Upload 9 files
Browse files- config.json +24 -0
- eval_results.txt +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +467 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.2.1",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
eval_results.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
eval_CR = 88.65
|
| 3 |
+
eval_MPQA = 89.58
|
| 4 |
+
eval_MR = 80.98
|
| 5 |
+
eval_MRPC = 75.27
|
| 6 |
+
eval_SST2 = 84.86
|
| 7 |
+
eval_SUBJ = 93.86
|
| 8 |
+
eval_TREC = 78.47
|
| 9 |
+
eval_avg_sts = 0.8323569009206506
|
| 10 |
+
eval_avg_transfer = 84.52428571428571
|
| 11 |
+
eval_sickr_spearman = 0.8193010796229231
|
| 12 |
+
eval_stsb_spearman = 0.8454127222183782
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b6179d6cf62f2f03a9fae56d4c7f5e39f82da4e7d411210fc5e423dff5cebea
|
| 3 |
+
size 534253890
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/data/lyhe/data/bert-base-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
train_runtime = 2256.7501
|
| 3 |
+
train_samples_per_second = 0.683
|
trainer_state.json
ADDED
|
@@ -0,0 +1,467 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8323569009206506,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/bert-base-uncased",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1542,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"eval_avg_sts": 0.8091205074434157,
|
| 13 |
+
"eval_sickr_spearman": 0.7855689811762409,
|
| 14 |
+
"eval_stsb_spearman": 0.8326720337105905,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"eval_avg_sts": 0.8102784124545166,
|
| 20 |
+
"eval_sickr_spearman": 0.7833337578086155,
|
| 21 |
+
"eval_stsb_spearman": 0.8372230671004176,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.15,
|
| 26 |
+
"eval_avg_sts": 0.8185920801302614,
|
| 27 |
+
"eval_sickr_spearman": 0.7990731655010734,
|
| 28 |
+
"eval_stsb_spearman": 0.8381109947594494,
|
| 29 |
+
"step": 75
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.19,
|
| 33 |
+
"eval_avg_sts": 0.8235606132721098,
|
| 34 |
+
"eval_sickr_spearman": 0.802081545508548,
|
| 35 |
+
"eval_stsb_spearman": 0.8450396810356716,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.24,
|
| 40 |
+
"eval_avg_sts": 0.8261107797978882,
|
| 41 |
+
"eval_sickr_spearman": 0.8095936578045705,
|
| 42 |
+
"eval_stsb_spearman": 0.8426279017912058,
|
| 43 |
+
"step": 125
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.29,
|
| 47 |
+
"eval_avg_sts": 0.8298711381476593,
|
| 48 |
+
"eval_sickr_spearman": 0.8175562057698793,
|
| 49 |
+
"eval_stsb_spearman": 0.8421860705254393,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.34,
|
| 54 |
+
"eval_avg_sts": 0.8268735580135445,
|
| 55 |
+
"eval_sickr_spearman": 0.809783716872961,
|
| 56 |
+
"eval_stsb_spearman": 0.843963399154128,
|
| 57 |
+
"step": 175
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.39,
|
| 61 |
+
"eval_avg_sts": 0.8269969778164787,
|
| 62 |
+
"eval_sickr_spearman": 0.8097261275823368,
|
| 63 |
+
"eval_stsb_spearman": 0.8442678280506208,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.44,
|
| 68 |
+
"eval_avg_sts": 0.8286377864730684,
|
| 69 |
+
"eval_sickr_spearman": 0.8138642471267373,
|
| 70 |
+
"eval_stsb_spearman": 0.8434113258193995,
|
| 71 |
+
"step": 225
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.49,
