0.7180178883360112
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 26 |
|
| 27 |
# bart-base-finetuned-xe_ey_fae
|
| 28 |
|
| 29 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the datasets/all_binary_and_xe_ey_fae_counterfactual dataset.
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
+
- Loss: 1.3945
|
| 32 |
+
- Accuracy: 0.7180
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7180178883360112,
|
| 4 |
+
"eval_loss": 1.3944889307022095,
|
| 5 |
+
"eval_runtime": 95.1252,
|
| 6 |
+
"eval_samples": 16928,
|
| 7 |
+
"eval_samples_per_second": 177.955,
|
| 8 |
+
"eval_steps_per_second": 22.244,
|
| 9 |
+
"perplexity": 4.032912947872197,
|
| 10 |
+
"train_loss": 2.057705193860182,
|
| 11 |
+
"train_runtime": 15314.6638,
|
| 12 |
+
"train_samples": 135339,
|
| 13 |
+
"train_samples_per_second": 26.512,
|
| 14 |
+
"train_steps_per_second": 1.657
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7180178883360112,
|
| 4 |
+
"eval_loss": 1.3944889307022095,
|
| 5 |
+
"eval_runtime": 95.1252,
|
| 6 |
+
"eval_samples": 16928,
|
| 7 |
+
"eval_samples_per_second": 177.955,
|
| 8 |
+
"eval_steps_per_second": 22.244,
|
| 9 |
+
"perplexity": 4.032912947872197
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.057705193860182,
|
| 4 |
+
"train_runtime": 15314.6638,
|
| 5 |
+
"train_samples": 135339,
|
| 6 |
+
"train_samples_per_second": 26.512,
|
| 7 |
+
"train_steps_per_second": 1.657
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,780 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3909834623336792,
|
| 3 |
+
"best_model_checkpoint": "finetuning/output/bart-base-finetuned_xe_ey_fae/checkpoint-25000",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 25377,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 9.804547424833511e-06,
|
| 14 |
+
"loss": 5.4226,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"eval_accuracy": 0.3627901941481408,
|
| 20 |
+
"eval_loss": 3.8137550354003906,
|
| 21 |
+
"eval_runtime": 98.6024,
|
| 22 |
+
"eval_samples_per_second": 171.679,
|
| 23 |
+
"eval_steps_per_second": 21.46,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12,
|
| 28 |
+
"learning_rate": 9.607518619222132e-06,
|
| 29 |
+
"loss": 4.0408,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12,
|
| 34 |
+
"eval_accuracy": 0.46300121473546585,
|
| 35 |
+
"eval_loss": 3.057621717453003,
|
| 36 |
+
"eval_runtime": 99.414,
|
| 37 |
+
"eval_samples_per_second": 170.278,
|
| 38 |
+
"eval_steps_per_second": 21.285,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.18,
|
| 43 |
+
"learning_rate": 9.41048981361075e-06,
|
| 44 |
+
"loss": 3.4979,
|
| 45 |
+
"step": 1500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.18,
|
| 49 |
+
"eval_accuracy": 0.5132904448434071,
|
| 50 |
+
"eval_loss": 2.70158314704895,
|
| 51 |
+
"eval_runtime": 99.9098,
|
| 52 |
+
"eval_samples_per_second": 169.433,
|
| 53 |
+
"eval_steps_per_second": 21.179,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.24,
|
| 58 |
+
"learning_rate": 9.21346100799937e-06,
|
| 59 |
+
"loss": 3.1691,
|
| 60 |
+
"step": 2000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.24,
|
| 64 |
+
"eval_accuracy": 0.5430825323065444,
|
| 65 |
+
"eval_loss": 2.4879872798919678,
|
| 66 |
+
"eval_runtime": 99.733,
|
| 67 |
+
"eval_samples_per_second": 169.733,
|
| 68 |
+
"eval_steps_per_second": 21.217,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.3,
|
| 73 |
+
"learning_rate": 9.01643220238799e-06,
|
| 74 |
+
"loss": 2.9564,
|
| 75 |
+
"step": 2500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.3,
|
| 79 |
+
