Training in progress, step 18000
Browse files- checkpoint-18000/config.json +28 -0
- checkpoint-18000/optimizer.pt +3 -0
- checkpoint-18000/pytorch_model.bin +3 -0
- checkpoint-18000/rng_state_0.pth +3 -0
- checkpoint-18000/rng_state_1.pth +3 -0
- checkpoint-18000/rng_state_2.pth +3 -0
- checkpoint-18000/rng_state_3.pth +3 -0
- checkpoint-18000/rng_state_4.pth +3 -0
- checkpoint-18000/rng_state_5.pth +3 -0
- checkpoint-18000/rng_state_6.pth +3 -0
- checkpoint-18000/rng_state_7.pth +3 -0
- checkpoint-18000/scheduler.pt +3 -0
- checkpoint-18000/special_tokens_map.json +7 -0
- checkpoint-18000/tokenizer.json +0 -0
- checkpoint-18000/tokenizer_config.json +5 -0
- checkpoint-18000/trainer_state.json +0 -0
- checkpoint-18000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-18000/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-18000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:620985c84228f847b94d6613043e7d6acea7592401ab6bc017b965f8db33a785
|
3 |
+
size 881521797
|
checkpoint-18000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:016493a1dba2fefdb505f4c2e40e0b6af929b74f168b208239dcc057a1a5efa8
|
3 |
+
size 440772077
|
checkpoint-18000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84b1e63141f3c797a6f77e87690535f224e59e76db8bc6fa44bc4c051c784a20
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d84082d36b504f1b908b5a81796598baa7c75c74a9910c14b09a8f35192d44d
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e066a6bf8782fc9ab578ebba6748c579b1a3af7ef20c2d044ffbdfc7c71ff1a
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82160516ac855d21d80ffb3fabba24ec1451a8f7d90939ef925e6d946857982f
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfbc7dbbfd413c6f9b4e6fe5d63054262b12b5fe4f833bf3a79f88230e79be9f
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c0a65165e21d5d36c54d082ac0195fc6282abaa517d1df0113ddf3e471a2c02
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c775b579f3f171b29e22ee0accebffc57dbbe8d5ce909024046c0aebff91bfa2
|
3 |
+
size 21623
|
checkpoint-18000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8421a251eb5b84dc430ff16b5720420f402982c5baebeb4b91e100c0dff1d19
|
3 |
+
size 21623
|
checkpoint-18000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25e0ec244778df9f12ccd248be46ae2cb9ff9d00b7dcf5ec2a9eb3801bf3b229
|
3 |
+
size 627
|
checkpoint-18000/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-18000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-18000/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-18000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-18000/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 sha256:016493a1dba2fefdb505f4c2e40e0b6af929b74f168b208239dcc057a1a5efa8
|
3 |
size 440772077
|