Delete human_ensembl_regulatory
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- human_ensembl_regulatory/base_3072/checkpoint-14000/config.json +0 -37
- human_ensembl_regulatory/base_3072/checkpoint-14000/model.safetensors +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14000/optimizer.pt +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14000/rng_state.pth +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14000/scheduler.pt +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14000/special_tokens_map.json +0 -7
- human_ensembl_regulatory/base_3072/checkpoint-14000/tokenizer.json +0 -0
- human_ensembl_regulatory/base_3072/checkpoint-14000/tokenizer_config.json +0 -56
- human_ensembl_regulatory/base_3072/checkpoint-14000/trainer_state.json +0 -929
- human_ensembl_regulatory/base_3072/checkpoint-14000/training_args.bin +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14200/config.json +0 -37
- human_ensembl_regulatory/base_3072/checkpoint-14200/model.safetensors +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14200/optimizer.pt +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14200/rng_state.pth +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14200/scheduler.pt +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14200/special_tokens_map.json +0 -7
- human_ensembl_regulatory/base_3072/checkpoint-14200/tokenizer.json +0 -0
- human_ensembl_regulatory/base_3072/checkpoint-14200/tokenizer_config.json +0 -56
- human_ensembl_regulatory/base_3072/checkpoint-14200/trainer_state.json +0 -942
- human_ensembl_regulatory/base_3072/checkpoint-14200/training_args.bin +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14400/config.json +0 -37
- human_ensembl_regulatory/base_3072/checkpoint-14400/model.safetensors +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14400/optimizer.pt +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14400/rng_state.pth +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14400/scheduler.pt +0 -3
- human_ensembl_regulatory/base_3072/checkpoint-14400/special_tokens_map.json +0 -7
- human_ensembl_regulatory/base_3072/checkpoint-14400/tokenizer.json +0 -0
- human_ensembl_regulatory/base_3072/checkpoint-14400/tokenizer_config.json +0 -56
- human_ensembl_regulatory/base_3072/checkpoint-14400/trainer_state.json +0 -955
- human_ensembl_regulatory/base_3072/checkpoint-14400/training_args.bin +0 -3
- human_ensembl_regulatory/base_3072/results/base_3072_hg38_BPE_3e-5_human_ensembl_regulatory_seed42/eval_results.json +0 -1
- human_ensembl_regulatory/base_4096/checkpoint-14000/config.json +0 -37
- human_ensembl_regulatory/base_4096/checkpoint-14000/model.safetensors +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14000/optimizer.pt +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14000/rng_state.pth +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14000/scheduler.pt +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14000/special_tokens_map.json +0 -7
- human_ensembl_regulatory/base_4096/checkpoint-14000/tokenizer.json +0 -0
- human_ensembl_regulatory/base_4096/checkpoint-14000/tokenizer_config.json +0 -56
- human_ensembl_regulatory/base_4096/checkpoint-14000/trainer_state.json +0 -929
- human_ensembl_regulatory/base_4096/checkpoint-14000/training_args.bin +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14200/config.json +0 -37
- human_ensembl_regulatory/base_4096/checkpoint-14200/model.safetensors +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14200/optimizer.pt +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14200/rng_state.pth +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14200/scheduler.pt +0 -3
- human_ensembl_regulatory/base_4096/checkpoint-14200/special_tokens_map.json +0 -7
- human_ensembl_regulatory/base_4096/checkpoint-14200/tokenizer.json +0 -0
- human_ensembl_regulatory/base_4096/checkpoint-14200/tokenizer_config.json +0 -56
- human_ensembl_regulatory/base_4096/checkpoint-14200/trainer_state.json +0 -942
human_ensembl_regulatory/base_3072/checkpoint-14000/config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_3072/checkpoint-100000",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"BertForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"classifier_dropout": null,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0",
|
| 13 |
-
"1": "LABEL_1",
|
| 14 |
-
"2": "LABEL_2"
|
| 15 |
-
},
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"LABEL_0": 0,
|
| 20 |
-
"LABEL_1": 1,
|
| 21 |
-
"LABEL_2": 2
|
| 22 |
-
},
|
| 23 |
-
"layer_norm_eps": 1e-12,
|
| 24 |
-
"max_length": 512,
|
| 25 |
-
"max_position_embeddings": 512,
|
| 26 |
-
"model_type": "bert",
|
| 27 |
-
"num_attention_heads": 12,
|
| 28 |
-
"num_hidden_layers": 12,
|
| 29 |
-
"pad_token_id": 0,
|
| 30 |
-
"position_embedding_type": "absolute",
|
| 31 |
-
"problem_type": "single_label_classification",
|
| 32 |
-
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.35.2",
|
| 34 |
-
"type_vocab_size": 2,
|
| 35 |
-
"use_cache": true,
|
| 36 |
-
"vocab_size": 3072
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b0e19bd93ece4f967c7004c4df3aedff2b052e0104ff9763e897812aec99df5e
|
| 3 |
-
size 353635228
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:69a2e9d51c97b60d2037972b86511c2ccbec2d79dae9b2c70b900244f4638f91
|
| 3 |
-
size 707392139
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f9336ff0936896ba2c3d97c93c6e4562fa949c0319bb80af06d44d0ab485df20
|
| 3 |
-
size 14709
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d2f837dafff62c1bd228c6ad32b5ce7253d7ea15836a63bcf26d8af49b30e4dc
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/tokenizer_config.json
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 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 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"cache_dir": null,
|
| 45 |
-
"clean_up_tokenization_spaces": true,
|
| 46 |
-
"cls_token": "[CLS]",
|
| 47 |
-
"mask_token": "[MASK]",
|
| 48 |
-
"model_max_length": 250,
|
| 49 |
-
"pad_token": "[PAD]",
|
| 50 |
-
"padding_side": "right",
|
| 51 |
-
"sep_token": "[SEP]",
|
| 52 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 53 |
-
"trust_remote_code": true,
|
| 54 |
-
"unk_token": "[UNK]",
|
| 55 |
-
"use_fast": true
|
| 56 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/trainer_state.json
DELETED
|
@@ -1,929 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.74764803541782,
|
| 5 |
-
"eval_steps": 200,
|
| 6 |
-
"global_step": 14000,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.11,
|
| 13 |
-
"eval_accuracy": 0.7631287621947,
|
| 14 |
-
"eval_f1": 0.7637252904097979,
|
| 15 |
-
"eval_loss": 0.5434313416481018,
|
| 16 |
-
"eval_matthews_correlation": 0.6445437687927822,
|
| 17 |
-
"eval_precision": 0.7637111046493135,
|
| 18 |
-
"eval_recall": 0.765490425188335,
|
| 19 |
-
"eval_runtime": 6.3466,
|
| 20 |
-
"eval_samples_per_second": 4554.569,
|
| 21 |
-
"eval_steps_per_second": 35.61,
|
| 22 |
-
"step": 200
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0.22,
|
| 26 |
-
"eval_accuracy": 0.8355012800110704,
|
| 27 |
-
"eval_f1": 0.8365614801773557,
|
| 28 |
-
"eval_loss": 0.41565728187561035,
|
| 29 |
-
"eval_matthews_correlation": 0.7574410510587669,
|
| 30 |
-
"eval_precision": 0.8547583068058389,
|
| 31 |
-
"eval_recall": 0.8309223755258941,
|
| 32 |
-
"eval_runtime": 6.3479,
|
| 33 |
-
"eval_samples_per_second": 4553.618,
|
| 34 |
-
"eval_steps_per_second": 35.602,
|
| 35 |
-
"step": 400
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 0.33,
|
| 39 |
-
"eval_accuracy": 0.8444959523974261,
|
| 40 |
-
"eval_f1": 0.8462633455095543,
|
| 41 |
-
"eval_loss": 0.39934343099594116,
|
| 42 |
-
"eval_matthews_correlation": 0.7666701235793097,
|
| 43 |
-
"eval_precision": 0.8539778966745382,
|
| 44 |
-
"eval_recall": 0.8423605635643182,
|
| 45 |
-
"eval_runtime": 6.3347,
|
| 46 |
-
"eval_samples_per_second": 4563.147,
|
| 47 |
-
"eval_steps_per_second": 35.677,
|
| 48 |
-
"step": 600
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.44,
|
| 52 |
-
"eval_accuracy": 0.8584722894900713,
|
| 53 |
-
"eval_f1": 0.8598909494500923,
|
| 54 |
-
"eval_loss": 0.35555699467658997,
|
| 55 |
-
"eval_matthews_correlation": 0.7875595996660668,
|
| 56 |
-
"eval_precision": 0.8648899799007316,
|
| 57 |
-
"eval_recall": 0.8572299805040989,
|
| 58 |
-
"eval_runtime": 6.332,
|
| 59 |
-
"eval_samples_per_second": 4565.079,
|
| 60 |
-
"eval_steps_per_second": 35.692,
|
| 61 |
-
"step": 800
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.55,
|
| 65 |
-
"eval_accuracy": 0.8430775617518854,
|
| 66 |
-
"eval_f1": 0.8454663268345574,
|
| 67 |
-
"eval_loss": 0.3819273114204407,
|
| 68 |
-
"eval_matthews_correlation": 0.7640650142321523,
|
| 69 |
-
"eval_precision": 0.8487232576971051,
|
| 70 |
-
"eval_recall": 0.8437015678940293,
|
| 71 |
-
"eval_runtime": 6.3315,
|
| 72 |
-
"eval_samples_per_second": 4565.442,
|
| 73 |
-
"eval_steps_per_second": 35.695,
|
| 74 |
-
"step": 1000
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.66,
|
| 78 |
-
"eval_accuracy": 0.8650799142046633,
|
| 79 |
-
"eval_f1": 0.8644083875976301,
|
| 80 |
-
"eval_loss": 0.33737584948539734,
|
| 81 |
-
"eval_matthews_correlation": 0.7999641131979995,
|
| 82 |
-
"eval_precision": 0.8726322998406989,
|
| 83 |
-
"eval_recall": 0.8638534177565756,
|
| 84 |
-
"eval_runtime": 6.3425,
|
| 85 |
-
"eval_samples_per_second": 4557.514,
|
| 86 |
-
"eval_steps_per_second": 35.633,
|
| 87 |
-
"step": 1200
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.77,
|
| 91 |
-
"eval_accuracy": 0.8665674946377915,
|
| 92 |
-
"eval_f1": 0.8682947296760272,
|
| 93 |
-
"eval_loss": 0.3294672966003418,
|
| 94 |
-
"eval_matthews_correlation": 0.8007303567504979,
