Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +67 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May28_22-52-53_trest/1653758655.5679317/events.out.tfevents.1653758655.trest.11615.1 +3 -0
- runs/May28_22-52-53_trest/events.out.tfevents.1653758655.trest.11615.0 +3 -0
- runs/May29_01-25-55_trest/1653767836.7484505/events.out.tfevents.1653767836.trest.11853.1 +3 -0
- runs/May29_01-25-55_trest/events.out.tfevents.1653767836.trest.11853.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sshleifer/distilbart-xsum-12-3",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"BartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.1,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 3,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"eos_token_ids": [
|
29 |
+
2
|
30 |
+
],
|
31 |
+
"extra_pos_embeddings": 2,
|
32 |
+
"force_bos_token_to_be_generated": false,
|
33 |
+
"forced_eos_token_id": 2,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1",
|
38 |
+
"2": "LABEL_2"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_length": 62,
|
48 |
+
"max_position_embeddings": 1024,
|
49 |
+
"min_length": 11,
|
50 |
+
"model_type": "bart",
|
51 |
+
"no_repeat_ngram_size": 3,
|
52 |
+
"normalize_before": false,
|
53 |
+
"normalize_embedding": true,
|
54 |
+
"num_beams": 6,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"output_past": true,
|
57 |
+
"pad_token_id": 1,
|
58 |
+
"prefix": " ",
|
59 |
+
"save_step": 58,
|
60 |
+
"scale_embedding": false,
|
61 |
+
"static_position_embeddings": false,
|
62 |
+
"task_specific_params": {},
|
63 |
+
"torch_dtype": "float32",
|
64 |
+
"transformers_version": "4.16.2",
|
65 |
+
"use_cache": true,
|
66 |
+
"vocab_size": 50264
|
67 |
+
}
|
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:d0c66435e1e643753a7dfe374b59fcbcc53b03ed5ce760d047c5377a7fe55505
|
3 |
+
size 1020785493
|
runs/May28_22-52-53_trest/1653758655.5679317/events.out.tfevents.1653758655.trest.11615.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:464261f966095fe6e0fe86bab39acffda90e57ddc487295a5587a6a87acab985
|
3 |
+
size 5005
|
runs/May28_22-52-53_trest/events.out.tfevents.1653758655.trest.11615.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62738258ecf45970a4641561e9a69429eb7e63eb2bd6149c1b96e3c70d8c5d7a
|
3 |
+
size 4515
|
runs/May29_01-25-55_trest/1653767836.7484505/events.out.tfevents.1653767836.trest.11853.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:851737319f9e0a058d05048bf402c48efc88b7bee8b88d2523a528a61ce4a1cf
|
3 |
+
size 5005
|
runs/May29_01-25-55_trest/events.out.tfevents.1653767836.trest.11853.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:599f1f920fe9e022036006ae89530acf8e8b5eb52e9ae49108df257178ecb36c
|
3 |
+
size 4515
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": "/home/trestadmin/store/nizam/.cache/huggingface/transformers/1a996eaa377bd0264a7fe1dc47e130bba901eafad886d704bfbfeb8f1069ec3c.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "sshleifer/distilbart-xsum-12-3", "tokenizer_class": "BartTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba9d2fcda5f00f61ff8e2c8b6a59508e866b26435ace62047e1ec59b075e4b38
|
3 |
+
size 3183
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|