End of training
Browse files- README.md +22 -2
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +868 -0
README.md
CHANGED
|
@@ -1,13 +1,30 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: bert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- glue
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: out-glue-sst2
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,7 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# out-glue-sst2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: bert-base-uncased
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- glue
|
| 10 |
+
metrics:
|
| 11 |
+
- accuracy
|
| 12 |
model-index:
|
| 13 |
- name: out-glue-sst2
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Text Classification
|
| 17 |
+
type: text-classification
|
| 18 |
+
dataset:
|
| 19 |
+
name: GLUE SST2
|
| 20 |
+
type: glue
|
| 21 |
+
config: sst2
|
| 22 |
+
split: validation
|
| 23 |
+
args: sst2
|
| 24 |
+
metrics:
|
| 25 |
+
- name: Accuracy
|
| 26 |
+
type: accuracy
|
| 27 |
+
value: 0.9243119266055045
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
# out-glue-sst2
|
| 34 |
|
| 35 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE SST2 dataset.
|
| 36 |
+
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 0.3727
|
| 38 |
+
- Accuracy: 0.9243
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9243119266055045,
|
| 4 |
+
"eval_loss": 0.3727177679538727,
|
| 5 |
+
"eval_runtime": 0.6609,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 1319.323,
|
| 8 |
+
"eval_steps_per_second": 6.052,
|
| 9 |
+
"train_loss": 0.0692601463139227,
|
| 10 |
+
"train_runtime": 1373.3603,
|
| 11 |
+
"train_samples": 67349,
|
| 12 |
+
"train_samples_per_second": 490.396,
|
| 13 |
+
"train_steps_per_second": 2.556
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9243119266055045,
|
| 4 |
+
"eval_loss": 0.3727177679538727,
|
| 5 |
+
"eval_runtime": 0.6609,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 1319.323,
|
| 8 |
+
"eval_steps_per_second": 6.052
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.0692601463139227,
|
| 4 |
+
"train_runtime": 1373.3603,
|
| 5 |
+
"train_samples": 67349,
|
| 6 |
+
"train_samples_per_second": 490.396,
|
| 7 |
+
"train_steps_per_second": 2.556
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,868 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1755,
|
| 6 |
+
"global_step": 3510,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 1.985754985754986e-05,
|
| 14 |
+
"loss": 0.5449,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.14,
|
| 19 |
+
"learning_rate": 1.9715099715099716e-05,
|
| 20 |
+
"loss": 0.3107,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.21,
|
| 25 |
+
"learning_rate": 1.9572649572649574e-05,
|
| 26 |
+
"loss": 0.2798,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.28,
|
| 31 |
+
"learning_rate": 1.943019943019943e-05,
|
| 32 |
+
"loss": 0.2448,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.36,
|
| 37 |
+
"learning_rate": 1.928774928774929e-05,
|
| 38 |
+
"loss": 0.2447,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.43,
|
| 43 |
+
"learning_rate": 1.914529914529915e-05,
|
| 44 |
+
"loss": 0.2314,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.5,
|
| 49 |
+
"learning_rate": 1.9002849002849003e-05,
|
| 50 |
+
"loss": 0.1924,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.57,
|
| 55 |
+
"learning_rate": 1.8860398860398864e-05,
|
| 56 |
+
"loss": 0.2063,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.64,
|
| 61 |
+
"learning_rate": 1.8717948717948718e-05,
|
| 62 |
+
"loss": 0.1999,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.71,
