Upload 12 files
Browse files- README.md +57 -1
- all_results.json +14 -0
- config.json +29 -0
- eval_predictions.json +0 -0
- eval_results.json +9 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +397 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,59 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: result
|
6 |
+
results: []
|
7 |
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# result
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
|
15 |
+
|
16 |
+
## Model description
|
17 |
+
|
18 |
+
More information needed
|
19 |
+
|
20 |
+
## Intended uses & limitations
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Training and evaluation data
|
25 |
+
|
26 |
+
NewsQA from https://github.com/mrqa/MRQA-Shared-Task-2019
|
27 |
+
|
28 |
+
|
29 |
+
## Training procedure
|
30 |
+
|
31 |
+
### Training hyperparameters
|
32 |
+
|
33 |
+
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 3e-05
|
35 |
+
- train_batch_size: 12
|
36 |
+
- eval_batch_size: 8
|
37 |
+
- seed: 42
|
38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
+
- lr_scheduler_type: linear
|
40 |
+
- num_epochs: 2.0
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
***** eval metrics *****
|
44 |
+
epoch = 2.0
|
45 |
+
eval_exact_match = 0.6648
|
46 |
+
eval_f1 = 4.3787
|
47 |
+
eval_runtime = 0:00:31.81
|
48 |
+
eval_samples = 10567
|
49 |
+
eval_samples_per_second = 332.115
|
50 |
+
eval_steps_per_second = 41.518
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.27.0.dev0
|
57 |
+
- Pytorch 1.13.1+cu116
|
58 |
+
- Datasets 2.9.0
|
59 |
+
- Tokenizers 0.13.2
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_exact_match": 0.6647673314339981,
|
4 |
+
"eval_f1": 4.378741273434903,
|
5 |
+
"eval_runtime": 31.8173,
|
6 |
+
"eval_samples": 10567,
|
7 |
+
"eval_samples_per_second": 332.115,
|
8 |
+
"eval_steps_per_second": 41.518,
|
9 |
+
"train_loss": 1.6433022868307863,
|
10 |
+
"train_runtime": 3179.4331,
|
11 |
+
"train_samples": 187263,
|
12 |
+
"train_samples_per_second": 117.796,
|
13 |
+
"train_steps_per_second": 9.817
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"cell": {},
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"emb_size": 312,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 1200,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 4,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"pre_trained": "",
|
23 |
+
"structure": [],
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.27.0.dev0",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 30522
|
29 |
+
}
|
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": 0.6647673314339981,
|
4 |
+
"eval_f1": 4.378741273434903,
|
5 |
+
"eval_runtime": 31.8173,
|
6 |
+
"eval_samples": 10567,
|
7 |
+
"eval_samples_per_second": 332.115,
|
8 |
+
"eval_steps_per_second": 41.518
|
9 |
+
}
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 1.6433022868307863,
|
4 |
+
"train_runtime": 3179.4331,
|
5 |
+
"train_samples": 187263,
|
6 |
+
"train_samples_per_second": 117.796,
|
7 |
+
"train_steps_per_second": 9.817
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,397 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 31212,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 2.9519415609381006e-05,
|
13 |
+
"loss": 2.3707,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 2.9038831218762015e-05,
|
19 |
+
"loss": 1.8657,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 2.8558246828143025e-05,
|
25 |
+
"loss": 1.8001,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.13,
|
30 |
+
"learning_rate": 2.807766243752403e-05,
|
31 |
+
"loss": 1.8241,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.16,
|
36 |
+
"learning_rate": 2.759707804690504e-05,
|
37 |
+
"loss": 1.8568,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.19,
|
42 |
+
"learning_rate": 2.7116493656286045e-05,
|
43 |
+
"loss": 1.7976,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.22,
|
48 |
+
"learning_rate": 2.663590926566705e-05,
|
49 |
+