|
| 95 |
-
"eval_precision": 0.8787531415676622,
|
| 96 |
-
"eval_recall": 0.8635116626335386,
|
| 97 |
-
"eval_runtime": 6.3602,
|
| 98 |
-
"eval_samples_per_second": 4544.791,
|
| 99 |
-
"eval_steps_per_second": 35.533,
|
| 100 |
-
"step": 1400
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.89,
|
| 104 |
-
"eval_accuracy": 0.8716183491316681,
|
| 105 |
-
"eval_f1": 0.8726660510894068,
|
| 106 |
-
"eval_loss": 0.32086172699928284,
|
| 107 |
-
"eval_matthews_correlation": 0.8102970184587044,
|
| 108 |
-
"eval_precision": 0.8857093298214904,
|
| 109 |
-
"eval_recall": 0.868057832538541,
|
| 110 |
-
"eval_runtime": 6.3417,
|
| 111 |
-
"eval_samples_per_second": 4558.115,
|
| 112 |
-
"eval_steps_per_second": 35.637,
|
| 113 |
-
"step": 1600
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.0,
|
| 117 |
-
"eval_accuracy": 0.8732097142461772,
|
| 118 |
-
"eval_f1": 0.8747467540360607,
|
| 119 |
-
"eval_loss": 0.31995540857315063,
|
| 120 |
-
"eval_matthews_correlation": 0.8114248425885828,
|
| 121 |
-
"eval_precision": 0.8852565763439663,
|
| 122 |
-
"eval_recall": 0.870275600961048,
|
| 123 |
-
"eval_runtime": 6.3409,
|
| 124 |
-
"eval_samples_per_second": 4558.634,
|
| 125 |
-
"eval_steps_per_second": 35.641,
|
| 126 |
-
"step": 1800
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.11,
|
| 130 |
-
"eval_accuracy": 0.869819414654397,
|
| 131 |
-
"eval_f1": 0.870027807466756,
|
| 132 |
-
"eval_loss": 0.3274751901626587,
|
| 133 |
-
"eval_matthews_correlation": 0.807806844099052,
|
| 134 |
-
"eval_precision": 0.8811302666871579,
|
| 135 |
-
"eval_recall": 0.8680597400838227,
|
| 136 |
-
"eval_runtime": 6.3277,
|
| 137 |
-
"eval_samples_per_second": 4568.189,
|
| 138 |
-
"eval_steps_per_second": 35.716,
|
| 139 |
-
"step": 2000
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 1.22,
|
| 143 |
-
"eval_accuracy": 0.8751124334048295,
|
| 144 |
-
"eval_f1": 0.8767794708217407,
|
| 145 |
-
"eval_loss": 0.31445378065109253,
|
| 146 |
-
"eval_matthews_correlation": 0.8129535421098832,
|
| 147 |
-
"eval_precision": 0.8823771754169298,
|
| 148 |
-
"eval_recall": 0.8740288172396674,
|
| 149 |
-
"eval_runtime": 6.3375,
|
| 150 |
-
"eval_samples_per_second": 4561.07,
|
| 151 |
-
"eval_steps_per_second": 35.66,
|
| 152 |
-
"step": 2200
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 1.33,
|
| 156 |
-
"eval_accuracy": 0.8786065176779907,
|
| 157 |
-
"eval_f1": 0.8804120457112202,
|
| 158 |
-
"eval_loss": 0.30376389622688293,
|
| 159 |
-
"eval_matthews_correlation": 0.818359828918223,
|
| 160 |
-
"eval_precision": 0.8873540250604574,
|
| 161 |
-
"eval_recall": 0.8768603619194306,
|
| 162 |
-
"eval_runtime": 6.3495,
|
| 163 |
-
"eval_samples_per_second": 4552.473,
|
| 164 |
-
"eval_steps_per_second": 35.593,
|
| 165 |
-
"step": 2400
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.44,
|
| 169 |
-
"eval_accuracy": 0.8689199474157614,
|
| 170 |
-
"eval_f1": 0.8695062971703474,
|
| 171 |
-
"eval_loss": 0.33015474677085876,
|
| 172 |
-
"eval_matthews_correlation": 0.8038507391919977,
|
| 173 |
-
"eval_precision": 0.8731098141522541,
|
| 174 |
-
"eval_recall": 0.869011988411034,
|
| 175 |
-
"eval_runtime": 6.341,
|
| 176 |
-
"eval_samples_per_second": 4558.589,
|
| 177 |
-
"eval_steps_per_second": 35.641,
|
| 178 |
-
"step": 2600
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.55,
|
| 182 |
-
"eval_accuracy": 0.8766692036255449,
|
| 183 |
-
"eval_f1": 0.8780737901306455,
|
| 184 |
-
"eval_loss": 0.3185276985168457,
|
| 185 |
-
"eval_matthews_correlation": 0.8159739463443503,
|
| 186 |
-
"eval_precision": 0.8854910478175612,
|
| 187 |
-
"eval_recall": 0.8749199751124719,
|
| 188 |
-
"eval_runtime": 6.3359,
|
| 189 |
-
"eval_samples_per_second": 4562.289,
|
| 190 |
-
"eval_steps_per_second": 35.67,
|
| 191 |
-
"step": 2800
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.66,
|
| 195 |
-
"eval_accuracy": 0.873451878502733,
|
| 196 |
-
"eval_f1": 0.8745153730554996,
|
| 197 |
-
"eval_loss": 0.3263399600982666,
|
| 198 |
-
"eval_matthews_correlation": 0.8119489865082196,
|
| 199 |
-
"eval_precision": 0.8834811606427829,
|
| 200 |
-
"eval_recall": 0.8715407218596346,
|
| 201 |
-
"eval_runtime": 6.3418,
|
| 202 |
-
"eval_samples_per_second": 4557.995,
|
| 203 |
-
"eval_steps_per_second": 35.636,
|
| 204 |
-
"step": 3000
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.77,
|
| 208 |
-
"eval_accuracy": 0.8813395142876911,
|
| 209 |
-
"eval_f1": 0.8818879844399303,
|
| 210 |
-
"eval_loss": 0.29727903008461,
|
| 211 |
-
"eval_matthews_correlation": 0.8259481285765669,
|
| 212 |
-
"eval_precision": 0.8956235096626705,
|
| 213 |
-
"eval_recall": 0.8783326544826559,
|
| 214 |
-
"eval_runtime": 6.3398,
|
| 215 |
-
"eval_samples_per_second": 4559.417,
|
| 216 |
-
"eval_steps_per_second": 35.648,
|
| 217 |
-
"step": 3200
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 1.88,
|
| 221 |
-
"eval_accuracy": 0.8827924998270256,
|
| 222 |
-
"eval_f1": 0.8841759014261692,
|
| 223 |
-
"eval_loss": 0.29565736651420593,
|
| 224 |
-
"eval_matthews_correlation": 0.8256178375822875,
|
| 225 |
-
"eval_precision": 0.892768390763086,
|
| 226 |
-
"eval_recall": 0.880666838238121,
|
| 227 |
-
"eval_runtime": 6.3407,
|
| 228 |
-
"eval_samples_per_second": 4558.804,
|
| 229 |
-
"eval_steps_per_second": 35.643,
|
| 230 |
-
"step": 3400
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 1.99,
|
| 234 |
-
"eval_accuracy": 0.8810627551373418,
|
| 235 |
-
"eval_f1": 0.8827766714455013,
|
| 236 |
-
"eval_loss": 0.29401829838752747,
|
| 237 |
-
"eval_matthews_correlation": 0.8216298754947776,
|
| 238 |
-
"eval_precision": 0.8887839973591874,
|
| 239 |
-
"eval_recall": 0.8794150912644644,
|
| 240 |
-
"eval_runtime": 6.3433,
|
| 241 |
-
"eval_samples_per_second": 4556.962,
|
| 242 |
-
"eval_steps_per_second": 35.628,
|
| 243 |
-
"step": 3600
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.1,
|
| 247 |
-
"eval_accuracy": 0.8796097695980073,
|
| 248 |
-
"eval_f1": 0.8805296255975588,
|
| 249 |
-
"eval_loss": 0.3111639618873596,
|
| 250 |
-
"eval_matthews_correlation": 0.8222095610456218,
|
| 251 |
-
"eval_precision": 0.8924941587035914,
|
| 252 |
-
"eval_recall": 0.8764907197445329,
|
| 253 |
-
"eval_runtime": 6.328,
|
| 254 |
-
"eval_samples_per_second": 4567.984,
|
| 255 |
-
"eval_steps_per_second": 35.715,
|
| 256 |
-
"step": 3800
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 2.21,
|
| 260 |
-
"eval_accuracy": 0.8824465508890887,
|
| 261 |
-
"eval_f1": 0.8836499737169107,
|
| 262 |
-
"eval_loss": 0.30004093050956726,
|
| 263 |
-
"eval_matthews_correlation": 0.8257179264635982,
|
| 264 |
-
"eval_precision": 0.8938452710102794,
|
| 265 |
-
"eval_recall": 0.8798082044973228,
|
| 266 |
-
"eval_runtime": 6.326,
|
| 267 |
-
"eval_samples_per_second": 4569.373,
|
| 268 |
-
"eval_steps_per_second": 35.725,
|
| 269 |
-
"step": 4000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.32,
|
| 273 |
-
"eval_accuracy": 0.8759773057496714,
|
| 274 |
-
"eval_f1": 0.8772153967910118,
|
| 275 |
-
"eval_loss": 0.31523868441581726,
|
| 276 |
-
"eval_matthews_correlation": 0.815377575453818,
|
| 277 |
-
"eval_precision": 0.8864289034661025,
|
| 278 |
-
"eval_recall": 0.87336045996798,
|
| 279 |
-
"eval_runtime": 6.3286,
|
| 280 |
-
"eval_samples_per_second": 4567.526,
|
| 281 |
-
"eval_steps_per_second": 35.711,
|
| 282 |
-
"step": 4200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 2.43,
|
| 286 |
-
"eval_accuracy": 0.8800595032173251,
|
| 287 |
-
"eval_f1": 0.8804022842955522,
|
| 288 |
-
"eval_loss": 0.3036770522594452,
|
| 289 |
-
"eval_matthews_correlation": 0.822361970881652,
|
| 290 |
-
"eval_precision": 0.8888145633651886,
|
| 291 |
-
"eval_recall": 0.8790141931629684,
|
| 292 |
-
"eval_runtime": 6.3289,
|
| 293 |
-
"eval_samples_per_second": 4567.335,
|
| 294 |
-
"eval_steps_per_second": 35.709,
|
| 295 |
-
"step": 4400
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 2.55,
|
| 299 |
-
"eval_accuracy": 0.8872206462326161,
|
| 300 |
-
"eval_f1": 0.8884178788215135,
|
| 301 |
-
"eval_loss": 0.2838316857814789,
|
| 302 |
-
"eval_matthews_correlation": 0.8325897438913511,
|
| 303 |
-
"eval_precision": 0.8972535403832396,
|
| 304 |
-
"eval_recall": 0.8851528361222756,
|
| 305 |
-
"eval_runtime": 6.3339,
|
| 306 |
-
"eval_samples_per_second": 4563.702,
|
| 307 |
-
"eval_steps_per_second": 35.681,
|
| 308 |
-
"step": 4600
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.66,
|
| 312 |
-
"eval_accuracy": 0.88358818238428,
|
| 313 |
-
"eval_f1": 0.885114187094025,
|
| 314 |
-
"eval_loss": 0.29305681586265564,
|
| 315 |
-
"eval_matthews_correlation": 0.8259291080645792,
|
| 316 |
-
"eval_precision": 0.8916206014101848,
|
| 317 |
-
"eval_recall": 0.881925767855031,
|
| 318 |
-
"eval_runtime": 6.3267,
|
| 319 |
-
"eval_samples_per_second": 4568.926,
|
| 320 |
-
"eval_steps_per_second": 35.722,
|
| 321 |
-
"step": 4800
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.77,
|
| 325 |
-
"eval_accuracy": 0.8854217117553449,
|
| 326 |
-
"eval_f1": 0.8857838454083451,
|
| 327 |
-
"eval_loss": 0.2878040373325348,
|
| 328 |
-
"eval_matthews_correlation": 0.8301977075488263,
|
| 329 |
-
"eval_precision": 0.8938206658601261,
|
| 330 |
-
"eval_recall": 0.884056956873887,
|
| 331 |
-
"eval_runtime": 6.3273,
|
| 332 |
-
"eval_samples_per_second": 4568.489,
|
| 333 |
-
"eval_steps_per_second": 35.718,
|
| 334 |
-
"step": 5000
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 2.88,
|
| 338 |
-
"eval_accuracy": 0.8821351968449457,
|
| 339 |
-
"eval_f1": 0.8839452239437287,
|
| 340 |
-
"eval_loss": 0.30110254883766174,
|
| 341 |
-
"eval_matthews_correlation": 0.8231792168311283,
|
| 342 |
-
"eval_precision": 0.8879817009125152,