|
| 67 |
+
"learning_rate": 1.8575498575498575e-05,
|
| 68 |
+
"loss": 0.1794,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.78,
|
| 73 |
+
"learning_rate": 1.8433048433048436e-05,
|
| 74 |
+
"loss": 0.1884,
|
| 75 |
+
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.85,
|
| 79 |
+
"learning_rate": 1.829059829059829e-05,
|
| 80 |
+
"loss": 0.1819,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.93,
|
| 85 |
+
"learning_rate": 1.814814814814815e-05,
|
| 86 |
+
"loss": 0.1682,
|
| 87 |
+
"step": 325
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.0,
|
| 91 |
+
"learning_rate": 1.8005698005698008e-05,
|
| 92 |
+
"loss": 0.1808,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.07,
|
| 97 |
+
"learning_rate": 1.7863247863247866e-05,
|
| 98 |
+
"loss": 0.1332,
|
| 99 |
+
"step": 375
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.14,
|
| 103 |
+
"learning_rate": 1.7720797720797723e-05,
|
| 104 |
+
"loss": 0.1152,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.21,
|
| 109 |
+
"learning_rate": 1.757834757834758e-05,
|
| 110 |
+
"loss": 0.1308,
|
| 111 |
+
"step": 425
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.28,
|
| 115 |
+
"learning_rate": 1.7435897435897438e-05,
|
| 116 |
+
"loss": 0.1344,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.35,
|
| 121 |
+
"learning_rate": 1.7293447293447295e-05,
|
| 122 |
+
"loss": 0.1267,
|
| 123 |
+
"step": 475
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.42,
|
| 127 |
+
"learning_rate": 1.7150997150997152e-05,
|
| 128 |
+
"loss": 0.1333,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.5,
|
| 133 |
+
"learning_rate": 1.700854700854701e-05,
|
| 134 |
+
"loss": 0.1278,
|
| 135 |
+
"step": 525
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.57,
|
| 139 |
+
"learning_rate": 1.6866096866096867e-05,
|
| 140 |
+
"loss": 0.1326,
|
| 141 |
+
"step": 550
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.64,
|
| 145 |
+
"learning_rate": 1.6723646723646725e-05,
|
| 146 |
+
"loss": 0.1148,
|
| 147 |
+
"step": 575
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.71,
|
| 151 |
+
"learning_rate": 1.6581196581196585e-05,
|
| 152 |
+
"loss": 0.1207,
|
| 153 |
+
"step": 600
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.78,
|
| 157 |
+
"learning_rate": 1.643874643874644e-05,
|
| 158 |
+
"loss": 0.12,
|
| 159 |
+
"step": 625
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.85,
|
| 163 |
+
"learning_rate": 1.6296296296296297e-05,
|
| 164 |
+
"loss": 0.1129,
|
| 165 |
+
"step": 650
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.92,
|
| 169 |
+
"learning_rate": 1.6153846153846154e-05,
|
| 170 |
+
"loss": 0.1295,
|
| 171 |
+
"step": 675
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.99,
|
| 175 |
+
"learning_rate": 1.601139601139601e-05,
|
| 176 |
+
"loss": 0.1244,
|
| 177 |
+
"step": 700
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.07,
|
| 181 |
+
"learning_rate": 1.5868945868945872e-05,
|
| 182 |
+
"loss": 0.0947,
|
| 183 |
+
"step": 725
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.14,
|
| 187 |
+
"learning_rate": 1.5726495726495726e-05,
|
| 188 |
+
"loss": 0.0791,
|
| 189 |
+
"step": 750
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.21,
|
| 193 |
+
"learning_rate": 1.5584045584045587e-05,
|
| 194 |
+
"loss": 0.0846,
|
| 195 |
+
"step": 775
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.28,
|
| 199 |
+
"learning_rate": 1.5441595441595444e-05,
|
| 200 |
+
"loss": 0.083,
|
| 201 |
+
"step": 800
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.35,
|
| 205 |
+
"learning_rate": 1.5299145299145298e-05,
|
| 206 |
+
"loss": 0.0859,
