Training in progress, step 500
Browse files- .gitattributes +1 -0
- config.json +23 -66
- model.safetensors +2 -2
- runs/Nov17_16-52-28_46bbe7f1dda0/events.out.tfevents.1700239950.46bbe7f1dda0.8609.2 +3 -0
- runs/Nov17_16-54-20_46bbe7f1dda0/events.out.tfevents.1700240063.46bbe7f1dda0.22459.0 +3 -0
- runs/Nov17_16-57-16_46bbe7f1dda0/events.out.tfevents.1700240237.46bbe7f1dda0.22459.1 +3 -0
- runs/Nov17_16-57-51_46bbe7f1dda0/events.out.tfevents.1700240272.46bbe7f1dda0.22459.2 +3 -0
- special_tokens_map.json +0 -10
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -26
- training_args.bin +1 -1
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -1,75 +1,32 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation_dropout": 0.1,
|
4 |
-
"activation_function": "gelu",
|
5 |
-
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
-
"
|
9 |
],
|
10 |
-
"attention_dropout": 0.1,
|
11 |
-
"bos_token_id": 0,
|
12 |
-
"classif_dropout": 0.1,
|
13 |
"classifier_dropout": 0.0,
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"encoder_ffn_dim": 3072,
|
24 |
-
"encoder_layerdrop": 0.0,
|
25 |
-
"encoder_layers": 6,
|
26 |
-
"eos_token_id": 2,
|
27 |
-
"forced_bos_token_id": 0,
|
28 |
-
"forced_eos_token_id": 2,
|
29 |
-
"gradient_checkpointing": false,
|
30 |
-
"id2label": {
|
31 |
-
"0": "LABEL_0",
|
32 |
-
"1": "LABEL_1",
|
33 |
-
"2": "LABEL_2"
|
34 |
-
},
|
35 |
-
"init_std": 0.02,
|
36 |
"is_encoder_decoder": true,
|
37 |
-
"
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"num_hidden_layers": 6,
|
49 |
-
"pad_token_id": 1,
|
50 |
-
"scale_embedding": false,
|
51 |
-
"task_specific_params": {
|
52 |
-
"summarization": {
|
53 |
-
"length_penalty": 1.0,
|
54 |
-
"max_length": 128,
|
55 |
-
"min_length": 12,
|
56 |
-
"num_beams": 4
|
57 |
-
},
|
58 |
-
"summarization_cnn": {
|
59 |
-
"length_penalty": 2.0,
|
60 |
-
"max_length": 142,
|
61 |
-
"min_length": 56,
|
62 |
-
"num_beams": 4
|
63 |
-
},
|
64 |
-
"summarization_xsum": {
|
65 |
-
"length_penalty": 1.0,
|
66 |
-
"max_length": 62,
|
67 |
-
"min_length": 11,
|
68 |
-
"num_beams": 6
|
69 |
-
}
|
70 |
-
},
|
71 |
"torch_dtype": "float32",
|
72 |
"transformers_version": "4.35.2",
|
73 |
"use_cache": true,
|
74 |
-
"vocab_size":
|
75 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "HURIDOCS/mt5-small-spanish-es",
|
|
|
|
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
],
|
|
|
|
|
|
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 1024,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 8,
|
21 |
+
"num_heads": 6,
|
22 |
+
"num_layers": 8,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.35.2",
|
30 |
"use_cache": true,
|
31 |
+
"vocab_size": 250100
|
32 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a72ec76c5c31ee5cd6f382b805b96c3847408acbc081e018d30bff496e933c1f
|
3 |
+
size 1200680360
|
runs/Nov17_16-52-28_46bbe7f1dda0/events.out.tfevents.1700239950.46bbe7f1dda0.8609.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b69fa9fe9e5d192f2db2a8a64f67b7f81b8b15d5d0be6205b5bbac53f2eaede
|
3 |
+
size 4184
|
runs/Nov17_16-54-20_46bbe7f1dda0/events.out.tfevents.1700240063.46bbe7f1dda0.22459.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2cf5474ec81c10948132d1061fa85f42fd11911b2d195d62ed2ebee5263ad8
|
3 |
+
size 4541
|
runs/Nov17_16-57-16_46bbe7f1dda0/events.out.tfevents.1700240237.46bbe7f1dda0.22459.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68ecd524bf5f27623895f0de1f05b40b32837c694c43a83cc9aa9085caddad52
|
3 |
+
size 4539
|
runs/Nov17_16-57-51_46bbe7f1dda0/events.out.tfevents.1700240272.46bbe7f1dda0.22459.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ee3b3bc20765cc3349c3933c3eae61903b08a256148a75227917024281cd8db
|
3 |
+
size 8361
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
"unk_token": "<unk>"
|
15 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"pad_token": "<pad>",
|
|
|
4 |
"unk_token": "<unk>"
|
5 |
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,15 +1,6 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
-
"content": "<s>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"1": {
|
13 |
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
@@ -17,7 +8,7 @@
|
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
-
"
|
21 |
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
@@ -25,33 +16,22 @@
|
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
-
"
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
"normalized": false,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
-
},
|
36 |
-
"4": {
|
37 |
-
"content": "<mask>",
|
38 |
-
"lstrip": true,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
}
|
44 |
},
|
45 |
-
"
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
-
"cls_token": "<s>",
|
48 |
"eos_token": "</s>",
|
49 |
-
"
|
50 |
-
"mask_token": "<mask>",
|
51 |
"model_max_length": 1000000000000000019884624838656,
|
52 |
"pad_token": "<pad>",
|
53 |
-
"
|
54 |
-
"tokenizer_class": "
|
55 |
-
"trim_offsets": true,
|
56 |
"unk_token": "<unk>"
|
57 |
}
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"content": "<pad>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
"content": "</s>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
"content": "<unk>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
"clean_up_tokenization_spaces": true,
|
|
|
30 |
"eos_token": "</s>",
|
31 |
+
"extra_ids": 0,
|
|
|
32 |
"model_max_length": 1000000000000000019884624838656,
|
33 |
"pad_token": "<pad>",
|
34 |
+
"sp_model_kwargs": {},
|
35 |
+
"tokenizer_class": "T5Tokenizer",
|
|
|
36 |
"unk_token": "<unk>"
|
37 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c900bd072af3e4d868e8275ec571f98dcbdb20138c7185c62bc1541f0a2d91d6
|
3 |
size 4728
|