"eval_accuracy": 0.5644360825553116,
|
| 80 |
+
"eval_loss": 2.330946445465088,
|
| 81 |
+
"eval_runtime": 100.0932,
|
| 82 |
+
"eval_samples_per_second": 169.122,
|
| 83 |
+
"eval_steps_per_second": 21.14,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.35,
|
| 88 |
+
"learning_rate": 8.819797454387831e-06,
|
| 89 |
+
"loss": 2.8078,
|
| 90 |
+
"step": 3000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.35,
|
| 94 |
+
"eval_accuracy": 0.5792018144043999,
|
| 95 |
+
"eval_loss": 2.232025384902954,
|
| 96 |
+
"eval_runtime": 100.0923,
|
| 97 |
+
"eval_samples_per_second": 169.124,
|
| 98 |
+
"eval_steps_per_second": 21.14,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.41,
|
| 103 |
+
"learning_rate": 8.622768648776452e-06,
|
| 104 |
+
"loss": 2.6741,
|
| 105 |
+
"step": 3500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.41,
|
| 109 |
+
"eval_accuracy": 0.592379386392151,
|
| 110 |
+
"eval_loss": 2.1506171226501465,
|
| 111 |
+
"eval_runtime": 99.9507,
|
| 112 |
+
"eval_samples_per_second": 169.364,
|
| 113 |
+
"eval_steps_per_second": 21.17,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.47,
|
| 118 |
+
"learning_rate": 8.425739843165071e-06,
|
| 119 |
+
"loss": 2.5323,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.47,
|
| 124 |
+
"eval_accuracy": 0.617633758132823,
|
| 125 |
+
"eval_loss": 1.9845681190490723,
|
| 126 |
+
"eval_runtime": 100.0279,
|
| 127 |
+
"eval_samples_per_second": 169.233,
|
| 128 |
+
"eval_steps_per_second": 21.154,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.53,
|
| 133 |
+
"learning_rate": 8.22871103755369e-06,
|
| 134 |
+
"loss": 2.3678,
|
| 135 |
+
"step": 4500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.53,
|
| 139 |
+
"eval_accuracy": 0.6374534268418744,
|
| 140 |
+
"eval_loss": 1.8812607526779175,
|
| 141 |
+
"eval_runtime": 100.101,
|
| 142 |
+
"eval_samples_per_second": 169.109,
|
| 143 |
+
"eval_steps_per_second": 21.139,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.59,
|
| 148 |
+
"learning_rate": 8.03168223194231e-06,
|
| 149 |
+
"loss": 2.25,
|
| 150 |
+
"step": 5000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.59,
|
| 154 |
+
"eval_accuracy": 0.6496838449438552,
|
| 155 |
+
"eval_loss": 1.809983253479004,
|
| 156 |
+
"eval_runtime": 100.2479,
|
| 157 |
+
"eval_samples_per_second": 168.861,
|
| 158 |
+
"eval_steps_per_second": 21.108,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.65,
|
| 163 |
+
"learning_rate": 7.83465342633093e-06,
|
| 164 |
+
"loss": 2.1795,
|
| 165 |
+
"step": 5500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.65,
|
| 169 |
+
"eval_accuracy": 0.6579494225370981,
|
| 170 |
+
"eval_loss": 1.7632389068603516,
|
| 171 |
+
"eval_runtime": 100.0951,
|
| 172 |
+
"eval_samples_per_second": 169.119,
|
| 173 |
+
"eval_steps_per_second": 21.14,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.71,
|
| 178 |
+
"learning_rate": 7.63762462071955e-06,
|
| 179 |
+
"loss": 2.1203,
|
| 180 |
+
"step": 6000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.71,
|
| 184 |
+
"eval_accuracy": 0.664559097259069,
|
| 185 |
+
"eval_loss": 1.7238309383392334,
|
| 186 |
+
"eval_runtime": 99.9087,
|
| 187 |
+
"eval_samples_per_second": 169.435,
|
| 188 |
+
"eval_steps_per_second": 21.179,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.77,
|
| 193 |
+
"learning_rate": 7.440595815108169e-06,
|
| 194 |
+
"loss": 2.0764,
|
| 195 |
+
"step": 6500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.77,
|
| 199 |
+
"eval_accuracy": 0.6713205569113848,
|
| 200 |
+
"eval_loss": 1.6855953931808472,
|
| 201 |
+