|
| 207 |
+
"step": 825
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.42,
|
| 211 |
+
"learning_rate": 1.5156695156695157e-05,
|
| 212 |
+
"loss": 0.0851,
|
| 213 |
+
"step": 850
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.49,
|
| 217 |
+
"learning_rate": 1.5014245014245015e-05,
|
| 218 |
+
"loss": 0.0916,
|
| 219 |
+
"step": 875
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.56,
|
| 223 |
+
"learning_rate": 1.4871794871794874e-05,
|
| 224 |
+
"loss": 0.0822,
|
| 225 |
+
"step": 900
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.64,
|
| 229 |
+
"learning_rate": 1.472934472934473e-05,
|
| 230 |
+
"loss": 0.0933,
|
| 231 |
+
"step": 925
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.71,
|
| 235 |
+
"learning_rate": 1.4586894586894588e-05,
|
| 236 |
+
"loss": 0.0829,
|
| 237 |
+
"step": 950
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.78,
|
| 241 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 242 |
+
"loss": 0.0908,
|
| 243 |
+
"step": 975
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.85,
|
| 247 |
+
"learning_rate": 1.4301994301994305e-05,
|
| 248 |
+
"loss": 0.0911,
|
| 249 |
+
"step": 1000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.92,
|
| 253 |
+
"learning_rate": 1.415954415954416e-05,
|
| 254 |
+
"loss": 0.0851,
|
| 255 |
+
"step": 1025
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.99,
|
| 259 |
+
"learning_rate": 1.4017094017094018e-05,
|
| 260 |
+
"loss": 0.0958,
|
| 261 |
+
"step": 1050
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.06,
|
| 265 |
+
"learning_rate": 1.3874643874643875e-05,
|
| 266 |
+
"loss": 0.0588,
|
| 267 |
+
"step": 1075
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.13,
|
| 271 |
+
"learning_rate": 1.3732193732193733e-05,
|
| 272 |
+
"loss": 0.0566,
|
| 273 |
+
"step": 1100
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.21,
|
| 277 |
+
"learning_rate": 1.3589743589743592e-05,
|
| 278 |
+
"loss": 0.0573,
|
| 279 |
+
"step": 1125
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.28,
|
| 283 |
+
"learning_rate": 1.3447293447293447e-05,
|
| 284 |
+
"loss": 0.0603,
|
| 285 |
+
"step": 1150
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.35,
|
| 289 |
+
"learning_rate": 1.3304843304843306e-05,
|
| 290 |
+
"loss": 0.0753,
|
| 291 |
+
"step": 1175
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.42,
|
| 295 |
+
"learning_rate": 1.3162393162393164e-05,
|
| 296 |
+
"loss": 0.0577,
|
| 297 |
+
"step": 1200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.49,
|
| 301 |
+
"learning_rate": 1.301994301994302e-05,
|
| 302 |
+
"loss": 0.0678,
|
| 303 |
+
"step": 1225
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.56,
|
| 307 |
+
"learning_rate": 1.2877492877492879e-05,
|
| 308 |
+
"loss": 0.0696,
|
| 309 |
+
"step": 1250
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.63,
|
| 313 |
+
"learning_rate": 1.2735042735042736e-05,
|
| 314 |
+
"loss": 0.067,
|
| 315 |
+
"step": 1275
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.7,
|
| 319 |
+
"learning_rate": 1.2592592592592593e-05,
|
| 320 |
+
"loss": 0.0658,
|
| 321 |
+
"step": 1300
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.77,
|
| 325 |
+
"learning_rate": 1.245014245014245e-05,
|
| 326 |
+
"loss": 0.0701,
|
| 327 |
+
"step": 1325
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.85,
|
| 331 |
+
"learning_rate": 1.230769230769231e-05,
|
| 332 |
+
"loss": 0.0634,
|
| 333 |
+
"step": 1350
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.92,
|
| 337 |
+
"learning_rate": 1.2165242165242165e-05,
|
| 338 |
+
"loss": 0.0711,
|
| 339 |
+
"step": 1375