|
| 343 |
-
"eval_recall": 0.8818214391632123,
|
| 344 |
-
"eval_runtime": 6.329,
|
| 345 |
-
"eval_samples_per_second": 4567.195,
|
| 346 |
-
"eval_steps_per_second": 35.708,
|
| 347 |
-
"step": 5200
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 2.99,
|
| 351 |
-
"eval_accuracy": 0.8851449526049955,
|
| 352 |
-
"eval_f1": 0.886308239213426,
|
| 353 |
-
"eval_loss": 0.2945020794868469,
|
| 354 |
-
"eval_matthews_correlation": 0.8303737613493637,
|
| 355 |
-
"eval_precision": 0.897756431496714,
|
| 356 |
-
"eval_recall": 0.8823199630167121,
|
| 357 |
-
"eval_runtime": 6.328,
|
| 358 |
-
"eval_samples_per_second": 4567.918,
|
| 359 |
-
"eval_steps_per_second": 35.714,
|
| 360 |
-
"step": 5400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 3.1,
|
| 364 |
-
"eval_accuracy": 0.8848681934546461,
|
| 365 |
-
"eval_f1": 0.8858670845855992,
|
| 366 |
-
"eval_loss": 0.2994346618652344,
|
| 367 |
-
"eval_matthews_correlation": 0.8285400641383184,
|
| 368 |
-
"eval_precision": 0.8926579786712784,
|
| 369 |
-
"eval_recall": 0.8836020295365422,
|
| 370 |
-
"eval_runtime": 6.3289,
|
| 371 |
-
"eval_samples_per_second": 4567.288,
|
| 372 |
-
"eval_steps_per_second": 35.709,
|
| 373 |
-
"step": 5600
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 3.21,
|
| 377 |
-
"eval_accuracy": 0.8870476717636477,
|
| 378 |
-
"eval_f1": 0.887896425962959,
|
| 379 |
-
"eval_loss": 0.2862726151943207,
|
| 380 |
-
"eval_matthews_correlation": 0.8339123150665094,
|
| 381 |
-
"eval_precision": 0.9001657168490554,
|
| 382 |
-
"eval_recall": 0.8843680937123602,
|
| 383 |
-
"eval_runtime": 6.3273,
|
| 384 |
-
"eval_samples_per_second": 4568.476,
|
| 385 |
-
"eval_steps_per_second": 35.718,
|
| 386 |
-
"step": 5800
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.32,
|
| 390 |
-
"eval_accuracy": 0.8860098249498374,
|
| 391 |
-
"eval_f1": 0.8874314355841011,
|
| 392 |
-
"eval_loss": 0.2849290668964386,
|
| 393 |
-
"eval_matthews_correlation": 0.8299739841185283,
|
| 394 |
-
"eval_precision": 0.894704396265502,
|
| 395 |
-
"eval_recall": 0.8842126035893482,
|
| 396 |
-
"eval_runtime": 6.3413,
|
| 397 |
-
"eval_samples_per_second": 4558.358,
|
| 398 |
-
"eval_steps_per_second": 35.639,
|
| 399 |
-
"step": 6000
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.43,
|
| 403 |
-
"eval_accuracy": 0.8904033764616343,
|
| 404 |
-
"eval_f1": 0.8914779910613806,
|
| 405 |
-
"eval_loss": 0.2752903997898102,
|
| 406 |
-
"eval_matthews_correlation": 0.8364867202399989,
|
| 407 |
-
"eval_precision": 0.8971261241739302,
|
| 408 |
-
"eval_recall": 0.8894531419411426,
|
| 409 |
-
"eval_runtime": 6.3307,
|
| 410 |
-
"eval_samples_per_second": 4565.983,
|
| 411 |
-
"eval_steps_per_second": 35.699,
|
| 412 |
-
"step": 6200
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"epoch": 3.54,
|
| 416 |
-
"eval_accuracy": 0.8873590258077908,
|
| 417 |
-
"eval_f1": 0.8882921639464642,
|
| 418 |
-
"eval_loss": 0.2815305292606354,
|
| 419 |
-
"eval_matthews_correlation": 0.8316060546498991,
|
| 420 |
-
"eval_precision": 0.8928030268824344,
|
| 421 |
-
"eval_recall": 0.8867802028593369,
|
| 422 |
-
"eval_runtime": 6.3328,
|
| 423 |
-
"eval_samples_per_second": 4564.487,
|
| 424 |
-
"eval_steps_per_second": 35.687,
|
| 425 |
-
"step": 6400
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 3.65,
|
| 429 |
-
"eval_accuracy": 0.8893309347540304,
|
| 430 |
-
"eval_f1": 0.8903653331168124,
|
| 431 |
-
"eval_loss": 0.28411537408828735,
|
| 432 |
-
"eval_matthews_correlation": 0.8367081606238141,
|
| 433 |
-
"eval_precision": 0.9012824783176558,
|
| 434 |
-
"eval_recall": 0.8868608966982018,
|
| 435 |
-
"eval_runtime": 6.3318,
|
| 436 |
-
"eval_samples_per_second": 4565.229,
|
| 437 |
-
"eval_steps_per_second": 35.693,
|
| 438 |
-
"step": 6600
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 3.76,
|
| 442 |
-
"eval_accuracy": 0.8848681934546461,
|
| 443 |
-
"eval_f1": 0.8866504352176569,
|
| 444 |
-
"eval_loss": 0.2806982696056366,
|
| 445 |
-
"eval_matthews_correlation": 0.8269026453375029,
|
| 446 |
-
"eval_precision": 0.8899918085446745,
|
| 447 |
-
"eval_recall": 0.8844727980389897,
|
| 448 |
-
"eval_runtime": 6.3318,
|
| 449 |
-
"eval_samples_per_second": 4565.232,
|
| 450 |
-
"eval_steps_per_second": 35.693,
|
| 451 |
-
"step": 6800
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 3.87,
|
| 455 |
-
"eval_accuracy": 0.8883276828340138,
|
| 456 |
-
"eval_f1": 0.8899090148440965,
|
| 457 |
-
"eval_loss": 0.28133419156074524,
|
| 458 |
-
"eval_matthews_correlation": 0.8333472890229207,
|
| 459 |
-
"eval_precision": 0.8968149574541151,
|
| 460 |
-
"eval_recall": 0.8867648269634268,
|
| 461 |
-
"eval_runtime": 6.3336,
|
| 462 |
-
"eval_samples_per_second": 4563.941,
|
| 463 |
-
"eval_steps_per_second": 35.683,
|
| 464 |
-
"step": 7000
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 3.98,
|
| 468 |
-
"eval_accuracy": 0.8881547083650453,
|
| 469 |
-
"eval_f1": 0.8894026496021189,
|
| 470 |
-
"eval_loss": 0.297502338886261,
|
| 471 |
-
"eval_matthews_correlation": 0.8334945205386666,
|
| 472 |
-
"eval_precision": 0.8966041254627256,
|
| 473 |
-
"eval_recall": 0.8867020495936117,
|
| 474 |
-
"eval_runtime": 6.335,
|
| 475 |
-
"eval_samples_per_second": 4562.884,
|
| 476 |
-
"eval_steps_per_second": 35.675,
|
| 477 |
-
"step": 7200
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 4.1,
|
| 481 |
-
"eval_accuracy": 0.8849027883484397,
|
| 482 |
-
"eval_f1": 0.8862039883812148,
|
| 483 |
-
"eval_loss": 0.301325261592865,
|
| 484 |
-
"eval_matthews_correlation": 0.8273884442911875,
|
| 485 |
-
"eval_precision": 0.889580662263925,
|
| 486 |
-
"eval_recall": 0.884713387934626,
|
| 487 |
-
"eval_runtime": 6.3295,
|
| 488 |
-
"eval_samples_per_second": 4566.865,
|
| 489 |
-
"eval_steps_per_second": 35.706,
|
| 490 |
-
"step": 7400
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 4.21,
|
| 494 |
-
"eval_accuracy": 0.891614197744413,
|
| 495 |
-
"eval_f1": 0.893011854474095,
|
| 496 |
-
"eval_loss": 0.2823241651058197,
|
| 497 |
-
"eval_matthews_correlation": 0.8388915171836414,
|
| 498 |
-
"eval_precision": 0.9015900643435097,
|
| 499 |
-
"eval_recall": 0.8893977713271144,
|
| 500 |
-
"eval_runtime": 6.3352,
|
| 501 |
-
"eval_samples_per_second": 4562.773,
|
| 502 |
-
"eval_steps_per_second": 35.674,
|
| 503 |
-
"step": 7600
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 4.32,
|
| 507 |
-
"eval_accuracy": 0.8899190479485228,
|
| 508 |
-
"eval_f1": 0.8911303872165929,
|
| 509 |
-
"eval_loss": 0.277401328086853,
|
| 510 |
-
"eval_matthews_correlation": 0.835208898716426,
|
| 511 |
-
"eval_precision": 0.8954442716084697,
|
| 512 |
-
"eval_recall": 0.8892804616842996,
|
| 513 |
-
"eval_runtime": 6.3312,
|
| 514 |
-
"eval_samples_per_second": 4565.613,
|
| 515 |
-
"eval_steps_per_second": 35.696,
|
| 516 |
-
"step": 7800
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 4.43,
|
| 520 |
-
"eval_accuracy": 0.8934477271154777,
|
| 521 |
-
"eval_f1": 0.8945062334448224,
|
| 522 |
-
"eval_loss": 0.2779960334300995,
|
| 523 |
-
"eval_matthews_correlation": 0.8416809998028856,
|
| 524 |
-
"eval_precision": 0.9020848134085252,
|
| 525 |
-
"eval_recall": 0.8917974318475038,
|
| 526 |
-
"eval_runtime": 6.3272,
|
| 527 |
-
"eval_samples_per_second": 4568.498,
|
| 528 |
-
"eval_steps_per_second": 35.719,
|
| 529 |
-
"step": 8000
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 4.54,
|
| 533 |
-
"eval_accuracy": 0.8847644087732651,
|
| 534 |
-
"eval_f1": 0.8857130853518814,
|
| 535 |
-
"eval_loss": 0.28888192772865295,
|
| 536 |
-
"eval_matthews_correlation": 0.8272079111106393,
|
| 537 |
-
"eval_precision": 0.8881516611221727,
|
| 538 |
-
"eval_recall": 0.8851166852917182,
|
| 539 |
-
"eval_runtime": 6.3314,
|
| 540 |
-
"eval_samples_per_second": 4565.469,
|
| 541 |
-
"eval_steps_per_second": 35.695,
|
| 542 |
-
"step": 8200
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 4.65,
|
| 546 |
-
"eval_accuracy": 0.8880509236836643,
|
| 547 |
-
"eval_f1": 0.8898717476564153,
|
| 548 |
-
"eval_loss": 0.2906430959701538,
|
| 549 |
-
"eval_matthews_correlation": 0.8326988493177964,
|
| 550 |
-
"eval_precision": 0.8965857564648291,
|
| 551 |
-
"eval_recall": 0.8865417456050507,
|
| 552 |
-
"eval_runtime": 6.3302,
|
| 553 |
-
"eval_samples_per_second": 4566.355,
|
| 554 |
-
"eval_steps_per_second": 35.702,
|
| 555 |
-
"step": 8400
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 4.76,
|
| 559 |
-
"eval_accuracy": 0.88829308794022,
|
| 560 |
-
"eval_f1": 0.8897630778211744,
|
| 561 |
-
"eval_loss": 0.27177920937538147,
|
| 562 |
-
"eval_matthews_correlation": 0.8322280376805495,
|
| 563 |
-
"eval_precision": 0.8921815887419909,
|
| 564 |
-
"eval_recall": 0.888582941893682,
|
| 565 |
-
"eval_runtime": 6.3301,
|
| 566 |
-
"eval_samples_per_second": 4566.456,
|
| 567 |
-
"eval_steps_per_second": 35.703,
|
| 568 |
-
"step": 8600
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 4.87,
|
| 572 |
-
"eval_accuracy": 0.8910260845499204,
|
| 573 |
-
"eval_f1": 0.8918365911417983,
|
| 574 |
-
"eval_loss": 0.27784451842308044,
|
| 575 |
-
"eval_matthews_correlation": 0.8389532823558397,
|
| 576 |
-
"eval_precision": 0.9012345264937309,
|
| 577 |
-
"eval_recall": 0.889235385671921,
|
| 578 |
-
"eval_runtime": 6.336,
|
| 579 |
-
"eval_samples_per_second": 4562.151,
|
| 580 |
-
"eval_steps_per_second": 35.669,
|
| 581 |
-
"step": 8800
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 4.98,
|
| 585 |
-
"eval_accuracy": 0.8914412232754445,
|
| 586 |
-
"eval_f1": 0.8924273277393427,
|
| 587 |
-
"eval_loss": 0.2901306748390198,
|
| 588 |
-
"eval_matthews_correlation": 0.8388554292097326,
|
| 589 |
-
"eval_precision": 0.9000611285527805,
|
| 590 |
-
