Training in progress, step 12000
Browse files- checkpoint-12000/config.json +28 -0
- checkpoint-12000/optimizer.pt +3 -0
- checkpoint-12000/pytorch_model.bin +3 -0
- checkpoint-12000/rng_state_0.pth +3 -0
- checkpoint-12000/rng_state_1.pth +3 -0
- checkpoint-12000/rng_state_2.pth +3 -0
- checkpoint-12000/rng_state_3.pth +3 -0
- checkpoint-12000/rng_state_4.pth +3 -0
- checkpoint-12000/rng_state_5.pth +3 -0
- checkpoint-12000/rng_state_6.pth +3 -0
- checkpoint-12000/rng_state_7.pth +3 -0
- checkpoint-12000/scheduler.pt +3 -0
- checkpoint-12000/special_tokens_map.json +7 -0
- checkpoint-12000/tokenizer.json +0 -0
- checkpoint-12000/tokenizer_config.json +5 -0
- checkpoint-12000/trainer_state.json +0 -0
- checkpoint-12000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-12000/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-12000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80296340e456af6c27e000a55f514efd50499d71d92fa8c87e2a19e1ce9a0f72
|
3 |
+
size 881521797
|
checkpoint-12000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:937e44a24fb8e67022a1a41581bb44fd4f537c14e456a1701daac5a004074f04
|
3 |
+
size 440772077
|
checkpoint-12000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50fe9d5c31763cfe796b8476d418bc47ced9193e9ed51cb815777213f7049fa8
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c522487f8858f51ad7b76fc398708a8ac1ae32c5fe8ec28a17b1d6c03522c7bc
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24cc2b112fe78badbf032d97d65239a50df7b5eb47b472241449d72cddb7ea5c
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96e257120aed4f7cb37a1374c241fc6ffcf1de3bcb8d518100723383c3cb223c
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eac54a5eb51add79c5420af288e8a31a13f1ba2559363601f05d75aa30e977a4
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a88a2fa1e506b393f1ec91eba38319b9c5927604924554d23ea4b16850590207
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b42a8fde3522c6285979902a938464da134576be7dd99a8e5ef2b6cf4155949
|
3 |
+
size 21623
|
checkpoint-12000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7944951138098d6567f72fda38cd6013de8fb4b824610cb15ae6f044a8a79bd5
|
3 |
+
size 21623
|
checkpoint-12000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d8bde28e0995a07404431e4ba43cbb9e6b574cdd4de65a6355c706803047378
|
3 |
+
size 627
|
checkpoint-12000/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-12000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-12000/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-12000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-12000/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 sha256:937e44a24fb8e67022a1a41581bb44fd4f537c14e456a1701daac5a004074f04
|
3 |
size 440772077
|