|
| 75 |
+
"eval_avg_sts": 0.8311901085527629,
|
| 76 |
+
"eval_sickr_spearman": 0.8156780936414463,
|
| 77 |
+
"eval_stsb_spearman": 0.8467021234640796,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.54,
|
| 82 |
+
"eval_avg_sts": 0.8239986377138246,
|
| 83 |
+
"eval_sickr_spearman": 0.8047907397851649,
|
| 84 |
+
"eval_stsb_spearman": 0.8432065356424845,
|
| 85 |
+
"step": 275
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.58,
|
| 89 |
+
"eval_avg_sts": 0.828722661892037,
|
| 90 |
+
"eval_sickr_spearman": 0.8108316114130363,
|
| 91 |
+
"eval_stsb_spearman": 0.8466137123710378,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.63,
|
| 96 |
+
"eval_avg_sts": 0.8283282637029816,
|
| 97 |
+
"eval_sickr_spearman": 0.8147261652420443,
|
| 98 |
+
"eval_stsb_spearman": 0.8419303621639188,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.68,
|
| 103 |
+
"eval_avg_sts": 0.8300155790519733,
|
| 104 |
+
"eval_sickr_spearman": 0.8170386706518836,
|
| 105 |
+
"eval_stsb_spearman": 0.842992487452063,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.73,
|
| 110 |
+
"eval_avg_sts": 0.8283238508507671,
|
| 111 |
+
"eval_sickr_spearman": 0.8139993586150827,
|
| 112 |
+
"eval_stsb_spearman": 0.8426483430864515,
|
| 113 |
+
"step": 375
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.78,
|
| 117 |
+
"eval_avg_sts": 0.8320405612243372,
|
| 118 |
+
"eval_sickr_spearman": 0.8164555730804248,
|
| 119 |
+
"eval_stsb_spearman": 0.8476255493682496,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.83,
|
| 124 |
+
"eval_avg_sts": 0.8285288492675393,
|
| 125 |
+
"eval_sickr_spearman": 0.8121700941168123,
|
| 126 |
+
"eval_stsb_spearman": 0.8448876044182664,
|
| 127 |
+
"step": 425
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.88,
|
| 131 |
+
"eval_avg_sts": 0.8323569009206506,
|
| 132 |
+
"eval_sickr_spearman": 0.8193010796229231,
|
| 133 |
+
"eval_stsb_spearman": 0.8454127222183782,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.92,
|
| 138 |
+
"eval_avg_sts": 0.825475145325371,
|
| 139 |
+
"eval_sickr_spearman": 0.8101125858245077,
|
| 140 |
+
"eval_stsb_spearman": 0.8408377048262344,
|
| 141 |
+
"step": 475
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.97,
|
| 145 |
+
"learning_rate": 3.378728923476006e-05,
|
| 146 |
+
"loss": 0.4728,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.97,
|
| 151 |
+
"eval_avg_sts": 0.8271573597477266,
|
| 152 |
+
"eval_sickr_spearman": 0.8153802527814284,
|
| 153 |
+
"eval_stsb_spearman": 0.8389344667140248,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.02,
|
| 158 |
+
"eval_avg_sts": 0.825308678275509,
|
| 159 |
+
"eval_sickr_spearman": 0.8106034636812054,
|
| 160 |
+
"eval_stsb_spearman": 0.8400138928698127,
|
| 161 |
+
"step": 525
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.07,
|
| 165 |
+
"eval_avg_sts": 0.8267825462568358,
|
| 166 |
+
"eval_sickr_spearman": 0.8081616105151932,
|
| 167 |
+
"eval_stsb_spearman": 0.8454034819984784,
|
| 168 |
+
"step": 550
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.12,
|
| 172 |
+
"eval_avg_sts": 0.8292667339957281,
|
| 173 |
+
"eval_sickr_spearman": 0.8131185642769106,
|
| 174 |
+
"eval_stsb_spearman": 0.8454149037145456,
|
| 175 |
+
"step": 575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.17,