"eval_runtime": 100.047,
|
| 202 |
+
"eval_samples_per_second": 169.201,
|
| 203 |
+
"eval_steps_per_second": 21.15,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.83,
|
| 208 |
+
"learning_rate": 7.2435670094967895e-06,
|
| 209 |
+
"loss": 2.026,
|
| 210 |
+
"step": 7000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.83,
|
| 214 |
+
"eval_accuracy": 0.6759595736369565,
|
| 215 |
+
"eval_loss": 1.6568557024002075,
|
| 216 |
+
"eval_runtime": 99.903,
|
| 217 |
+
"eval_samples_per_second": 169.444,
|
| 218 |
+
"eval_steps_per_second": 21.181,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.89,
|
| 223 |
+
"learning_rate": 7.046932261496632e-06,
|
| 224 |
+
"loss": 1.9942,
|
| 225 |
+
"step": 7500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.89,
|
| 229 |
+
"eval_accuracy": 0.6803347736385223,
|
| 230 |
+
"eval_loss": 1.6309233903884888,
|
| 231 |
+
"eval_runtime": 100.1047,
|
| 232 |
+
"eval_samples_per_second": 169.103,
|
| 233 |
+
"eval_steps_per_second": 21.138,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.95,
|
| 238 |
+
"learning_rate": 6.849903455885251e-06,
|
| 239 |
+
"loss": 1.9665,
|
| 240 |
+
"step": 8000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.95,
|
| 244 |
+
"eval_accuracy": 0.6836478246699454,
|
| 245 |
+
"eval_loss": 1.612231731414795,
|
| 246 |
+
"eval_runtime": 206.2817,
|
| 247 |
+
"eval_samples_per_second": 82.063,
|
| 248 |
+
"eval_steps_per_second": 10.258,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0,
|
| 253 |
+
"learning_rate": 6.652874650273871e-06,
|
| 254 |
+
"loss": 1.9395,
|
| 255 |
+
"step": 8500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0,
|
| 259 |
+
"eval_accuracy": 0.6866433413548132,
|
| 260 |
+
"eval_loss": 1.5912940502166748,
|
| 261 |
+
"eval_runtime": 206.5703,
|
| 262 |
+
"eval_samples_per_second": 81.948,
|
| 263 |
+
"eval_steps_per_second": 10.243,
|
| 264 |
+
"step": 8500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.06,
|
| 268 |
+
"learning_rate": 6.455845844662491e-06,
|
| 269 |
+
"loss": 1.9155,
|
| 270 |
+
"step": 9000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.06,
|
| 274 |
+
"eval_accuracy": 0.6894629039599454,
|
| 275 |
+
"eval_loss": 1.5758066177368164,
|
| 276 |
+
"eval_runtime": 206.7537,
|
| 277 |
+
"eval_samples_per_second": 81.875,
|
| 278 |
+
"eval_steps_per_second": 10.234,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.12,
|
| 283 |
+
"learning_rate": 6.25881703905111e-06,
|
| 284 |
+
"loss": 1.8828,
|
| 285 |
+
"step": 9500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.12,
|
| 289 |
+
"eval_accuracy": 0.6918324332777558,
|
| 290 |
+
"eval_loss": 1.5607072114944458,
|
| 291 |
+
"eval_runtime": 203.7553,
|
| 292 |
+
"eval_samples_per_second": 83.08,
|
| 293 |
+
"eval_steps_per_second": 10.385,
|
| 294 |
+
"step": 9500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.18,
|
| 298 |
+
"learning_rate": 6.06178823343973e-06,
|
| 299 |
+
"loss": 1.8721,
|
| 300 |
+
"step": 10000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.18,
|
| 304 |
+
"eval_accuracy": 0.6948063170580184,
|
| 305 |
+
"eval_loss": 1.5421587228775024,
|
| 306 |
+
"eval_runtime": 205.9617,
|
| 307 |
+
"eval_samples_per_second": 82.19,
|
| 308 |
+
"eval_steps_per_second": 10.274,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.24,
|
| 313 |
+
"learning_rate": 5.8647594278283496e-06,
|
| 314 |
+
"loss": 1.8474,
|
| 315 |
+
"step": 10500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.24,
|
| 319 |
+
"eval_accuracy": 0.6963892745418871,
|
| 320 |
+
"eval_loss": 1.5320152044296265,
|
| 321 |
