Add files
Browse files- added_tokens.json +0 -1
- config.json +0 -57
- pytorch_model.bin +0 -3
- rng_state.pth +0 -3
- scheduler.pt +0 -3
- special_tokens_map.json +0 -1
- spiece.model +0 -3
- test.txt +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +0 -1
- trainer_state.json +0 -192
- training_args.bin +0 -3
added_tokens.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"PROFANITY_TOKEN": 32110, "NO_SEGMENT_TOKEN": 32111, "[Music]": 32107, "NUMBER_TOKEN": 32104, "URL_TOKEN": 32101, "HYPHENATED_URL_TOKEN": 32102, "BETWEEN_SEGMENTS_TOKEN": 32118, "NUMBER_PERCENTAGE_TOKEN": 32103, "SHORT_HYPHENATED_TOKEN": 32105, "[Laughter]": 32109, "START_INTERACTION_TOKEN": 32116, "END_INTERACTION_TOKEN": 32117, "[Applause]": 32108, "END_SPONSOR_TOKEN": 32113, "END_SELFPROMO_TOKEN": 32115, "LONG_WORD_TOKEN": 32106, "START_SELFPROMO_TOKEN": 32114, "EXTRACT_SEGMENTS: ": 32100, "START_SPONSOR_TOKEN": 32112}
|
|
|
|
config.json
DELETED
@@ -1,57 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "/1TB_SSD/SB_AI/out_orig2",
|
3 |
-
"architectures": [
|
4 |
-
"T5ForConditionalGeneration"
|
5 |
-
],
|
6 |
-
"d_ff": 3072,
|
7 |
-
"d_kv": 64,
|
8 |
-
"d_model": 768,
|
9 |
-
"decoder_start_token_id": 0,
|
10 |
-
"dropout_rate": 0.1,
|
11 |
-
"eos_token_id": 1,
|
12 |
-
"feed_forward_proj": "relu",
|
13 |
-
"initializer_factor": 1.0,
|
14 |
-
"is_encoder_decoder": true,
|
15 |
-
"layer_norm_epsilon": 1e-06,
|
16 |
-
"model_type": "t5",
|
17 |
-
"n_positions": 512,
|
18 |
-
"num_decoder_layers": 12,
|
19 |
-
"num_heads": 12,
|
20 |
-
"num_layers": 12,
|
21 |
-
"output_past": true,
|
22 |
-
"pad_token_id": 0,
|
23 |
-
"relative_attention_num_buckets": 32,
|
24 |
-
"task_specific_params": {
|
25 |
-
"summarization": {
|
26 |
-
"early_stopping": true,
|
27 |
-
"length_penalty": 2.0,
|
28 |
-
"max_length": 200,
|
29 |
-
"min_length": 30,
|
30 |
-
"no_repeat_ngram_size": 3,
|
31 |
-
"num_beams": 4,
|
32 |
-
"prefix": "summarize: "
|
33 |
-
},
|
34 |
-
"translation_en_to_de": {
|
35 |
-
"early_stopping": true,
|
36 |
-
"max_length": 300,
|
37 |
-
"num_beams": 4,
|
38 |
-
"prefix": "translate English to German: "
|
39 |
-
},
|
40 |
-
"translation_en_to_fr": {
|
41 |
-
"early_stopping": true,
|
42 |
-
"max_length": 300,
|
43 |
-
"num_beams": 4,
|
44 |
-
"prefix": "translate English to French: "
|
45 |
-
},
|
46 |
-
"translation_en_to_ro": {
|
47 |
-
"early_stopping": true,
|
48 |
-
"max_length": 300,
|
49 |
-
"num_beams": 4,
|
50 |
-
"prefix": "translate English to Romanian: "
|
51 |
-
}
|
52 |
-
},
|
53 |
-
"torch_dtype": "float32",
|
54 |
-
"transformers_version": "4.15.0",
|
55 |
-
"use_cache": true,
|
56 |
-
"vocab_size": 32119
|
57 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f000cd69cd2b64c5ce9ec3bf5badbc86a9211a66a6b0ee56778d524a877a6905
|
3 |
-
size 891703231
|
|
|
|
|
|
|
|
rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a4a6962d8c00a9faf2eef36f6a55688966060b860527434094ef374f61c62b55
|
3 |
-
size 14439
|
|
|
|
|
|
|
|
scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:9ed930ce9097cc22b6cc772597df186d1d87eea1be7cafe5d9a9438ae758cf95
|
3 |
-
size 623
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
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
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
-
size 791656
|
|
|
|
|
|
|
|
test.txt
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
hello
|
|
|
|
tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
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": 512, "special_tokens_map_file": null, "name_or_path": "/1TB_SSD/SB_AI/out_orig2", "tokenizer_class": "T5Tokenizer"}
|
|
|
|
trainer_state.json
DELETED
@@ -1,192 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.12538129346924665,
|
5 |
-
"global_step": 140000,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.0,
|
12 |
-
"learning_rate": 4.977610483309063e-05,
|
13 |
-
"loss": 0.0854,
|
14 |
-
"step": 5000
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.01,
|
18 |
-
"learning_rate": 4.955220966618126e-05,
|
19 |
-
"loss": 0.0801,
|
20 |
-
"step": 10000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.01,
|
24 |
-
"learning_rate": 4.9328314499271894e-05,
|
25 |
-
"loss": 0.082,
|
26 |
-
"step": 15000
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.02,
|
30 |
-
"learning_rate": 4.910441933236253e-05,
|
31 |
-
"loss": 0.0851,
|
32 |
-