"loss": 1.7969,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.26,
|
54 |
+
"learning_rate": 2.6155324875048056e-05,
|
55 |
+
"loss": 1.772,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.29,
|
60 |
+
"learning_rate": 2.567474048442907e-05,
|
61 |
+
"loss": 1.7746,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.32,
|
66 |
+
"learning_rate": 2.5194156093810074e-05,
|
67 |
+
"loss": 1.7575,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.35,
|
72 |
+
"learning_rate": 2.471357170319108e-05,
|
73 |
+
"loss": 1.7777,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.38,
|
78 |
+
"learning_rate": 2.423298731257209e-05,
|
79 |
+
"loss": 1.7731,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.42,
|
84 |
+
"learning_rate": 2.3752402921953095e-05,
|
85 |
+
"loss": 1.7775,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.45,
|
90 |
+
"learning_rate": 2.32718185313341e-05,
|
91 |
+
"loss": 1.7627,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.48,
|
96 |
+
"learning_rate": 2.2791234140715113e-05,
|
97 |
+
"loss": 1.7435,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.51,
|
102 |
+
"learning_rate": 2.231064975009612e-05,
|
103 |
+
"loss": 1.7182,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.54,
|
108 |
+
"learning_rate": 2.1830065359477124e-05,
|
109 |
+
"loss": 1.7493,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.58,
|
114 |
+
"learning_rate": 2.1349480968858133e-05,
|
115 |
+
"loss": 1.715,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.61,
|
120 |
+
"learning_rate": 2.086889657823914e-05,
|
121 |
+
"loss": 1.7109,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.64,
|
126 |
+
"learning_rate": 2.0388312187620145e-05,
|
127 |
+
"loss": 1.651,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.67,
|
132 |
+
"learning_rate": 1.9907727797001154e-05,
|
133 |
+
"loss": 1.7383,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.7,
|
138 |
+
"learning_rate": 1.9427143406382163e-05,
|
139 |
+
"loss": 1.6754,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.74,
|
144 |
+
"learning_rate": 1.8946559015763168e-05,
|
145 |
+
"loss": 1.5948,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.77,
|
150 |
+
"learning_rate": 1.8465974625144174e-05,
|
151 |
+
"loss": 1.6431,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.8,
|
156 |
+
"learning_rate": 1.7985390234525183e-05,
|
157 |
+
"loss": 1.6536,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.83,
|
162 |
+
"learning_rate": 1.7504805843906192e-05,
|
163 |
+
"loss": 1.5941,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.87,
|
168 |
+
"learning_rate": 1.7024221453287198e-05,
|
169 |
+
"loss": 1.6606,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.9,
|
174 |
+
"learning_rate": 1.6543637062668207e-05,
|
175 |
+
"loss": 1.6621,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.93,
|
180 |
+
"learning_rate": 1.6063052672049212e-05,
|
181 |
+
"loss": 1.622,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.96,
|
186 |
+
"learning_rate": 1.5582468281430218e-05,
|
187 |
+
"loss": 1.6216,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.99,
|
192 |
+
"learning_rate": 1.5101883890811225e-05,
|
193 |
+
"loss": 1.618,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.03,
|
198 |
+
"learning_rate": 1.4621299500192235e-05,
|
199 |
+
"loss": 1.5934,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.06,
|
204 |
+
"learning_rate": 1.414071510957324e-05,
|
205 |
+
"loss": 1.602,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.09,
|
210 |
+
"learning_rate": 1.366013071895425e-05,
|
211 |
+
"loss": 1.5458,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.12,
|
216 |
+
"learning_rate": 1.3179546328335255e-05,
|
217 |
+
"loss": 1.5039,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.15,
|
222 |
+
"learning_rate": 1.2698961937716264e-05,
|
223 |
+
"loss": 1.5694,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.19,
|
228 |
+
"learning_rate": 1.2218377547097271e-05,
|
229 |
+
