ZhangYunchenY commited on
Commit ·
569f189
1
Parent(s): 46b9440
[Model] bert-base-uncased-stsb
Browse files- config.json +34 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +524 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"finetuning_task": "stsb",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "regression",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.13.0.dev0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ae11f0df38f5795865ba1d3997efb24b8729f301afe94832cdd5f36870272f
|
| 3 |
+
size 875991075
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99a426d8487002df8623f33011771fe7fb759da0271cd42673303c4c6ae047fb
|
| 3 |
+
size 438021779
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3a7c8a4c63ab300071a77268a406ee50547f5793c538dcde70593def84c9ed8
|
| 3 |
+
size 14659
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b6298878d15035f3cba5611cfa3c9c3ddf0a2576fe0e93990d6695ababd1f34
|
| 3 |
+
size 623
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,524 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4471864700317383,
|
| 3 |
+
"best_model_checkpoint": "output_dir/finetuned_best_stsb/checkpoint-1900",
|
| 4 |
+
"epoch": 6.111111111111111,
|
| 5 |
+
"global_step": 2200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"eval_combined_score": 0.8343080271135384,
|
| 13 |
+
"eval_loss": 0.7862432599067688,
|
| 14 |
+
"eval_pearson": 0.829615903016159,
|
| 15 |
+
"eval_runtime": 7.9747,
|
| 16 |
+
"eval_samples_per_second": 188.095,
|
| 17 |
+
"eval_spearmanr": 0.8390001512109179,
|
| 18 |
+
"eval_steps_per_second": 11.787,
|
| 19 |
+
"step": 50
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.28,
|
| 23 |
+
"eval_combined_score": 0.8549898629109538,
|
| 24 |
+
"eval_loss": 0.6401779055595398,
|
| 25 |
+
"eval_pearson": 0.8531715498817952,
|
| 26 |
+
"eval_runtime": 5.6147,
|
| 27 |
+
"eval_samples_per_second": 267.156,
|
| 28 |
+
"eval_spearmanr": 0.8568081759401125,
|
| 29 |
+
"eval_steps_per_second": 16.742,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.42,
|
| 34 |
+
"eval_combined_score": 0.8443191275483415,
|
| 35 |
+
"eval_loss": 0.6554257273674011,
|
| 36 |
+
"eval_pearson": 0.8474110080447523,
|
| 37 |
+
"eval_runtime": 5.6204,
|
| 38 |
+
"eval_samples_per_second": 266.887,
|
| 39 |
+
"eval_spearmanr": 0.8412272470519305,
|
| 40 |
+
"eval_steps_per_second": 16.725,
|
| 41 |
+
"step": 150
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.56,
|
| 45 |
+
"eval_combined_score": 0.8673615699410524,
|
| 46 |
+
"eval_loss": 0.5701442956924438,
|
| 47 |
+
"eval_pearson": 0.8692556554827053,
|
| 48 |
+
"eval_runtime": 5.9834,
|
| 49 |
+
"eval_samples_per_second": 250.694,
|
| 50 |
+
"eval_spearmanr": 0.8654674843993996,
|
| 51 |
+
"eval_steps_per_second": 15.71,
|
| 52 |
+
"step": 200
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.69,
|
| 56 |
+
"eval_combined_score": 0.8721712658068579,
|
| 57 |
+
"eval_loss": 0.5915741920471191,
|
| 58 |
+
"eval_pearson": 0.8722910960572966,
|
| 59 |
+
"eval_runtime": 5.5689,
|
| 60 |
+
"eval_samples_per_second": 269.355,
|
| 61 |
+
"eval_spearmanr": 0.8720514355564192,
|
| 62 |
+
"eval_steps_per_second": 16.88,
|
| 63 |
+
"step": 250
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.83,
|
| 67 |
+
"eval_combined_score": 0.8812625681870452,
|
| 68 |
+
"eval_loss": 0.5046865344047546,
|
| 69 |
+
