upload ipc_level1_G model
Browse files- config.json +63 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +220 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../models/roberta-large/",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "ipc1",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "01",
|
16 |
+
"1": "02",
|
17 |
+
"2": "03",
|
18 |
+
"3": "04",
|
19 |
+
"4": "05",
|
20 |
+
"5": "06",
|
21 |
+
"6": "07",
|
22 |
+
"7": "08",
|
23 |
+
"8": "09",
|
24 |
+
"9": "10",
|
25 |
+
"10": "11",
|
26 |
+
"11": "12",
|
27 |
+
"12": "16",
|
28 |
+
"13": "21",
|
29 |
+
"14": "99"
|
30 |
+
},
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 4096,
|
33 |
+
"label2id": {
|
34 |
+
"01": 0,
|
35 |
+
"02": 1,
|
36 |
+
"03": 2,
|
37 |
+
"04": 3,
|
38 |
+
"05": 4,
|
39 |
+
"06": 5,
|
40 |
+
"07": 6,
|
41 |
+
"08": 7,
|
42 |
+
"09": 8,
|
43 |
+
"10": 9,
|
44 |
+
"11": 10,
|
45 |
+
"12": 11,
|
46 |
+
"16": 12,
|
47 |
+
"21": 13,
|
48 |
+
"99": 14
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-05,
|
51 |
+
"max_position_embeddings": 514,
|
52 |
+
"model_type": "roberta",
|
53 |
+
"num_attention_heads": 16,
|
54 |
+
"num_hidden_layers": 24,
|
55 |
+
"pad_token_id": 1,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"problem_type": "multi_label_classification",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.9.2",
|
60 |
+
"type_vocab_size": 1,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 50265
|
63 |
+
}
|
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:da3a92db5bc9dfb55bf0b56cba33d7c91c72b198598f9819fbaa6ed580903b7b
|
3 |
+
size 1421664557
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46df9fa0b0f11fbf3401de806fc1a967c7fd25b901534d06ed530221bf803d03
|
3 |
+
size 15523
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
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": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "../models/roberta-large/", "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8754267260214113,
|
3 |
+
"best_model_checkpoint": "./output//roberta-large_ipc1_G_5_32_5e-6_0.01_0.06_07-08-22_06-40/checkpoint-24000",
|
4 |
+
"epoch": 0.14484881405033495,
|
5 |
+
"global_step": 24000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 2.0117890840324302e-07,
|
13 |
+
"loss": 0.4247,
|
14 |
+
"step": 2000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"eval_accuracy": 0.03380152270937254,
|
19 |
+
"eval_f1": 0.0619012340183338,
|
20 |
+
"eval_loss": 0.20814624428749084,
|
21 |
+
"eval_roc_auc": 0.5159319239399485,
|
22 |
+
"eval_runtime": 8197.4985,
|
23 |
+
"eval_samples_per_second": 33.455,
|
24 |
+
"eval_steps_per_second": 2.091,
|
25 |
+
"step": 2000
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.02,
|
29 |
+
"learning_rate": 4.0235781680648604e-07,
|
30 |
+
"loss": 0.1716,
|
31 |
+
"step": 4000
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.02,
|
35 |
+
"eval_accuracy": 0.6045477086432718,
|
36 |
+
"eval_f1": 0.7149013381719211,
|
37 |
+
"eval_loss": 0.12680654227733612,
|
38 |
+
"eval_roc_auc": 0.7994218657046591,
|
39 |
+
"eval_runtime": 8196.5733,
|
40 |
+
"eval_samples_per_second": 33.459,
|
41 |
+
"eval_steps_per_second": 2.091,
|
42 |
+
"step": 4000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.04,
|
46 |
+
"learning_rate": 6.03536725209729e-07,
|
47 |
+
"loss": 0.114,
|
48 |
+
"step": 6000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.04,
|
52 |
+
"eval_accuracy": 0.7269478719990665,
|
53 |
+
"eval_f1": 0.8064969810911458,
|
54 |
+
"eval_loss": 0.09042555838823318,
|
55 |
+
"eval_roc_auc": 0.863152127136236,
|
56 |
+
"eval_runtime": 8195.1585,
|
57 |
+
"eval_samples_per_second": 33.465,
|
58 |
+
"eval_steps_per_second": 2.092,
|
59 |
+
"step": 6000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.05,
|
63 |
+
"learning_rate": 8.047156336129721e-07,
|
64 |
+
"loss": 0.0865,
|
65 |
+
"step": 8000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.05,
|
69 |
+
"eval_accuracy": 0.774762258977276,
|
70 |
+
"eval_f1": 0.8402673463726624,
|
71 |
+
"eval_loss": 0.07436466217041016,
|
72 |
+
"eval_roc_auc": 0.8920166546037435,
|
73 |
+
"eval_runtime": 8191.8248,
|
74 |
+
"eval_samples_per_second": 33.478,
|
75 |
+
"eval_steps_per_second": 2.092,
|
76 |
+
"step": 8000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.06,
|
80 |
+
"learning_rate": 1.005894542016215e-06,
|
81 |
+
"loss": 0.0743,
|
82 |
+
"step": 10000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.06,
|
86 |
+