"eval_recall": 0.8900983830518662,
|
| 591 |
-
"eval_runtime": 6.3311,
|
| 592 |
-
"eval_samples_per_second": 4565.683,
|
| 593 |
-
"eval_steps_per_second": 35.697,
|
| 594 |
-
"step": 9000
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 5.09,
|
| 598 |
-
"eval_accuracy": 0.8910952743375078,
|
| 599 |
-
"eval_f1": 0.8928927255737659,
|
| 600 |
-
"eval_loss": 0.2787802815437317,
|
| 601 |
-
"eval_matthews_correlation": 0.836709202455403,
|
| 602 |
-
"eval_precision": 0.8970330284962715,
|
| 603 |
-
"eval_recall": 0.8906967390543823,
|
| 604 |
-
"eval_runtime": 6.3339,
|
| 605 |
-
"eval_samples_per_second": 4563.666,
|
| 606 |
-
"eval_steps_per_second": 35.681,
|
| 607 |
-
"step": 9200
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 5.2,
|
| 611 |
-
"eval_accuracy": 0.893205562858922,
|
| 612 |
-
"eval_f1": 0.894408918102502,
|
| 613 |
-
"eval_loss": 0.2776887118816376,
|
| 614 |
-
"eval_matthews_correlation": 0.8409755945954501,
|
| 615 |
-
"eval_precision": 0.9011576771528516,
|
| 616 |
-
"eval_recall": 0.8918337037228231,
|
| 617 |
-
"eval_runtime": 6.3322,
|
| 618 |
-
"eval_samples_per_second": 4564.904,
|
| 619 |
-
"eval_steps_per_second": 35.69,
|
| 620 |
-
"step": 9400
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 5.31,
|
| 624 |
-
"eval_accuracy": 0.8913028437002698,
|
| 625 |
-
"eval_f1": 0.8933449768029128,
|
| 626 |
-
"eval_loss": 0.27147313952445984,
|
| 627 |
-
"eval_matthews_correlation": 0.8367984636801901,
|
| 628 |
-
"eval_precision": 0.8974813228562427,
|
| 629 |
-
"eval_recall": 0.8908149800074497,
|
| 630 |
-
"eval_runtime": 6.3282,
|
| 631 |
-
"eval_samples_per_second": 4567.801,
|
| 632 |
-
"eval_steps_per_second": 35.713,
|
| 633 |
-
"step": 9600
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 5.42,
|
| 637 |
-
"eval_accuracy": 0.8931709679651283,
|
| 638 |
-
"eval_f1": 0.8947893988605209,
|
| 639 |
-
"eval_loss": 0.27668192982673645,
|
| 640 |
-
"eval_matthews_correlation": 0.839987634471219,
|
| 641 |
-
"eval_precision": 0.8996660888128512,
|
| 642 |
-
"eval_recall": 0.8922345752395212,
|
| 643 |
-
"eval_runtime": 6.3307,
|
| 644 |
-
"eval_samples_per_second": 4566.001,
|
| 645 |
-
"eval_steps_per_second": 35.699,
|
| 646 |
-
"step": 9800
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 5.53,
|
| 650 |
-
"eval_accuracy": 0.8901612122050785,
|
| 651 |
-
"eval_f1": 0.892030241440469,
|
| 652 |
-
"eval_loss": 0.27250680327415466,
|
| 653 |
-
"eval_matthews_correlation": 0.8348770244980368,
|
| 654 |
-
"eval_precision": 0.8948523734539041,
|
| 655 |
-
"eval_recall": 0.8902169928340783,
|
| 656 |
-
"eval_runtime": 6.3268,
|
| 657 |
-
"eval_samples_per_second": 4568.789,
|
| 658 |
-
"eval_steps_per_second": 35.721,
|
| 659 |
-
"step": 10000
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 5.64,
|
| 663 |
-
"eval_accuracy": 0.8936207015844462,
|
| 664 |
-
"eval_f1": 0.8950406066984883,
|
| 665 |
-
"eval_loss": 0.26825740933418274,
|
| 666 |
-
"eval_matthews_correlation": 0.8412864778456299,
|
| 667 |
-
"eval_precision": 0.9016571518017655,
|
| 668 |
-
"eval_recall": 0.8920421848866268,
|
| 669 |
-
"eval_runtime": 6.3326,
|
| 670 |
-
"eval_samples_per_second": 4564.614,
|
| 671 |
-
"eval_steps_per_second": 35.688,
|
| 672 |
-
"step": 10200
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 5.76,
|
| 676 |
-
"eval_accuracy": 0.8946931432920501,
|
| 677 |
-
"eval_f1": 0.895911504105032,
|
| 678 |
-
"eval_loss": 0.2863098382949829,
|
| 679 |
-
"eval_matthews_correlation": 0.8426744355500755,
|
| 680 |
-
"eval_precision": 0.9009237338326513,
|
| 681 |
-
"eval_recall": 0.893906711706501,
|
| 682 |
-
"eval_runtime": 6.3382,
|
| 683 |
-
"eval_samples_per_second": 4560.586,
|
| 684 |
-
"eval_steps_per_second": 35.657,
|
| 685 |
-
"step": 10400
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 5.87,
|
| 689 |
-
"eval_accuracy": 0.894589358610669,
|
| 690 |
-
"eval_f1": 0.8961857432709598,
|
| 691 |
-
"eval_loss": 0.27857667207717896,
|
| 692 |
-
"eval_matthews_correlation": 0.8425697307237311,
|
| 693 |
-
"eval_precision": 0.902446347217679,
|
| 694 |
-
"eval_recall": 0.8931898746627281,
|
| 695 |
-
"eval_runtime": 6.3289,
|
| 696 |
-
"eval_samples_per_second": 4567.286,
|
| 697 |
-
"eval_steps_per_second": 35.709,
|
| 698 |
-
"step": 10600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 5.98,
|
| 702 |
-
"eval_accuracy": 0.893205562858922,
|
| 703 |
-
"eval_f1": 0.8946394925604301,
|
| 704 |
-
"eval_loss": 0.27962467074394226,
|
| 705 |
-
"eval_matthews_correlation": 0.8404729678330028,
|
| 706 |
-
"eval_precision": 0.9002145861000929,
|
| 707 |
-
"eval_recall": 0.8922083556654631,
|
| 708 |
-
"eval_runtime": 6.353,
|
| 709 |
-
"eval_samples_per_second": 4549.964,
|
| 710 |
-
"eval_steps_per_second": 35.574,
|
| 711 |
-
"step": 10800
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 6.09,
|
| 715 |
-
"eval_accuracy": 0.8906109458243964,
|
| 716 |
-
"eval_f1": 0.8924024545347345,
|
| 717 |
-
"eval_loss": 0.29711011052131653,
|
| 718 |
-
"eval_matthews_correlation": 0.8361735155967818,
|
| 719 |
-
"eval_precision": 0.8972474385584807,
|
| 720 |
-
"eval_recall": 0.8899490012257618,
|
| 721 |
-
"eval_runtime": 6.3296,
|
| 722 |
-
"eval_samples_per_second": 4566.77,
|
| 723 |
-
"eval_steps_per_second": 35.705,
|
| 724 |
-
"step": 11000
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 6.2,
|
| 728 |
-
"eval_accuracy": 0.8944509790354943,
|
| 729 |
-
"eval_f1": 0.8959234303209875,
|
| 730 |
-
"eval_loss": 0.2769003212451935,
|
| 731 |
-
"eval_matthews_correlation": 0.8418614081465325,
|
| 732 |
-
"eval_precision": 0.8999328555907699,
|
| 733 |
-
"eval_recall": 0.8939905889542185,
|
| 734 |
-
"eval_runtime": 6.3393,
|
| 735 |
-
"eval_samples_per_second": 4559.806,
|
| 736 |
-
"eval_steps_per_second": 35.651,
|
| 737 |
-
"step": 11200
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 6.31,
|
| 741 |
-
"eval_accuracy": 0.8936207015844462,
|
| 742 |
-
"eval_f1": 0.8952128070488539,
|
| 743 |
-
"eval_loss": 0.2829510271549225,
|
| 744 |
-
"eval_matthews_correlation": 0.8407021453916385,
|
| 745 |
-
"eval_precision": 0.8998640802112573,
|
| 746 |
-
"eval_recall": 0.8928955041267032,
|
| 747 |
-
"eval_runtime": 6.3367,
|
| 748 |
-
"eval_samples_per_second": 4561.689,
|
| 749 |
-
"eval_steps_per_second": 35.665,
|
| 750 |
-
"step": 11400
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 6.42,
|
| 754 |
-
"eval_accuracy": 0.8921677160451117,
|
| 755 |
-
"eval_f1": 0.8941286765370976,
|
| 756 |
-
"eval_loss": 0.2832199037075043,
|
| 757 |
-
"eval_matthews_correlation": 0.8382049893653651,
|
| 758 |
-
"eval_precision": 0.8986185080667188,
|
| 759 |
-
"eval_recall": 0.8914790820569541,
|
| 760 |
-
"eval_runtime": 6.3444,
|
| 761 |
-
"eval_samples_per_second": 4556.111,
|
| 762 |
-
"eval_steps_per_second": 35.622,
|
| 763 |
-
"step": 11600
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 6.53,
|
| 767 |
-
"eval_accuracy": 0.8926866394520169,
|
| 768 |
-
"eval_f1": 0.8936186466410277,
|
| 769 |
-
"eval_loss": 0.2926216125488281,
|
| 770 |
-
"eval_matthews_correlation": 0.8404882223115158,
|
| 771 |
-
"eval_precision": 0.9005394048744494,
|
| 772 |
-
"eval_recall": 0.8914742456721587,
|
| 773 |
-
"eval_runtime": 6.3293,
|
| 774 |
-
"eval_samples_per_second": 4567.005,
|
| 775 |
-
"eval_steps_per_second": 35.707,
|
| 776 |
-
"step": 11800
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 6.64,
|
| 780 |
-
"eval_accuracy": 0.8909914896561267,
|
| 781 |
-
"eval_f1": 0.8920870410180105,
|
| 782 |
-
"eval_loss": 0.3084053099155426,
|
| 783 |
-
"eval_matthews_correlation": 0.8378209285395514,
|
| 784 |
-
"eval_precision": 0.8986281823984682,
|
| 785 |
-
"eval_recall": 0.8901018199742271,
|
| 786 |
-
"eval_runtime": 6.338,
|
| 787 |
-
"eval_samples_per_second": 4560.739,
|
| 788 |
-
"eval_steps_per_second": 35.658,
|
| 789 |
-
"step": 12000
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 6.75,
|
| 793 |
-
"eval_accuracy": 0.8949699024423995,
|
| 794 |
-
"eval_f1": 0.8963528705414717,
|
| 795 |
-
"eval_loss": 0.2815876305103302,
|
| 796 |
-
"eval_matthews_correlation": 0.8434602442050388,
|
| 797 |
-
"eval_precision": 0.902663149581604,
|
| 798 |
-
"eval_recall": 0.8938368242795476,
|
| 799 |
-
"eval_runtime": 6.3463,
|
| 800 |
-
"eval_samples_per_second": 4554.791,
|
| 801 |
-
"eval_steps_per_second": 35.611,
|
| 802 |
-
"step": 12200
|
| 803 |
-
},
|
| 804 |
-
{
|
| 805 |
-
"epoch": 6.86,
|
| 806 |
-
"eval_accuracy": 0.8950390922299869,
|
| 807 |
-
"eval_f1": 0.8960369227358638,
|
| 808 |
-
"eval_loss": 0.2833254635334015,
|
| 809 |
-
"eval_matthews_correlation": 0.8436664985568201,
|
| 810 |
-
"eval_precision": 0.9018676150542063,
|
| 811 |
-
"eval_recall": 0.8941823694062445,
|
| 812 |
-
"eval_runtime": 6.3446,
|
| 813 |
-
"eval_samples_per_second": 4555.994,
|
| 814 |
-
"eval_steps_per_second": 35.621,
|
| 815 |
-
"step": 12400
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 6.97,
|
| 819 |
-
"eval_accuracy": 0.895869369681035,
|
| 820 |
-
"eval_f1": 0.8971085385306447,
|
| 821 |
-
"eval_loss": 0.28908270597457886,
|
| 822 |
-
"eval_matthews_correlation": 0.8445141159069601,
|
| 823 |
-
"eval_precision": 0.9021799006291262,
|
| 824 |
-
"eval_recall": 0.8951668393446816,
|
| 825 |
-
"eval_runtime": 6.3451,
|
| 826 |
-
"eval_samples_per_second": 4555.656,
|
| 827 |
-
"eval_steps_per_second": 35.618,
|
| 828 |
-
"step": 12600
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 7.08,
|
| 832 |
-
"eval_accuracy": 0.8937244862658271,
|
| 833 |
-
"eval_f1": 0.8954805911287705,
|
| 834 |
-
"eval_loss": 0.29825320839881897,
|
| 835 |
-
"eval_matthews_correlation": 0.8406403827862651,
|
| 836 |
-
"eval_precision": 0.8994945554758117,
|
| 837 |
-
