Training in progress, step 6000
Browse files- checkpoint-6000/config.json +28 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/pytorch_model.bin +3 -0
- checkpoint-6000/rng_state_0.pth +3 -0
- checkpoint-6000/rng_state_1.pth +3 -0
- checkpoint-6000/rng_state_2.pth +3 -0
- checkpoint-6000/rng_state_3.pth +3 -0
- checkpoint-6000/rng_state_4.pth +3 -0
- checkpoint-6000/rng_state_5.pth +3 -0
- checkpoint-6000/rng_state_6.pth +3 -0
- checkpoint-6000/rng_state_7.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/special_tokens_map.json +7 -0
- checkpoint-6000/tokenizer.json +0 -0
- checkpoint-6000/tokenizer_config.json +5 -0
- checkpoint-6000/trainer_state.json +0 -0
- checkpoint-6000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-6000/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-6000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fd7ede3547da213333d42e4ffcf99c0dca30deb4e77af271a01ccb4e27474c8
|
3 |
+
size 881521797
|
checkpoint-6000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86282bfd46f32d6e05b61e7b23e1a86b0597f90a3211aa2397631af9791a9889
|
3 |
+
size 440772077
|
checkpoint-6000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:506e18e37cdcd6f69cd2f1fa60ee5a367d02479a58799b3b90809c380473ad5b
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7a716a5e17bc8569152bb4abb94e88d0331fb238f9bd51b16d1c376ffc2bbd9
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82bba60bb349e436036b3c61b604ebad867252584504f649dc33ef1f3bac70a4
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2782c7cf79284b13043404f2b76082dd877e9ddea242d63ba338c3ad7539f645
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb8f152486c584ccd26d7b92e86ac5b2f9dc04e3f77ceda207cfc45031a53da8
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e85249d14f271f0eeb0c1219e51a78df8fba624d5e85cb844318adc86610162
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c274b025518c9eca3a45d3566af7a41d4e5a87d938ac9006144095546ec83ee
|
3 |
+
size 21623
|
checkpoint-6000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c27fb35b49403a14504be88ff3aade1ce96e7f200273d6dae5f02d8cb25c1a8
|
3 |
+
size 21623
|
checkpoint-6000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29293b1e08dd561c897f0bc222762d6a4f97d7d594e6174f2a6edf67812c3f85
|
3 |
+
size 627
|
checkpoint-6000/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-6000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6000/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-6000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6000/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 sha256:86282bfd46f32d6e05b61e7b23e1a86b0597f90a3211aa2397631af9791a9889
|
3 |
size 440772077
|