End of training
Browse files- added_tokens.json +1 -3
- config.json +17 -16
- generation_config.json +2 -1
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- runs/May19_11-51-14_DESKTOP-2LG01LF/1684461077.901282/events.out.tfevents.1684461077.DESKTOP-2LG01LF.12500.1 +3 -0
- runs/May19_11-51-14_DESKTOP-2LG01LF/events.out.tfevents.1684461077.DESKTOP-2LG01LF.12500.0 +3 -0
- runs/May19_11-54-25_DESKTOP-2LG01LF/1684461269.4669511/events.out.tfevents.1684461269.DESKTOP-2LG01LF.12500.3 +3 -0
- runs/May19_11-54-25_DESKTOP-2LG01LF/events.out.tfevents.1684461269.DESKTOP-2LG01LF.12500.2 +3 -0
- runs/May19_11-57-09_DESKTOP-2LG01LF/1684461433.3930838/events.out.tfevents.1684461433.DESKTOP-2LG01LF.12500.5 +3 -0
- runs/May19_11-57-09_DESKTOP-2LG01LF/events.out.tfevents.1684461433.DESKTOP-2LG01LF.12500.4 +3 -0
- special_tokens_map.json +22 -4
- tokenizer_config.json +6 -6
- training_args.bin +1 -1
- vocab.json +2 -2
added_tokens.json
CHANGED
@@ -1,5 +1,3 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"<mask>": 54946,
|
4 |
-
"<s>": 54945
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"<mask>": 8008
|
|
|
|
|
3 |
}
|
config.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm":
|
7 |
"architectures": [
|
8 |
"BlenderbotForConditionalGeneration"
|
9 |
],
|
@@ -11,20 +11,21 @@
|
|
11 |
"bos_token_id": 1,
|
12 |
"classif_dropout": 0.0,
|
13 |
"classifier_dropout": 0.0,
|
14 |
-
"d_model":
|
15 |
-
"decoder_attention_heads":
|
16 |
-
"decoder_ffn_dim":
|
17 |
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers":
|
19 |
"decoder_start_token_id": 1,
|
20 |
"do_blenderbot_90_layernorm": true,
|
21 |
"dropout": 0.1,
|
22 |
-
"encoder_attention_heads":
|
23 |
-
"encoder_ffn_dim":
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
-
"encoder_layers":
|
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,
|
@@ -41,17 +42,17 @@
|
|
41 |
"LABEL_1": 1,
|
42 |
"LABEL_2": 2
|
43 |
},
|
44 |
-
"layernorm_variant": "
|
45 |
"length_penalty": 0.65,
|
46 |
-
"max_length":
|
47 |
-
"max_position_embeddings":
|
48 |
"min_length": 20,
|
49 |
"model_type": "blenderbot",
|
50 |
"no_repeat_ngram_size": 3,
|
51 |
-
"normalize_before":
|
52 |
-
"normalize_embedding":
|
53 |
"num_beams": 10,
|
54 |
-
"num_hidden_layers":
|
55 |
"pad_token_id": 0,
|
56 |
"scale_embedding": true,
|
57 |
"static_position_embeddings": false,
|
@@ -59,5 +60,5 @@
|
|
59 |
"transformers_version": "4.29.1",
|
60 |
"unk_token_id": 3,
|
61 |
"use_cache": true,
|
62 |
-
"vocab_size":
|
63 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/blenderbot-400M-distill",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
"architectures": [
|
8 |
"BlenderbotForConditionalGeneration"
|
9 |
],
|
|
|
11 |
"bos_token_id": 1,
|
12 |
"classif_dropout": 0.0,
|
13 |
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1280,
|
15 |
+
"decoder_attention_heads": 32,
|
16 |
+
"decoder_ffn_dim": 5120,
|
17 |
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
"decoder_start_token_id": 1,
|
20 |
"do_blenderbot_90_layernorm": true,
|
21 |
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 32,
|
23 |
+
"encoder_ffn_dim": 5120,
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 2,
|
26 |
"encoder_no_repeat_ngram_size": 3,
|
27 |
"eos_token_id": 2,
|
28 |
+
"extra_layer_norm": false,
|
29 |
"extra_pos_embeddings": 0,
|
30 |
"force_bos_token_to_be_generated": false,
|
31 |
"forced_eos_token_id": 2,
|
|
|
42 |
"LABEL_1": 1,
|
43 |
"LABEL_2": 2
|
44 |
},
|
45 |
+
"layernorm_variant": "prelayernorm",
|
46 |
"length_penalty": 0.65,
|
47 |
+
"max_length": 60,
|
48 |
+
"max_position_embeddings": 128,
|
49 |
"min_length": 20,
|
50 |
"model_type": "blenderbot",
|
51 |
"no_repeat_ngram_size": 3,
|
52 |
+
"normalize_before": true,
|
53 |
+
"normalize_embedding": false,
|
54 |
"num_beams": 10,
|
55 |
+
"num_hidden_layers": 2,
|
56 |
"pad_token_id": 0,
|
57 |
"scale_embedding": true,
|
58 |
"static_position_embeddings": false,
|
|
|
60 |
"transformers_version": "4.29.1",
|
61 |
"unk_token_id": 3,
|
62 |
"use_cache": true,
|
63 |
+
"vocab_size": 8008
|
64 |
}
|
generation_config.json
CHANGED
@@ -2,10 +2,11 @@
|
|
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":
|
9 |
"min_length": 20,
|
10 |
"no_repeat_ngram_size": 3,
|
11 |
"num_beams": 10,
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"decoder_start_token_id": 1,
|
5 |
+
"encoder_no_repeat_ngram_size": 3,
|
6 |
"eos_token_id": 2,
|
7 |
"forced_eos_token_id": 2,
|
8 |
"length_penalty": 0.65,
|
9 |
+
"max_length": 60,
|
10 |
"min_length": 20,
|
11 |
"no_repeat_ngram_size": 3,