"eval_recall": 0.8933288486109117,
|
| 838 |
-
"eval_runtime": 6.3488,
|
| 839 |
-
"eval_samples_per_second": 4552.997,
|
| 840 |
-
"eval_steps_per_second": 35.597,
|
| 841 |
-
"step": 12800
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 7.19,
|
| 845 |
-
"eval_accuracy": 0.8937244862658271,
|
| 846 |
-
"eval_f1": 0.8955952693876258,
|
| 847 |
-
"eval_loss": 0.2996089458465576,
|
| 848 |
-
"eval_matthews_correlation": 0.8404833026989822,
|
| 849 |
-
"eval_precision": 0.8993078971139616,
|
| 850 |
-
"eval_recall": 0.8934347551004255,
|
| 851 |
-
"eval_runtime": 6.3457,
|
| 852 |
-
"eval_samples_per_second": 4555.189,
|
| 853 |
-
"eval_steps_per_second": 35.614,
|
| 854 |
-
"step": 13000
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 7.3,
|
| 858 |
-
"eval_accuracy": 0.8937590811596209,
|
| 859 |
-
"eval_f1": 0.8948487273918467,
|
| 860 |
-
"eval_loss": 0.3090289831161499,
|
| 861 |
-
"eval_matthews_correlation": 0.8415939853008771,
|
| 862 |
-
"eval_precision": 0.9003448838076126,
|
| 863 |
-
"eval_recall": 0.8930370390861109,
|
| 864 |
-
"eval_runtime": 6.3449,
|
| 865 |
-
"eval_samples_per_second": 4555.749,
|
| 866 |
-
"eval_steps_per_second": 35.619,
|
| 867 |
-
"step": 13200
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 7.42,
|
| 871 |
-
"eval_accuracy": 0.8930325883899537,
|
| 872 |
-
"eval_f1": 0.8947355938263941,
|
| 873 |
-
"eval_loss": 0.29815882444381714,
|
| 874 |
-
"eval_matthews_correlation": 0.8396636290801262,
|
| 875 |
-
"eval_precision": 0.8987888710247001,
|
| 876 |
-
"eval_recall": 0.8926619116746521,
|
| 877 |
-
"eval_runtime": 6.3488,
|
| 878 |
-
"eval_samples_per_second": 4553.004,
|
| 879 |
-
"eval_steps_per_second": 35.597,
|
| 880 |
-
"step": 13400
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 7.53,
|
| 884 |
-
"eval_accuracy": 0.8944163841417007,
|
| 885 |
-
"eval_f1": 0.8962893288359082,
|
| 886 |
-
"eval_loss": 0.2949025630950928,
|
| 887 |
-
"eval_matthews_correlation": 0.8415722880989316,
|
| 888 |
-
"eval_precision": 0.9003635530512929,
|
| 889 |
-
"eval_recall": 0.8939143909193757,
|
| 890 |
-
"eval_runtime": 6.3544,
|
| 891 |
-
"eval_samples_per_second": 4548.955,
|
| 892 |
-
"eval_steps_per_second": 35.566,
|
| 893 |
-
"step": 13600
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 7.64,
|
| 897 |
-
"eval_accuracy": 0.8934823220092715,
|
| 898 |
-
"eval_f1": 0.8949615122382938,
|
| 899 |
-
"eval_loss": 0.3010229766368866,
|
| 900 |
-
"eval_matthews_correlation": 0.8404772500610511,
|
| 901 |
-
"eval_precision": 0.8990321494366329,
|
| 902 |
-
"eval_recall": 0.8931151783605705,
|
| 903 |
-
"eval_runtime": 6.3416,
|
| 904 |
-
"eval_samples_per_second": 4558.141,
|
| 905 |
-
"eval_steps_per_second": 35.638,
|
| 906 |
-
"step": 13800
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 7.75,
|
| 910 |
-
"eval_accuracy": 0.8925136649830485,
|
| 911 |
-
"eval_f1": 0.8942310761211139,
|
| 912 |
-
"eval_loss": 0.29808488488197327,
|
| 913 |
-
"eval_matthews_correlation": 0.8385560869137584,
|
| 914 |
-
"eval_precision": 0.8970918955574861,
|
| 915 |
-
"eval_recall": 0.8926049483431046,
|
| 916 |
-
"eval_runtime": 6.3386,
|
| 917 |
-
"eval_samples_per_second": 4560.306,
|
| 918 |
-
"eval_steps_per_second": 35.655,
|
| 919 |
-
"step": 14000
|
| 920 |
-
}
|
| 921 |
-
],
|
| 922 |
-
"logging_steps": 100000,
|
| 923 |
-
"max_steps": 14456,
|
| 924 |
-
"num_train_epochs": 8,
|
| 925 |
-
"save_steps": 200,
|
| 926 |
-
"total_flos": 1.7033398988046336e+17,
|
| 927 |
-
"trial_name": null,
|
| 928 |
-
"trial_params": null
|
| 929 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c400db087c38744401d19be767ade3d2582aedda503020b3908045286998db99
|
| 3 |
-
size 5329
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_3072/checkpoint-100000",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"BertForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"classifier_dropout": null,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0",
|
| 13 |
-
"1": "LABEL_1",
|
| 14 |
-
"2": "LABEL_2"
|
| 15 |
-
},
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"LABEL_0": 0,
|
| 20 |
-
"LABEL_1": 1,
|
| 21 |
-
"LABEL_2": 2
|
| 22 |
-
},
|
| 23 |
-
"layer_norm_eps": 1e-12,
|
| 24 |
-
"max_length": 512,
|
| 25 |
-
"max_position_embeddings": 512,
|
| 26 |
-
"model_type": "bert",
|
| 27 |
-
"num_attention_heads": 12,
|
| 28 |
-
"num_hidden_layers": 12,
|
| 29 |
-
"pad_token_id": 0,
|
| 30 |
-
"position_embedding_type": "absolute",
|
| 31 |
-
"problem_type": "single_label_classification",
|
| 32 |
-
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.35.2",
|
| 34 |
-
"type_vocab_size": 2,
|
| 35 |
-
"use_cache": true,
|
| 36 |
-
"vocab_size": 3072
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b2ce7f4e236d5b31596e895b16d3400b48944d173fce3c3e4feee31390e90e3f
|
| 3 |
-
size 353635228
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7fcc525582eec59c6a120e1e085a244bd442e4dd1b588da8fb5652f413b5bc94
|
| 3 |
-
size 707392139
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a40c0771075b677d7a2273a2379a2fc00551653fdcc5871321621860312c5b07
|
| 3 |
-
size 14709
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ca23367cb8b18de412dfcd7160aabae082c84d7dbe85b24e18ff908be1b0119e
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/tokenizer_config.json
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 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 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"cache_dir": null,
|
| 45 |
-
"clean_up_tokenization_spaces": true,
|
| 46 |
-
"cls_token": "[CLS]",
|
| 47 |
-
"mask_token": "[MASK]",
|
| 48 |
-
"model_max_length": 250,
|
| 49 |
-
"pad_token": "[PAD]",
|
| 50 |
-
"padding_side": "right",
|
| 51 |
-
"sep_token": "[SEP]",
|
| 52 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 53 |
-
"trust_remote_code": true,
|
| 54 |
-
"unk_token": "[UNK]",
|
| 55 |
-
"use_fast": true
|
| 56 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/trainer_state.json
DELETED
|
@@ -1,942 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.858328721638074,
|
| 5 |
-
"eval_steps": 200,
|
| 6 |
-
"global_step": 14200,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.11,
|
| 13 |
-
"eval_accuracy": 0.7631287621947,
|
| 14 |
-
"eval_f1": 0.7637252904097979,
|
| 15 |
-
"eval_loss": 0.5434313416481018,
|
| 16 |
-
"eval_matthews_correlation": 0.6445437687927822,
|
| 17 |
-
"eval_precision": 0.7637111046493135,
|
| 18 |
-
"eval_recall": 0.765490425188335,
|
| 19 |
-
"eval_runtime": 6.3466,
|
| 20 |
-
"eval_samples_per_second": 4554.569,
|
| 21 |
-
"eval_steps_per_second": 35.61,
|
| 22 |
-
"step": 200
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0.22,
|
| 26 |
-
"eval_accuracy": 0.8355012800110704,
|
| 27 |
-
"eval_f1": 0.8365614801773557,
|
| 28 |
-
"eval_loss": 0.41565728187561035,
|
| 29 |
-
"eval_matthews_correlation": 0.7574410510587669,
|
| 30 |
-
"eval_precision": 0.8547583068058389,
|
| 31 |
-
"eval_recall": 0.8309223755258941,
|
| 32 |
-
"eval_runtime": 6.3479,
|
| 33 |
-
"eval_samples_per_second": 4553.618,
|
| 34 |
-
"eval_steps_per_second": 35.602,
|
| 35 |
-
"step": 400
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 0.33,
|
| 39 |
-
"eval_accuracy": 0.8444959523974261,
|
| 40 |
-
"eval_f1": 0.8462633455095543,
|
| 41 |
-
"eval_loss": 0.39934343099594116,
|
| 42 |
-
"eval_matthews_correlation": 0.7666701235793097,
|
| 43 |
-
"eval_precision": 0.8539778966745382,
|
| 44 |
-
"eval_recall": 0.8423605635643182,
|
| 45 |
-
"eval_runtime": 6.3347,
|
| 46 |
-
"eval_samples_per_second": 4563.147,
|
| 47 |
-
"eval_steps_per_second": 35.677,
|
| 48 |
-
"step": 600
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.44,
|
| 52 |
-
"eval_accuracy": 0.8584722894900713,
|
| 53 |
-
"eval_f1": 0.8598909494500923,
|
| 54 |
-
"eval_loss": 0.35555699467658997,
|
| 55 |
-
"eval_matthews_correlation": 0.7875595996660668,
|
| 56 |
-
"eval_precision": 0.8648899799007316,
|
| 57 |
-
"eval_recall": 0.8572299805040989,
|
| 58 |
-
"eval_runtime": 6.332,
|
| 59 |
-
"eval_samples_per_second": 4565.079,
|
| 60 |
-
"eval_steps_per_second": 35.692,
|
| 61 |
-
"step": 800
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.55,
|
| 65 |
-
"eval_accuracy": 0.8430775617518854,
|
| 66 |
-
"eval_f1": 0.8454663268345574,
|
| 67 |
-
"eval_loss": 0.3819273114204407,
|
| 68 |
-
"eval_matthews_correlation": 0.7640650142321523,
|
| 69 |
-
"eval_precision": 0.8487232576971051,
|
| 70 |
-
"eval_recall": 0.8437015678940293,
|
| 71 |
-
"eval_runtime": 6.3315,
|
| 72 |
-
"eval_samples_per_second": 4565.442,
|
| 73 |
-
"eval_steps_per_second": 35.695,
|
| 74 |
-
"step": 1000
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.66,
|
| 78 |
-
"eval_accuracy": 0.8650799142046633,
|
| 79 |
-
"eval_f1": 0.8644083875976301,
|
| 80 |
-
"eval_loss": 0.33737584948539734,
|
| 81 |
-
"eval_matthews_correlation": 0.7999641131979995,
|
| 82 |
-
"eval_precision": 0.8726322998406989,
|
| 83 |
-
"eval_recall": 0.8638534177565756,
|
| 84 |
-
"eval_runtime": 6.3425,
|
| 85 |
-
"eval_samples_per_second": 4557.514,
|
| 86 |
-
"eval_steps_per_second": 35.633,
|
| 87 |
-
"step": 1200
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.77,
|
| 91 |
-
"eval_accuracy": 0.8665674946377915,
|
| 92 |
-
"eval_f1": 0.8682947296760272,
|
| 93 |
-
"eval_loss": 0.3294672966003418,
|
| 94 |
-
"eval_matthews_correlation": 0.8007303567504979,
|
| 95 |
-
"eval_precision": 0.8787531415676622,
|
| 96 |
-
"eval_recall": 0.8635116626335386,
|
| 97 |
-
"eval_runtime": 6.3602,
|
| 98 |
-
"eval_samples_per_second": 4544.791,
|
| 99 |
-
"eval_steps_per_second": 35.533,
|
| 100 |
-
"step": 1400
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.89,
|
| 104 |
-
"eval_accuracy": 0.8716183491316681,
|
