Training in progress, step 500
Browse files- config.json +56 -0
- model.safetensors +3 -0
- runs/Dec24_05-12-01_6c2867b5126f/events.out.tfevents.1735017135.6c2867b5126f.204.2 +3 -0
- runs/Dec24_05-17-30_6c2867b5126f/events.out.tfevents.1735017470.6c2867b5126f.204.3 +3 -0
- source.spm +0 -0
- special_tokens_map.json +23 -0
- target.spm +0 -0
- tokenizer_config.json +39 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/opus-mt-mul-en-finetuned-en-to-dz-n1/checkpoint-500",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 64109,
|
20 |
+
"decoder_vocab_size": 64110,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 8,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 0,
|
27 |
+
"extra_pos_embeddings": 64110,
|
28 |
+
"forced_eos_token_id": 0,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_length": null,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "marian",
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": null,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 64109,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"share_encoder_decoder_embeddings": true,
|
51 |
+
"static_position_embeddings": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.47.1",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 64110
|
56 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9f2d9a09b5a20f65a0cc6c457efcc90d4d2d892adf24bf409ac93b8d0227794
|
3 |
+
size 308136760
|
runs/Dec24_05-12-01_6c2867b5126f/events.out.tfevents.1735017135.6c2867b5126f.204.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35d06b4719f8ffec4775dce50b09521ac3bf56ea4e622d324138774c8610740a
|
3 |
+
size 6932
|
runs/Dec24_05-17-30_6c2867b5126f/events.out.tfevents.1735017470.6c2867b5126f.204.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b19718cccb80798e1b083f913445d9c29bd8937695cf30c9bb0ffc765c73539
|
3 |
+
size 6222
|
source.spm
ADDED
Binary file (790 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
target.spm
ADDED
Binary file (707 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "</s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"64109": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": false,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"extra_special_tokens": {},
|
31 |
+
"model_max_length": 512,
|
32 |
+
"pad_token": "<pad>",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "eng",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "mul",
|
37 |
+
"tokenizer_class": "MarianTokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f57ae7e42574d60eea4b5f4c20e2a90da2bad357d5b6c8b733db54a65f93de7
|
3 |
+
size 5496
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|