+
"eval_runtime": 206.4027,
|
| 322 |
+
"eval_samples_per_second": 82.014,
|
| 323 |
+
"eval_steps_per_second": 10.252,
|
| 324 |
+
"step": 10500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.3,
|
| 328 |
+
"learning_rate": 5.667730622216968e-06,
|
| 329 |
+
"loss": 1.8293,
|
| 330 |
+
"step": 11000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.3,
|
| 334 |
+
"eval_accuracy": 0.6978303363523796,
|
| 335 |
+
"eval_loss": 1.5213782787322998,
|
| 336 |
+
"eval_runtime": 206.4515,
|
| 337 |
+
"eval_samples_per_second": 81.995,
|
| 338 |
+
"eval_steps_per_second": 10.249,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.36,
|
| 343 |
+
"learning_rate": 5.471095874216811e-06,
|
| 344 |
+
"loss": 1.8129,
|
| 345 |
+
"step": 11500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.36,
|
| 349 |
+
"eval_accuracy": 0.6997515674908317,
|
| 350 |
+
"eval_loss": 1.5102019309997559,
|
| 351 |
+
"eval_runtime": 203.4625,
|
| 352 |
+
"eval_samples_per_second": 83.2,
|
| 353 |
+
"eval_steps_per_second": 10.4,
|
| 354 |
+
"step": 11500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.42,
|
| 358 |
+
"learning_rate": 5.274067068605431e-06,
|
| 359 |
+
"loss": 1.8148,
|
| 360 |
+
"step": 12000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.42,
|
| 364 |
+
"eval_accuracy": 0.7013130680794967,
|
| 365 |
+
"eval_loss": 1.5009928941726685,
|
| 366 |
+
"eval_runtime": 206.7456,
|
| 367 |
+
"eval_samples_per_second": 81.878,
|
| 368 |
+
"eval_steps_per_second": 10.235,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.48,
|
| 373 |
+
"learning_rate": 5.077038262994051e-06,
|
| 374 |
+
"loss": 1.7903,
|
| 375 |
+
"step": 12500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.48,
|
| 379 |
+
"eval_accuracy": 0.7037519606361885,
|
| 380 |
+
"eval_loss": 1.484366774559021,
|
| 381 |
+
"eval_runtime": 207.0125,
|
| 382 |
+
"eval_samples_per_second": 81.773,
|
| 383 |
+
"eval_steps_per_second": 10.222,
|
| 384 |
+
"step": 12500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.54,
|
| 388 |
+
"learning_rate": 4.88000945738267e-06,
|
| 389 |
+
"loss": 1.7815,
|
| 390 |
+
"step": 13000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.54,
|
| 394 |
+
"eval_accuracy": 0.7039102273054718,
|
| 395 |
+
"eval_loss": 1.4823458194732666,
|
| 396 |
+
"eval_runtime": 206.0669,
|
| 397 |
+
"eval_samples_per_second": 82.148,
|
| 398 |
+
"eval_steps_per_second": 10.269,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.6,
|
| 403 |
+
"learning_rate": 4.68298065177129e-06,
|
| 404 |
+
"loss": 1.7637,
|
| 405 |
+
"step": 13500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.6,
|
| 409 |
+
"eval_accuracy": 0.705173223800616,
|
| 410 |
+
"eval_loss": 1.4746402502059937,
|
| 411 |
+
"eval_runtime": 202.4173,
|
| 412 |
+
"eval_samples_per_second": 83.629,
|
| 413 |
+
"eval_steps_per_second": 10.454,
|
| 414 |
+
"step": 13500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.66,
|
| 418 |
+
"learning_rate": 4.485951846159909e-06,
|
| 419 |
+
"loss": 1.7623,
|
| 420 |
+
"step": 14000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.66,
|
| 424 |
+
"eval_accuracy": 0.706123367116372,
|
| 425 |
+
"eval_loss": 1.470130205154419,
|
| 426 |
+
"eval_runtime": 205.8377,
|
| 427 |
+
"eval_samples_per_second": 82.24,
|
| 428 |
+
"eval_steps_per_second": 10.28,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.71,
|
| 433 |
+
"learning_rate": 4.289317098159752e-06,
|
| 434 |
+
"loss": 1.7402,
|
| 435 |
+
"step": 14500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.71,
|
| 439 |
+
"eval_accuracy": 0.7075649407306767,
