Upload model and auxiliary files
#3
by
olfMombach
- opened
- .gitattributes +1 -0
- all_results.json +14 -0
- config.json +26 -0
- eval_nbest_predictions.json +3 -0
- eval_predictions.json +0 -0
- eval_results.json +9 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- train_results.json +8 -0
- trainer_state.json +204 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_exact_match": 76.80499325236167,
|
4 |
+
"eval_f1": 85.78998205229026,
|
5 |
+
"eval_runtime": 32.987,
|
6 |
+
"eval_samples": 6056,
|
7 |
+
"eval_samples_per_second": 183.587,
|
8 |
+
"eval_steps_per_second": 22.948,
|
9 |
+
"train_loss": 1.3483753287818292,
|
10 |
+
"train_runtime": 2670.4215,
|
11 |
+
"train_samples": 87739,
|
12 |
+
"train_samples_per_second": 65.712,
|
13 |
+
"train_steps_per_second": 5.476
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/xtremedistil-l6-h384-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.0.dev0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
eval_nbest_predictions.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2b6387515c64ad85b175de8109231a5c65d26a4878f0cb12b90b41089eb5eb6
|
3 |
+
size 27739432
|
eval_predictions.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_exact_match": 76.80499325236167,
|
4 |
+
"eval_f1": 85.78998205229026,
|
5 |
+
"eval_runtime": 32.987,
|
6 |
+
"eval_samples": 6056,
|
7 |
+
"eval_samples_per_second": 183.587,
|
8 |
+
"eval_steps_per_second": 22.948
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b049ac2723d75fd5784b479c798dc51b3665b232eb27decb96aedf65bfd797b
|
3 |
+
size 90276408
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
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 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 1.3483753287818292,
|
4 |
+
"train_runtime": 2670.4215,
|
5 |
+
"train_samples": 87739,
|
6 |
+
"train_samples_per_second": 65.712,
|
7 |
+
"train_steps_per_second": 5.476
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 14624,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07,
|
13 |
+
"learning_rate": 2.897428884026258e-05,
|
14 |
+
"loss": 3.4331,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.14,
|
19 |
+
"learning_rate": 2.7948577680525165e-05,
|
20 |
+
"loss": 2.1219,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.21,
|
25 |
+
"learning_rate": 2.6922866520787748e-05,
|
26 |
+
"loss": 1.8112,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.27,
|
31 |
+
"learning_rate": 2.589715536105033e-05,
|
32 |
+
"loss": 1.6588,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.34,
|
37 |
+
"learning_rate": 2.4871444201312912e-05,
|
38 |
+
"loss": 1.5237,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.41,
|
43 |
+
"learning_rate": 2.3845733041575492e-05,
|
44 |
+
"loss": 1.463,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.48,
|
49 |
+
"learning_rate": 2.2820021881838072e-05,
|
50 |
+
"loss": 1.4293,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.55,
|
55 |
+
"learning_rate": 2.179431072210066e-05,
|
56 |
+
"loss": 1.3813,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.62,
|
61 |
+
"learning_rate": 2.076859956236324e-05,
|
62 |
+
"loss": 1.3349,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.68,
|
67 |
+
"learning_rate": 1.9742888402625823e-05,
|
68 |
+
"loss": 1.2893,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.75,
|
73 |
+
"learning_rate": 1.8717177242888403e-05,
|
74 |
+
"loss": 1.3047,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.82,
|
79 |
+
"learning_rate": 1.7691466083150983e-05,
|
80 |
+
"loss": 1.2601,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.89,
|
85 |
+
"learning_rate": 1.6665754923413567e-05,
|
86 |
+
"loss": 1.2731,
|
87 |
+
"step": 6500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.96,
|
91 |
+
"learning_rate": 1.564004376367615e-05,
|
92 |
+
"loss": 1.2453,
|
93 |
+
"step": 7000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.03,
|
97 |
+
"learning_rate": 1.4614332603938733e-05,
|
98 |
+
"loss": 1.2107,
|
99 |
+
"step": 7500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.09,
|
103 |
+
"learning_rate": 1.3588621444201313e-05,
|
104 |
+
"loss": 1.1359,
|
105 |
+
"step": 8000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 1.16,
|
109 |
+
"learning_rate": 1.2562910284463895e-05,
|
110 |
+
"loss": 1.1168,
|
111 |
+
"step": 8500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.23,
|
115 |
+
"learning_rate": 1.1537199124726478e-05,
|
116 |
+
"loss": 1.1197,
|
117 |
+
"step": 9000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 1.3,
|
121 |
+
"learning_rate": 1.0511487964989058e-05,
|
122 |
+
"loss": 1.1077,
|
123 |
+
"step": 9500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.37,
|
127 |
+
"learning_rate": 9.485776805251642e-06,
|
128 |
+
"loss": 1.1104,
|
129 |
+
"step": 10000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.44,
|
133 |
+
"learning_rate": 8.460065645514224e-06,
|
134 |
+
"loss": 1.1168,
|
135 |
+
"step": 10500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.5,
|
139 |
+
"learning_rate": 7.434354485776806e-06,
|
140 |
+
"loss": 1.1007,
|
141 |
+
"step": 11000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.57,
|
145 |
+
"learning_rate": 6.408643326039388e-06,
|
146 |
+
"loss": 1.066,
|
147 |
+
"step": 11500
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.64,
|
151 |
+
"learning_rate": 5.3829321663019695e-06,
|
152 |
+
"loss": 1.1172,
|
153 |
+
"step": 12000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.71,
|
157 |
+
"learning_rate": 4.357221006564551e-06,
|
158 |
+
"loss": 1.1203,
|
159 |
+
"step": 12500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 1.78,
|
163 |
+
"learning_rate": 3.3315098468271337e-06,
|
164 |
+
"loss": 1.0972,
|
165 |
+
"step": 13000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.85,
|
169 |
+
"learning_rate": 2.3057986870897156e-06,
|
170 |
+
"loss": 1.0766,
|
171 |
+
"step": 13500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.91,
|
175 |
+
"learning_rate": 1.2800875273522977e-06,
|
176 |
+
"loss": 1.0916,
|
177 |
+
"step": 14000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.98,
|
181 |
+
"learning_rate": 2.543763676148797e-07,
|
182 |
+
"loss": 1.0628,
|
183 |
+
"step": 14500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 2.0,
|
187 |
+
"step": 14624,
|
188 |
+
"total_flos": 4305130555198464.0,
|
189 |
+
"train_loss": 1.3483753287818292,
|
190 |
+
"train_runtime": 2670.4215,
|
191 |
+
"train_samples_per_second": 65.712,
|
192 |
+
"train_steps_per_second": 5.476
|
193 |
+
}
|
194 |
+
],
|
195 |
+
"logging_steps": 500,
|
196 |
+
"max_steps": 14624,
|
197 |
+
"num_input_tokens_seen": 0,
|
198 |
+
"num_train_epochs": 2,
|
199 |
+
"save_steps": 500,
|
200 |
+
"total_flos": 4305130555198464.0,
|
201 |
+
"train_batch_size": 12,
|
202 |
+
"trial_name": null,
|
203 |
+
"trial_params": null
|
204 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdce91777575d68d947a37ab9ddd61f085907d54dba6a98c4df9e028a4d09453
|
3 |
+
size 4728
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|