Training in progress, step 16000
Browse files- checkpoint-16000/config.json +28 -0
- checkpoint-16000/optimizer.pt +3 -0
- checkpoint-16000/pytorch_model.bin +3 -0
- checkpoint-16000/rng_state_0.pth +3 -0
- checkpoint-16000/rng_state_1.pth +3 -0
- checkpoint-16000/rng_state_2.pth +3 -0
- checkpoint-16000/rng_state_3.pth +3 -0
- checkpoint-16000/rng_state_4.pth +3 -0
- checkpoint-16000/rng_state_5.pth +3 -0
- checkpoint-16000/rng_state_6.pth +3 -0
- checkpoint-16000/rng_state_7.pth +3 -0
- checkpoint-16000/scheduler.pt +3 -0
- checkpoint-16000/special_tokens_map.json +7 -0
- checkpoint-16000/tokenizer.json +0 -0
- checkpoint-16000/tokenizer_config.json +5 -0
- checkpoint-16000/trainer_state.json +0 -0
- checkpoint-16000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-16000/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-16000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:344d1cf5bec2023d079da6fa047ee599c77d120c2fe6028d012ebcda83b7d629
|
3 |
+
size 881521797
|
checkpoint-16000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d6d64180855ddc0744cd993df62109e8c38ff2a3e45a47e5361acaf6be302d1
|
3 |
+
size 440772077
|
checkpoint-16000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bda142e15503f6960890788c9c7104a22f5c22328d6b1e24e2d3026ed1de79bd
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ece093d30342d78a31cee909d45651eabf48357abeb054d2c5af46afaf7ea22e
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc7902e51800aa5c8ad64340ecf6cb850820b47eadeacb9f862a37207c0b598
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7d86b6b63f6583b38616a2901d09d927c4209666a7b2ef1b043b1a64fcc3e43
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86379c89160cd8e99aa87c0e57940cf4cb9b30d4e703e1a6f28e570984194c5e
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fed14e0accf20f62f8b61134946e1ddf4fbf2cebaf7cf62cb5d0386ff18367ff
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82c99b05b85214d275aeb7631a9cada2f4d915f1eb3e171115724aa1db213bef
|
3 |
+
size 21623
|
checkpoint-16000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94521798681a1837cf85e17656ba96ea212df19e044ca8702ab84e0918033992
|
3 |
+
size 21623
|
checkpoint-16000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:859c41f1c601a550bc1a8ad057dde91336b0eec131d3a35286292ec0fb3d4eac
|
3 |
+
size 627
|
checkpoint-16000/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-16000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-16000/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-16000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-16000/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 sha256:7d6d64180855ddc0744cd993df62109e8c38ff2a3e45a47e5361acaf6be302d1
|
3 |
size 440772077
|