Commit
·
d898fce
1
Parent(s):
b703de2
End of training
Browse files- .gitignore +1 -0
- config.json +39 -0
- merges.txt +23 -0
- pytorch_model.bin +3 -0
- runs/Jun10_21-31-17_f73b007c23cf/1654896718.7938695/events.out.tfevents.1654896718.f73b007c23cf.72.1 +3 -0
- runs/Jun10_21-31-17_f73b007c23cf/events.out.tfevents.1654896718.f73b007c23cf.72.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +123 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +1 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 128,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.19.4",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 49
|
| 39 |
+
}
|
merges.txt
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
+
2 5
|
| 3 |
+
Ġ n
|
| 4 |
+
Ġ c
|
| 5 |
+
Ġ r
|
| 6 |
+
7 5
|
| 7 |
+
1 2
|
| 8 |
+
1 1
|
| 9 |
+
1 3
|
| 10 |
+
1 7
|
| 11 |
+
2 3
|
| 12 |
+
1 9
|
| 13 |
+
2 4
|
| 14 |
+
1 0
|
| 15 |
+
2 9
|
| 16 |
+
3 5
|
| 17 |
+
3 7
|
| 18 |
+
1 25
|
| 19 |
+
3 75
|
| 20 |
+
2 0
|
| 21 |
+
4 1
|
| 22 |
+
5 3
|
| 23 |
+
4 9
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28240473f8c99804a0cf25ab9d4f5b9a78a898d8f451e3f67c00b7a7feca811e
|
| 3 |
+
size 356157545
|
runs/Jun10_21-31-17_f73b007c23cf/1654896718.7938695/events.out.tfevents.1654896718.f73b007c23cf.72.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12c06dc732c74a44b30006b3da39bbb3c534d45c951a8d1baf775296682c624c
|
| 3 |
+
size 5150
|
runs/Jun10_21-31-17_f73b007c23cf/events.out.tfevents.1654896718.f73b007c23cf.72.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e15780b809d02826076152bd4f885fb2a4de302192d1577511e56c27618a3a60
|
| 3 |
+
size 4076
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
],
|
| 21 |
+
"normalizer": null,
|
| 22 |
+
"pre_tokenizer": {
|
| 23 |
+
"type": "ByteLevel",
|
| 24 |
+
"add_prefix_space": false,
|
| 25 |
+
"trim_offsets": true,
|
| 26 |
+
"use_regex": true
|
| 27 |
+
},
|
| 28 |
+
"post_processor": {
|
| 29 |
+
"type": "ByteLevel",
|
| 30 |
+
"add_prefix_space": true,
|
| 31 |
+
"trim_offsets": false,
|
| 32 |
+
"use_regex": true
|
| 33 |
+
},
|
| 34 |
+
"decoder": {
|
| 35 |
+
"type": "ByteLevel",
|
| 36 |
+
"add_prefix_space": true,
|
| 37 |
+
"trim_offsets": true,
|
| 38 |
+
"use_regex": true
|
| 39 |
+
},
|
| 40 |
+
"model": {
|
| 41 |
+
"type": "BPE",
|
| 42 |
+
"dropout": null,
|
| 43 |
+
"unk_token": null,
|
| 44 |
+
"continuing_subword_prefix": null,
|
| 45 |
+
"end_of_word_suffix": null,
|
| 46 |
+
"fuse_unk": false,
|
| 47 |
+
"vocab": {
|
| 48 |
+
"<|endoftext|>": 0,
|
| 49 |
+
"#": 1,
|
| 50 |
+
"-": 2,
|
| 51 |
+
".": 3,
|
| 52 |
+
"/": 4,
|
| 53 |
+
"0": 5,
|
| 54 |
+
"1": 6,
|
| 55 |
+
"2": 7,
|
| 56 |
+
"3": 8,
|
| 57 |
+
"4": 9,
|
| 58 |
+
"5": 10,
|
| 59 |
+
"6": 11,
|
| 60 |
+
"7": 12,
|
| 61 |
+
"8": 13,
|
| 62 |
+
"9": 14,
|
| 63 |
+
"A": 15,
|
| 64 |
+
"B": 16,
|
| 65 |
+
"C": 17,
|
| 66 |
+
"D": 18,
|
| 67 |
+
"E": 19,
|
| 68 |
+
"F": 20,
|
| 69 |
+
"G": 21,
|
| 70 |
+
"_": 22,
|
| 71 |
+
"c": 23,
|
| 72 |
+
"n": 24,
|
| 73 |
+
"r": 25,
|
| 74 |
+
"Ġ": 26,
|
| 75 |
+
"25": 27,
|
| 76 |
+
"Ġn": 28,
|
| 77 |
+
"Ġc": 29,
|
| 78 |
+
"Ġr": 30,
|
| 79 |
+
"75": 31,
|
| 80 |
+
"12": 32,
|
| 81 |
+
"11": 33,
|
| 82 |
+
"13": 34,
|
| 83 |
+
"17": 35,
|
| 84 |
+
"23": 36,
|
| 85 |
+
"19": 37,
|
| 86 |
+
"24": 38,
|
| 87 |
+
"10": 39,
|
| 88 |
+
"29": 40,
|
| 89 |
+
"35": 41,
|
| 90 |
+
"37": 42,
|
| 91 |
+
"125": 43,
|
| 92 |
+
"375": 44,
|
| 93 |
+
"20": 45,
|
| 94 |
+
"41": 46,
|
| 95 |
+
"53": 47,
|
| 96 |
+
"49": 48
|
| 97 |
+
},
|
| 98 |
+
"merges": [
|
| 99 |
+
"2 5",
|
| 100 |
+
"Ġ n",
|
| 101 |
+
"Ġ c",
|
| 102 |
+
"Ġ r",
|
| 103 |
+
"7 5",
|
| 104 |
+
"1 2",
|
| 105 |
+
"1 1",
|
| 106 |
+
"1 3",
|
| 107 |
+
"1 7",
|
| 108 |
+
"2 3",
|
| 109 |
+
"1 9",
|
| 110 |
+
"2 4",
|
| 111 |
+
"1 0",
|
| 112 |
+
"2 9",
|
| 113 |
+
"3 5",
|
| 114 |
+
"3 7",
|
| 115 |
+
"1 25",
|
| 116 |
+
"3 75",
|
| 117 |
+
"2 0",
|
| 118 |
+
"4 1",
|
| 119 |
+
"5 3",
|
| 120 |
+
"4 9"
|
| 121 |
+
]
|
| 122 |
+
}
|
| 123 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "tokenizer_class": "GPT2Tokenizer"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0436b2ed813b8ba3e8d830b36a61ad4f1346332cbd191e8d642cdcac207465b7
|
| 3 |
+
size 3183
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<|endoftext|>":0,"#":1,"-":2,".":3,"/":4,"0":5,"1":6,"2":7,"3":8,"4":9,"5":10,"6":11,"7":12,"8":13,"9":14,"A":15,"B":16,"C":17,"D":18,"E":19,"F":20,"G":21,"_":22,"c":23,"n":24,"r":25,"Ġ":26,"25":27,"Ġn":28,"Ġc":29,"Ġr":30,"75":31,"12":32,"11":33,"13":34,"17":35,"23":36,"19":37,"24":38,"10":39,"29":40,"35":41,"37":42,"125":43,"375":44,"20":45,"41":46,"53":47,"49":48}
|