josecannete commited on
Commit
6ebeb24
1 Parent(s): 7e21c9f

uploading model

Browse files
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ALBERT Base Spanish
2
+
3
+ This is an [ALBERT](https://github.com/google-research/albert) model trained on a [big spanish corpora](https://github.com/josecannete/spanish-corpora).
4
+ The model was trained on a single TPU v3-8 with the following hyperparameters and steps/time:
5
+ - LR: 0.0008838834765
6
+ - Batch Size: 960
7
+ - Warmup ratio: 0.00625
8
+ - Warmup steps: 53333.33333
9
+ - Goal steps: 8533333.333
10
+ - Total steps: 3650000
11
+ - Total training time (aprox): 70.4 days.
12
+
13
+ ## Training loss
14
+
15
+ ![https://drive.google.com/uc?export=view&id=1IsxcgMwd7Hl-3bSnNl8W9jUrHJeHtZql](https://drive.google.com/uc?export=view&id=1IsxcgMwd7Hl-3bSnNl8W9jUrHJeHtZql)
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../convert_models/albert_base_spanish/converted",
3
+ "architectures": [
4
+ "AlbertForPreTraining"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "transformers_version": "4.8.2",
30
+ "type_vocab_size": 2,
31
+ "vocab_size": 31000
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d6e4d323d97a89d5f9112abf8d4b2e9af83cfeb7f375702016e2be30c037c0
3
+ size 47789144
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c98d44f2c8ba92d861c8705ca4386454387ac7070fb00e9cd934f401387656
3
+ size 797897
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57db1136371c009fef73d6700f6570062471080cdbb5a4acdb9d143e5f78cd2e
3
+ size 64088144
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "../albert_tiny", "tokenizer_class": "AlbertTokenizer"}