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.99,
|
| 343 |
+
"learning_rate": 1.2022792022792024e-05,
|
| 344 |
+
"loss": 0.0667,
|
| 345 |
+
"step": 1400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.06,
|
| 349 |
+
"learning_rate": 1.1880341880341882e-05,
|
| 350 |
+
"loss": 0.048,
|
| 351 |
+
"step": 1425
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.13,
|
| 355 |
+
"learning_rate": 1.1737891737891738e-05,
|
| 356 |
+
"loss": 0.0461,
|
| 357 |
+
"step": 1450
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.2,
|
| 361 |
+
"learning_rate": 1.1595441595441597e-05,
|
| 362 |
+
"loss": 0.0418,
|
| 363 |
+
"step": 1475
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.27,
|
| 367 |
+
"learning_rate": 1.1452991452991454e-05,
|
| 368 |
+
"loss": 0.0578,
|
| 369 |
+
"step": 1500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.34,
|
| 373 |
+
"learning_rate": 1.1310541310541311e-05,
|
| 374 |
+
"loss": 0.0463,
|
| 375 |
+
"step": 1525
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.42,
|
| 379 |
+
"learning_rate": 1.1168091168091169e-05,
|
| 380 |
+
"loss": 0.0458,
|
| 381 |
+
"step": 1550
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.49,
|
| 385 |
+
"learning_rate": 1.1025641025641028e-05,
|
| 386 |
+
"loss": 0.0509,
|
| 387 |
+
"step": 1575
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.56,
|
| 391 |
+
"learning_rate": 1.0883190883190883e-05,
|
| 392 |
+
"loss": 0.0509,
|
| 393 |
+
"step": 1600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.63,
|
| 397 |
+
"learning_rate": 1.0740740740740742e-05,
|
| 398 |
+
"loss": 0.0453,
|
| 399 |
+
"step": 1625
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.7,
|
| 403 |
+
"learning_rate": 1.05982905982906e-05,
|
| 404 |
+
"loss": 0.0425,
|
| 405 |
+
"step": 1650
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.77,
|
| 409 |
+
"learning_rate": 1.0455840455840456e-05,
|
| 410 |
+
"loss": 0.0596,
|
| 411 |
+
"step": 1675
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.84,
|
| 415 |
+
"learning_rate": 1.0313390313390315e-05,
|
| 416 |
+
"loss": 0.0461,
|
| 417 |
+
"step": 1700
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.91,
|
| 421 |
+
"learning_rate": 1.0170940170940172e-05,
|
| 422 |
+
"loss": 0.0561,
|
| 423 |
+
"step": 1725
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.99,
|
| 427 |
+
"learning_rate": 1.002849002849003e-05,
|
| 428 |
+
"loss": 0.0523,
|
| 429 |
+
"step": 1750
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.06,
|
| 433 |
+
"learning_rate": 9.886039886039887e-06,
|
| 434 |
+
"loss": 0.0352,
|
| 435 |
+
"step": 1775
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 5.13,
|
| 439 |
+
"learning_rate": 9.743589743589744e-06,
|
| 440 |
+
"loss": 0.036,
|
| 441 |
+
"step": 1800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 5.2,
|
| 445 |
+
"learning_rate": 9.601139601139601e-06,
|
| 446 |
+
"loss": 0.036,
|
| 447 |
+
"step": 1825
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 5.27,
|
| 451 |
+
"learning_rate": 9.458689458689459e-06,
|
| 452 |
+
"loss": 0.0343,
|
| 453 |
+
"step": 1850
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.34,
|
| 457 |
+
"learning_rate": 9.316239316239318e-06,
|
| 458 |
+
"loss": 0.0332,
|
| 459 |
+
"step": 1875
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 5.41,
|
| 463 |
+
"learning_rate": 9.173789173789175e-06,
|
| 464 |
+
"loss": 0.0398,
|
| 465 |
+
"step": 1900
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 5.48,
|
| 469 |
+
"learning_rate": 9.031339031339033e-06,
|
| 470 |
+
"loss": 0.0412,
|
| 471 |
+
"step": 1925
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 5.56,
