sayanmandal
commited on
Commit
•
070c6ec
1
Parent(s):
2907fbb
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +74 -0
- pytorch_model.bin +3 -0
- runs/May26_06-44-34_sayan/1653540313.4569154/events.out.tfevents.1653540313.sayan.79503.1 +3 -0
- runs/May26_06-44-34_sayan/events.out.tfevents.1653540298.sayan.79503.0 +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./t5_small_6_3",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"init_metadata": {
|
14 |
+
"copied_decoder_layers": [
|
15 |
+
0,
|
16 |
+
2,
|
17 |
+
5
|
18 |
+
],
|
19 |
+
"copied_encoder_layers": [
|
20 |
+
0,
|
21 |
+
1,
|
22 |
+
2,
|
23 |
+
3,
|
24 |
+
4,
|
25 |
+
5
|
26 |
+
],
|
27 |
+
"teacher_type": "t5"
|
28 |
+
},
|
29 |
+
"initializer_factor": 1.0,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"layer_norm_epsilon": 1e-06,
|
32 |
+
"model_type": "t5",
|
33 |
+
"n_positions": 512,
|
34 |
+
"num_decoder_layers": 3,
|
35 |
+
"num_heads": 8,
|
36 |
+
"num_layers": 6,
|
37 |
+
"output_past": true,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"relative_attention_max_distance": 128,
|
40 |
+
"relative_attention_num_buckets": 32,
|
41 |
+
"task_specific_params": {
|
42 |
+
"summarization": {
|
43 |
+
"early_stopping": true,
|
44 |
+
"length_penalty": 2.0,
|
45 |
+
"max_length": 200,
|
46 |
+
"min_length": 30,
|
47 |
+
"no_repeat_ngram_size": 3,
|
48 |
+
"num_beams": 4,
|
49 |
+
"prefix": "summarize: "
|
50 |
+
},
|
51 |
+
"translation_en_to_de": {
|
52 |
+
"early_stopping": true,
|
53 |
+
"max_length": 300,
|
54 |
+
"num_beams": 4,
|
55 |
+
"prefix": "translate English to German: "
|
56 |
+
},
|
57 |
+
"translation_en_to_fr": {
|
58 |
+
"early_stopping": true,
|
59 |
+
"max_length": 300,
|
60 |
+
"num_beams": 4,
|
61 |
+
"prefix": "translate English to French: "
|
62 |
+
},
|
63 |
+
"translation_en_to_ro": {
|
64 |
+
"early_stopping": true,
|
65 |
+
"max_length": 300,
|
66 |
+
"num_beams": 4,
|
67 |
+
"prefix": "translate English to Romanian: "
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.20.0.dev0",
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 32128
|
74 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbaa6c46d94759793d2714da4fa0930a7f73b8f6d847e679613bc87876688efa
|
3 |
+
size 191708801
|
runs/May26_06-44-34_sayan/1653540313.4569154/events.out.tfevents.1653540313.sayan.79503.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e03263e34085769592c7989b6e1e7f1bb4fb2daa421bdcd7b7c808ea03c3b6a7
|
3 |
+
size 5470
|
runs/May26_06-44-34_sayan/events.out.tfevents.1653540298.sayan.79503.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ac3b3e8abd9f71cf5bb8d5b8cce1fd31088a36fa9683399f214b39f6be8369a
|
3 |
+
size 6575
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 42, "special_tokens_map_file": null, "name_or_path": "./t5_small_6_3", "tokenizer_class": "T5Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dff4ad916cf4038c8fb684bd5882e48ac6eeb790df9bf5a9d6e7d321b88fe783
|
3 |
+
size 3375
|