"eval_pearson": 0.881670075532939,
|
| 70 |
+
"eval_runtime": 6.0146,
|
| 71 |
+
"eval_samples_per_second": 249.392,
|
| 72 |
+
"eval_spearmanr": 0.8808550608411514,
|
| 73 |
+
"eval_steps_per_second": 15.629,
|
| 74 |
+
"step": 300
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.97,
|
| 78 |
+
"eval_combined_score": 0.878795558425897,
|
| 79 |
+
"eval_loss": 0.5713155269622803,
|
| 80 |
+
"eval_pearson": 0.8736557247061164,
|
| 81 |
+
"eval_runtime": 6.0781,
|
| 82 |
+
"eval_samples_per_second": 246.786,
|
| 83 |
+
"eval_spearmanr": 0.8839353921456775,
|
| 84 |
+
"eval_steps_per_second": 15.465,
|
| 85 |
+
"step": 350
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.11,
|
| 89 |
+
"eval_combined_score": 0.8778669265351486,
|
| 90 |
+
"eval_loss": 0.5400073528289795,
|
| 91 |
+
"eval_pearson": 0.8804620985683852,
|
| 92 |
+
"eval_runtime": 5.5918,
|
| 93 |
+
"eval_samples_per_second": 268.248,
|
| 94 |
+
"eval_spearmanr": 0.875271754501912,
|
| 95 |
+
"eval_steps_per_second": 16.81,
|
| 96 |
+
"step": 400
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.25,
|
| 100 |
+
"eval_combined_score": 0.8833550106755617,
|
| 101 |
+
"eval_loss": 0.49523210525512695,
|
| 102 |
+
"eval_pearson": 0.8858630637184036,
|
| 103 |
+
"eval_runtime": 5.7638,
|
| 104 |
+
"eval_samples_per_second": 260.246,
|
| 105 |
+
"eval_spearmanr": 0.8808469576327196,
|
| 106 |
+
"eval_steps_per_second": 16.309,
|
| 107 |
+
"step": 450
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.39,
|
| 111 |
+
"learning_rate": 4.1319444444444445e-05,
|
| 112 |
+
"loss": 0.7828,
|
| 113 |
+
"step": 500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.39,
|
| 117 |
+
"eval_combined_score": 0.8827148836128291,
|
| 118 |
+
"eval_loss": 0.5279519557952881,
|
| 119 |
+
"eval_pearson": 0.8845811601256096,
|
| 120 |
+
"eval_runtime": 5.9061,
|
| 121 |
+
"eval_samples_per_second": 253.975,
|
| 122 |
+
"eval_spearmanr": 0.8808486071000486,
|
| 123 |
+
"eval_steps_per_second": 15.916,
|
| 124 |
+
"step": 500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.53,
|
| 128 |
+
"eval_combined_score": 0.8801981392571121,
|
| 129 |
+
"eval_loss": 0.5072206258773804,
|
| 130 |
+
"eval_pearson": 0.8810815176670656,
|
| 131 |
+
"eval_runtime": 5.5676,
|
| 132 |
+
"eval_samples_per_second": 269.418,
|
| 133 |
+
"eval_spearmanr": 0.8793147608471588,
|
| 134 |
+
"eval_steps_per_second": 16.884,
|
| 135 |
+
"step": 550
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.67,
|
| 139 |
+
"eval_combined_score": 0.8851362735229233,
|
| 140 |
+
"eval_loss": 0.49581071734428406,
|
| 141 |
+
"eval_pearson": 0.8875092909393476,
|
| 142 |
+
"eval_runtime": 5.6319,
|
| 143 |
+
"eval_samples_per_second": 266.34,
|
| 144 |
+
"eval_spearmanr": 0.8827632561064991,
|
| 145 |
+
"eval_steps_per_second": 16.691,
|
| 146 |
+
"step": 600
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.81,
|
| 150 |
+
"eval_combined_score": 0.8852476609333064,
|
| 151 |
+
"eval_loss": 0.4841392934322357,
|
| 152 |
+
"eval_pearson": 0.8870465421559632,
|
| 153 |
+
"eval_runtime": 5.8286,
|
| 154 |
+
"eval_samples_per_second": 257.351,
|
| 155 |
+
"eval_spearmanr": 0.8834487797106495,
|
| 156 |
+
"eval_steps_per_second": 16.127,
|
| 157 |
+
"step": 650
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.94,
|
| 161 |
+
"eval_combined_score": 0.8837498972174722,
|
| 162 |