"step": 20000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.02,
|
36 |
-
"learning_rate": 4.8880524165453154e-05,
|
37 |
-
"loss": 0.0858,
|
38 |
-
"step": 25000
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.03,
|
42 |
-
"learning_rate": 4.865662899854379e-05,
|
43 |
-
"loss": 0.0777,
|
44 |
-
"step": 30000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.03,
|
48 |
-
"learning_rate": 4.843273383163442e-05,
|
49 |
-
"loss": 0.0853,
|
50 |
-
"step": 35000
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.04,
|
54 |
-
"learning_rate": 4.8208838664725045e-05,
|
55 |
-
"loss": 0.0838,
|
56 |
-
"step": 40000
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.04,
|
60 |
-
"learning_rate": 4.798494349781568e-05,
|
61 |
-
"loss": 0.084,
|
62 |
-
"step": 45000
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.04,
|
66 |
-
"learning_rate": 4.776104833090631e-05,
|
67 |
-
"loss": 0.0794,
|
68 |
-
"step": 50000
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.05,
|
72 |
-
"learning_rate": 4.753715316399694e-05,
|
73 |
-
"loss": 0.0805,
|
74 |
-
"step": 55000
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.05,
|
78 |
-
"learning_rate": 4.7313257997087574e-05,
|
79 |
-
"loss": 0.0876,
|
80 |
-
"step": 60000
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.06,
|
84 |
-
"learning_rate": 4.708936283017821e-05,
|
85 |
-
"loss": 0.0773,
|
86 |
-
"step": 65000
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.06,
|
90 |
-
"learning_rate": 4.6865467663268834e-05,
|
91 |
-
"loss": 0.0846,
|
92 |
-
"step": 70000
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.07,
|
96 |
-
"learning_rate": 4.6641572496359465e-05,
|
97 |
-
"loss": 0.0867,
|
98 |
-
"step": 75000
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.07,
|
102 |
-
"eval_loss": 0.07421331852674484,
|
103 |
-
"eval_runtime": 1684.9579,
|
104 |
-
"eval_samples_per_second": 36.816,
|
105 |
-
"eval_steps_per_second": 36.816,
|
106 |
-
"step": 75000
|
107 |
-
},
|
108 |
-
{
|
109 |
-
"epoch": 0.07,
|
110 |
-
"learning_rate": 4.64176773294501e-05,
|
111 |
-
"loss": 0.0779,
|
112 |
-
"step": 80000
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"epoch": 0.08,
|
116 |
-
"learning_rate": 4.6193782162540726e-05,
|
117 |
-
"loss": 0.0795,
|
118 |
-
"step": 85000
|
119 |
-
},
|
120 |
-
{
|
121 |
-
"epoch": 0.08,
|
122 |
-
"learning_rate": 4.596988699563136e-05,
|
123 |
-
"loss": 0.082,
|
124 |
-
"step": 90000
|
125 |
-
},
|
126 |
-
{
|
127 |
-
"epoch": 0.09,
|
128 |
-
"learning_rate": 4.574599182872199e-05,
|
129 |
-
"loss": 0.0821,
|
130 |
-
"step": 95000
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"epoch": 0.09,
|
134 |
-
"learning_rate": 4.5522096661812623e-05,
|
135 |
-
"loss": 0.0787,
|
136 |
-
"step": 100000
|
137 |
-
},
|
138 |
-
{
|
139 |
-
"epoch": 0.09,
|
140 |
-
"learning_rate": 4.5298201494903254e-05,
|
141 |
-
"loss": 0.0803,
|
142 |
-
"step": 105000
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 0.1,
|
146 |
-
"learning_rate": 4.5074306327993884e-05,
|
147 |
-
"loss": 0.0788,
|
148 |
-
"step": 110000
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"epoch": 0.1,
|
152 |
-
"learning_rate": 4.4850411161084515e-05,
|
153 |
-
"loss": 0.0822,
|
154 |
-
"step": 115000
|
155 |
-
},
|
156 |
-
{
|
157 |
-
"epoch": 0.11,
|
158 |
-
"learning_rate": 4.4626515994175145e-05,
|
159 |
-
"loss": 0.0782,
|
160 |
-
"step": 120000
|
161 |
-
},
|
162 |
-
{
|
163 |
-
"epoch": 0.11,
|
164 |
-
"learning_rate": 4.4402620827265775e-05,
|
165 |
-
"loss": 0.0804,
|
166 |
-
"step": 125000
|
167 |
-
},
|
168 |
-
{
|
169 |
-
"epoch": 0.12,
|
170 |
-
"learning_rate": 4.4178725660356406e-05,
|
171 |
-
"loss": 0.0778,
|
172 |
-
"step": 130000
|
173 |
-
},
|
174 |
-
{
|
175 |
-
"epoch": 0.12,
|
176 |
-
"learning_rate": 4.3954830493447036e-05,
|
177 |
-
"loss": 0.0772,
|
178 |
-
"step": 135000
|
179 |
-
},
|
180 |
-
{
|
181 |
-
"epoch": 0.13,
|
182 |
-
"learning_rate": 4.3730935326537667e-05,
|
183 |
-
"loss": 0.0819,
|
184 |
-
"step": 140000
|
185 |
-
}
|
186 |
-
],
|
187 |
-
"max_steps": 1116594,
|
188 |
-
"num_train_epochs": 1,
|
189 |
-
"total_flos": 4.198632159495168e+16,
|
190 |
-
"trial_name": null,
|
191 |
-
"trial_params": null
|
192 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:626bad985fb1862f6b32ba4ebd7449b96bad7c0595dcabc271cd02a0adcc193d
|
3 |
-
size 3119
|
|
|
|
|
|
|
|