End of training
Browse files- README.md +5 -0
- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Dec07_09-39-39_19e0ce5cd803/events.out.tfevents.1701942656.19e0ce5cd803.1409.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +59 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
3 |
base_model: distilbert-base-multilingual-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: text-classification-model-multilingual
|
8 |
results: []
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# text-classification-model-multilingual
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: distilbert-base-multilingual-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: text-classification-model-multilingual
|
10 |
results: []
|
|
|
16 |
# text-classification-model-multilingual
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2706
|
21 |
+
- Accuracy: 0.9373
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.9373333333333334,
|
4 |
+
"eval_loss": 0.2706108093261719,
|
5 |
+
"eval_runtime": 11.0779,
|
6 |
+
"eval_samples": 3000,
|
7 |
+
"eval_samples_per_second": 270.809,
|
8 |
+
"eval_steps_per_second": 33.851,
|
9 |
+
"train_loss": 0.8795227316481558,
|
10 |
+
"train_runtime": 626.0855,
|
11 |
+
"train_samples": 15000,
|
12 |
+
"train_samples_per_second": 71.875,
|
13 |
+
"train_steps_per_second": 4.495
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.9373333333333334,
|
4 |
+
"eval_loss": 0.2706108093261719,
|
5 |
+
"eval_runtime": 11.0779,
|
6 |
+
"eval_samples": 3000,
|
7 |
+
"eval_samples_per_second": 270.809,
|
8 |
+
"eval_steps_per_second": 33.851
|
9 |
+
}
|
runs/Dec07_09-39-39_19e0ce5cd803/events.out.tfevents.1701942656.19e0ce5cd803.1409.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:417e07558071dd435859a7914b26e599270b8e2da7ec266b7fcee3d12f125fa8
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.8795227316481558,
|
4 |
+
"train_runtime": 626.0855,
|
5 |
+
"train_samples": 15000,
|
6 |
+
"train_samples_per_second": 71.875,
|
7 |
+
"train_steps_per_second": 4.495
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2814,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.53,
|
13 |
+
"learning_rate": 4.111584932480455e-05,
|
14 |
+
"loss": 3.3646,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.07,
|
19 |
+
"learning_rate": 3.2231698649609096e-05,
|
20 |
+
"loss": 0.932,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.6,
|
25 |
+
"learning_rate": 2.3347547974413646e-05,
|
26 |
+
"loss": 0.3383,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.13,
|
31 |
+
"learning_rate": 1.4463397299218195e-05,
|
32 |
+
"loss": 0.1763,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.67,
|
37 |
+
"learning_rate": 5.579246624022743e-06,
|
38 |
+
"loss": 0.0893,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"step": 2814,
|
44 |
+
"total_flos": 1494191577600000.0,
|
45 |
+
"train_loss": 0.8795227316481558,
|
46 |
+
"train_runtime": 626.0855,
|
47 |
+
"train_samples_per_second": 71.875,
|
48 |
+
"train_steps_per_second": 4.495
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"logging_steps": 500,
|
52 |
+
"max_steps": 2814,
|
53 |
+
"num_input_tokens_seen": 0,
|
54 |
+
"num_train_epochs": 3,
|
55 |
+
"save_steps": 500,
|
56 |
+
"total_flos": 1494191577600000.0,
|
57 |
+
"trial_name": null,
|
58 |
+
"trial_params": null
|
59 |
+
}
|