Training in progress, epoch 1
Browse files- config.json +62 -0
- model.safetensors +3 -0
- runs/Dec29_15-29-08_5afd44ae1cda/events.out.tfevents.1703863759.5afd44ae1cda.1892.0 +3 -0
- runs/Dec29_15-33-28_5afd44ae1cda/events.out.tfevents.1703864018.5afd44ae1cda.1892.1 +3 -0
- runs/Dec29_15-34-35_5afd44ae1cda/events.out.tfevents.1703864088.5afd44ae1cda.1892.2 +3 -0
- runs/Dec29_15-35-56_5afd44ae1cda/events.out.tfevents.1703864175.5afd44ae1cda.1892.3 +3 -0
- runs/Dec29_15-37-39_5afd44ae1cda/events.out.tfevents.1703864270.5afd44ae1cda.1892.4 +3 -0
- runs/Dec29_15-39-02_5afd44ae1cda/events.out.tfevents.1703864353.5afd44ae1cda.1892.5 +3 -0
- runs/Dec29_15-42-12_5afd44ae1cda/events.out.tfevents.1703864545.5afd44ae1cda.1892.6 +3 -0
- runs/Dec29_15-42-12_5afd44ae1cda/events.out.tfevents.1703866094.5afd44ae1cda.1892.7 +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +39 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
59513
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 59513,
|
26 |
+
"decoder_vocab_size": 59514,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 8,
|
29 |
+
"encoder_ffn_dim": 2048,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 0,
|
33 |
+
"forced_eos_token_id": 0,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1",
|
38 |
+
"2": "LABEL_2"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_length": 512,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "marian",
|
50 |
+
"normalize_before": false,
|
51 |
+
"normalize_embedding": false,
|
52 |
+
"num_beams": 4,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 59513,
|
55 |
+
"scale_embedding": true,
|
56 |
+
"share_encoder_decoder_embeddings": true,
|
57 |
+
"static_position_embeddings": true,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.35.2",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 59514
|
62 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab47b5a72f4d14c05886953f8a42844e08378a4dc307d67bca574a4611900953
|
3 |
+
size 298705768
|
runs/Dec29_15-29-08_5afd44ae1cda/events.out.tfevents.1703863759.5afd44ae1cda.1892.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcf985baf56a6441ad509cefa4b64ac18945dcdf935d906bb88f810c712c83db
|
3 |
+
size 342
|
runs/Dec29_15-33-28_5afd44ae1cda/events.out.tfevents.1703864018.5afd44ae1cda.1892.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f7facd08480a3d8b62455fa4e7f67b7cbad4ce3a6b92c0b1766949182e69878
|
3 |
+
size 342
|
runs/Dec29_15-34-35_5afd44ae1cda/events.out.tfevents.1703864088.5afd44ae1cda.1892.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f26d3be4a293e8b1b6a40b9aab19dcd20c74a4b8fb038b07733eeb3a42937640
|
3 |
+
size 5418
|
runs/Dec29_15-35-56_5afd44ae1cda/events.out.tfevents.1703864175.5afd44ae1cda.1892.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ab1cf592d0e77d00dd438dfe86aa0b4232ebb1e33480b2e3c1c40d64f0d59a2
|
3 |
+
size 5418
|
runs/Dec29_15-37-39_5afd44ae1cda/events.out.tfevents.1703864270.5afd44ae1cda.1892.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f0012184a6d6165850e8c7319bf1ecc5ab283ce72a04c6dd0d761a5a5973cb
|
3 |
+
size 342
|
runs/Dec29_15-39-02_5afd44ae1cda/events.out.tfevents.1703864353.5afd44ae1cda.1892.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54b4d2fcc6512eccb3b7a12cf88a03af3376b91c81fab2f353f0df3235d27387
|
3 |
+
size 342
|
runs/Dec29_15-42-12_5afd44ae1cda/events.out.tfevents.1703864545.5afd44ae1cda.1892.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd4130a87f5d0432108bf0a3e6c38c6ae0fcc8f10ddc92f693afcc6d8b860836
|
3 |
+
size 342
|
runs/Dec29_15-42-12_5afd44ae1cda/events.out.tfevents.1703866094.5afd44ae1cda.1892.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1df09877d288b79adcc239eb252cc3e5ca2e8617bac79463f6053d5c9c29926b
|
3 |
+
size 7145
|
source.spm
ADDED
Binary file (778 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (802 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 |
+
"59513": {
|
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": true,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"model_max_length": 512,
|
31 |
+
"pad_token": "<pad>",
|
32 |
+
"return_tensors": "pt",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "en",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "fr",
|
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:dc19d401b0af8b2228ccc5f165cf63c623ffdc659277bc52b91a510a1a330267
|
3 |
+
size 4792
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|