Tristan Thrush
commited on
Commit
·
071f134
1
Parent(s):
4a5ea74
Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +27 -0
- logs/1670820975.9072165/events.out.tfevents.1670820975.tristan-olm-training-a100-80.9040.1 +3 -0
- logs/1670822165.2464192/events.out.tfevents.1670822165.tristan-olm-training-a100-80.9671.1 +3 -0
- logs/events.out.tfevents.1670820975.tristan-olm-training-a100-80.9040.0 +3 -0
- logs/events.out.tfevents.1670822165.tristan-olm-training-a100-80.9671.0 +3 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.24.0",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
logs/1670820975.9072165/events.out.tfevents.1670820975.tristan-olm-training-a100-80.9040.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25187b66fbd092a65d9cbf359c556088af43dfdabd287cd23c7b68457c4fa8e6
|
3 |
+
size 5575
|
logs/1670822165.2464192/events.out.tfevents.1670822165.tristan-olm-training-a100-80.9671.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aba839efae3a752272dd9f8b1a8a4672cb849d98e167f3f31b4d425d6407b1e
|
3 |
+
size 5575
|
logs/events.out.tfevents.1670820975.tristan-olm-training-a100-80.9040.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:164a7f175aa8f3ad9377be3b5d65f62d079024497ad8b7434c3d4e3d2917f762
|
3 |
+
size 4135
|
logs/events.out.tfevents.1670822165.tristan-olm-training-a100-80.9671.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f3bcb3b24e4027348f4de27098f14fcf0ff98b5ab89ea3dbc175174fe50420e
|
3 |
+
size 8844
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a26dd54e72db6237c426710fcfe55f13950bbff63201b4b3a851730a69c48403
|
3 |
+
size 498863417
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"errors": "replace",
|
7 |
+
"mask_token": {
|
8 |
+
"__type": "AddedToken",
|
9 |
+
"content": "<mask>",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"model_max_length": 512,
|
16 |
+
"name_or_path": "Tristan/olm-tokenizer",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"special_tokens_map_file": null,
|
20 |
+
"tokenizer_class": "RobertaTokenizer",
|
21 |
+
"trim_offsets": true,
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2400a3d7d41a567c115c775613a80047012e7f119032f775268c4926710b98af
|
3 |
+
size 3451
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|