Training in progress, step 500
Browse files- README.md +56 -0
- all_results.json +7 -0
- config.json +24 -0
- mlm_eval_results.json +7 -0
- model.safetensors +3 -0
- trainer_state.json +100 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: dccuchile/distilbert-base-spanish-uncased
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: distilbert-base-spanish-uncased
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# distilbert-base-spanish-uncased
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.3324
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 5e-05
|
37 |
+
- train_batch_size: 16
|
38 |
+
- eval_batch_size: 16
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 1
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| 2.611 | 0.59 | 500 | 2.3444 |
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.35.0
|
54 |
+
- Pytorch 2.1.0+cu121
|
55 |
+
- Datasets 2.14.6
|
56 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 2.3465805053710938,
|
4 |
+
"eval_runtime": 34.7916,
|
5 |
+
"eval_samples_per_second": 128.968,
|
6 |
+
"eval_steps_per_second": 8.077
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": true,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.35.0",
|
23 |
+
"vocab_size": 31002
|
24 |
+
}
|
mlm_eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 2.3465805053710938,
|
4 |
+
"eval_runtime": 34.7916,
|
5 |
+
"eval_samples_per_second": 128.968,
|
6 |
+
"eval_steps_per_second": 8.077
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2fd26286a495086c0d6cb8c7104d2a1fc60f0b85b24b00d46cac0ddb49db273
|
3 |
+
size 269431248
|
trainer_state.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.3443617820739746,
|
3 |
+
"best_model_checkpoint": "output_dir/checkpoint-500",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 842,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.12,
|
13 |
+
"learning_rate": 4.406175771971497e-05,
|
14 |
+
"loss": 3.5848,
|
15 |
+
"step": 100
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.24,
|
19 |
+
"learning_rate": 3.812351543942993e-05,
|
20 |
+
"loss": 3.0455,
|
21 |
+
"step": 200
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.36,
|
25 |
+
"learning_rate": 3.21852731591449e-05,
|
26 |
+
"loss": 2.8043,
|
27 |
+
"step": 300
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.48,
|
31 |
+
"learning_rate": 2.6247030878859858e-05,
|
32 |
+
"loss": 2.6995,
|
33 |
+
"step": 400
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.59,
|
37 |
+
"learning_rate": 2.0308788598574824e-05,
|
38 |
+
"loss": 2.611,
|
39 |
+
"step": 500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.59,
|
43 |
+
"eval_loss": 2.3443617820739746,
|
44 |
+
"eval_runtime": 34.7863,
|
45 |
+
"eval_samples_per_second": 128.988,
|
46 |
+
"eval_steps_per_second": 8.078,
|
47 |
+
"step": 500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.71,
|
51 |
+
"learning_rate": 1.4370546318289787e-05,
|
52 |
+
"loss": 2.5726,
|
53 |
+
"step": 600
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.83,
|
57 |
+
"learning_rate": 8.432304038004752e-06,
|
58 |
+
"loss": 2.4666,
|
59 |
+
"step": 700
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.95,
|
63 |
+
"learning_rate": 2.494061757719715e-06,
|
64 |
+
"loss": 2.4894,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.0,
|
69 |
+
"step": 842,
|
70 |
+
"total_flos": 1784293008629760.0,
|
71 |
+
"train_loss": 2.7663106034883693,
|
72 |
+
"train_runtime": 344.8745,
|
73 |
+
"train_samples_per_second": 39.029,
|
74 |
+
"train_steps_per_second": 2.441
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.0,
|
78 |
+
"eval_loss": 2.3465805053710938,
|
79 |
+
"eval_runtime": 34.7916,
|
80 |
+
"eval_samples_per_second": 128.968,
|
81 |
+
"eval_steps_per_second": 8.077,
|
82 |
+
"step": 842
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 1.0,
|
86 |
+
"eval_loss": 2.332395076751709,
|
87 |
+
"eval_runtime": 34.8727,
|
88 |
+
"eval_samples_per_second": 128.668,
|
89 |
+
"eval_steps_per_second": 8.058,
|
90 |
+
"step": 842
|
91 |
+
}
|
92 |
+
],
|
93 |
+
"logging_steps": 100,
|
94 |
+
"max_steps": 842,
|
95 |
+
"num_train_epochs": 1,
|
96 |
+
"save_steps": 500,
|
97 |
+
"total_flos": 1784293008629760.0,
|
98 |
+
"trial_name": null,
|
99 |
+
"trial_params": null
|
100 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59225db1c65a9be65684c3b77d42b385d846b72f805144559ebc2ff6f544ee6b
|
3 |
+
size 4664
|