Training in progress, step 14000
Browse files- checkpoint-14000/config.json +28 -0
- checkpoint-14000/optimizer.pt +3 -0
- checkpoint-14000/pytorch_model.bin +3 -0
- checkpoint-14000/rng_state_0.pth +3 -0
- checkpoint-14000/rng_state_1.pth +3 -0
- checkpoint-14000/rng_state_2.pth +3 -0
- checkpoint-14000/rng_state_3.pth +3 -0
- checkpoint-14000/rng_state_4.pth +3 -0
- checkpoint-14000/rng_state_5.pth +3 -0
- checkpoint-14000/rng_state_6.pth +3 -0
- checkpoint-14000/rng_state_7.pth +3 -0
- checkpoint-14000/scheduler.pt +3 -0
- checkpoint-14000/special_tokens_map.json +7 -0
- checkpoint-14000/tokenizer.json +0 -0
- checkpoint-14000/tokenizer_config.json +5 -0
- checkpoint-14000/trainer_state.json +0 -0
- checkpoint-14000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-14000/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-14000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af24a66bcfee6367831a9e158f595e52a1c9db85959e195aa600363bd83e031f
|
3 |
+
size 881521797
|
checkpoint-14000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f512cebf1e4bd444c770715a7e9d288c4a2c46ac41cf564011d25aad0e6a2563
|
3 |
+
size 440772077
|
checkpoint-14000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8adf7ba43d2a062ab660f79e630eddfe08343d4bf0b5e0b90c5940f35ad83b99
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8eefa35e85e35eb05c0141b58fb5415e3249348688143e8f9bc30da7b839011
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40e8256be261f9822624e905d7b806583f3b6dbb60df80d6903717d3ac8f73fc
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7c573c2a9f7f4be197f14dca957d11f396d85eb03770ec34e7d66af3f164fc5
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56992baf76e803ff3622778713d42b7347f55aaf881dda875d4c402e236b6ce
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:187afdbc979248e4d82ba2ddff3beb2882acd9a57c8763ef63095bccc8cc1f18
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46aa258ca4c72fb620920a9bd57f61c583ed9fbdac8ab4f08cfaa51167758ad6
|
3 |
+
size 21623
|
checkpoint-14000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:672a59c0741a36991ed8b6a9e614b0ddabe6fd2ccbc2273835787a7fe41d9cf8
|
3 |
+
size 21623
|
checkpoint-14000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e809d664b27a86d2f7a9641ec1eae666e50958bfa68c53a31105a102589b940f
|
3 |
+
size 627
|
checkpoint-14000/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-14000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/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-14000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/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:f512cebf1e4bd444c770715a7e9d288c4a2c46ac41cf564011d25aad0e6a2563
|
3 |
size 440772077
|