stealthwriter
commited on
Commit
•
c4be4d9
1
Parent(s):
d102c13
End of training
Browse files- README.md +5 -0
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +28 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
3 |
base_model: albert-base-v2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: HorAI-medium-17k-albertv2
|
8 |
results: []
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# HorAI-medium-17k-albertv2
|
15 |
|
16 |
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: albert-base-v2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: HorAI-medium-17k-albertv2
|
10 |
results: []
|
|
|
16 |
# HorAI-medium-17k-albertv2
|
17 |
|
18 |
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3538
|
21 |
+
- Accuracy: 0.8442
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.8441890166028098,
|
4 |
+
"eval_loss": 0.3537946343421936,
|
5 |
+
"eval_runtime": 11.3499,
|
6 |
+
"eval_samples": 1566,
|
7 |
+
"eval_samples_per_second": 137.975,
|
8 |
+
"eval_steps_per_second": 2.908,
|
9 |
+
"train_loss": 0.34923382270626907,
|
10 |
+
"train_runtime": 105.6994,
|
11 |
+
"train_samples": 15658,
|
12 |
+
"train_samples_per_second": 740.685,
|
13 |
+
"train_steps_per_second": 1.939
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.8441890166028098,
|
4 |
+
"eval_loss": 0.3537946343421936,
|
5 |
+
"eval_runtime": 11.3499,
|
6 |
+
"eval_samples": 1566,
|
7 |
+
"eval_samples_per_second": 137.975,
|
8 |
+
"eval_steps_per_second": 2.908
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.34923382270626907,
|
4 |
+
"train_runtime": 105.6994,
|
5 |
+
"train_samples": 15658,
|
6 |
+
"train_samples_per_second": 740.685,
|
7 |
+
"train_steps_per_second": 1.939
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 205,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 5.0,
|
13 |
+
"step": 205,
|
14 |
+
"total_flos": 233872798348800.0,
|
15 |
+
"train_loss": 0.34923382270626907,
|
16 |
+
"train_runtime": 105.6994,
|
17 |
+
"train_samples_per_second": 740.685,
|
18 |
+
"train_steps_per_second": 1.939
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 205,
|
23 |
+
"num_train_epochs": 5,
|
24 |
+
"save_steps": 500,
|
25 |
+
"total_flos": 233872798348800.0,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": null
|
28 |
+
}
|