"loss": 1.5937,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.22,
|
234 |
+
"learning_rate": 1.1737793156478277e-05,
|
235 |
+
"loss": 1.5364,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.25,
|
240 |
+
"learning_rate": 1.1257208765859286e-05,
|
241 |
+
"loss": 1.5487,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.28,
|
246 |
+
"learning_rate": 1.0776624375240293e-05,
|
247 |
+
"loss": 1.5565,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.31,
|
252 |
+
"learning_rate": 1.0296039984621299e-05,
|
253 |
+
"loss": 1.5503,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.35,
|
258 |
+
"learning_rate": 9.815455594002308e-06,
|
259 |
+
"loss": 1.577,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.38,
|
264 |
+
"learning_rate": 9.334871203383314e-06,
|
265 |
+
"loss": 1.5346,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.41,
|
270 |
+
"learning_rate": 8.854286812764321e-06,
|
271 |
+
"loss": 1.5686,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.44,
|
276 |
+
"learning_rate": 8.37370242214533e-06,
|
277 |
+
"loss": 1.5372,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.47,
|
282 |
+
"learning_rate": 7.893118031526336e-06,
|
283 |
+
"loss": 1.5534,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.51,
|
288 |
+
"learning_rate": 7.412533640907344e-06,
|
289 |
+
"loss": 1.5061,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.54,
|
294 |
+
"learning_rate": 6.9319492502883506e-06,
|
295 |
+
"loss": 1.5766,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.57,
|
300 |
+
"learning_rate": 6.451364859669358e-06,
|
301 |
+
"loss": 1.5215,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.6,
|
306 |
+
"learning_rate": 5.970780469050365e-06,
|
307 |
+
"loss": 1.5602,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.63,
|
312 |
+
"learning_rate": 5.490196078431373e-06,
|
313 |
+
"loss": 1.5311,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.67,
|
318 |
+
"learning_rate": 5.00961168781238e-06,
|
319 |
+
"loss": 1.5018,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.7,
|
324 |
+
"learning_rate": 4.529027297193387e-06,
|
325 |
+
"loss": 1.5673,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.73,
|
330 |
+
"learning_rate": 4.048442906574395e-06,
|
331 |
+
"loss": 1.5459,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.76,
|
336 |
+
"learning_rate": 3.5678585159554016e-06,
|
337 |
+
"loss": 1.5127,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.79,
|
342 |
+
"learning_rate": 3.0872741253364094e-06,
|
343 |
+
"loss": 1.4852,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.83,
|
348 |
+
"learning_rate": 2.6066897347174164e-06,
|
349 |
+
"loss": 1.5609,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.86,
|
354 |
+
"learning_rate": 2.1261053440984237e-06,
|
355 |
+
"loss": 1.4866,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.89,
|
360 |
+
"learning_rate": 1.645520953479431e-06,
|
361 |
+
"loss": 1.5449,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.92,
|
366 |
+
"learning_rate": 1.1649365628604384e-06,
|
367 |
+
"loss": 1.4855,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.95,
|
372 |
+
"learning_rate": 6.843521722414456e-07,
|
373 |
+
"loss": 1.5881,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.99,
|
378 |
+
"learning_rate": 2.037677816224529e-07,
|
379 |
+
"loss": 1.5224,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.0,
|
384 |
+
"step": 31212,
|
385 |
+
"total_flos": 3943477040569344.0,
|
386 |
+
"train_loss": 1.6433022868307863,
|
387 |
+
"train_runtime": 3179.4331,
|
388 |
+
"train_samples_per_second": 117.796,
|
389 |
+
"train_steps_per_second": 9.817
|
390 |
+
}
|
391 |
+
],
|
392 |
+
"max_steps": 31212,
|
393 |
+
"num_train_epochs": 2,
|
394 |
+
"total_flos": 3943477040569344.0,
|
395 |
+
"trial_name": null,
|
396 |
+
"trial_params": null
|
397 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f6f0801f0a956245416f3c234f8d21eeab500c17d16001b5c22aa9021d74d2
|
3 |
+
size 3451
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|