Kerem P
commited on
Commit
•
cb4b708
1
Parent(s):
45b9879
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: mit
|
|
3 |
base_model: microsoft/deberta-v3-large
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: deberta-em-large
|
8 |
results: []
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# deberta-em-large
|
15 |
|
16 |
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: microsoft/deberta-v3-large
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
model-index:
|
9 |
- name: deberta-em-large
|
10 |
results: []
|
|
|
16 |
# deberta-em-large
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1008
|
21 |
+
- F1: 0.9367
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"eval_f1": 0.9366515837104072,
|
4 |
+
"eval_loss": 0.10084846615791321,
|
5 |
+
"eval_runtime": 26.7722,
|
6 |
+
"eval_samples": 1439,
|
7 |
+
"eval_samples_per_second": 53.75,
|
8 |
+
"eval_steps_per_second": 1.681,
|
9 |
+
"train_loss": 0.17317123087043437,
|
10 |
+
"train_runtime": 1075.8425,
|
11 |
+
"train_samples": 5010,
|
12 |
+
"train_samples_per_second": 13.97,
|
13 |
+
"train_steps_per_second": 0.218
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"eval_f1": 0.9366515837104072,
|
4 |
+
"eval_loss": 0.10084846615791321,
|
5 |
+
"eval_runtime": 26.7722,
|
6 |
+
"eval_samples": 1439,
|
7 |
+
"eval_samples_per_second": 53.75,
|
8 |
+
"eval_steps_per_second": 1.681
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"train_loss": 0.17317123087043437,
|
4 |
+
"train_runtime": 1075.8425,
|
5 |
+
"train_samples": 5010,
|
6 |
+
"train_samples_per_second": 13.97,
|
7 |
+
"train_steps_per_second": 0.218
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.980891719745223,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 234,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.98,
|
13 |
+
"step": 234,
|
14 |
+
"total_flos": 1751693284868096.0,
|
15 |
+
"train_loss": 0.17317123087043437,
|
16 |
+
"train_runtime": 1075.8425,
|
17 |
+
"train_samples_per_second": 13.97,
|
18 |
+
"train_steps_per_second": 0.218
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 234,
|
23 |
+
"num_train_epochs": 3,
|
24 |
+
"save_steps": 500,
|
25 |
+
"total_flos": 1751693284868096.0,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": null
|
28 |
+
}
|