| 105 |
-
"eval_f1": 0.8726660510894068,
|
| 106 |
-
"eval_loss": 0.32086172699928284,
|
| 107 |
-
"eval_matthews_correlation": 0.8102970184587044,
|
| 108 |
-
"eval_precision": 0.8857093298214904,
|
| 109 |
-
"eval_recall": 0.868057832538541,
|
| 110 |
-
"eval_runtime": 6.3417,
|
| 111 |
-
"eval_samples_per_second": 4558.115,
|
| 112 |
-
"eval_steps_per_second": 35.637,
|
| 113 |
-
"step": 1600
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.0,
|
| 117 |
-
"eval_accuracy": 0.8732097142461772,
|
| 118 |
-
"eval_f1": 0.8747467540360607,
|
| 119 |
-
"eval_loss": 0.31995540857315063,
|
| 120 |
-
"eval_matthews_correlation": 0.8114248425885828,
|
| 121 |
-
"eval_precision": 0.8852565763439663,
|
| 122 |
-
"eval_recall": 0.870275600961048,
|
| 123 |
-
"eval_runtime": 6.3409,
|
| 124 |
-
"eval_samples_per_second": 4558.634,
|
| 125 |
-
"eval_steps_per_second": 35.641,
|
| 126 |
-
"step": 1800
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.11,
|
| 130 |
-
"eval_accuracy": 0.869819414654397,
|
| 131 |
-
"eval_f1": 0.870027807466756,
|
| 132 |
-
"eval_loss": 0.3274751901626587,
|
| 133 |
-
"eval_matthews_correlation": 0.807806844099052,
|
| 134 |
-
"eval_precision": 0.8811302666871579,
|
| 135 |
-
"eval_recall": 0.8680597400838227,
|
| 136 |
-
"eval_runtime": 6.3277,
|
| 137 |
-
"eval_samples_per_second": 4568.189,
|
| 138 |
-
"eval_steps_per_second": 35.716,
|
| 139 |
-
"step": 2000
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 1.22,
|
| 143 |
-
"eval_accuracy": 0.8751124334048295,
|
| 144 |
-
"eval_f1": 0.8767794708217407,
|
| 145 |
-
"eval_loss": 0.31445378065109253,
|
| 146 |
-
"eval_matthews_correlation": 0.8129535421098832,
|
| 147 |
-
"eval_precision": 0.8823771754169298,
|
| 148 |
-
"eval_recall": 0.8740288172396674,
|
| 149 |
-
"eval_runtime": 6.3375,
|
| 150 |
-
"eval_samples_per_second": 4561.07,
|
| 151 |
-
"eval_steps_per_second": 35.66,
|
| 152 |
-
"step": 2200
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 1.33,
|
| 156 |
-
"eval_accuracy": 0.8786065176779907,
|
| 157 |
-
"eval_f1": 0.8804120457112202,
|
| 158 |
-
"eval_loss": 0.30376389622688293,
|
| 159 |
-
"eval_matthews_correlation": 0.818359828918223,
|
| 160 |
-
"eval_precision": 0.8873540250604574,
|
| 161 |
-
"eval_recall": 0.8768603619194306,
|
| 162 |
-
"eval_runtime": 6.3495,
|
| 163 |
-
"eval_samples_per_second": 4552.473,
|
| 164 |
-
"eval_steps_per_second": 35.593,
|
| 165 |
-
"step": 2400
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.44,
|
| 169 |
-
"eval_accuracy": 0.8689199474157614,
|
| 170 |
-
"eval_f1": 0.8695062971703474,
|
| 171 |
-
"eval_loss": 0.33015474677085876,
|
| 172 |
-
"eval_matthews_correlation": 0.8038507391919977,
|
| 173 |
-
"eval_precision": 0.8731098141522541,
|
| 174 |
-
"eval_recall": 0.869011988411034,
|
| 175 |
-
"eval_runtime": 6.341,
|
| 176 |
-
"eval_samples_per_second": 4558.589,
|
| 177 |
-
"eval_steps_per_second": 35.641,
|
| 178 |
-
"step": 2600
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.55,
|
| 182 |
-
"eval_accuracy": 0.8766692036255449,
|
| 183 |
-
"eval_f1": 0.8780737901306455,
|
| 184 |
-
"eval_loss": 0.3185276985168457,
|
| 185 |
-
"eval_matthews_correlation": 0.8159739463443503,
|
| 186 |
-
"eval_precision": 0.8854910478175612,
|
| 187 |
-
"eval_recall": 0.8749199751124719,
|
| 188 |
-
"eval_runtime": 6.3359,
|
| 189 |
-
"eval_samples_per_second": 4562.289,
|
| 190 |
-
"eval_steps_per_second": 35.67,
|
| 191 |
-
"step": 2800
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.66,
|
| 195 |
-
"eval_accuracy": 0.873451878502733,
|
| 196 |
-
"eval_f1": 0.8745153730554996,
|
| 197 |
-
"eval_loss": 0.3263399600982666,
|
| 198 |
-
"eval_matthews_correlation": 0.8119489865082196,
|
| 199 |
-
"eval_precision": 0.8834811606427829,
|
| 200 |
-
"eval_recall": 0.8715407218596346,
|
| 201 |
-
"eval_runtime": 6.3418,
|
| 202 |
-
"eval_samples_per_second": 4557.995,
|
| 203 |
-
"eval_steps_per_second": 35.636,
|
| 204 |
-
"step": 3000
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.77,
|
| 208 |
-
"eval_accuracy": 0.8813395142876911,
|
| 209 |
-
"eval_f1": 0.8818879844399303,
|
| 210 |
-
"eval_loss": 0.29727903008461,
|
| 211 |
-
"eval_matthews_correlation": 0.8259481285765669,
|
| 212 |
-
"eval_precision": 0.8956235096626705,
|
| 213 |
-
"eval_recall": 0.8783326544826559,
|
| 214 |
-
"eval_runtime": 6.3398,
|
| 215 |
-
"eval_samples_per_second": 4559.417,
|
| 216 |
-
"eval_steps_per_second": 35.648,
|
| 217 |
-
"step": 3200
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 1.88,
|
| 221 |
-
"eval_accuracy": 0.8827924998270256,
|
| 222 |
-
"eval_f1": 0.8841759014261692,
|
| 223 |
-
"eval_loss": 0.29565736651420593,
|
| 224 |
-
"eval_matthews_correlation": 0.8256178375822875,
|
| 225 |
-
"eval_precision": 0.892768390763086,
|
| 226 |
-
"eval_recall": 0.880666838238121,
|
| 227 |
-
"eval_runtime": 6.3407,
|
| 228 |
-
"eval_samples_per_second": 4558.804,
|
| 229 |
-
"eval_steps_per_second": 35.643,
|
| 230 |
-
"step": 3400
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 1.99,
|
| 234 |
-
"eval_accuracy": 0.8810627551373418,
|
| 235 |
-
"eval_f1": 0.8827766714455013,
|
| 236 |
-
"eval_loss": 0.29401829838752747,
|
| 237 |
-
"eval_matthews_correlation": 0.8216298754947776,
|
| 238 |
-
"eval_precision": 0.8887839973591874,
|
| 239 |
-
"eval_recall": 0.8794150912644644,
|
| 240 |
-
"eval_runtime": 6.3433,
|
| 241 |
-
"eval_samples_per_second": 4556.962,
|
| 242 |
-
"eval_steps_per_second": 35.628,
|
| 243 |
-
"step": 3600
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.1,
|
| 247 |
-
"eval_accuracy": 0.8796097695980073,
|
| 248 |
-
"eval_f1": 0.8805296255975588,
|
| 249 |
-
"eval_loss": 0.3111639618873596,
|
| 250 |
-
"eval_matthews_correlation": 0.8222095610456218,
|
| 251 |
-
"eval_precision": 0.8924941587035914,
|
| 252 |
-
"eval_recall": 0.8764907197445329,
|
| 253 |
-
"eval_runtime": 6.328,
|
| 254 |
-
"eval_samples_per_second": 4567.984,
|
| 255 |
-
"eval_steps_per_second": 35.715,
|
| 256 |
-
"step": 3800
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 2.21,
|
| 260 |
-
"eval_accuracy": 0.8824465508890887,
|
| 261 |
-
"eval_f1": 0.8836499737169107,
|
| 262 |
-
"eval_loss": 0.30004093050956726,
|
| 263 |
-
"eval_matthews_correlation": 0.8257179264635982,
|
| 264 |
-
"eval_precision": 0.8938452710102794,
|
| 265 |
-
"eval_recall": 0.8798082044973228,
|
| 266 |
-
"eval_runtime": 6.326,
|
| 267 |
-
"eval_samples_per_second": 4569.373,
|
| 268 |
-
"eval_steps_per_second": 35.725,
|
| 269 |
-
"step": 4000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.32,
|
| 273 |
-
"eval_accuracy": 0.8759773057496714,
|
| 274 |
-
"eval_f1": 0.8772153967910118,
|
| 275 |
-
"eval_loss": 0.31523868441581726,
|
| 276 |
-
"eval_matthews_correlation": 0.815377575453818,
|
| 277 |
-
"eval_precision": 0.8864289034661025,
|
| 278 |
-
"eval_recall": 0.87336045996798,
|
| 279 |
-
"eval_runtime": 6.3286,
|
| 280 |
-
"eval_samples_per_second": 4567.526,
|
| 281 |
-
"eval_steps_per_second": 35.711,
|
| 282 |
-
"step": 4200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 2.43,
|
| 286 |
-
"eval_accuracy": 0.8800595032173251,
|
| 287 |
-
"eval_f1": 0.8804022842955522,
|
| 288 |
-
"eval_loss": 0.3036770522594452,
|
| 289 |
-
"eval_matthews_correlation": 0.822361970881652,
|
| 290 |
-
"eval_precision": 0.8888145633651886,
|
| 291 |
-
"eval_recall": 0.8790141931629684,
|
| 292 |
-
"eval_runtime": 6.3289,
|
| 293 |
-
"eval_samples_per_second": 4567.335,
|
| 294 |
-
"eval_steps_per_second": 35.709,
|
| 295 |
-
"step": 4400
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 2.55,
|
| 299 |
-
"eval_accuracy": 0.8872206462326161,
|
| 300 |
-
"eval_f1": 0.8884178788215135,
|
| 301 |
-
"eval_loss": 0.2838316857814789,
|
| 302 |
-
"eval_matthews_correlation": 0.8325897438913511,
|
| 303 |
-
"eval_precision": 0.8972535403832396,
|
| 304 |
-
"eval_recall": 0.8851528361222756,
|
| 305 |
-
"eval_runtime": 6.3339,
|
| 306 |
-
"eval_samples_per_second": 4563.702,
|
| 307 |
-
"eval_steps_per_second": 35.681,
|
| 308 |
-
"step": 4600
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.66,
|
| 312 |
-
"eval_accuracy": 0.88358818238428,
|
| 313 |
-
"eval_f1": 0.885114187094025,
|
| 314 |
-
"eval_loss": 0.29305681586265564,
|
| 315 |
-
"eval_matthews_correlation": 0.8259291080645792,
|
| 316 |
-
"eval_precision": 0.8916206014101848,
|
| 317 |
-
"eval_recall": 0.881925767855031,
|
| 318 |
-
"eval_runtime": 6.3267,
|
| 319 |
-
"eval_samples_per_second": 4568.926,
|
| 320 |
-
"eval_steps_per_second": 35.722,
|
| 321 |
-
"step": 4800
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.77,
|
| 325 |
-
"eval_accuracy": 0.8854217117553449,
|
| 326 |
-
"eval_f1": 0.8857838454083451,
|
| 327 |
-
"eval_loss": 0.2878040373325348,
|
| 328 |
-
"eval_matthews_correlation": 0.8301977075488263,
|
| 329 |
-
"eval_precision": 0.8938206658601261,
|
| 330 |
-
"eval_recall": 0.884056956873887,
|
| 331 |
-
"eval_runtime": 6.3273,
|
| 332 |
-
"eval_samples_per_second": 4568.489,
|
| 333 |
-
"eval_steps_per_second": 35.718,
|
| 334 |
-
"step": 5000
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 2.88,
|
| 338 |
-
"eval_accuracy": 0.8821351968449457,
|
| 339 |
-
"eval_f1": 0.8839452239437287,
|
| 340 |
-
"eval_loss": 0.30110254883766174,
|
| 341 |
-
"eval_matthews_correlation": 0.8231792168311283,
|
| 342 |
-
"eval_precision": 0.8879817009125152,
|
| 343 |
-
"eval_recall": 0.8818214391632123,
|
| 344 |
-
"eval_runtime": 6.329,
|
| 345 |
-
"eval_samples_per_second": 4567.195,
|
| 346 |
-
"eval_steps_per_second": 35.708,
|
| 347 |
-
"step": 5200
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 2.99,
|
| 351 |
-
"eval_accuracy": 0.8851449526049955,
|
| 352 |
-
"eval_f1": 0.886308239213426,
|
| 353 |
-
