Training in progress, step 9000
Browse files- checkpoint-9000/config.json +28 -0
- checkpoint-9000/optimizer.pt +3 -0
- checkpoint-9000/pytorch_model.bin +3 -0
- checkpoint-9000/rng_state_0.pth +3 -0
- checkpoint-9000/rng_state_1.pth +3 -0
- checkpoint-9000/rng_state_2.pth +3 -0
- checkpoint-9000/rng_state_3.pth +3 -0
- checkpoint-9000/rng_state_4.pth +3 -0
- checkpoint-9000/rng_state_5.pth +3 -0
- checkpoint-9000/rng_state_6.pth +3 -0
- checkpoint-9000/rng_state_7.pth +3 -0
- checkpoint-9000/scheduler.pt +3 -0
- checkpoint-9000/special_tokens_map.json +7 -0
- checkpoint-9000/tokenizer.json +0 -0
- checkpoint-9000/tokenizer_config.json +5 -0
- checkpoint-9000/trainer_state.json +0 -0
- checkpoint-9000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-9000/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-9000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5ba95b8e3741d93f91dacd608d9c41e0426082827eef76d3a82b65dc302d41f
|
3 |
+
size 881521797
|
checkpoint-9000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1877460871f5ff5c422c50ff72bdd4bcd0d97017c387dcb0e9b167ffde0bf40
|
3 |
+
size 440772077
|
checkpoint-9000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8f217ffc4476d86d2cd484bdfd141c234b3da2f13d0bbcd1f164e677b9e261a
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75f41837ac1678c5a3f5a8e5787635c4eabf8d644f9e475a6525f503067e554
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378852a96f499afb4365ebffe9eeaadb5e56f0ce59c820aa5dbb5b69162fe9f1
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d47f45c8fab2710bcaf9da584954e050c7a920b0f0cbf3843c204469aa9a3857
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bedf796c37df61f6bf59748aaf74a9be1842ee7142498349ecc94e9c1c8730e7
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5896c365f591080091ef910491b4afe0b33cf1c24ee8f05ced0cd0153ee674d3
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab152313462c3858ce237e8e970e182185c7d9cf41f39cf7107edce9d67aa8f3
|
3 |
+
size 21623
|
checkpoint-9000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d33622b1a6f347de55ca0c1f6b30d8f5021c5e50292b0c70687d224e2554273f
|
3 |
+
size 21623
|
checkpoint-9000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98e99a53ca8e5ac7991f9540c302d16bf9817ed1583268245ec0817fb2781247
|
3 |
+
size 627
|
checkpoint-9000/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-9000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-9000/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-9000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-9000/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:c1877460871f5ff5c422c50ff72bdd4bcd0d97017c387dcb0e9b167ffde0bf40
|
3 |
size 440772077
|