"eval_accuracy": 0.7829883900703013,
|
87 |
+
"eval_f1": 0.8487029462020401,
|
88 |
+
"eval_loss": 0.06654931604862213,
|
89 |
+
"eval_roc_auc": 0.9001618402078589,
|
90 |
+
"eval_runtime": 8196.3415,
|
91 |
+
"eval_samples_per_second": 33.46,
|
92 |
+
"eval_steps_per_second": 2.091,
|
93 |
+
"step": 10000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.07,
|
97 |
+
"learning_rate": 1.207073450419458e-06,
|
98 |
+
"loss": 0.0664,
|
99 |
+
"step": 12000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.07,
|
103 |
+
"eval_accuracy": 0.794452466380794,
|
104 |
+
"eval_f1": 0.859163976123391,
|
105 |
+
"eval_loss": 0.061000920832157135,
|
106 |
+
"eval_roc_auc": 0.9083440937813021,
|
107 |
+
"eval_runtime": 8197.7585,
|
108 |
+
"eval_samples_per_second": 33.454,
|
109 |
+
"eval_steps_per_second": 2.091,
|
110 |
+
"step": 12000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.08,
|
114 |
+
"learning_rate": 1.4082523588227012e-06,
|
115 |
+
"loss": 0.062,
|
116 |
+
"step": 14000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.08,
|
120 |
+
"eval_accuracy": 0.7962172923777019,
|
121 |
+
"eval_f1": 0.8624403660379281,
|
122 |
+
"eval_loss": 0.05871045961976051,
|
123 |
+
"eval_roc_auc": 0.9133217347648154,
|
124 |
+
"eval_runtime": 8199.4678,
|
125 |
+
"eval_samples_per_second": 33.447,
|
126 |
+
"eval_steps_per_second": 2.091,
|
127 |
+
"step": 14000
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.1,
|
131 |
+
"learning_rate": 1.6094312672259442e-06,
|
132 |
+
"loss": 0.0599,
|
133 |
+
"step": 16000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.1,
|
137 |
+
"eval_accuracy": 0.7979055453458184,
|
138 |
+
"eval_f1": 0.8656510165555269,
|
139 |
+
"eval_loss": 0.05596928298473358,
|
140 |
+
"eval_roc_auc": 0.9150237468241987,
|
141 |
+
"eval_runtime": 8200.3089,
|
142 |
+
"eval_samples_per_second": 33.444,
|
143 |
+
"eval_steps_per_second": 2.09,
|
144 |
+
"step": 16000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.11,
|
148 |
+
"learning_rate": 1.8106101756291871e-06,
|
149 |
+
"loss": 0.0569,
|
150 |
+
"step": 18000
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.11,
|
154 |
+
"eval_accuracy": 0.8009939908404072,
|
155 |
+
"eval_f1": 0.8665697356924421,
|
156 |
+
"eval_loss": 0.05469416454434395,
|
157 |
+
"eval_roc_auc": 0.9135503362863645,
|
158 |
+
"eval_runtime": 8201.2258,
|
159 |
+
"eval_samples_per_second": 33.44,
|
160 |
+
"eval_steps_per_second": 2.09,
|
161 |
+
"step": 18000
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.12,
|
165 |
+
"learning_rate": 2.01178908403243e-06,
|
166 |
+
"loss": 0.0554,
|
167 |
+
"step": 20000
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.12,
|
171 |
+
"eval_accuracy": 0.8071891135031066,
|
172 |
+
"eval_f1": 0.8723540166082954,
|
173 |
+
"eval_loss": 0.052826616913080215,
|
174 |
+
"eval_roc_auc": 0.9192588608785235,
|
175 |
+
"eval_runtime": 8204.8057,
|
176 |
+
"eval_samples_per_second": 33.425,
|
177 |
+
"eval_steps_per_second": 2.089,
|
178 |
+
"step": 20000
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.13,
|
182 |
+
"learning_rate": 2.2129679924356733e-06,
|
183 |
+
"loss": 0.0541,
|
184 |
+
"step": 22000
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.13,
|
188 |
+
"eval_accuracy": 0.8054935678655816,
|
189 |
+
"eval_f1": 0.8706366827585739,
|
190 |
+
"eval_loss": 0.05298588052392006,
|
191 |
+
"eval_roc_auc": 0.9176729146649489,
|
192 |
+
"eval_runtime": 8206.5949,
|
193 |
+
"eval_samples_per_second": 33.418,
|
194 |
+
"eval_steps_per_second": 2.089,
|
195 |
+
"step": 22000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.14,
|
199 |
+
"learning_rate": 2.414146900838916e-06,
|
200 |
+
"loss": 0.0522,
|
201 |
+
"step": 24000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.14,
|
205 |
+
"eval_accuracy": 0.8137306379627198,
|
206 |
+
"eval_f1": 0.8754267260214113,
|
207 |
+
"eval_loss": 0.05081520974636078,
|
208 |
+
"eval_roc_auc": 0.9180724092422241,
|
209 |
+
"eval_runtime": 8275.6912,
|
210 |
+
"eval_samples_per_second": 33.139,
|
211 |
+
"eval_steps_per_second": 2.071,
|
212 |
+
"step": 24000
|
213 |
+
}
|
214 |
+
],
|
215 |
+
"max_steps": 828450,
|
216 |
+
"num_train_epochs": 5,
|
217 |
+
"total_flos": 7.15754724655104e+17,
|
218 |
+
"trial_name": null,
|
219 |
+
"trial_params": null
|
220 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34c37f67c21e6efe2882d0cdfa94321def51beccd3525adee20f2d06e4cb5a3b
|
3 |
+
size 2735
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|