Upload folder using huggingface_hub
Browse files- config.json +28 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +195 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.37.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0294b9fb5725623cc654f276d10ac84f529ff82bd570a46aac804ba2ebada7bf
|
3 |
+
size 498612824
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9774e3e326beda4ac0bd8f1b9a173012decd211f0fe5fb16b662421f22089026
|
3 |
+
size 997345530
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7377babedd7b8472d083b1abcffec26d0d6a644b2a9b36d56adb964fb22676f2
|
3 |
+
size 14512
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caf89778b3e447d0191bcd1682d41799e652149f1f60c48905386d7c0408eb07
|
3 |
+
size 14512
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27c9111fd0b4cb5653b336151db712b0b5c627f4f6ebcc3aabf6a4bd3a9d7fd9
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8454458293384468,
|
3 |
+
"best_model_checkpoint": "test4-pairwise/checkpoint-516",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 516,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08,
|
13 |
+
"learning_rate": 3.0769230769230774e-05,
|
14 |
+
"loss": 0.6865,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.16,
|
19 |
+
"learning_rate": 5.538461538461539e-05,
|
20 |
+
"loss": 0.3337,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.23,
|
25 |
+
"learning_rate": 7.998533144893137e-05,
|
26 |
+
"loss": 0.1844,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.31,
|
31 |
+
"learning_rate": 7.947306090166105e-05,
|
32 |
+
"loss": 0.1622,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.39,
|
37 |
+
"learning_rate": 7.823808570686448e-05,
|
38 |
+
"loss": 0.1337,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.47,
|
43 |
+
"learning_rate": 7.63030167868383e-05,
|
44 |
+
"loss": 0.1452,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.54,
|
49 |
+
"learning_rate": 7.370328294466597e-05,
|
50 |
+
"loss": 0.0922,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.62,
|
55 |
+
"learning_rate": 7.048648220510546e-05,
|
56 |
+
"loss": 0.0946,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.7,
|
61 |
+
"learning_rate": 6.671151035154783e-05,
|
62 |
+
"loss": 0.0903,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.78,
|
67 |
+
"learning_rate": 6.24474826144953e-05,
|
68 |
+
"loss": 0.075,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.85,
|
73 |
+
"learning_rate": 5.7772468254156155e-05,
|
74 |
+
"loss": 0.0801,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.93,
|
79 |
+
"learning_rate": 5.27720612054392e-05,
|
80 |
+
"loss": 0.0864,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.0,
|
85 |
+
"eval_loss": 2.4745593070983887,
|
86 |
+
"eval_runtime": 8.6606,
|
87 |
+
"eval_samples_per_second": 10129.044,
|
88 |
+
"eval_steps_per_second": 79.209,
|
89 |
+
"eval_top-1-accuracy": 0.7670182166826462,
|
90 |
+
"eval_top-10-accuracy": 0.9311601150527326,
|
91 |
+
"eval_top-3-accuracy": 0.8186001917545541,
|
92 |
+
"eval_top-5-accuracy": 0.8705656759348035,
|
93 |
+
"step": 258
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.01,
|
97 |
+
"learning_rate": 4.753781295513274e-05,
|
98 |
+
"loss": 0.0629,
|
99 |
+
"step": 260
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.09,
|
103 |
+
"learning_rate": 4.216555634341671e-05,
|
104 |
+
"loss": 0.0654,
|
105 |
+
"step": 280
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 1.16,
|
109 |
+
"learning_rate": 3.675365097890276e-05,
|
110 |
+
"loss": 0.0585,
|
111 |
+
"step": 300
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.24,
|
115 |
+
"learning_rate": 3.140118239155904e-05,
|
116 |
+
"loss": 0.0525,
|
117 |
+
"step": 320
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 1.32,
|
121 |
+
"learning_rate": 2.6206147894881193e-05,
|
122 |
+
"loss": 0.0377,
|
123 |
+
"step": 340
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.4,
|
127 |
+
"learning_rate": 2.12636623720084e-05,
|
128 |
+
"loss": 0.0415,
|
129 |
+
"step": 360
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.47,
|
133 |
+
"learning_rate": 1.666421683570024e-05,
|
134 |
+
"loss": 0.0453,
|
135 |
+
"step": 380
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.55,
|
139 |
+
"learning_rate": 1.2492021645863064e-05,
|
140 |
+
"loss": 0.0457,
|
141 |
+
"step": 400
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.63,
|
145 |
+
"learning_rate": 8.823464718336336e-06,
|
146 |
+
"loss": 0.0369,
|
147 |
+
"step": 420
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.71,
|
151 |
+
"learning_rate": 5.725712953296439e-06,
|
152 |
+
"loss": 0.0272,
|
153 |
+
"step": 440
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.78,
|
157 |
+
"learning_rate": 3.2554824894551306e-06,
|
158 |
+
"loss": 0.0316,
|
159 |
+
"step": 460
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 1.86,
|
163 |
+
"learning_rate": 1.4580002992310837e-06,
|
164 |
+
"loss": 0.0363,
|
165 |
+
"step": 480
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.94,
|
169 |
+
"learning_rate": 3.66176136847729e-07,
|
170 |
+
"loss": 0.0411,
|
171 |
+
"step": 500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 2.0,
|
175 |
+
"eval_loss": 3.0463552474975586,
|
176 |
+
"eval_runtime": 8.6788,
|
177 |
+
"eval_samples_per_second": 10107.877,
|
178 |
+
"eval_steps_per_second": 79.043,
|
179 |
+
"eval_top-1-accuracy": 0.7946308724832215,
|
180 |
+
"eval_top-10-accuracy": 0.9497603068072866,
|
181 |
+
"eval_top-3-accuracy": 0.8454458293384468,
|
182 |
+
"eval_top-5-accuracy": 0.8928092042186002,
|
183 |
+
"step": 516
|
184 |
+
}
|
185 |
+
],
|
186 |
+
"logging_steps": 20,
|
187 |
+
"max_steps": 516,
|
188 |
+
"num_input_tokens_seen": 0,
|
189 |
+
"num_train_epochs": 2,
|
190 |
+
"save_steps": 500,
|
191 |
+
"total_flos": 2415688357511168.0,
|
192 |
+
"train_batch_size": 64,
|
193 |
+
"trial_name": null,
|
194 |
+
"trial_params": null
|
195 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa6dcd7f8a1f6f7069d8fd6c34ec2e2b43dad2ca1ea8f63a0fbc71667441aa6a
|
3 |
+
size 4856
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|