|
| 440 |
+
"eval_loss": 1.4597938060760498,
|
| 441 |
+
"eval_runtime": 206.177,
|
| 442 |
+
"eval_samples_per_second": 82.104,
|
| 443 |
+
"eval_steps_per_second": 10.263,
|
| 444 |
+
"step": 14500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.77,
|
| 448 |
+
"learning_rate": 4.092288292548371e-06,
|
| 449 |
+
"loss": 1.7376,
|
| 450 |
+
"step": 15000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.77,
|
| 454 |
+
"eval_accuracy": 0.7089666967285505,
|
| 455 |
+
"eval_loss": 1.451911449432373,
|
| 456 |
+
"eval_runtime": 206.3085,
|
| 457 |
+
"eval_samples_per_second": 82.052,
|
| 458 |
+
"eval_steps_per_second": 10.256,
|
| 459 |
+
"step": 15000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.83,
|
| 463 |
+
"learning_rate": 3.89525948693699e-06,
|
| 464 |
+
"loss": 1.7287,
|
| 465 |
+
"step": 15500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.83,
|
| 469 |
+
"eval_accuracy": 0.7101150715078346,
|
| 470 |
+
"eval_loss": 1.4501255750656128,
|
| 471 |
+
"eval_runtime": 100.0594,
|
| 472 |
+
"eval_samples_per_second": 169.18,
|
| 473 |
+
"eval_steps_per_second": 21.147,
|
| 474 |
+
"step": 15500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.89,
|
| 478 |
+
"learning_rate": 3.6982306813256103e-06,
|
| 479 |
+
"loss": 1.7273,
|
| 480 |
+
"step": 16000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.89,
|
| 484 |
+
"eval_accuracy": 0.7106747872019036,
|
| 485 |
+
"eval_loss": 1.4408985376358032,
|
| 486 |
+
"eval_runtime": 100.2351,
|
| 487 |
+
"eval_samples_per_second": 168.883,
|
| 488 |
+
"eval_steps_per_second": 21.11,
|
| 489 |
+
"step": 16000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.95,
|
| 493 |
+
"learning_rate": 3.5012018757142298e-06,
|
| 494 |
+
"loss": 1.7119,
|
| 495 |
+
"step": 16500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.95,
|
| 499 |
+
"eval_accuracy": 0.7125312598082394,
|
| 500 |
+
"eval_loss": 1.431384563446045,
|
| 501 |
+
"eval_runtime": 100.206,
|
| 502 |
+
"eval_samples_per_second": 168.932,
|
| 503 |
+
"eval_steps_per_second": 21.117,
|
| 504 |
+
"step": 16500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.01,
|
| 508 |
+
"learning_rate": 3.3045671277140724e-06,
|
| 509 |
+
"loss": 1.7098,
|
| 510 |
+
"step": 17000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.01,
|
| 514 |
+
"eval_accuracy": 0.712873669928985,
|
| 515 |
+
"eval_loss": 1.4268542528152466,
|
| 516 |
+
"eval_runtime": 99.9713,
|
| 517 |
+
"eval_samples_per_second": 169.329,
|
| 518 |
+
"eval_steps_per_second": 21.166,
|
| 519 |
+
"step": 17000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.07,
|
| 523 |
+
"learning_rate": 3.1075383221026915e-06,
|
| 524 |
+
"loss": 1.6978,
|
| 525 |
+
"step": 17500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.07,
|
| 529 |
+
"eval_accuracy": 0.7132452679915875,
|
| 530 |
+
"eval_loss": 1.4275221824645996,
|
| 531 |
+
"eval_runtime": 100.0415,
|
| 532 |
+
"eval_samples_per_second": 169.21,
|
| 533 |
+
"eval_steps_per_second": 21.151,
|
| 534 |
+
"step": 17500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.13,
|
| 538 |
+
"learning_rate": 2.910509516491311e-06,
|
| 539 |
+
"loss": 1.698,
|
| 540 |
+
"step": 18000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.13,
|
| 544 |
+
"eval_accuracy": 0.7139832935058783,
|
| 545 |
+
"eval_loss": 1.421799898147583,
|
| 546 |
+
"eval_runtime": 100.2878,
|
| 547 |
+
"eval_samples_per_second": 168.794,
|
| 548 |
+
"eval_steps_per_second": 21.099,
|
| 549 |
+
"step": 18000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.19,
|
| 553 |
+