"eval_loss": 0.2945020794868469,
|
| 354 |
-
"eval_matthews_correlation": 0.8303737613493637,
|
| 355 |
-
"eval_precision": 0.897756431496714,
|
| 356 |
-
"eval_recall": 0.8823199630167121,
|
| 357 |
-
"eval_runtime": 6.328,
|
| 358 |
-
"eval_samples_per_second": 4567.918,
|
| 359 |
-
"eval_steps_per_second": 35.714,
|
| 360 |
-
"step": 5400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 3.1,
|
| 364 |
-
"eval_accuracy": 0.8848681934546461,
|
| 365 |
-
"eval_f1": 0.8858670845855992,
|
| 366 |
-
"eval_loss": 0.2994346618652344,
|
| 367 |
-
"eval_matthews_correlation": 0.8285400641383184,
|
| 368 |
-
"eval_precision": 0.8926579786712784,
|
| 369 |
-
"eval_recall": 0.8836020295365422,
|
| 370 |
-
"eval_runtime": 6.3289,
|
| 371 |
-
"eval_samples_per_second": 4567.288,
|
| 372 |
-
"eval_steps_per_second": 35.709,
|
| 373 |
-
"step": 5600
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 3.21,
|
| 377 |
-
"eval_accuracy": 0.8870476717636477,
|
| 378 |
-
"eval_f1": 0.887896425962959,
|
| 379 |
-
"eval_loss": 0.2862726151943207,
|
| 380 |
-
"eval_matthews_correlation": 0.8339123150665094,
|
| 381 |
-
"eval_precision": 0.9001657168490554,
|
| 382 |
-
"eval_recall": 0.8843680937123602,
|
| 383 |
-
"eval_runtime": 6.3273,
|
| 384 |
-
"eval_samples_per_second": 4568.476,
|
| 385 |
-
"eval_steps_per_second": 35.718,
|
| 386 |
-
"step": 5800
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.32,
|
| 390 |
-
"eval_accuracy": 0.8860098249498374,
|
| 391 |
-
"eval_f1": 0.8874314355841011,
|
| 392 |
-
"eval_loss": 0.2849290668964386,
|
| 393 |
-
"eval_matthews_correlation": 0.8299739841185283,
|
| 394 |
-
"eval_precision": 0.894704396265502,
|
| 395 |
-
"eval_recall": 0.8842126035893482,
|
| 396 |
-
"eval_runtime": 6.3413,
|
| 397 |
-
"eval_samples_per_second": 4558.358,
|
| 398 |
-
"eval_steps_per_second": 35.639,
|
| 399 |
-
"step": 6000
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.43,
|
| 403 |
-
"eval_accuracy": 0.8904033764616343,
|
| 404 |
-
"eval_f1": 0.8914779910613806,
|
| 405 |
-
"eval_loss": 0.2752903997898102,
|
| 406 |
-
"eval_matthews_correlation": 0.8364867202399989,
|
| 407 |
-
"eval_precision": 0.8971261241739302,
|
| 408 |
-
"eval_recall": 0.8894531419411426,
|
| 409 |
-
"eval_runtime": 6.3307,
|
| 410 |
-
"eval_samples_per_second": 4565.983,
|
| 411 |
-
"eval_steps_per_second": 35.699,
|
| 412 |
-
"step": 6200
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"epoch": 3.54,
|
| 416 |
-
"eval_accuracy": 0.8873590258077908,
|
| 417 |
-
"eval_f1": 0.8882921639464642,
|
| 418 |
-
"eval_loss": 0.2815305292606354,
|
| 419 |
-
"eval_matthews_correlation": 0.8316060546498991,
|
| 420 |
-
"eval_precision": 0.8928030268824344,
|
| 421 |
-
"eval_recall": 0.8867802028593369,
|
| 422 |
-
"eval_runtime": 6.3328,
|
| 423 |
-
"eval_samples_per_second": 4564.487,
|
| 424 |
-
"eval_steps_per_second": 35.687,
|
| 425 |
-
"step": 6400
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 3.65,
|
| 429 |
-
"eval_accuracy": 0.8893309347540304,
|
| 430 |
-
"eval_f1": 0.8903653331168124,
|
| 431 |
-
"eval_loss": 0.28411537408828735,
|
| 432 |
-
"eval_matthews_correlation": 0.8367081606238141,
|
| 433 |
-
"eval_precision": 0.9012824783176558,
|
| 434 |
-
"eval_recall": 0.8868608966982018,
|
| 435 |
-
"eval_runtime": 6.3318,
|
| 436 |
-
"eval_samples_per_second": 4565.229,
|
| 437 |
-
"eval_steps_per_second": 35.693,
|
| 438 |
-
"step": 6600
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 3.76,
|
| 442 |
-
"eval_accuracy": 0.8848681934546461,
|
| 443 |
-
"eval_f1": 0.8866504352176569,
|
| 444 |
-
"eval_loss": 0.2806982696056366,
|
| 445 |
-
"eval_matthews_correlation": 0.8269026453375029,
|
| 446 |
-
"eval_precision": 0.8899918085446745,
|
| 447 |
-
"eval_recall": 0.8844727980389897,
|
| 448 |
-
"eval_runtime": 6.3318,
|
| 449 |
-
"eval_samples_per_second": 4565.232,
|
| 450 |
-
"eval_steps_per_second": 35.693,
|
| 451 |
-
"step": 6800
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 3.87,
|
| 455 |
-
"eval_accuracy": 0.8883276828340138,
|
| 456 |
-
"eval_f1": 0.8899090148440965,
|
| 457 |
-
"eval_loss": 0.28133419156074524,
|
| 458 |
-
"eval_matthews_correlation": 0.8333472890229207,
|
| 459 |
-
"eval_precision": 0.8968149574541151,
|
| 460 |
-
"eval_recall": 0.8867648269634268,
|
| 461 |
-
"eval_runtime": 6.3336,
|
| 462 |
-
"eval_samples_per_second": 4563.941,
|
| 463 |
-
"eval_steps_per_second": 35.683,
|
| 464 |
-
"step": 7000
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 3.98,
|
| 468 |
-
"eval_accuracy": 0.8881547083650453,
|
| 469 |
-
"eval_f1": 0.8894026496021189,
|
| 470 |
-
"eval_loss": 0.297502338886261,
|
| 471 |
-
"eval_matthews_correlation": 0.8334945205386666,
|
| 472 |
-
"eval_precision": 0.8966041254627256,
|
| 473 |
-
"eval_recall": 0.8867020495936117,
|
| 474 |
-
"eval_runtime": 6.335,
|
| 475 |
-
"eval_samples_per_second": 4562.884,
|
| 476 |
-
"eval_steps_per_second": 35.675,
|
| 477 |
-
"step": 7200
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 4.1,
|
| 481 |
-
"eval_accuracy": 0.8849027883484397,
|
| 482 |
-
"eval_f1": 0.8862039883812148,
|
| 483 |
-
"eval_loss": 0.301325261592865,
|
| 484 |
-
"eval_matthews_correlation": 0.8273884442911875,
|
| 485 |
-
"eval_precision": 0.889580662263925,
|
| 486 |
-
"eval_recall": 0.884713387934626,
|
| 487 |
-
"eval_runtime": 6.3295,
|
| 488 |
-
"eval_samples_per_second": 4566.865,
|
| 489 |
-
"eval_steps_per_second": 35.706,
|
| 490 |
-
"step": 7400
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 4.21,
|
| 494 |
-
"eval_accuracy": 0.891614197744413,
|
| 495 |
-
"eval_f1": 0.893011854474095,
|
| 496 |
-
"eval_loss": 0.2823241651058197,
|
| 497 |
-
"eval_matthews_correlation": 0.8388915171836414,
|
| 498 |
-
"eval_precision": 0.9015900643435097,
|
| 499 |
-
"eval_recall": 0.8893977713271144,
|
| 500 |
-
"eval_runtime": 6.3352,
|
| 501 |
-
"eval_samples_per_second": 4562.773,
|
| 502 |
-
"eval_steps_per_second": 35.674,
|
| 503 |
-
"step": 7600
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 4.32,
|
| 507 |
-
"eval_accuracy": 0.8899190479485228,
|
| 508 |
-
"eval_f1": 0.8911303872165929,
|
| 509 |
-
"eval_loss": 0.277401328086853,
|
| 510 |
-
"eval_matthews_correlation": 0.835208898716426,
|
| 511 |
-
"eval_precision": 0.8954442716084697,
|
| 512 |
-
"eval_recall": 0.8892804616842996,
|
| 513 |
-
"eval_runtime": 6.3312,
|
| 514 |
-
"eval_samples_per_second": 4565.613,
|
| 515 |
-
"eval_steps_per_second": 35.696,
|
| 516 |
-
"step": 7800
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 4.43,
|
| 520 |
-
"eval_accuracy": 0.8934477271154777,
|
| 521 |
-
"eval_f1": 0.8945062334448224,
|
| 522 |
-
"eval_loss": 0.2779960334300995,
|
| 523 |
-
"eval_matthews_correlation": 0.8416809998028856,
|
| 524 |
-
"eval_precision": 0.9020848134085252,
|
| 525 |
-
"eval_recall": 0.8917974318475038,
|
| 526 |
-
"eval_runtime": 6.3272,
|
| 527 |
-
"eval_samples_per_second": 4568.498,
|
| 528 |
-
"eval_steps_per_second": 35.719,
|
| 529 |
-
"step": 8000
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 4.54,
|
| 533 |
-
"eval_accuracy": 0.8847644087732651,
|
| 534 |
-
"eval_f1": 0.8857130853518814,
|
| 535 |
-
"eval_loss": 0.28888192772865295,
|
| 536 |
-
"eval_matthews_correlation": 0.8272079111106393,
|
| 537 |
-
"eval_precision": 0.8881516611221727,
|
| 538 |
-
"eval_recall": 0.8851166852917182,
|
| 539 |
-
"eval_runtime": 6.3314,
|
| 540 |
-
"eval_samples_per_second": 4565.469,
|
| 541 |
-
"eval_steps_per_second": 35.695,
|
| 542 |
-
"step": 8200
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 4.65,
|
| 546 |
-
"eval_accuracy": 0.8880509236836643,
|
| 547 |
-
"eval_f1": 0.8898717476564153,
|
| 548 |
-
"eval_loss": 0.2906430959701538,
|
| 549 |
-
"eval_matthews_correlation": 0.8326988493177964,
|
| 550 |
-
"eval_precision": 0.8965857564648291,
|
| 551 |
-
"eval_recall": 0.8865417456050507,
|
| 552 |
-
"eval_runtime": 6.3302,
|
| 553 |
-
"eval_samples_per_second": 4566.355,
|
| 554 |
-
"eval_steps_per_second": 35.702,
|
| 555 |
-
"step": 8400
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 4.76,
|
| 559 |
-
"eval_accuracy": 0.88829308794022,
|
| 560 |
-
"eval_f1": 0.8897630778211744,
|
| 561 |
-
"eval_loss": 0.27177920937538147,
|
| 562 |
-
"eval_matthews_correlation": 0.8322280376805495,
|
| 563 |
-
"eval_precision": 0.8921815887419909,
|
| 564 |
-
"eval_recall": 0.888582941893682,
|
| 565 |
-
"eval_runtime": 6.3301,
|
| 566 |
-
"eval_samples_per_second": 4566.456,
|
| 567 |
-
"eval_steps_per_second": 35.703,
|
| 568 |
-
"step": 8600
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 4.87,
|
| 572 |
-
"eval_accuracy": 0.8910260845499204,
|
| 573 |
-
"eval_f1": 0.8918365911417983,
|
| 574 |
-
"eval_loss": 0.27784451842308044,
|
| 575 |
-
"eval_matthews_correlation": 0.8389532823558397,
|
| 576 |
-
"eval_precision": 0.9012345264937309,
|
| 577 |
-
"eval_recall": 0.889235385671921,
|
| 578 |
-
"eval_runtime": 6.336,
|
| 579 |
-
"eval_samples_per_second": 4562.151,
|
| 580 |
-
"eval_steps_per_second": 35.669,
|
| 581 |
-
"step": 8800
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 4.98,
|
| 585 |
-
"eval_accuracy": 0.8914412232754445,
|
| 586 |
-
"eval_f1": 0.8924273277393427,
|
| 587 |
-
"eval_loss": 0.2901306748390198,
|
| 588 |
-
"eval_matthews_correlation": 0.8388554292097326,
|
| 589 |
-
"eval_precision": 0.9000611285527805,
|
| 590 |
-
"eval_recall": 0.8900983830518662,
|
| 591 |
-
"eval_runtime": 6.3311,
|
| 592 |
-
"eval_samples_per_second": 4565.683,
|
| 593 |
-
"eval_steps_per_second": 35.697,
|
| 594 |
-
"step": 9000
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 5.09,
|
| 598 |
-
"eval_accuracy": 0.8910952743375078,
|
| 599 |
-
"eval_f1": 0.8928927255737659,
|
| 600 |
-
"eval_loss": 0.2787802815437317,