+
"eval_loss": 0.5464913845062256,
|
| 163 |
+
"eval_pearson": 0.8849881470427847,
|
| 164 |
+
"eval_runtime": 5.5884,
|
| 165 |
+
"eval_samples_per_second": 268.412,
|
| 166 |
+
"eval_spearmanr": 0.8825116473921596,
|
| 167 |
+
"eval_steps_per_second": 16.82,
|
| 168 |
+
"step": 700
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.08,
|
| 172 |
+
"eval_combined_score": 0.8858322086355523,
|
| 173 |
+
"eval_loss": 0.48856478929519653,
|
| 174 |
+
"eval_pearson": 0.8881076481621831,
|
| 175 |
+
"eval_runtime": 5.6259,
|
| 176 |
+
"eval_samples_per_second": 266.624,
|
| 177 |
+
"eval_spearmanr": 0.8835567691089214,
|
| 178 |
+
"eval_steps_per_second": 16.708,
|
| 179 |
+
"step": 750
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.22,
|
| 183 |
+
"eval_combined_score": 0.8865111243309827,
|
| 184 |
+
"eval_loss": 0.4807361662387848,
|
| 185 |
+
"eval_pearson": 0.8892892267625273,
|
| 186 |
+
"eval_runtime": 5.825,
|
| 187 |
+
"eval_samples_per_second": 257.512,
|
| 188 |
+
"eval_spearmanr": 0.8837330218994379,
|
| 189 |
+
"eval_steps_per_second": 16.137,
|
| 190 |
+
"step": 800
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.36,
|
| 194 |
+
"eval_combined_score": 0.8881887854009817,
|
| 195 |
+
"eval_loss": 0.48988330364227295,
|
| 196 |
+
"eval_pearson": 0.8898428387864722,
|
| 197 |
+
"eval_runtime": 6.1177,
|
| 198 |
+
"eval_samples_per_second": 245.192,
|
| 199 |
+
"eval_spearmanr": 0.8865347320154912,
|
| 200 |
+
"eval_steps_per_second": 15.365,
|
| 201 |
+
"step": 850
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.5,
|
| 205 |
+
"eval_combined_score": 0.8868479524643782,
|
| 206 |
+
"eval_loss": 0.4934450387954712,
|
| 207 |
+
"eval_pearson": 0.8891167810226788,
|
| 208 |
+
"eval_runtime": 5.6331,
|
| 209 |
+
"eval_samples_per_second": 266.284,
|
| 210 |
+
"eval_spearmanr": 0.8845791239060775,
|
| 211 |
+
"eval_steps_per_second": 16.687,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.64,
|
| 216 |
+
"eval_combined_score": 0.8889778694122226,
|
| 217 |
+
"eval_loss": 0.4866905212402344,
|
| 218 |
+
"eval_pearson": 0.8890192489258524,
|
| 219 |
+
"eval_runtime": 5.7954,
|
| 220 |
+
"eval_samples_per_second": 258.824,
|
| 221 |
+
"eval_spearmanr": 0.8889364898985929,
|
| 222 |
+
"eval_steps_per_second": 16.22,
|
| 223 |
+
"step": 950
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.78,
|
| 227 |
+
"learning_rate": 3.263888888888889e-05,
|
| 228 |
+
"loss": 0.2778,
|
| 229 |
+
"step": 1000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.78,
|
| 233 |
+
"eval_combined_score": 0.88330796900741,
|
| 234 |
+
"eval_loss": 0.49821072816848755,
|
| 235 |
+
"eval_pearson": 0.8849717556333476,
|
| 236 |
+
"eval_runtime": 6.4097,
|
| 237 |
+
"eval_samples_per_second": 234.021,
|
| 238 |
+
"eval_spearmanr": 0.8816441823814725,
|
| 239 |
+
"eval_steps_per_second": 14.665,
|
| 240 |
+
"step": 1000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.92,
|
| 244 |
+
"eval_combined_score": 0.8847183157645039,
|
| 245 |
+
"eval_loss": 0.5095486044883728,
|
| 246 |
+
"eval_pearson": 0.8871448241460179,
|
| 247 |
+
"eval_runtime": 5.596,
|
| 248 |
+
"eval_samples_per_second": 268.047,
|
| 249 |
+
"eval_spearmanr": 0.8822918073829898,
|
| 250 |
+
"eval_steps_per_second": 16.798,
|
| 251 |
+
"step": 1050
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.06,
|
| 255 |
+