|
| 179 |
+
"eval_avg_sts": 0.8282847493542007,
|
| 180 |
+
"eval_sickr_spearman": 0.8099082134878887,
|
| 181 |
+
"eval_stsb_spearman": 0.8466612852205128,
|
| 182 |
+
"step": 600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.22,
|
| 186 |
+
"eval_avg_sts": 0.8284726818422365,
|
| 187 |
+
"eval_sickr_spearman": 0.8136914792548644,
|
| 188 |
+
"eval_stsb_spearman": 0.8432538844296088,
|
| 189 |
+
"step": 625
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.26,
|
| 193 |
+
"eval_avg_sts": 0.8264807699499799,
|
| 194 |
+
"eval_sickr_spearman": 0.8101471201864417,
|
| 195 |
+
"eval_stsb_spearman": 0.8428144197135181,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.31,
|
| 200 |
+
"eval_avg_sts": 0.825789312158798,
|
| 201 |
+
"eval_sickr_spearman": 0.8071726981676838,
|
| 202 |
+
"eval_stsb_spearman": 0.8444059261499122,
|
| 203 |
+
"step": 675
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.36,
|
| 207 |
+
"eval_avg_sts": 0.8263077667234103,
|
| 208 |
+
"eval_sickr_spearman": 0.809834918027094,
|
| 209 |
+
"eval_stsb_spearman": 0.8427806154197267,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.41,
|
| 214 |
+
"eval_avg_sts": 0.8269124521441422,
|
| 215 |
+
"eval_sickr_spearman": 0.8103127314242003,
|
| 216 |
+
"eval_stsb_spearman": 0.8435121728640842,
|
| 217 |
+
"step": 725
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.46,
|
| 221 |
+
"eval_avg_sts": 0.8284054639641667,
|
| 222 |
+
"eval_sickr_spearman": 0.812405014233946,
|
| 223 |
+
"eval_stsb_spearman": 0.8444059136943874,
|
| 224 |
+
"step": 750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.51,
|
| 228 |
+
"eval_avg_sts": 0.82848047976913,
|
| 229 |
+
"eval_sickr_spearman": 0.8127376776425065,
|
| 230 |
+
"eval_stsb_spearman": 0.8442232818957535,
|
| 231 |
+
"step": 775
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.56,
|
| 235 |
+
"eval_avg_sts": 0.827488956868254,
|
| 236 |
+
"eval_sickr_spearman": 0.8100566776224338,
|
| 237 |
+
"eval_stsb_spearman": 0.844921236114074,
|
| 238 |
+
"step": 800
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.61,
|
| 242 |
+
"eval_avg_sts": 0.8279657581459612,
|
| 243 |
+
"eval_sickr_spearman": 0.8108479419875253,
|
| 244 |
+
"eval_stsb_spearman": 0.845083574304397,
|
| 245 |
+
"step": 825
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.65,
|
| 249 |
+
"eval_avg_sts": 0.8273853394613049,
|
| 250 |
+
"eval_sickr_spearman": 0.8107756071487595,
|
| 251 |
+
"eval_stsb_spearman": 0.8439950717738504,
|
| 252 |
+
"step": 850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.7,
|
| 256 |
+
"eval_avg_sts": 0.8313352689680793,
|
| 257 |
+
"eval_sickr_spearman": 0.8172410737133439,
|
| 258 |
+
"eval_stsb_spearman": 0.8454294642228147,
|
| 259 |
+
"step": 875
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.75,
|
| 263 |
+
"eval_avg_sts": 0.8319193188081185,
|
| 264 |
+
"eval_sickr_spearman": 0.8177730661928723,
|
| 265 |
+
"eval_stsb_spearman": 0.8460655714233648,
|
| 266 |
+
"step": 900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.8,
|
| 270 |
+
"eval_avg_sts": 0.8290710541535955,
|
| 271 |
+
"eval_sickr_spearman": 0.8117156718661062,
|
| 272 |
+
"eval_stsb_spearman": 0.8464264364410848,
|
| 273 |
+
"step": 925
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.85,
