Nuevo reto, nuevo tema en Platzi! 🤗
Browse files- README.md +9 -1
- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Jun23_16-21-02_44df2b91e38b/events.out.tfevents.1719164314.44df2b91e38b.17693.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +42 -0
README.md
CHANGED
@@ -2,7 +2,11 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilroberta-base
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: platzi-distilroberta-base-mrpc-wgcv
|
8 |
results: []
|
@@ -13,7 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# platzi-distilroberta-base-mrpc-wgcv
|
15 |
|
16 |
-
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilroberta-base
|
4 |
tags:
|
5 |
+
- text-classification
|
6 |
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
model-index:
|
11 |
- name: platzi-distilroberta-base-mrpc-wgcv
|
12 |
results: []
|
|
|
17 |
|
18 |
# platzi-distilroberta-base-mrpc-wgcv
|
19 |
|
20 |
+
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue and the mrpc datasets.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.4053
|
23 |
+
- Accuracy: 0.8358
|
24 |
+
- F1: 0.8847
|
25 |
|
26 |
## Model description
|
27 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8357843137254902,
|
4 |
+
"eval_f1": 0.8846815834767642,
|
5 |
+
"eval_loss": 0.4053478538990021,
|
6 |
+
"eval_runtime": 35.0691,
|
7 |
+
"eval_samples_per_second": 11.634,
|
8 |
+
"eval_steps_per_second": 0.371,
|
9 |
+
"total_flos": 235624315556256.0,
|
10 |
+
"train_loss": 0.4036261074784873,
|
11 |
+
"train_runtime": 3078.6117,
|
12 |
+
"train_samples_per_second": 3.574,
|
13 |
+
"train_steps_per_second": 0.112
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8357843137254902,
|
4 |
+
"eval_f1": 0.8846815834767642,
|
5 |
+
"eval_loss": 0.4053478538990021,
|
6 |
+
"eval_runtime": 35.0691,
|
7 |
+
"eval_samples_per_second": 11.634,
|
8 |
+
"eval_steps_per_second": 0.371
|
9 |
+
}
|
runs/Jun23_16-21-02_44df2b91e38b/events.out.tfevents.1719164314.44df2b91e38b.17693.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4459f04c13d236012100afbba6322f404b6fb1db2f6382a0dc8b04a5d07038bc
|
3 |
+
size 457
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 235624315556256.0,
|
4 |
+
"train_loss": 0.4036261074784873,
|
5 |
+
"train_runtime": 3078.6117,
|
6 |
+
"train_samples_per_second": 3.574,
|
7 |
+
"train_steps_per_second": 0.112
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 345,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 3.0,
|
13 |
+
"step": 345,
|
14 |
+
"total_flos": 235624315556256.0,
|
15 |
+
"train_loss": 0.4036261074784873,
|
16 |
+
"train_runtime": 3078.6117,
|
17 |
+
"train_samples_per_second": 3.574,
|
18 |
+
"train_steps_per_second": 0.112
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 345,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 3,
|
25 |
+
"save_steps": 500,
|
26 |
+
"stateful_callbacks": {
|
27 |
+
"TrainerControl": {
|
28 |
+
"args": {
|
29 |
+
"should_epoch_stop": false,
|
30 |
+
"should_evaluate": false,
|
31 |
+
"should_log": false,
|
32 |
+
"should_save": false,
|
33 |
+
"should_training_stop": false
|
34 |
+
},
|
35 |
+
"attributes": {}
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"total_flos": 235624315556256.0,
|
39 |
+
"train_batch_size": 32,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": null
|
42 |
+
}
|