"eval_combined_score": 0.8874272464175201,
|
| 256 |
+
"eval_loss": 0.4730277955532074,
|
| 257 |
+
"eval_pearson": 0.8895831976333978,
|
| 258 |
+
"eval_runtime": 5.6819,
|
| 259 |
+
"eval_samples_per_second": 263.994,
|
| 260 |
+
"eval_spearmanr": 0.8852712952016424,
|
| 261 |
+
"eval_steps_per_second": 16.544,
|
| 262 |
+
"step": 1100
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.19,
|
| 266 |
+
"eval_combined_score": 0.886644981813258,
|
| 267 |
+
"eval_loss": 0.4820166826248169,
|
| 268 |
+
"eval_pearson": 0.8884315334781125,
|
| 269 |
+
"eval_runtime": 6.0521,
|
| 270 |
+
"eval_samples_per_second": 247.847,
|
| 271 |
+
"eval_spearmanr": 0.8848584301484034,
|
| 272 |
+
"eval_steps_per_second": 15.532,
|
| 273 |
+
"step": 1150
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.33,
|
| 277 |
+
"eval_combined_score": 0.8894357915147134,
|
| 278 |
+
"eval_loss": 0.47540178894996643,
|
| 279 |
+
"eval_pearson": 0.8913766457258069,
|
| 280 |
+
"eval_runtime": 5.6258,
|
| 281 |
+
"eval_samples_per_second": 266.631,
|
| 282 |
+
"eval_spearmanr": 0.88749493730362,
|
| 283 |
+
"eval_steps_per_second": 16.709,
|
| 284 |
+
"step": 1200
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.47,
|
| 288 |
+
"eval_combined_score": 0.8882337266236713,
|
| 289 |
+
"eval_loss": 0.47845378518104553,
|
| 290 |
+
"eval_pearson": 0.8898157282686552,
|
| 291 |
+
"eval_runtime": 5.9023,
|
| 292 |
+
"eval_samples_per_second": 254.137,
|
| 293 |
+
"eval_spearmanr": 0.8866517249786874,
|
| 294 |
+
"eval_steps_per_second": 15.926,
|
| 295 |
+
"step": 1250
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.61,
|
| 299 |
+
"eval_combined_score": 0.88903651674165,
|
| 300 |
+
"eval_loss": 0.4937942624092102,
|
| 301 |
+
"eval_pearson": 0.8910047139114365,
|
| 302 |
+
"eval_runtime": 6.1737,
|
| 303 |
+
"eval_samples_per_second": 242.964,
|
| 304 |
+
"eval_spearmanr": 0.8870683195718634,
|
| 305 |
+
"eval_steps_per_second": 15.226,
|
| 306 |
+
"step": 1300
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.75,
|
| 310 |
+
"eval_combined_score": 0.8901558681204902,
|
| 311 |
+
"eval_loss": 0.46190693974494934,
|
| 312 |
+
"eval_pearson": 0.8927358825114844,
|
| 313 |
+
"eval_runtime": 5.7562,
|
| 314 |
+
"eval_samples_per_second": 260.588,
|
| 315 |
+
"eval_spearmanr": 0.887575853729496,
|
| 316 |
+
"eval_steps_per_second": 16.33,
|
| 317 |
+
"step": 1350
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.89,
|
| 321 |
+
"eval_combined_score": 0.8889376492175258,
|
| 322 |
+
"eval_loss": 0.49563419818878174,
|
| 323 |
+
"eval_pearson": 0.8915857107166335,
|
| 324 |
+
"eval_runtime": 5.5793,
|
| 325 |
+
"eval_samples_per_second": 268.853,
|
| 326 |
+
"eval_spearmanr": 0.8862895877184183,
|
| 327 |
+
"eval_steps_per_second": 16.848,
|
| 328 |
+
"step": 1400
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.03,
|
| 332 |
+
"eval_combined_score": 0.8911112435797486,
|
| 333 |
+
"eval_loss": 0.4565975069999695,
|
| 334 |
+
"eval_pearson": 0.8938483143744439,
|
| 335 |
+
"eval_runtime": 6.0592,
|
| 336 |
+
"eval_samples_per_second": 247.559,
|
| 337 |
+
"eval_spearmanr": 0.8883741727850532,
|
| 338 |
+
"eval_steps_per_second": 15.514,
|
| 339 |
+
"step": 1450
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.17,
|
| 343 |
+
"learning_rate": 2.3958333333333334e-05,
|
| 344 |
+
"loss": 0.141,
|
| 345 |
+