|
| 277 |
+
"eval_avg_sts": 0.8304411183144629,
|
| 278 |
+
"eval_sickr_spearman": 0.8173339178324237,
|
| 279 |
+
"eval_stsb_spearman": 0.8435483187965022,
|
| 280 |
+
"step": 950
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.9,
|
| 284 |
+
"eval_avg_sts": 0.8278597990068485,
|
| 285 |
+
"eval_sickr_spearman": 0.8122580390635454,
|
| 286 |
+
"eval_stsb_spearman": 0.8434615589501515,
|
| 287 |
+
"step": 975
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.95,
|
| 291 |
+
"learning_rate": 1.7574578469520103e-05,
|
| 292 |
+
"loss": 0.2979,
|
| 293 |
+
"step": 1000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.95,
|
| 297 |
+
"eval_avg_sts": 0.8302680866123784,
|
| 298 |
+
"eval_sickr_spearman": 0.8155675260459356,
|
| 299 |
+
"eval_stsb_spearman": 0.8449686471788213,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.99,
|
| 304 |
+
"eval_avg_sts": 0.8254828270469559,
|
| 305 |
+
"eval_sickr_spearman": 0.8089062366807882,
|
| 306 |
+
"eval_stsb_spearman": 0.8420594174131236,
|
| 307 |
+
"step": 1025
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.04,
|
| 311 |
+
"eval_avg_sts": 0.828821293584806,
|
| 312 |
+
"eval_sickr_spearman": 0.8119630800696138,
|
| 313 |
+
"eval_stsb_spearman": 0.8456795070999983,
|
| 314 |
+
"step": 1050
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.09,
|
| 318 |
+
"eval_avg_sts": 0.828469666832049,
|
| 319 |
+
"eval_sickr_spearman": 0.8131763937230422,
|
| 320 |
+
"eval_stsb_spearman": 0.8437629399410558,
|
| 321 |
+
"step": 1075
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.14,
|
| 325 |
+
"eval_avg_sts": 0.8282850923377056,
|
| 326 |
+
"eval_sickr_spearman": 0.8126665916123781,
|
| 327 |
+
"eval_stsb_spearman": 0.8439035930630331,
|
| 328 |
+
"step": 1100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.19,
|
| 332 |
+
"eval_avg_sts": 0.8305188158369109,
|
| 333 |
+
"eval_sickr_spearman": 0.8153585427235783,
|
| 334 |
+
"eval_stsb_spearman": 0.8456790889502435,
|
| 335 |
+
"step": 1125
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.24,
|
| 339 |
+
"eval_avg_sts": 0.827633691614419,
|
| 340 |
+
"eval_sickr_spearman": 0.8116303205988508,
|
| 341 |
+
"eval_stsb_spearman": 0.8436370626299873,
|
| 342 |
+
"step": 1150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.29,
|
| 346 |
+
"eval_avg_sts": 0.8282905337553752,
|
| 347 |
+
"eval_sickr_spearman": 0.8129372468689818,
|
| 348 |
+
"eval_stsb_spearman": 0.8436438206417686,
|
| 349 |
+
"step": 1175
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.33,
|
| 353 |
+
"eval_avg_sts": 0.8284000990759287,
|
| 354 |
+
"eval_sickr_spearman": 0.8133387388459029,
|
| 355 |
+
"eval_stsb_spearman": 0.8434614593059545,
|
| 356 |
+
"step": 1200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.38,
|
| 360 |
+
"eval_avg_sts": 0.8281162332936303,
|
| 361 |
+
"eval_sickr_spearman": 0.8138668123079954,
|
| 362 |
+
"eval_stsb_spearman": 0.8423656542792651,
|
| 363 |
+
"step": 1225
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.43,
|
| 367 |
+
"eval_avg_sts": 0.8294468108598559,
|
| 368 |
+
"eval_sickr_spearman": 0.8161867430056757,
|
| 369 |
+
"eval_stsb_spearman": 0.8427068787140362,
|
| 370 |
+
"step": 1250
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.48,
|
| 374 |
+