|
| 475 |
+
"learning_rate": 8.888888888888888e-06,
|
| 476 |
+
"loss": 0.0397,
|
| 477 |
+
"step": 1950
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 5.63,
|
| 481 |
+
"learning_rate": 8.746438746438747e-06,
|
| 482 |
+
"loss": 0.0421,
|
| 483 |
+
"step": 1975
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.7,
|
| 487 |
+
"learning_rate": 8.603988603988605e-06,
|
| 488 |
+
"loss": 0.0386,
|
| 489 |
+
"step": 2000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.77,
|
| 493 |
+
"learning_rate": 8.461538461538462e-06,
|
| 494 |
+
"loss": 0.0405,
|
| 495 |
+
"step": 2025
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.84,
|
| 499 |
+
"learning_rate": 8.31908831908832e-06,
|
| 500 |
+
"loss": 0.0431,
|
| 501 |
+
"step": 2050
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 5.91,
|
| 505 |
+
"learning_rate": 8.176638176638177e-06,
|
| 506 |
+
"loss": 0.0464,
|
| 507 |
+
"step": 2075
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 5.98,
|
| 511 |
+
"learning_rate": 8.034188034188036e-06,
|
| 512 |
+
"loss": 0.0462,
|
| 513 |
+
"step": 2100
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 6.05,
|
| 517 |
+
"learning_rate": 7.891737891737893e-06,
|
| 518 |
+
"loss": 0.0261,
|
| 519 |
+
"step": 2125
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 6.13,
|
| 523 |
+
"learning_rate": 7.749287749287749e-06,
|
| 524 |
+
"loss": 0.0304,
|
| 525 |
+
"step": 2150
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.2,
|
| 529 |
+
"learning_rate": 7.606837606837607e-06,
|
| 530 |
+
"loss": 0.029,
|
| 531 |
+
"step": 2175
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 6.27,
|
| 535 |
+
"learning_rate": 7.4643874643874645e-06,
|
| 536 |
+
"loss": 0.0316,
|
| 537 |
+
"step": 2200
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 6.34,
|
| 541 |
+
"learning_rate": 7.321937321937323e-06,
|
| 542 |
+
"loss": 0.0306,
|
| 543 |
+
"step": 2225
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 6.41,
|
| 547 |
+
"learning_rate": 7.17948717948718e-06,
|
| 548 |
+
"loss": 0.035,
|
| 549 |
+
"step": 2250
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 6.48,
|
| 553 |
+
"learning_rate": 7.0370370370370375e-06,
|
| 554 |
+
"loss": 0.0245,
|
| 555 |
+
"step": 2275
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 6.55,
|
| 559 |
+
"learning_rate": 6.894586894586896e-06,
|
| 560 |
+
"loss": 0.0207,
|
| 561 |
+
"step": 2300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 6.62,
|
| 565 |
+
"learning_rate": 6.752136752136753e-06,
|
| 566 |
+
"loss": 0.0314,
|
| 567 |
+
"step": 2325
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.7,
|
| 571 |
+
"learning_rate": 6.60968660968661e-06,
|
| 572 |
+
"loss": 0.0291,
|
| 573 |
+
"step": 2350
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 6.77,
|
| 577 |
+
"learning_rate": 6.467236467236467e-06,
|
| 578 |
+
"loss": 0.0331,
|
| 579 |
+
"step": 2375
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 6.84,
|
| 583 |
+
"learning_rate": 6.324786324786325e-06,
|
| 584 |
+
"loss": 0.0297,
|
| 585 |
+
"step": 2400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 6.91,
|
| 589 |
+
"learning_rate": 6.1823361823361825e-06,
|
| 590 |
+
"loss": 0.0321,
|
| 591 |
+
"step": 2425
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 6.98,
|
| 595 |
+
"learning_rate": 6.039886039886041e-06,
|
| 596 |
+
"loss": 0.0313,
|
| 597 |
+
"step": 2450
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.05,
|
| 601 |
+
"learning_rate": 5.897435897435898e-06,
|
| 602 |
+
"loss": 0.0228,
|
| 603 |
+
"step": 2475
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 7.12,
|
| 607 |
+
