Training in progress, step 8000
Browse files- checkpoint-8000/config.json +28 -0
- checkpoint-8000/optimizer.pt +3 -0
- checkpoint-8000/pytorch_model.bin +3 -0
- checkpoint-8000/rng_state_0.pth +3 -0
- checkpoint-8000/rng_state_1.pth +3 -0
- checkpoint-8000/rng_state_2.pth +3 -0
- checkpoint-8000/rng_state_3.pth +3 -0
- checkpoint-8000/rng_state_4.pth +3 -0
- checkpoint-8000/rng_state_5.pth +3 -0
- checkpoint-8000/rng_state_6.pth +3 -0
- checkpoint-8000/rng_state_7.pth +3 -0
- checkpoint-8000/scheduler.pt +3 -0
- checkpoint-8000/special_tokens_map.json +7 -0
- checkpoint-8000/tokenizer.json +0 -0
- checkpoint-8000/tokenizer_config.json +5 -0
- checkpoint-8000/trainer_state.json +0 -0
- checkpoint-8000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-8000/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-8000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b726060cfc7338b33744b0ae9636c509cdc6d9c426bf81846463c91df206cd22
|
3 |
+
size 881521797
|
checkpoint-8000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3900738131984e2ffb0a66a22f43074fc2361428f41de2cee9a8c31404a61f6
|
3 |
+
size 440772077
|
checkpoint-8000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fca3d8f5bc521c3d05e0a169693c9e96740ed22086ce968192575368e74998b8
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a2c8ee521b2405f818d6b0efcf64d53b94b77a37fb25e5c36f2363c65d933f3
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73a589ed4753e86d4acfab7e104664166f071edd6bb72a3fb5522e4d26ff08a1
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33d1077e350e17e904e81fd3f6bed3c16c2502e306ed1168d2673c2c923f5158
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf286f5cd52f803c50d8ac2be9ac79ece317e618898bf0f1499a7a375b53d7ac
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216b7d60bcacf0efea403675fb1decc3ffffda86347d6a37ee62a60461f7f9bb
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95bdabbb521c544334d9ec694c5b797cb95a88f720fdd197c9a23c6d3a673610
|
3 |
+
size 21623
|
checkpoint-8000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:496cb70e38f16e0b10c501330094d9e9a54e1b8258afc09bc4108b12c0f188d7
|
3 |
+
size 21623
|
checkpoint-8000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e743ddb7b1580164a308e3b6edf2bf801581c9b428e1aa470be8e8e403dd538
|
3 |
+
size 627
|
checkpoint-8000/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-8000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-8000/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-8000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-8000/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:b3900738131984e2ffb0a66a22f43074fc2361428f41de2cee9a8c31404a61f6
|
3 |
size 440772077
|