"eval_avg_sts": 0.8283226082193897,
|
| 375 |
+
"eval_sickr_spearman": 0.813798972859883,
|
| 376 |
+
"eval_stsb_spearman": 0.8428462435788966,
|
| 377 |
+
"step": 1275
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.53,
|
| 381 |
+
"eval_avg_sts": 0.8292589856543454,
|
| 382 |
+
"eval_sickr_spearman": 0.8143020025852442,
|
| 383 |
+
"eval_stsb_spearman": 0.8442159687234466,
|
| 384 |
+
"step": 1300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.58,
|
| 388 |
+
"eval_avg_sts": 0.8276816481179423,
|
| 389 |
+
"eval_sickr_spearman": 0.8122173567206272,
|
| 390 |
+
"eval_stsb_spearman": 0.8431459395152573,
|
| 391 |
+
"step": 1325
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.63,
|
| 395 |
+
"eval_avg_sts": 0.828135742102698,
|
| 396 |
+
"eval_sickr_spearman": 0.8131700536176523,
|
| 397 |
+
"eval_stsb_spearman": 0.8431014305877439,
|
| 398 |
+
"step": 1350
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.68,
|
| 402 |
+
"eval_avg_sts": 0.8272048038824943,
|
| 403 |
+
"eval_sickr_spearman": 0.8118982380826725,
|
| 404 |
+
"eval_stsb_spearman": 0.8425113696823161,
|
| 405 |
+
"step": 1375
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.72,
|
| 409 |
+
"eval_avg_sts": 0.8277882199813771,
|
| 410 |
+
"eval_sickr_spearman": 0.8125238431789039,
|
| 411 |
+
"eval_stsb_spearman": 0.8430525967838501,
|
| 412 |
+
"step": 1400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.77,
|
| 416 |
+
"eval_avg_sts": 0.8280258441957502,
|
| 417 |
+
"eval_sickr_spearman": 0.8130684198070092,
|
| 418 |
+
"eval_stsb_spearman": 0.8429832685844911,
|
| 419 |
+
"step": 1425
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.82,
|
| 423 |
+
"eval_avg_sts": 0.8283991403128114,
|
| 424 |
+
"eval_sickr_spearman": 0.8137915280391601,
|
| 425 |
+
"eval_stsb_spearman": 0.8430067525864626,
|
| 426 |
+
"step": 1450
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.87,
|
| 430 |
+
"eval_avg_sts": 0.8277659521731837,
|
| 431 |
+
"eval_sickr_spearman": 0.8129026644759463,
|
| 432 |
+
"eval_stsb_spearman": 0.842629239870421,
|
| 433 |
+
"step": 1475
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.92,
|
| 437 |
+
"learning_rate": 1.3618677042801557e-06,
|
| 438 |
+
"loss": 0.2608,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.92,
|
| 443 |
+
"eval_avg_sts": 0.8277817426384378,
|
| 444 |
+
"eval_sickr_spearman": 0.812730280852885,
|
| 445 |
+
"eval_stsb_spearman": 0.8428332044239907,
|
| 446 |
+
"step": 1500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.97,
|
| 450 |
+
"eval_avg_sts": 0.8276246266790095,
|
| 451 |
+
"eval_sickr_spearman": 0.8125702892539944,
|
| 452 |
+
"eval_stsb_spearman": 0.8426789641040247,
|
| 453 |
+
"step": 1525
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.0,
|
| 457 |
+
"step": 1542,
|
| 458 |
+
"train_runtime": 2256.7501,
|
| 459 |
+
"train_samples_per_second": 0.683
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"max_steps": 1542,
|
| 463 |
+
"num_train_epochs": 3,
|
| 464 |
+
"total_flos": 121335504616820736,
|
| 465 |
+
"trial_name": null,
|
| 466 |
+
"trial_params": null
|
| 467 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9803ce63c9d245f74802c71cdd9ee99424d6d90228eb7b71cc02c9e3cdef8a8a
|
| 3 |
+
size 2488
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|