End of training
Browse files- .gitignore +1 -0
- config.json +52 -0
- pytorch_model.bin +3 -0
- runs/Apr15_00-47-12_fa5dd7fa8be3/1649983732.7802498/events.out.tfevents.1649983732.fa5dd7fa8be3.70.1 +3 -0
- runs/Apr15_00-47-12_fa5dd7fa8be3/1649983855.623314/events.out.tfevents.1649983855.fa5dd7fa8be3.70.2 +3 -0
- runs/Apr15_00-47-12_fa5dd7fa8be3/1649983916.5339713/events.out.tfevents.1649983916.fa5dd7fa8be3.70.3 +3 -0
- runs/Apr15_00-47-12_fa5dd7fa8be3/events.out.tfevents.1649983732.fa5dd7fa8be3.70.0 +3 -0
- source.spm +0 -0
- special_tokens_map.json +1 -0
- target.spm +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AI-Lab-Makerere/lg_en",
|
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 |
+
"bad_words_ids": [
|
12 |
+
[
|
13 |
+
64171
|
14 |
+
]
|
15 |
+
],
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"classif_dropout": 0.0,
|
18 |
+
"classifier_dropout": 0.0,
|
19 |
+
"d_model": 512,
|
20 |
+
"decoder_attention_heads": 8,
|
21 |
+
"decoder_ffn_dim": 2048,
|
22 |
+
"decoder_layerdrop": 0.0,
|
23 |
+
"decoder_layers": 6,
|
24 |
+
"decoder_start_token_id": 64171,
|
25 |
+
"decoder_vocab_size": 64172,
|
26 |
+
"dropout": 0.1,
|
27 |
+
"encoder_attention_heads": 8,
|
28 |
+
"encoder_ffn_dim": 2048,
|
29 |
+
"encoder_layerdrop": 0.0,
|
30 |
+
"encoder_layers": 6,
|
31 |
+
"eos_token_id": 0,
|
32 |
+
"extra_pos_embeddings": 64172,
|
33 |
+
"forced_eos_token_id": 0,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"max_length": 512,
|
38 |
+
"max_position_embeddings": 512,
|
39 |
+
"model_type": "marian",
|
40 |
+
"normalize_before": false,
|
41 |
+
"normalize_embedding": false,
|
42 |
+
"num_beams": 6,
|
43 |
+
"num_hidden_layers": 6,
|
44 |
+
"pad_token_id": 64171,
|
45 |
+
"scale_embedding": true,
|
46 |
+
"share_encoder_decoder_embeddings": true,
|
47 |
+
"static_position_embeddings": true,
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.18.0",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 64172
|
52 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25abbce1e423a4cb90b3526306a4e6fab91e4d8f2d1325b43dc67df0e4fad41a
|
3 |
+
size 308319365
|
runs/Apr15_00-47-12_fa5dd7fa8be3/1649983732.7802498/events.out.tfevents.1649983732.fa5dd7fa8be3.70.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05392236402f86fa21e3a798f41441691003b14269bc4354ea628ee2e2db018a
|
3 |
+
size 5065
|
runs/Apr15_00-47-12_fa5dd7fa8be3/1649983855.623314/events.out.tfevents.1649983855.fa5dd7fa8be3.70.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:328380aaa094544eb22e1ded6dcfffad68e357e20d4c09b5940d0430c654bb76
|
3 |
+
size 5065
|
runs/Apr15_00-47-12_fa5dd7fa8be3/1649983916.5339713/events.out.tfevents.1649983916.fa5dd7fa8be3.70.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a901bebf4f5d9f49614240728ac9340c439ea96fab6753ffbbe8f1b4b60254dd
|
3 |
+
size 5065
|
runs/Apr15_00-47-12_fa5dd7fa8be3/events.out.tfevents.1649983732.fa5dd7fa8be3.70.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc28e58bccc62d1a921cadc3b90e96fb86d709cf3b529342f17bbfdae2d45c2d
|
3 |
+
size 13024
|
source.spm
ADDED
Binary file (707 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
Binary file (791 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"source_lang": "mul", "target_lang": "eng", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "AI-Lab-Makerere/lg_en", "tokenizer_class": "MarianTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6901e37b2ad3b7662d7acca2b40c7f361f0714fe1443b15549ad0d247f2485ff
|
3 |
+
size 3183
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|