Training in progress, step 13000
Browse files- checkpoint-13000/config.json +28 -0
- checkpoint-13000/optimizer.pt +3 -0
- checkpoint-13000/pytorch_model.bin +3 -0
- checkpoint-13000/rng_state_0.pth +3 -0
- checkpoint-13000/rng_state_1.pth +3 -0
- checkpoint-13000/rng_state_2.pth +3 -0
- checkpoint-13000/rng_state_3.pth +3 -0
- checkpoint-13000/rng_state_4.pth +3 -0
- checkpoint-13000/rng_state_5.pth +3 -0
- checkpoint-13000/rng_state_6.pth +3 -0
- checkpoint-13000/rng_state_7.pth +3 -0
- checkpoint-13000/scheduler.pt +3 -0
- checkpoint-13000/special_tokens_map.json +7 -0
- checkpoint-13000/tokenizer.json +0 -0
- checkpoint-13000/tokenizer_config.json +5 -0
- checkpoint-13000/trainer_state.json +0 -0
- checkpoint-13000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-13000/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-13000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a522d8d8a12dbcd958f55cfbac5a1f97daa48bbcc057114c308df82958ecbd6c
|
3 |
+
size 881521797
|
checkpoint-13000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:337dfeeff968e2448c44fdaa6d2db0b2e84088d3868306691ff8699b35900d46
|
3 |
+
size 440772077
|
checkpoint-13000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b347e5eed167c28d4c893e67630a1de386dc683b485442d61c2ab678cf10b29
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7025c6e6e050625a39e2d83be66743e2df1f92ad5c92f17c29c35a66116fe05
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3851d4da9161e3792b54728d22c0e65bce5b0e2b74bb053a7cb98ea53bad14e
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c6ee406fd886854aec51d1a32bd6c4a86e3f3fe18398755628c94cfc80baad9
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b78457e16207c2ca1b6294c087ae2c29f86403dc6051254b7972bc2b5c2d97a
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8429dd1df4e7bab17408f3822ec7fddfff7959101044f8f59af31e53f4cc258c
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8f7c283360ef6fbf1225f8a6bd5e5ede182637f55a859952897e55eb82f6c34
|
3 |
+
size 21623
|
checkpoint-13000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae420027c0befea9035c5d1e8361b256b5e9c448c9be5083cdb72140d01150e
|
3 |
+
size 21623
|
checkpoint-13000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57fa25eaa3dec315ee6e986e1b2e543bd441bdfb94e8b3016c430114f171d70b
|
3 |
+
size 627
|
checkpoint-13000/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-13000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-13000/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-13000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-13000/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 sha256:337dfeeff968e2448c44fdaa6d2db0b2e84088d3868306691ff8699b35900d46
|
3 |
size 440772077
|