Training in progress, step 15000
Browse files- checkpoint-15000/config.json +28 -0
- checkpoint-15000/optimizer.pt +3 -0
- checkpoint-15000/pytorch_model.bin +3 -0
- checkpoint-15000/rng_state_0.pth +3 -0
- checkpoint-15000/rng_state_1.pth +3 -0
- checkpoint-15000/rng_state_2.pth +3 -0
- checkpoint-15000/rng_state_3.pth +3 -0
- checkpoint-15000/rng_state_4.pth +3 -0
- checkpoint-15000/rng_state_5.pth +3 -0
- checkpoint-15000/rng_state_6.pth +3 -0
- checkpoint-15000/rng_state_7.pth +3 -0
- checkpoint-15000/scheduler.pt +3 -0
- checkpoint-15000/special_tokens_map.json +7 -0
- checkpoint-15000/tokenizer.json +0 -0
- checkpoint-15000/tokenizer_config.json +5 -0
- checkpoint-15000/trainer_state.json +0 -0
- checkpoint-15000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-15000/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-15000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb3f7deb6019619274e3bbd1518321a23211cd2c025732de500abfa66c6fbaf
|
3 |
+
size 881521797
|
checkpoint-15000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1540c59815c706dc7b27eaaae95e00ade639892d99ac57173e45e6c472de37a
|
3 |
+
size 440772077
|
checkpoint-15000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e90df5f866cbd653347829b4163971ef4997dec29821950e5e2cd3a64daeeae6
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8046a6217c57c3a8069ab314b611a76a255a428a7629f60e5bb6ff2325006235
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c96bcc6fda08c9fef02052abca60367b7693fca37b10c2a9ca5dab25575acba
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88a824bc46280a58e6ea6a4db81f8b2cbd887d60c41ed3d6925391c0caba928a
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22adaa6f16a6d2a57eaccd58626c59faf86423ad60fc2e6855ae32bd0e415c72
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d95fc3197fea70af62079469292c213a8ab4845e362b90fc5f4070129a6ae47
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d8736e706c90fef3a0260ffdfd4ae031982b10fd876fff61771a7d2ad258548
|
3 |
+
size 21623
|
checkpoint-15000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0bae5e83fe96d6d5a687ccf449eb92f46370d4d02e6acbd457073ef05f08c6e
|
3 |
+
size 21623
|
checkpoint-15000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d178ff6344dc6f3c0deb3e638bbe7249d295a5b9571711a07051b3d2acf4db29
|
3 |
+
size 627
|
checkpoint-15000/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-15000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/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-15000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/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:e1540c59815c706dc7b27eaaae95e00ade639892d99ac57173e45e6c472de37a
|
3 |
size 440772077
|