Training in progress, step 25000
Browse files- checkpoint-25000/config.json +28 -0
- checkpoint-25000/optimizer.pt +3 -0
- checkpoint-25000/pytorch_model.bin +3 -0
- checkpoint-25000/rng_state_0.pth +3 -0
- checkpoint-25000/rng_state_1.pth +3 -0
- checkpoint-25000/rng_state_2.pth +3 -0
- checkpoint-25000/rng_state_3.pth +3 -0
- checkpoint-25000/rng_state_4.pth +3 -0
- checkpoint-25000/rng_state_5.pth +3 -0
- checkpoint-25000/rng_state_6.pth +3 -0
- checkpoint-25000/rng_state_7.pth +3 -0
- checkpoint-25000/scheduler.pt +3 -0
- checkpoint-25000/special_tokens_map.json +7 -0
- checkpoint-25000/tokenizer.json +0 -0
- checkpoint-25000/tokenizer_config.json +5 -0
- checkpoint-25000/trainer_state.json +0 -0
- checkpoint-25000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-25000/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-25000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bce402b50dc6820f2b6ac98193d09d08fd7adf146e11d672ab2f059b3e1f73e
|
3 |
+
size 881521797
|
checkpoint-25000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a78d8111e2a63160cdbcb2950eadf50c4c1a0b6615a284dc90ed2c88a0b39d7
|
3 |
+
size 440772077
|
checkpoint-25000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e621c4bbbac9b4281b58d3ba89ce75280cfef70a51b9c8ba4041c0a3043f9d1
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c4e97d94b37dde91c592058da3215eaa56dc13570b4d50f4293e03da11e4f7b
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e55e0695f6e15ed06010a62ede0b013b490de602951432c769ffe2a9128cf150
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdd441f68fd81580427863ad17a36af7f36d8bd09ec4b1966172a9102cb57954
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9387fc7f109e62a8a23abaab5f11b7d497e4f4066067fafff6899c396c43112a
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0091bc96eb416256a1a947cee19647ac34b79557748ef55851f76750004b30f6
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:070beb5a965269abcd829b49bd6951623ab8b58535f759e244c11e9aabf0ee38
|
3 |
+
size 21623
|
checkpoint-25000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98d209463c11a1077bc3c2fa0e4592273e7df8305c7f10cb6ba3e0e66a048df4
|
3 |
+
size 21623
|
checkpoint-25000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca8841cf73342861b1b69ee875170c21860dfde319556a9f258565fa91277564
|
3 |
+
size 627
|
checkpoint-25000/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-25000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-25000/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-25000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-25000/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 sha256:0a78d8111e2a63160cdbcb2950eadf50c4c1a0b6615a284dc90ed2c88a0b39d7
|
3 |
size 440772077
|