End of training
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- added_tokens.json +5 -0
- config.json +63 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May19_01-26-04_DESKTOP-2LG01LF/1684423571.9937332/events.out.tfevents.1684423571.DESKTOP-2LG01LF.16580.5 +3 -0
- runs/May19_01-26-04_DESKTOP-2LG01LF/events.out.tfevents.1684423571.DESKTOP-2LG01LF.16580.4 +3 -0
- runs/May19_01-42-13_DESKTOP-2LG01LF/1684424536.6791902/events.out.tfevents.1684424536.DESKTOP-2LG01LF.16580.7 +3 -0
- runs/May19_01-42-13_DESKTOP-2LG01LF/events.out.tfevents.1684424536.DESKTOP-2LG01LF.16580.6 +3 -0
- special_tokens_map.json +27 -0
- tokenizer_config.json +64 -0
- training_args.bin +3 -0
- vocab.json +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
vocab.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 54944,
|
3 |
+
"<mask>": 54946,
|
4 |
+
"<s>": 54945
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/blenderbot_small-90m",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BlenderbotForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 8,
|
19 |
+
"decoder_start_token_id": 1,
|
20 |
+
"do_blenderbot_90_layernorm": true,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 8,
|
26 |
+
"encoder_no_repeat_ngram_size": 3,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 0,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"gradient_checkpointing": false,
|
32 |
+
"id2label": {
|
33 |
+
"0": "LABEL_0",
|
34 |
+
"1": "LABEL_1",
|
35 |
+
"2": "LABEL_2"
|
36 |
+
},
|
37 |
+
"init_std": 0.02,
|
38 |
+
"is_encoder_decoder": true,
|
39 |
+
"label2id": {
|
40 |
+
"LABEL_0": 0,
|
41 |
+
"LABEL_1": 1,
|
42 |
+
"LABEL_2": 2
|
43 |
+
},
|
44 |
+
"layernorm_variant": "xlm",
|
45 |
+
"length_penalty": 0.65,
|
46 |
+
"max_length": 128,
|
47 |
+
"max_position_embeddings": 512,
|
48 |
+
"min_length": 20,
|
49 |
+
"model_type": "blenderbot",
|
50 |
+
"no_repeat_ngram_size": 3,
|
51 |
+
"normalize_before": false,
|
52 |
+
"normalize_embedding": true,
|
53 |
+
"num_beams": 10,
|
54 |
+
"num_hidden_layers": 8,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"scale_embedding": true,
|
57 |
+
"static_position_embeddings": false,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.29.1",
|
60 |
+
"unk_token_id": 3,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 54944
|
63 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"decoder_start_token_id": 1,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"length_penalty": 0.65,
|
8 |
+
"max_length": 128,
|
9 |
+
"min_length": 20,
|
10 |
+
"no_repeat_ngram_size": 3,
|
11 |
+
"num_beams": 10,
|
12 |
+
"pad_token_id": 0,
|
13 |
+
"transformers_version": "4.29.1"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08cf310e873f501575b0742cd7ed436342df2fd17047749dc9a689a09665279b
|
3 |
+
size 350368045
|
runs/May19_01-26-04_DESKTOP-2LG01LF/1684423571.9937332/events.out.tfevents.1684423571.DESKTOP-2LG01LF.16580.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d234fdb75b9dbf54da4a41d84942e152ffa4fea8af437fa0bc9c6b1210ef2a2
|
3 |
+
size 5886
|
runs/May19_01-26-04_DESKTOP-2LG01LF/events.out.tfevents.1684423571.DESKTOP-2LG01LF.16580.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2750fd5d31b29ee6bfe54277fe36c0dcfcb183101c7a4dc8eebf17c4714d227
|
3 |
+
size 4943
|
runs/May19_01-42-13_DESKTOP-2LG01LF/1684424536.6791902/events.out.tfevents.1684424536.DESKTOP-2LG01LF.16580.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:946f9284453569bb51638a376aafeeba5fcafc91f10bf34d577cbda5c9f3fae4
|
3 |
+
size 5886
|
runs/May19_01-42-13_DESKTOP-2LG01LF/events.out.tfevents.1684424536.DESKTOP-2LG01LF.16580.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f62081e6eabade82644fa5a072550746f689ff1bcb7489cc0b7d457110359c9b
|
3 |
+
size 5262
|
special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "__start__",
|
3 |
+
"cls_token": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"eos_token": "__end__",
|
11 |
+
"mask_token": {
|
12 |
+
"content": "<mask>",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"pad_token": "__end__",
|
19 |
+
"sep_token": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": "__unk__"
|
27 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "__start__",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "__end__",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"errors": "replace",
|
29 |
+
"mask_token": {
|
30 |
+
"__type": "AddedToken",
|
31 |
+
"content": "<mask>",
|
32 |
+
"lstrip": true,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"model_max_length": 1000000000000000019884624838656,
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "__null__",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"tokenizer_class": "BlenderbotTokenizer",
|
55 |
+
"tokenizer_file": null,
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "__unk__",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:483b092b54aedf4108f3ec7b4514dc8cfb39d413cdcda330edab1d33381e427e
|
3 |
+
size 3899
|
vocab.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8832092c8d923f8e995a0363a4d1caa5741d080d88367244098f9c553439da5
|
3 |
+
size 1046602
|