"learning_rate": 5.7549857549857555e-06,
|
| 608 |
+
"loss": 0.0167,
|
| 609 |
+
"step": 2500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 7.19,
|
| 613 |
+
"learning_rate": 5.612535612535614e-06,
|
| 614 |
+
"loss": 0.0193,
|
| 615 |
+
"step": 2525
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 7.26,
|
| 619 |
+
"learning_rate": 5.470085470085471e-06,
|
| 620 |
+
"loss": 0.0244,
|
| 621 |
+
"step": 2550
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 7.34,
|
| 625 |
+
"learning_rate": 5.327635327635328e-06,
|
| 626 |
+
"loss": 0.0234,
|
| 627 |
+
"step": 2575
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 7.41,
|
| 631 |
+
"learning_rate": 5.185185185185185e-06,
|
| 632 |
+
"loss": 0.0232,
|
| 633 |
+
"step": 2600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 7.48,
|
| 637 |
+
"learning_rate": 5.042735042735043e-06,
|
| 638 |
+
"loss": 0.025,
|
| 639 |
+
"step": 2625
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.55,
|
| 643 |
+
"learning_rate": 4.9002849002849006e-06,
|
| 644 |
+
"loss": 0.0265,
|
| 645 |
+
"step": 2650
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 7.62,
|
| 649 |
+
"learning_rate": 4.757834757834758e-06,
|
| 650 |
+
"loss": 0.0251,
|
| 651 |
+
"step": 2675
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 7.69,
|
| 655 |
+
"learning_rate": 4.615384615384616e-06,
|
| 656 |
+
"loss": 0.0269,
|
| 657 |
+
"step": 2700
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 7.76,
|
| 661 |
+
"learning_rate": 4.4729344729344735e-06,
|
| 662 |
+
"loss": 0.0264,
|
| 663 |
+
"step": 2725
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 7.83,
|
| 667 |
+
"learning_rate": 4.330484330484331e-06,
|
| 668 |
+
"loss": 0.0211,
|
| 669 |
+
"step": 2750
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 7.91,
|
| 673 |
+
"learning_rate": 4.188034188034188e-06,
|
| 674 |
+
"loss": 0.03,
|
| 675 |
+
"step": 2775
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 7.98,
|
| 679 |
+
"learning_rate": 4.0455840455840465e-06,
|
| 680 |
+
"loss": 0.0224,
|
| 681 |
+
"step": 2800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.05,
|
| 685 |
+
"learning_rate": 3.903133903133903e-06,
|
| 686 |
+
"loss": 0.0233,
|
| 687 |
+
"step": 2825
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 8.12,
|
| 691 |
+
"learning_rate": 3.760683760683761e-06,
|
| 692 |
+
"loss": 0.0213,
|
| 693 |
+
"step": 2850
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 8.19,
|
| 697 |
+
"learning_rate": 3.6182336182336186e-06,
|
| 698 |
+
"loss": 0.0157,
|
| 699 |
+
"step": 2875
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 8.26,
|
| 703 |
+
"learning_rate": 3.4757834757834764e-06,
|
| 704 |
+
"loss": 0.0171,
|
| 705 |
+
"step": 2900
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 8.33,
|
| 709 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 710 |
+
"loss": 0.0189,
|
| 711 |
+
"step": 2925
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.4,
|
| 715 |
+
"learning_rate": 3.190883190883191e-06,
|
| 716 |
+
"loss": 0.0154,
|
| 717 |
+
"step": 2950
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 8.48,
|
| 721 |
+
"learning_rate": 3.048433048433049e-06,
|
| 722 |
+
"loss": 0.0178,
|
| 723 |
+
"step": 2975
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 8.55,
|
| 727 |
+
"learning_rate": 2.9059829059829063e-06,
|
| 728 |
+
"loss": 0.0257,
|
| 729 |
+
"step": 3000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 8.62,
|
| 733 |
+
"learning_rate": 2.7635327635327636e-06,
|
| 734 |
+
"loss": 0.0166,
|
| 735 |
+
"step": 3025
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 8.69,
|
| 739 |
+
"learning_rate": 2.6210826210826214e-06,
