hiroshi-matsuda-rit
commited on
Commit
·
649e86b
1
Parent(s):
d54e9f4
add files
Browse files- .gitattributes +1 -0
- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- trainer_state.json +76 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "out/roberta3/checkpoint-1000",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
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": 1282,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.20.0.dev0",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2fc3c368968d75e4b29a8ea0c2c5a631c7168b1518952fa0f7210ca2cbc10d1
|
3 |
+
size 1569345
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6b48b98edacb03701acf4a7ca4105fc34f182063852bb2a4a2c5b4b848f7cc0
|
3 |
+
size 445047083
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef1f0dd5512911e16eed57604aa773745ecce5597ecf83eb8311f9b0a11cb8d
|
3 |
+
size 14503
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:018632b7efb97680221078f777b72fc854385a42730f0e76446b2116c7b5ff33
|
3 |
+
size 559
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15d7a00d8db0739c58b399f3c1bdfc92189e52fc2356e823cabd9929acb3bdc2
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "[PAD]",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7f87f538d8c73fb0a6a34efb7ba6e3488f920341119c02c208bce7965cf248e
|
3 |
+
size 810161
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"keep_accents": true,
|
7 |
+
"mask_token": {
|
8 |
+
"__type": "AddedToken",
|
9 |
+
"content": "[MASK]",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"name_or_path": "nlp-waseda/roberta-base-japanese",
|
16 |
+
"pad_token": "[PAD]",
|
17 |
+
"remove_space": true,
|
18 |
+
"sep_token": "[SEP]",
|
19 |
+
"sp_model_kwargs": {},
|
20 |
+
"special_tokens_map_file": null,
|
21 |
+
"tokenizer_class": "AlbertTokenizer",
|
22 |
+
"unk_token": "[UNK]"
|
23 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 79.36167076167077,
|
5 |
+
"global_step": 5000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 7.93,
|
12 |
+
"learning_rate": 4.603174603174603e-05,
|
13 |
+
"loss": 2.3851,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 15.86,
|
18 |
+
"learning_rate": 4.2063492063492065e-05,
|
19 |
+
"loss": 2.3266,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 23.8,
|
24 |
+
"learning_rate": 3.809523809523809e-05,
|
25 |
+
"loss": 2.2793,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 31.74,
|
30 |
+
"learning_rate": 3.412698412698413e-05,
|
31 |
+
"loss": 2.2354,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 39.68,
|
36 |
+
"learning_rate": 3.0158730158730158e-05,
|
37 |
+
"loss": 2.1978,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 47.61,
|
42 |
+
"learning_rate": 2.6190476190476192e-05,
|
43 |
+
"loss": 2.1656,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 55.55,
|
48 |
+
"learning_rate": 2.2222222222222223e-05,
|
49 |
+
"loss": 2.1374,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 63.49,
|
54 |
+
"learning_rate": 1.8253968253968254e-05,
|
55 |
+
"loss": 2.1132,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 71.42,
|
60 |
+
"learning_rate": 1.4285714285714285e-05,
|
61 |
+
"loss": 2.0931,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 79.36,
|
66 |
+
"learning_rate": 1.0317460317460318e-05,
|
67 |
+
"loss": 2.0763,
|
68 |
+
"step": 5000
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"max_steps": 6300,
|
72 |
+
"num_train_epochs": 100,
|
73 |
+
"total_flos": 2.720215956373635e+19,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e2e7e674b10b9e37c2deacd93968eb14231b51da8f464fa640943770e44aeb3
|
3 |
+
size 3183
|