Training in progress, step 11000
Browse files- checkpoint-11000/config.json +28 -0
- checkpoint-11000/optimizer.pt +3 -0
- checkpoint-11000/pytorch_model.bin +3 -0
- checkpoint-11000/rng_state_0.pth +3 -0
- checkpoint-11000/rng_state_1.pth +3 -0
- checkpoint-11000/rng_state_2.pth +3 -0
- checkpoint-11000/rng_state_3.pth +3 -0
- checkpoint-11000/rng_state_4.pth +3 -0
- checkpoint-11000/rng_state_5.pth +3 -0
- checkpoint-11000/rng_state_6.pth +3 -0
- checkpoint-11000/rng_state_7.pth +3 -0
- checkpoint-11000/scheduler.pt +3 -0
- checkpoint-11000/special_tokens_map.json +7 -0
- checkpoint-11000/tokenizer.json +0 -0
- checkpoint-11000/tokenizer_config.json +5 -0
- checkpoint-11000/trainer_state.json +0 -0
- checkpoint-11000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-11000/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-11000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc9c90ff3af8cc3422bc1dbac72be7948deabf5f8e0d90d2a4f38ea1fe7cc1b1
|
3 |
+
size 881521797
|
checkpoint-11000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6da9247c9d2e11cee0f6416c4ec3e030741a0aab0106ae58bfd7daa77cd92f6a
|
3 |
+
size 440772077
|
checkpoint-11000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6a8f9dcd85e5b854dfa860b77caa7b2c0a4530f212fd6ba0902357832da638e
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c7c6dcece353efb9ee5e8b8d70a29833797e89019308fbac8f243d48174c4cb
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cc2d2245357ac10b1ce7a8d7c4c611ab9efb6358055f66a8e642a7fe0733dca
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e20832c349cb2a93e24f047080071a8f4d93b3b7cd17d9ec2b7fa45509a0ed6
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fbe2731e4695e5399fdc935637164bfa54bd6d5c3b44eb5a5c39c4ec5776d6e
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1b48bf108abd8281d612406343e625cd042a80c7b4dff884894a796bccfbf77
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc18eae608daebfbd57cf491857c68a8e44f771b97f444beccf0dd1bb28bde8c
|
3 |
+
size 21623
|
checkpoint-11000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2828b5daaa2b78a00de42d44a8f803ea639dbe677c6219cd0029b20b77d87db
|
3 |
+
size 21623
|
checkpoint-11000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0e1ed05bbb826851a72aa835231721a015eb8f9593a0f55b8c60582fcf67cd4
|
3 |
+
size 627
|
checkpoint-11000/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-11000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-11000/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-11000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-11000/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 sha256:6da9247c9d2e11cee0f6416c4ec3e030741a0aab0106ae58bfd7daa77cd92f6a
|
3 |
size 440772077
|