|
| 740 |
+
"loss": 0.0202,
|
| 741 |
+
"step": 3050
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 8.76,
|
| 745 |
+
"learning_rate": 2.478632478632479e-06,
|
| 746 |
+
"loss": 0.0176,
|
| 747 |
+
"step": 3075
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 8.83,
|
| 751 |
+
"learning_rate": 2.336182336182336e-06,
|
| 752 |
+
"loss": 0.0128,
|
| 753 |
+
"step": 3100
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.9,
|
| 757 |
+
"learning_rate": 2.193732193732194e-06,
|
| 758 |
+
"loss": 0.0263,
|
| 759 |
+
"step": 3125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 8.97,
|
| 763 |
+
"learning_rate": 2.0512820512820513e-06,
|
| 764 |
+
"loss": 0.025,
|
| 765 |
+
"step": 3150
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 9.05,
|
| 769 |
+
"learning_rate": 1.908831908831909e-06,
|
| 770 |
+
"loss": 0.0151,
|
| 771 |
+
"step": 3175
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 9.12,
|
| 775 |
+
"learning_rate": 1.7663817663817665e-06,
|
| 776 |
+
"loss": 0.015,
|
| 777 |
+
"step": 3200
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 9.19,
|
| 781 |
+
"learning_rate": 1.623931623931624e-06,
|
| 782 |
+
"loss": 0.0125,
|
| 783 |
+
"step": 3225
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.26,
|
| 787 |
+
"learning_rate": 1.4814814814814815e-06,
|
| 788 |
+
"loss": 0.0116,
|
| 789 |
+
"step": 3250
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 9.33,
|
| 793 |
+
"learning_rate": 1.3390313390313392e-06,
|
| 794 |
+
"loss": 0.0197,
|
| 795 |
+
"step": 3275
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 9.4,
|
| 799 |
+
"learning_rate": 1.1965811965811968e-06,
|
| 800 |
+
"loss": 0.0196,
|
| 801 |
+
"step": 3300
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 9.47,
|
| 805 |
+
"learning_rate": 1.0541310541310542e-06,
|
| 806 |
+
"loss": 0.0183,
|
| 807 |
+
"step": 3325
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 9.54,
|
| 811 |
+
"learning_rate": 9.116809116809118e-07,
|
| 812 |
+
"loss": 0.0171,
|
| 813 |
+
"step": 3350
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 9.62,
|
| 817 |
+
"learning_rate": 7.692307692307694e-07,
|
| 818 |
+
"loss": 0.0139,
|
| 819 |
+
"step": 3375
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 9.69,
|
| 823 |
+
"learning_rate": 6.267806267806268e-07,
|
| 824 |
+
"loss": 0.0158,
|
| 825 |
+
"step": 3400
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.76,
|
| 829 |
+
"learning_rate": 4.843304843304843e-07,
|
| 830 |
+
"loss": 0.0178,
|
| 831 |
+
"step": 3425
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 9.83,
|
| 835 |
+
"learning_rate": 3.4188034188034194e-07,
|
| 836 |
+
"loss": 0.0112,
|
| 837 |
+
"step": 3450
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 9.9,
|
| 841 |
+
"learning_rate": 1.9943019943019944e-07,
|
| 842 |
+
"loss": 0.0146,
|
| 843 |
+
"step": 3475
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 9.97,
|
| 847 |
+
"learning_rate": 5.6980056980056986e-08,
|
| 848 |
+
"loss": 0.0108,
|
| 849 |
+
"step": 3500
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 10.0,
|
| 853 |
+
"step": 3510,
|
| 854 |
+
"total_flos": 4.43006661686016e+16,
|
| 855 |
+
"train_loss": 0.0692601463139227,
|
| 856 |
+
"train_runtime": 1373.3603,
|
| 857 |
+
"train_samples_per_second": 490.396,
|
| 858 |
+
"train_steps_per_second": 2.556
|
| 859 |
+
}
|
| 860 |
+
],
|
| 861 |
+
"logging_steps": 25,
|
| 862 |
+
"max_steps": 3510,
|
| 863 |
+
"num_train_epochs": 10,
|
| 864 |
+
"save_steps": 500,
|
| 865 |
+
"total_flos": 4.43006661686016e+16,
|
| 866 |
+
"trial_name": null,
|
| 867 |
+
"trial_params": null
|
| 868 |
+
}
|