"step": 1500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.17,
|
| 349 |
+
"eval_combined_score": 0.890231579373417,
|
| 350 |
+
"eval_loss": 0.4669683873653412,
|
| 351 |
+
"eval_pearson": 0.8928537444959865,
|
| 352 |
+
"eval_runtime": 6.214,
|
| 353 |
+
"eval_samples_per_second": 241.389,
|
| 354 |
+
"eval_spearmanr": 0.8876094142508474,
|
| 355 |
+
"eval_steps_per_second": 15.127,
|
| 356 |
+
"step": 1500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.31,
|
| 360 |
+
"eval_combined_score": 0.8917620927758609,
|
| 361 |
+
"eval_loss": 0.4545550048351288,
|
| 362 |
+
"eval_pearson": 0.8941284924896612,
|
| 363 |
+
"eval_runtime": 5.6167,
|
| 364 |
+
"eval_samples_per_second": 267.062,
|
| 365 |
+
"eval_spearmanr": 0.8893956930620608,
|
| 366 |
+
"eval_steps_per_second": 16.736,
|
| 367 |
+
"step": 1550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.44,
|
| 371 |
+
"eval_combined_score": 0.8919076890360074,
|
| 372 |
+
"eval_loss": 0.46239447593688965,
|
| 373 |
+
"eval_pearson": 0.8939787505423513,
|
| 374 |
+
"eval_runtime": 6.1392,
|
| 375 |
+
"eval_samples_per_second": 244.33,
|
| 376 |
+
"eval_spearmanr": 0.8898366275296635,
|
| 377 |
+
"eval_steps_per_second": 15.311,
|
| 378 |
+
"step": 1600
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.58,
|
| 382 |
+
"eval_combined_score": 0.8905705624659631,
|
| 383 |
+
"eval_loss": 0.4560569226741791,
|
| 384 |
+
"eval_pearson": 0.8930309291971393,
|
| 385 |
+
"eval_runtime": 5.7715,
|
| 386 |
+
"eval_samples_per_second": 259.896,
|
| 387 |
+
"eval_spearmanr": 0.8881101957347869,
|
| 388 |
+
"eval_steps_per_second": 16.287,
|
| 389 |
+
"step": 1650
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 4.72,
|
| 393 |
+
"eval_combined_score": 0.89164078789547,
|
| 394 |
+
"eval_loss": 0.47078728675842285,
|
| 395 |
+
"eval_pearson": 0.8931105725859777,
|
| 396 |
+
"eval_runtime": 5.5689,
|
| 397 |
+
"eval_samples_per_second": 269.352,
|
| 398 |
+
"eval_spearmanr": 0.8901710032049623,
|
| 399 |
+
"eval_steps_per_second": 16.879,
|
| 400 |
+
"step": 1700
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.86,
|
| 404 |
+
"eval_combined_score": 0.8922518284784362,
|
| 405 |
+
"eval_loss": 0.5126345157623291,
|
| 406 |
+
"eval_pearson": 0.8948084725851928,
|
| 407 |
+
"eval_runtime": 5.5913,
|
| 408 |
+
"eval_samples_per_second": 268.275,
|
| 409 |
+
"eval_spearmanr": 0.8896951843716796,
|
| 410 |
+
"eval_steps_per_second": 16.812,
|
| 411 |
+
"step": 1750
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 5.0,
|
| 415 |
+
"eval_combined_score": 0.8936765208721354,
|
| 416 |
+
"eval_loss": 0.4546430706977844,
|
| 417 |
+
"eval_pearson": 0.8960807975667862,
|
| 418 |
+
"eval_runtime": 5.6821,
|
| 419 |
+
"eval_samples_per_second": 263.988,
|
| 420 |
+
"eval_spearmanr": 0.8912722441774847,
|
| 421 |
+
"eval_steps_per_second": 16.543,
|
| 422 |
+
"step": 1800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.14,
|
| 426 |
+
"eval_combined_score": 0.8930431248747293,
|
| 427 |
+
"eval_loss": 0.44920727610588074,
|
| 428 |
+
"eval_pearson": 0.8947890019960217,
|
| 429 |
+
"eval_runtime": 5.9173,
|
| 430 |
+
"eval_samples_per_second": 253.493,
|
| 431 |
+
"eval_spearmanr": 0.8912972477534367,
|
| 432 |
+
"eval_steps_per_second": 15.886,
|
| 433 |
+
"step": 1850
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.28,
|
| 437 |
+
