Training in progress, step 17000
Browse files- checkpoint-17000/config.json +28 -0
- checkpoint-17000/optimizer.pt +3 -0
- checkpoint-17000/pytorch_model.bin +3 -0
- checkpoint-17000/rng_state_0.pth +3 -0
- checkpoint-17000/rng_state_1.pth +3 -0
- checkpoint-17000/rng_state_2.pth +3 -0
- checkpoint-17000/rng_state_3.pth +3 -0
- checkpoint-17000/rng_state_4.pth +3 -0
- checkpoint-17000/rng_state_5.pth +3 -0
- checkpoint-17000/rng_state_6.pth +3 -0
- checkpoint-17000/rng_state_7.pth +3 -0
- checkpoint-17000/scheduler.pt +3 -0
- checkpoint-17000/special_tokens_map.json +7 -0
- checkpoint-17000/tokenizer.json +0 -0
- checkpoint-17000/tokenizer_config.json +5 -0
- checkpoint-17000/trainer_state.json +0 -0
- checkpoint-17000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-17000/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MarindaForMaskedLMWithEdgePrediction"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"ep_add_linear_projection": true,
|
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-12,
|
16 |
+
"max_position_embeddings": 600,
|
17 |
+
"max_relative_position_embeddings": 8,
|
18 |
+
"model_type": "marinda",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 3,
|
22 |
+
"position_embedding_type": "mixed",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.31.0",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30523
|
28 |
+
}
|
checkpoint-17000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86cdf3c6d0f0966672f37271beb470fa82438e8a6095ab470b6fbc922ea73c6d
|
3 |
+
size 881521797
|
checkpoint-17000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abceecb6cec77326a56ce60e54fed7cb77e8c0804d78de2afe8547abb340765c
|
3 |
+
size 440772077
|
checkpoint-17000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:748094542206cc9270d71d9fa78fd21220c7a72950c388cc25bfca43072c1fae
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbf48ac5b2c29b6052f85768731844b69a819cba14fa0bc5e543f7bca2552453
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af7a38d66a646d0ba09b8ac918e5d7ce2424d673f98a5b9c3c5be6f361c8dcba
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f544585717f59c32480a8586c82d5181f0335b936236b996f1652bb275016fb7
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24599655e9204358f29303735255d85eae0cbb0c7ae0c50ae446fba600bf7c2d
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f9a01997ccfe013b0cef772917e8dbd6a41cd9878addcb885b08352a916c39
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5641fa735c2aa27d2c3db8160fd187f084c1b16de1df4edb677118df5bf5fe9
|
3 |
+
size 21623
|
checkpoint-17000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65afc30ceb98d4c285a0fcf0fa59d873ace1cad1428bef32f7e4c4edc915e55d
|
3 |
+
size 21623
|
checkpoint-17000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d7656f75884a9d0574117bbad6e85932149c98fc2745b4d7b8891e379caebd8
|
3 |
+
size 627
|
checkpoint-17000/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
checkpoint-17000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-17000/tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"tokenizer_class": "MarindaTokenizer"
|
5 |
+
}
|
checkpoint-17000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-17000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbbced2969d3c34b5ea7f356c253acf2a826f9e9dea1f238559fc37a4cf95a6d
|
3 |
+
size 4027
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 440772077
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abceecb6cec77326a56ce60e54fed7cb77e8c0804d78de2afe8547abb340765c
|
3 |
size 440772077
|