Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +54 -0
- pytorch_model.bin +3 -0
- runs/Nov29_19-45-27_ffsouza/1638226737.5379748/events.out.tfevents.1638226737.ffsouza.13313.1 +3 -0
- runs/Nov29_19-45-27_ffsouza/1638226865.5668783/events.out.tfevents.1638226865.ffsouza.13313.2 +3 -0
- runs/Nov29_19-45-27_ffsouza/events.out.tfevents.1638226737.ffsouza.13313.0 +3 -0
- runs/Nov29_20-01-18_ffsouza/1638226890.147298/events.out.tfevents.1638226890.ffsouza.13313.4 +3 -0
- runs/Nov29_20-01-18_ffsouza/events.out.tfevents.1638226890.ffsouza.13313.3 +3 -0
- runs/Nov29_20-06-42_ffsouza/1638227214.2790768/events.out.tfevents.1638227214.ffsouza.18902.1 +3 -0
- runs/Nov29_20-06-42_ffsouza/events.out.tfevents.1638227214.ffsouza.18902.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sshleifer/tiny-mbart",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": true,
|
8 |
+
"architectures": [
|
9 |
+
"MBartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 2,
|
16 |
+
"decoder_attention_heads": 1,
|
17 |
+
"decoder_ffn_dim": 4,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"encoder_attention_heads": 1,
|
22 |
+
"encoder_ffn_dim": 4,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 2,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"extra_pos_embeddings": 2,
|
27 |
+
"forced_eos_token_id": 2,
|
28 |
+
"id2label": {
|
29 |
+
"0": "LABEL_0",
|
30 |
+
"1": "LABEL_1",
|
31 |
+
"2": "LABEL_2"
|
32 |
+
},
|
33 |
+
"init_std": 0.02,
|
34 |
+
"is_encoder_decoder": true,
|
35 |
+
"label2id": {
|
36 |
+
"LABEL_0": 0,
|
37 |
+
"LABEL_1": 1,
|
38 |
+
"LABEL_2": 2
|
39 |
+
},
|
40 |
+
"max_position_embeddings": 1024,
|
41 |
+
"model_type": "mbart",
|
42 |
+
"normalize_before": true,
|
43 |
+
"normalize_embedding": true,
|
44 |
+
"num_beams": 2,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"output_past": true,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"scale_embedding": true,
|
49 |
+
"static_position_embeddings": false,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.12.5",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 250027
|
54 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73f4aba95bd5e2a878122352bac0491ce81e91fb2423d5784b7d88254d89d806
|
3 |
+
size 3052101
|
runs/Nov29_19-45-27_ffsouza/1638226737.5379748/events.out.tfevents.1638226737.ffsouza.13313.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf5d0af251525a5560be30f34e2c163b22204ba15753eda9ecc68301626fa288
|
3 |
+
size 4776
|
runs/Nov29_19-45-27_ffsouza/1638226865.5668783/events.out.tfevents.1638226865.ffsouza.13313.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ae4796fbd1b1dfa2b7b9ab62091ecb8b60c95076338ccf74459c82704a693b0
|
3 |
+
size 4776
|
runs/Nov29_19-45-27_ffsouza/events.out.tfevents.1638226737.ffsouza.13313.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f461af260da22af5d02f333f016542b3a6b0b1660dcd976165b4d43025c75cad
|
3 |
+
size 7762
|
runs/Nov29_20-01-18_ffsouza/1638226890.147298/events.out.tfevents.1638226890.ffsouza.13313.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1409ea1a99e4eb1a619c9432421ed1fdebe26042ad379118d6a3f43088aa67e0
|
3 |
+
size 4776
|
runs/Nov29_20-01-18_ffsouza/events.out.tfevents.1638226890.ffsouza.13313.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3e98186b97a66b7b35860ba5d2f8dc3c57f2d4dd99d47050dd686c5585a8502
|
3 |
+
size 3899
|
runs/Nov29_20-06-42_ffsouza/1638227214.2790768/events.out.tfevents.1638227214.ffsouza.18902.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6582066e6def019a20990d27e38ade7560a93735daaadfe1c55082116a581501
|
3 |
+
size 4776
|
runs/Nov29_20-06-42_ffsouza/events.out.tfevents.1638227214.ffsouza.18902.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bae19ef964a84aa9b8842331f55666ecfbf975752ff4ed97be3b2e49db9deb0
|
3 |
+
size 4056
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "src_lang": null, "tgt_lang": null, "additional_special_tokens": null, "model_max_length": 1024, "special_tokens_map_file": "/home/ffsouza/.cache/huggingface/transformers/33fa7894ab257a74cede3060dca6d2fc609918785e80160f6c057723ece47292.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "sshleifer/tiny-mbart", "sp_model_kwargs": {}, "tokenizer_class": "MBartTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3008fcbc1f4b651bcdd644678c2f8f616ae1104165a676d16aee7c7673f06069
|
3 |
+
size 2991
|