"eval_combined_score": 0.894053370656966,
|
| 438 |
+
"eval_loss": 0.4471864700317383,
|
| 439 |
+
"eval_pearson": 0.8965503528124947,
|
| 440 |
+
"eval_runtime": 5.6396,
|
| 441 |
+
"eval_samples_per_second": 265.978,
|
| 442 |
+
"eval_spearmanr": 0.8915563885014371,
|
| 443 |
+
"eval_steps_per_second": 16.668,
|
| 444 |
+
"step": 1900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.42,
|
| 448 |
+
"eval_combined_score": 0.8948116388641144,
|
| 449 |
+
"eval_loss": 0.470526784658432,
|
| 450 |
+
"eval_pearson": 0.8971476181305765,
|
| 451 |
+
"eval_runtime": 5.7724,
|
| 452 |
+
"eval_samples_per_second": 259.855,
|
| 453 |
+
"eval_spearmanr": 0.8924756595976523,
|
| 454 |
+
"eval_steps_per_second": 16.284,
|
| 455 |
+
"step": 1950
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.56,
|
| 459 |
+
"learning_rate": 1.527777777777778e-05,
|
| 460 |
+
"loss": 0.0844,
|
| 461 |
+
"step": 2000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.56,
|
| 465 |
+
"eval_combined_score": 0.8922658461057144,
|
| 466 |
+
"eval_loss": 0.46638524532318115,
|
| 467 |
+
"eval_pearson": 0.8939377420957451,
|
| 468 |
+
"eval_runtime": 5.7907,
|
| 469 |
+
"eval_samples_per_second": 259.036,
|
| 470 |
+
"eval_spearmanr": 0.8905939501156837,
|
| 471 |
+
"eval_steps_per_second": 16.233,
|
| 472 |
+
"step": 2000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 5.69,
|
| 476 |
+
"eval_combined_score": 0.8915829503407375,
|
| 477 |
+
"eval_loss": 0.49491751194000244,
|
| 478 |
+
"eval_pearson": 0.8941690530900368,
|
| 479 |
+
"eval_runtime": 5.6201,
|
| 480 |
+
"eval_samples_per_second": 266.9,
|
| 481 |
+
"eval_spearmanr": 0.8889968475914382,
|
| 482 |
+
"eval_steps_per_second": 16.726,
|
| 483 |
+
"step": 2050
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.83,
|
| 487 |
+
"eval_combined_score": 0.8940547207791253,
|
| 488 |
+
"eval_loss": 0.451761394739151,
|
| 489 |
+
"eval_pearson": 0.8965362985968673,
|
| 490 |
+
"eval_runtime": 6.0011,
|
| 491 |
+
"eval_samples_per_second": 249.956,
|
| 492 |
+
"eval_spearmanr": 0.8915731429613832,
|
| 493 |
+
"eval_steps_per_second": 15.664,
|
| 494 |
+
"step": 2100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.97,
|
| 498 |
+
"eval_combined_score": 0.8923553049941013,
|
| 499 |
+
"eval_loss": 0.45326724648475647,
|
| 500 |
+
"eval_pearson": 0.8945634893619782,
|
| 501 |
+
"eval_runtime": 5.6075,
|
| 502 |
+
"eval_samples_per_second": 267.501,
|
| 503 |
+
"eval_spearmanr": 0.8901471206262244,
|
| 504 |
+
"eval_steps_per_second": 16.763,
|
| 505 |
+
"step": 2150
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 6.11,
|
| 509 |
+
"eval_combined_score": 0.8949367985553012,
|
| 510 |
+
"eval_loss": 0.44921526312828064,
|
| 511 |
+
"eval_pearson": 0.8970393518565526,
|
| 512 |
+
"eval_runtime": 5.5418,
|
| 513 |
+
"eval_samples_per_second": 270.668,
|
| 514 |
+
"eval_spearmanr": 0.8928342452540498,
|
| 515 |
+
"eval_steps_per_second": 16.962,
|
| 516 |
+
"step": 2200
|
| 517 |
+
}
|
| 518 |
+
],
|
| 519 |
+
"max_steps": 2880,
|
| 520 |
+
"num_train_epochs": 8,
|
| 521 |
+
"total_flos": 2311015204895232.0,
|
| 522 |
+
"trial_name": null,
|
| 523 |
+
"trial_params": null
|
| 524 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4ef45588b98ee4ba395f9b88a031be7a5cdda64e25e3b6bf85dd70623d9274f
|
| 3 |
+
size 2927
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|