Training in progress, step 19000
Browse files- checkpoint-19000/config.json +28 -0
- checkpoint-19000/optimizer.pt +3 -0
- checkpoint-19000/pytorch_model.bin +3 -0
- checkpoint-19000/rng_state_0.pth +3 -0
- checkpoint-19000/rng_state_1.pth +3 -0
- checkpoint-19000/rng_state_2.pth +3 -0
- checkpoint-19000/rng_state_3.pth +3 -0
- checkpoint-19000/rng_state_4.pth +3 -0
- checkpoint-19000/rng_state_5.pth +3 -0
- checkpoint-19000/rng_state_6.pth +3 -0
- checkpoint-19000/rng_state_7.pth +3 -0
- checkpoint-19000/scheduler.pt +3 -0
- checkpoint-19000/special_tokens_map.json +7 -0
- checkpoint-19000/tokenizer.json +0 -0
- checkpoint-19000/tokenizer_config.json +5 -0
- checkpoint-19000/trainer_state.json +0 -0
- checkpoint-19000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-19000/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-19000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b37e7f55d1413a5307e4183c0e3bd9fa679c85847d44b25cda690ce682ec000
|
3 |
+
size 881521797
|
checkpoint-19000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f323e1b3ed65c603edb4095e114ca83d99002212944ace1dbf196306a0061a34
|
3 |
+
size 440772077
|
checkpoint-19000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9bc7a805df3467f7adc5fe0cdcbbd8f561bb26f6c28431b13b3fc8d1527d24b
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0150a04e0a091f45227e807dcde07de7bf6119391f8f305a7b6450f4d418338b
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7733ff79c59162aeb2133945614b1ed3614d04d1217706e69d78978fbf1c7669
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0998817b66c7b138dea8ab28ba310a3acd2c206f69e7c02333607911a954b4c
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8869527f59213267a77be046ab3e33ce238532440637bd419fc1f72938abcda
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14cb329fb5c2a2bc3e81e5ac059391079579a7852f8ed92bc3b48b154b2a2558
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8f673a544d56f350c3a1e27bf58dc81d1c4a2b8534129eb10bc5db782ea91fb
|
3 |
+
size 21623
|
checkpoint-19000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a0b3c39cf429f89394c9051e8e99cfbff3fe47af08e1bc9e80d2aca8304870
|
3 |
+
size 21623
|
checkpoint-19000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dbdf85cc26c317c11ba4696f06c76ba634196e7abbc6b92e0056b4304931df4
|
3 |
+
size 627
|
checkpoint-19000/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-19000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-19000/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-19000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-19000/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:f323e1b3ed65c603edb4095e114ca83d99002212944ace1dbf196306a0061a34
|
3 |
size 440772077
|