Training in progress, step 500
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +52 -0
- pytorch_model.bin +3 -0
- runs/Feb15_08-39-35_43aace13c501/1676450395.842999/events.out.tfevents.1676450395.43aace13c501.1030.1 +3 -0
- runs/Feb15_08-39-35_43aace13c501/events.out.tfevents.1676450395.43aace13c501.1030.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +3 -0
- tokenizer_config.json +6 -0
- training_args.bin +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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "digit82/kobart-summarization",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.1,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 1,
|
27 |
+
"extra_pos_embeddings": 2,
|
28 |
+
"force_bos_token_to_be_generated": false,
|
29 |
+
"forced_eos_token_id": 2,
|
30 |
+
"id2label": {
|
31 |
+
"0": "NEGATIVE",
|
32 |
+
"1": "POSITIVE"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"NEGATIVE": 0,
|
38 |
+
"POSITIVE": 1
|
39 |
+
},
|
40 |
+
"max_position_embeddings": 1026,
|
41 |
+
"model_type": "bart",
|
42 |
+
"normalize_before": false,
|
43 |
+
"normalize_embedding": true,
|
44 |
+
"num_hidden_layers": 6,
|
45 |
+
"pad_token_id": 3,
|
46 |
+
"scale_embedding": false,
|
47 |
+
"static_position_embeddings": false,
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.26.1",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 30000
|
52 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c34caae9ee71bf0d1054affed1cbfc990649bdade9d0fedb2b89c2cedcff992a
|
3 |
+
size 495648413
|
runs/Feb15_08-39-35_43aace13c501/1676450395.842999/events.out.tfevents.1676450395.43aace13c501.1030.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b66beb785963c4ed079053228621319e7e7cb47b97759ff50e4cc674274f5390
|
3 |
+
size 5896
|
runs/Feb15_08-39-35_43aace13c501/events.out.tfevents.1676450395.43aace13c501.1030.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8b95bd21420e30654596e9fc6b4ccf2cb4db28c784e7d76f24e7117dfb240d3
|
3 |
+
size 4136
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4928689272fa77a7fc842b4fcd74159fc8a921774ad2644adaf71325cc34a902
|
3 |
+
size 1049434
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"name_or_path": "digit82/kobart-summarization",
|
4 |
+
"special_tokens_map_file": "/Users/digit82/.cache/huggingface/transformers/3e6abf40f4fadbea9e7b539c182868d979838d8f7e6cdcdf2ed52ddcf01420c0.15447ae63ad4a2eba8bc7a5146360711dc32b315b4f1488b4806debf35315e9a",
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ed6763be99613befdf1ea0b63b729d264c01eff18ea73433ef74079c5ca4ff
|
3 |
+
size 3579
|