"learning_rate": 2.713480710879931e-06,
|
| 554 |
+
"loss": 1.6837,
|
| 555 |
+
"step": 18500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.19,
|
| 559 |
+
"eval_accuracy": 0.7146896815582429,
|
| 560 |
+
"eval_loss": 1.4150662422180176,
|
| 561 |
+
"eval_runtime": 100.1729,
|
| 562 |
+
"eval_samples_per_second": 168.988,
|
| 563 |
+
"eval_steps_per_second": 21.123,
|
| 564 |
+
"step": 18500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.25,
|
| 568 |
+
"learning_rate": 2.5164519052685504e-06,
|
| 569 |
+
"loss": 1.6908,
|
| 570 |
+
"step": 19000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.25,
|
| 574 |
+
"eval_accuracy": 0.7148777636104067,
|
| 575 |
+
"eval_loss": 1.413697361946106,
|
| 576 |
+
"eval_runtime": 100.0403,
|
| 577 |
+
"eval_samples_per_second": 169.212,
|
| 578 |
+
"eval_steps_per_second": 21.151,
|
| 579 |
+
"step": 19000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.31,
|
| 583 |
+
"learning_rate": 2.3194230996571703e-06,
|
| 584 |
+
"loss": 1.6902,
|
| 585 |
+
"step": 19500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.31,
|
| 589 |
+
"eval_accuracy": 0.7161167332062431,
|
| 590 |
+
"eval_loss": 1.4084678888320923,
|
| 591 |
+
"eval_runtime": 99.9514,
|
| 592 |
+
"eval_samples_per_second": 169.362,
|
| 593 |
+
"eval_steps_per_second": 21.17,
|
| 594 |
+
"step": 19500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.36,
|
| 598 |
+
"learning_rate": 2.12239429404579e-06,
|
| 599 |
+
"loss": 1.6741,
|
| 600 |
+
"step": 20000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.36,
|
| 604 |
+
"eval_accuracy": 0.7153571848548731,
|
| 605 |
+
"eval_loss": 1.4121222496032715,
|
| 606 |
+
"eval_runtime": 99.7721,
|
| 607 |
+
"eval_samples_per_second": 169.667,
|
| 608 |
+
"eval_steps_per_second": 21.208,
|
| 609 |
+
"step": 20000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.42,
|
| 613 |
+
"learning_rate": 1.925759546045632e-06,
|
| 614 |
+
"loss": 1.6823,
|
| 615 |
+
"step": 20500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.42,
|
| 619 |
+
"eval_accuracy": 0.7164751883355099,
|
| 620 |
+
"eval_loss": 1.4036943912506104,
|
| 621 |
+
"eval_runtime": 96.9786,
|
| 622 |
+
"eval_samples_per_second": 174.554,
|
| 623 |
+
"eval_steps_per_second": 21.819,
|
| 624 |
+
"step": 20500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.48,
|
| 628 |
+
"learning_rate": 1.7287307404342515e-06,
|
| 629 |
+
"loss": 1.6692,
|
| 630 |
+
"step": 21000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.48,
|
| 634 |
+
"eval_accuracy": 0.7164227335870778,
|
| 635 |
+
"eval_loss": 1.4038887023925781,
|
| 636 |
+
"eval_runtime": 96.6299,
|
| 637 |
+
"eval_samples_per_second": 175.184,
|
| 638 |
+
"eval_steps_per_second": 21.898,
|
| 639 |
+
"step": 21000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.54,
|
| 643 |
+
"learning_rate": 1.5317019348228712e-06,
|
| 644 |
+
"loss": 1.6669,
|
| 645 |
+
"step": 21500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.54,
|
| 649 |
+
"eval_accuracy": 0.7171810007042829,
|
| 650 |
+
"eval_loss": 1.4014757871627808,
|
| 651 |
+
"eval_runtime": 96.5289,
|
| 652 |
+
"eval_samples_per_second": 175.367,
|
| 653 |
+
"eval_steps_per_second": 21.921,
|
| 654 |
+
"step": 21500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.6,
|
| 658 |
+
"learning_rate": 1.334673129211491e-06,
|
| 659 |
+
"loss": 1.6613,
|
| 660 |
+
"step": 22000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.6,
|
| 664 |
+
"eval_accuracy": 0.7179443895145537,
|
| 665 |
+
"eval_loss": 1.3979177474975586,
|
| 666 |
+
"eval_runtime": 96.4739,
|
| 667 |
+