|
12 |
"num_beams": 10,
|
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9680b47d359a3349cf9d3a4d0262dc3fc96988a017c0d7dab1a8776a65da219
|
3 |
+
size 1459357453
|
runs/May19_11-51-14_DESKTOP-2LG01LF/1684461077.901282/events.out.tfevents.1684461077.DESKTOP-2LG01LF.12500.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8db77e2c546916ad27b750d5b81bbb4abbcb7d2d2e7de733ff3b689051376fe9
|
3 |
+
size 5886
|
runs/May19_11-51-14_DESKTOP-2LG01LF/events.out.tfevents.1684461077.DESKTOP-2LG01LF.12500.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06cb98adcac4fe0c65d66d33bf13b404e27ea74330380a942284da111296be7b
|
3 |
+
size 4943
|
runs/May19_11-54-25_DESKTOP-2LG01LF/1684461269.4669511/events.out.tfevents.1684461269.DESKTOP-2LG01LF.12500.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:795b3064a0db10cedf5ea6e85db9de17e9b561fccfd904b0421a3fab282d47b7
|
3 |
+
size 5886
|
runs/May19_11-54-25_DESKTOP-2LG01LF/events.out.tfevents.1684461269.DESKTOP-2LG01LF.12500.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2107dcb17e7ca2790bbb47ae3165f68d8f27adb330495ace2a2292f5595f73a9
|
3 |
+
size 4943
|
runs/May19_11-57-09_DESKTOP-2LG01LF/1684461433.3930838/events.out.tfevents.1684461433.DESKTOP-2LG01LF.12500.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ed238b18161c792706a346668180c9e933f782902c3e739e4bfea2109c59ecc
|
3 |
+
size 5886
|
runs/May19_11-57-09_DESKTOP-2LG01LF/events.out.tfevents.1684461433.DESKTOP-2LG01LF.12500.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7a565872a2360580bd6aafb1ca2021ca5822d7d55af9f45a89c5b035efbebfd
|
3 |
+
size 5297
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,11 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"cls_token": {
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
@@ -7,7 +13,13 @@
|
|
7 |
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
10 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"mask_token": {
|
12 |
"content": "<mask>",
|
13 |
"lstrip": true,
|
@@ -15,7 +27,7 @@
|
|
15 |
"rstrip": false,
|
16 |
"single_word": false
|
17 |
},
|
18 |
-
"pad_token": "
|
19 |
"sep_token": {
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
@@ -23,5 +35,11 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false
|
25 |
},
|
26 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"cls_token": {
|
10 |
"content": "<s>",
|
11 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
+
"pad_token": "</s>",
|
31 |
"sep_token": {
|
32 |
"content": "</s>",
|
33 |
"lstrip": false,
|
|
|
35 |
"rstrip": false,
|
36 |
"single_word": false
|
37 |
},
|
38 |
+
"unk_token": {
|
39 |
+
"content": "<unk>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
}
|
45 |
}
|
tokenizer_config.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space":
|
3 |
"bos_token": {
|
4 |
"__type": "AddedToken",
|
5 |
-
"content": "
|
6 |
"lstrip": false,
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
@@ -19,7 +19,7 @@
|
|
19 |
},
|
20 |
"eos_token": {
|
21 |
"__type": "AddedToken",
|
22 |
-
"content": "
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
25 |
"rstrip": false,
|
@@ -34,10 +34,10 @@
|
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
-
"model_max_length":
|
38 |
"pad_token": {
|
39 |
"__type": "AddedToken",
|
40 |
-
"content": "
|
41 |
"lstrip": false,
|
42 |
"normalized": true,
|
43 |
"rstrip": false,
|
@@ -55,7 +55,7 @@
|
|
55 |
"tokenizer_file": null,
|
56 |
"unk_token": {
|
57 |
"__type": "AddedToken",
|
58 |
-
"content": "
|
59 |
"lstrip": false,
|
60 |
"normalized": true,
|
61 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
3 |
"bos_token": {
|
4 |
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
|
|
19 |
},
|
20 |
"eos_token": {
|
21 |
"__type": "AddedToken",
|
22 |
+
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
25 |
"rstrip": false,
|
|
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
+
"model_max_length": 128,
|
38 |
"pad_token": {
|
39 |
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
"lstrip": false,
|
42 |
"normalized": true,
|
43 |
"rstrip": false,
|
|
|
55 |
"tokenizer_file": null,
|
56 |
"unk_token": {
|
57 |
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
"lstrip": false,
|
60 |
"normalized": true,
|
61 |
"rstrip": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3899
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:177de5e413c9a9a8ff0a26ad97f28132925b508b85c111b7693ca0bdc1176647
|
3 |
size 3899
|
vocab.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c648ba108a954432cac35063663611942b734416caf91147dda23064a753de
|
3 |
+
size 150920
|