"eval_samples_per_second": 175.467,
|
| 668 |
+
"eval_steps_per_second": 21.933,
|
| 669 |
+
"step": 22000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.66,
|
| 673 |
+
"learning_rate": 1.1376443236001104e-06,
|
| 674 |
+
"loss": 1.664,
|
| 675 |
+
"step": 22500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.66,
|
| 679 |
+
"eval_accuracy": 0.7180417425737022,
|
| 680 |
+
"eval_loss": 1.3960251808166504,
|
| 681 |
+
"eval_runtime": 96.2769,
|
| 682 |
+
"eval_samples_per_second": 175.826,
|
| 683 |
+
"eval_steps_per_second": 21.978,
|
| 684 |
+
"step": 22500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.72,
|
| 688 |
+
"learning_rate": 9.406155179887299e-07,
|
| 689 |
+
"loss": 1.6615,
|
| 690 |
+
"step": 23000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.72,
|
| 694 |
+
"eval_accuracy": 0.71719773048631,
|
| 695 |
+
"eval_loss": 1.4012339115142822,
|
| 696 |
+
"eval_runtime": 96.2915,
|
| 697 |
+
"eval_samples_per_second": 175.8,
|
| 698 |
+
"eval_steps_per_second": 21.975,
|
| 699 |
+
"step": 23000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.78,
|
| 703 |
+
"learning_rate": 7.435867123773496e-07,
|
| 704 |
+
"loss": 1.6627,
|
| 705 |
+
"step": 23500
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.78,
|
| 709 |
+
"eval_accuracy": 0.7177754487686726,
|
| 710 |
+
"eval_loss": 1.3974287509918213,
|
| 711 |
+
"eval_runtime": 96.2242,
|
| 712 |
+
"eval_samples_per_second": 175.922,
|
| 713 |
+
"eval_steps_per_second": 21.99,
|
| 714 |
+
"step": 23500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.84,
|
| 718 |
+
"learning_rate": 5.465579067659692e-07,
|
| 719 |
+
"loss": 1.6489,
|
| 720 |
+
"step": 24000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.84,
|
| 724 |
+
"eval_accuracy": 0.7182007239397646,
|
| 725 |
+
"eval_loss": 1.3947515487670898,
|
| 726 |
+
"eval_runtime": 96.06,
|
| 727 |
+
"eval_samples_per_second": 176.223,
|
| 728 |
+
"eval_steps_per_second": 22.028,
|
| 729 |
+
"step": 24000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.9,
|
| 733 |
+
"learning_rate": 3.499231587658116e-07,
|
| 734 |
+
"loss": 1.6429,
|
| 735 |
+
"step": 24500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.9,
|
| 739 |
+
"eval_accuracy": 0.7183795073646381,
|
| 740 |
+
"eval_loss": 1.3920938968658447,
|
| 741 |
+
"eval_runtime": 96.1507,
|
| 742 |
+
"eval_samples_per_second": 176.057,
|
| 743 |
+
"eval_steps_per_second": 22.007,
|
| 744 |
+
"step": 24500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.96,
|
| 748 |
+
"learning_rate": 1.528943531544312e-07,
|
| 749 |
+
"loss": 1.6477,
|
| 750 |
+
"step": 25000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.96,
|
| 754 |
+
"eval_accuracy": 0.7182484820177487,
|
| 755 |
+
"eval_loss": 1.3909834623336792,
|
| 756 |
+
"eval_runtime": 96.1141,
|
| 757 |
+
"eval_samples_per_second": 176.124,
|
| 758 |
+
"eval_steps_per_second": 22.016,
|
| 759 |
+
"step": 25000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.0,
|
| 763 |
+
"step": 25377,
|
| 764 |
+
"total_flos": 1.2378168378261504e+17,
|
| 765 |
+
"train_loss": 2.057705193860182,
|
| 766 |
+
"train_runtime": 15314.6638,
|
| 767 |
+
"train_samples_per_second": 26.512,
|
| 768 |
+
"train_steps_per_second": 1.657
|
| 769 |
+
}
|
| 770 |
+
],
|
| 771 |
+
"logging_steps": 500,
|
| 772 |
+
"max_steps": 25377,
|
| 773 |
+
"num_input_tokens_seen": 0,
|
| 774 |
+
"num_train_epochs": 3,
|
| 775 |
+
"save_steps": 500,
|
| 776 |
+
"total_flos": 1.2378168378261504e+17,
|
| 777 |
+
"train_batch_size": 8,
|
| 778 |
+
"trial_name": null,
|
| 779 |
+
"trial_params": null
|
| 780 |
+
}
|