|
| 601 |
-
"eval_matthews_correlation": 0.836709202455403,
|
| 602 |
-
"eval_precision": 0.8970330284962715,
|
| 603 |
-
"eval_recall": 0.8906967390543823,
|
| 604 |
-
"eval_runtime": 6.3339,
|
| 605 |
-
"eval_samples_per_second": 4563.666,
|
| 606 |
-
"eval_steps_per_second": 35.681,
|
| 607 |
-
"step": 9200
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 5.2,
|
| 611 |
-
"eval_accuracy": 0.893205562858922,
|
| 612 |
-
"eval_f1": 0.894408918102502,
|
| 613 |
-
"eval_loss": 0.2776887118816376,
|
| 614 |
-
"eval_matthews_correlation": 0.8409755945954501,
|
| 615 |
-
"eval_precision": 0.9011576771528516,
|
| 616 |
-
"eval_recall": 0.8918337037228231,
|
| 617 |
-
"eval_runtime": 6.3322,
|
| 618 |
-
"eval_samples_per_second": 4564.904,
|
| 619 |
-
"eval_steps_per_second": 35.69,
|
| 620 |
-
"step": 9400
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 5.31,
|
| 624 |
-
"eval_accuracy": 0.8913028437002698,
|
| 625 |
-
"eval_f1": 0.8933449768029128,
|
| 626 |
-
"eval_loss": 0.27147313952445984,
|
| 627 |
-
"eval_matthews_correlation": 0.8367984636801901,
|
| 628 |
-
"eval_precision": 0.8974813228562427,
|
| 629 |
-
"eval_recall": 0.8908149800074497,
|
| 630 |
-
"eval_runtime": 6.3282,
|
| 631 |
-
"eval_samples_per_second": 4567.801,
|
| 632 |
-
"eval_steps_per_second": 35.713,
|
| 633 |
-
"step": 9600
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 5.42,
|
| 637 |
-
"eval_accuracy": 0.8931709679651283,
|
| 638 |
-
"eval_f1": 0.8947893988605209,
|
| 639 |
-
"eval_loss": 0.27668192982673645,
|
| 640 |
-
"eval_matthews_correlation": 0.839987634471219,
|
| 641 |
-
"eval_precision": 0.8996660888128512,
|
| 642 |
-
"eval_recall": 0.8922345752395212,
|
| 643 |
-
"eval_runtime": 6.3307,
|
| 644 |
-
"eval_samples_per_second": 4566.001,
|
| 645 |
-
"eval_steps_per_second": 35.699,
|
| 646 |
-
"step": 9800
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 5.53,
|
| 650 |
-
"eval_accuracy": 0.8901612122050785,
|
| 651 |
-
"eval_f1": 0.892030241440469,
|
| 652 |
-
"eval_loss": 0.27250680327415466,
|
| 653 |
-
"eval_matthews_correlation": 0.8348770244980368,
|
| 654 |
-
"eval_precision": 0.8948523734539041,
|
| 655 |
-
"eval_recall": 0.8902169928340783,
|
| 656 |
-
"eval_runtime": 6.3268,
|
| 657 |
-
"eval_samples_per_second": 4568.789,
|
| 658 |
-
"eval_steps_per_second": 35.721,
|
| 659 |
-
"step": 10000
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 5.64,
|
| 663 |
-
"eval_accuracy": 0.8936207015844462,
|
| 664 |
-
"eval_f1": 0.8950406066984883,
|
| 665 |
-
"eval_loss": 0.26825740933418274,
|
| 666 |
-
"eval_matthews_correlation": 0.8412864778456299,
|
| 667 |
-
"eval_precision": 0.9016571518017655,
|
| 668 |
-
"eval_recall": 0.8920421848866268,
|
| 669 |
-
"eval_runtime": 6.3326,
|
| 670 |
-
"eval_samples_per_second": 4564.614,
|
| 671 |
-
"eval_steps_per_second": 35.688,
|
| 672 |
-
"step": 10200
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 5.76,
|
| 676 |
-
"eval_accuracy": 0.8946931432920501,
|
| 677 |
-
"eval_f1": 0.895911504105032,
|
| 678 |
-
"eval_loss": 0.2863098382949829,
|
| 679 |
-
"eval_matthews_correlation": 0.8426744355500755,
|
| 680 |
-
"eval_precision": 0.9009237338326513,
|
| 681 |
-
"eval_recall": 0.893906711706501,
|
| 682 |
-
"eval_runtime": 6.3382,
|
| 683 |
-
"eval_samples_per_second": 4560.586,
|
| 684 |
-
"eval_steps_per_second": 35.657,
|
| 685 |
-
"step": 10400
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 5.87,
|
| 689 |
-
"eval_accuracy": 0.894589358610669,
|
| 690 |
-
"eval_f1": 0.8961857432709598,
|
| 691 |
-
"eval_loss": 0.27857667207717896,
|
| 692 |
-
"eval_matthews_correlation": 0.8425697307237311,
|
| 693 |
-
"eval_precision": 0.902446347217679,
|
| 694 |
-
"eval_recall": 0.8931898746627281,
|
| 695 |
-
"eval_runtime": 6.3289,
|
| 696 |
-
"eval_samples_per_second": 4567.286,
|
| 697 |
-
"eval_steps_per_second": 35.709,
|
| 698 |
-
"step": 10600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 5.98,
|
| 702 |
-
"eval_accuracy": 0.893205562858922,
|
| 703 |
-
"eval_f1": 0.8946394925604301,
|
| 704 |
-
"eval_loss": 0.27962467074394226,
|
| 705 |
-
"eval_matthews_correlation": 0.8404729678330028,
|
| 706 |
-
"eval_precision": 0.9002145861000929,
|
| 707 |
-
"eval_recall": 0.8922083556654631,
|
| 708 |
-
"eval_runtime": 6.353,
|
| 709 |
-
"eval_samples_per_second": 4549.964,
|
| 710 |
-
"eval_steps_per_second": 35.574,
|
| 711 |
-
"step": 10800
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 6.09,
|
| 715 |
-
"eval_accuracy": 0.8906109458243964,
|
| 716 |
-
"eval_f1": 0.8924024545347345,
|
| 717 |
-
"eval_loss": 0.29711011052131653,
|
| 718 |
-
"eval_matthews_correlation": 0.8361735155967818,
|
| 719 |
-
"eval_precision": 0.8972474385584807,
|
| 720 |
-
"eval_recall": 0.8899490012257618,
|
| 721 |
-
"eval_runtime": 6.3296,
|
| 722 |
-
"eval_samples_per_second": 4566.77,
|
| 723 |
-
"eval_steps_per_second": 35.705,
|
| 724 |
-
"step": 11000
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 6.2,
|
| 728 |
-
"eval_accuracy": 0.8944509790354943,
|
| 729 |
-
"eval_f1": 0.8959234303209875,
|
| 730 |
-
"eval_loss": 0.2769003212451935,
|
| 731 |
-
"eval_matthews_correlation": 0.8418614081465325,
|
| 732 |
-
"eval_precision": 0.8999328555907699,
|
| 733 |
-
"eval_recall": 0.8939905889542185,
|
| 734 |
-
"eval_runtime": 6.3393,
|
| 735 |
-
"eval_samples_per_second": 4559.806,
|
| 736 |
-
"eval_steps_per_second": 35.651,
|
| 737 |
-
"step": 11200
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 6.31,
|
| 741 |
-
"eval_accuracy": 0.8936207015844462,
|
| 742 |
-
"eval_f1": 0.8952128070488539,
|
| 743 |
-
"eval_loss": 0.2829510271549225,
|
| 744 |
-
"eval_matthews_correlation": 0.8407021453916385,
|
| 745 |
-
"eval_precision": 0.8998640802112573,
|
| 746 |
-
"eval_recall": 0.8928955041267032,
|
| 747 |
-
"eval_runtime": 6.3367,
|
| 748 |
-
"eval_samples_per_second": 4561.689,
|
| 749 |
-
"eval_steps_per_second": 35.665,
|
| 750 |
-
"step": 11400
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 6.42,
|
| 754 |
-
"eval_accuracy": 0.8921677160451117,
|
| 755 |
-
"eval_f1": 0.8941286765370976,
|
| 756 |
-
"eval_loss": 0.2832199037075043,
|
| 757 |
-
"eval_matthews_correlation": 0.8382049893653651,
|
| 758 |
-
"eval_precision": 0.8986185080667188,
|
| 759 |
-
"eval_recall": 0.8914790820569541,
|
| 760 |
-
"eval_runtime": 6.3444,
|
| 761 |
-
"eval_samples_per_second": 4556.111,
|
| 762 |
-
"eval_steps_per_second": 35.622,
|
| 763 |
-
"step": 11600
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 6.53,
|
| 767 |
-
"eval_accuracy": 0.8926866394520169,
|
| 768 |
-
"eval_f1": 0.8936186466410277,
|
| 769 |
-
"eval_loss": 0.2926216125488281,
|
| 770 |
-
"eval_matthews_correlation": 0.8404882223115158,
|
| 771 |
-
"eval_precision": 0.9005394048744494,
|
| 772 |
-
"eval_recall": 0.8914742456721587,
|
| 773 |
-
"eval_runtime": 6.3293,
|
| 774 |
-
"eval_samples_per_second": 4567.005,
|
| 775 |
-
"eval_steps_per_second": 35.707,
|
| 776 |
-
"step": 11800
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 6.64,
|
| 780 |
-
"eval_accuracy": 0.8909914896561267,
|
| 781 |
-
"eval_f1": 0.8920870410180105,
|
| 782 |
-
"eval_loss": 0.3084053099155426,
|
| 783 |
-
"eval_matthews_correlation": 0.8378209285395514,
|
| 784 |
-
"eval_precision": 0.8986281823984682,
|
| 785 |
-
"eval_recall": 0.8901018199742271,
|
| 786 |
-
"eval_runtime": 6.338,
|
| 787 |
-
"eval_samples_per_second": 4560.739,
|
| 788 |
-
"eval_steps_per_second": 35.658,
|
| 789 |
-
"step": 12000
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 6.75,
|
| 793 |
-
"eval_accuracy": 0.8949699024423995,
|
| 794 |
-
"eval_f1": 0.8963528705414717,
|
| 795 |
-
"eval_loss": 0.2815876305103302,
|
| 796 |
-
"eval_matthews_correlation": 0.8434602442050388,
|
| 797 |
-
"eval_precision": 0.902663149581604,
|
| 798 |
-
"eval_recall": 0.8938368242795476,
|
| 799 |
-
"eval_runtime": 6.3463,
|
| 800 |
-
"eval_samples_per_second": 4554.791,
|
| 801 |
-
"eval_steps_per_second": 35.611,
|
| 802 |
-
"step": 12200
|
| 803 |
-
},
|
| 804 |
-
{
|
| 805 |
-
"epoch": 6.86,
|
| 806 |
-
"eval_accuracy": 0.8950390922299869,
|
| 807 |
-
"eval_f1": 0.8960369227358638,
|
| 808 |
-
"eval_loss": 0.2833254635334015,
|
| 809 |
-
"eval_matthews_correlation": 0.8436664985568201,
|
| 810 |
-
"eval_precision": 0.9018676150542063,
|
| 811 |
-
"eval_recall": 0.8941823694062445,
|
| 812 |
-
"eval_runtime": 6.3446,
|
| 813 |
-
"eval_samples_per_second": 4555.994,
|
| 814 |
-
"eval_steps_per_second": 35.621,
|
| 815 |
-
"step": 12400
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 6.97,
|
| 819 |
-
"eval_accuracy": 0.895869369681035,
|
| 820 |
-
"eval_f1": 0.8971085385306447,
|
| 821 |
-
"eval_loss": 0.28908270597457886,
|
| 822 |
-
"eval_matthews_correlation": 0.8445141159069601,
|
| 823 |
-
"eval_precision": 0.9021799006291262,
|
| 824 |
-
"eval_recall": 0.8951668393446816,
|
| 825 |
-
"eval_runtime": 6.3451,
|
| 826 |
-
"eval_samples_per_second": 4555.656,
|
| 827 |
-
"eval_steps_per_second": 35.618,
|
| 828 |
-
"step": 12600
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 7.08,
|
| 832 |
-
"eval_accuracy": 0.8937244862658271,
|
| 833 |
-
"eval_f1": 0.8954805911287705,
|
| 834 |
-
"eval_loss": 0.29825320839881897,
|
| 835 |
-
"eval_matthews_correlation": 0.8406403827862651,
|
| 836 |
-
"eval_precision": 0.8994945554758117,
|
| 837 |
-
"eval_recall": 0.8933288486109117,
|
| 838 |
-
"eval_runtime": 6.3488,
|
| 839 |
-
"eval_samples_per_second": 4552.997,
|
| 840 |
-
"eval_steps_per_second": 35.597,
|
| 841 |
-
"step": 12800
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 7.19,
|
| 845 |
-
"eval_accuracy": 0.8937244862658271,
|
| 846 |
-
"eval_f1": 0.8955952693876258,
|
| 847 |
-
"eval_loss": 0.2996089458465576,
|
| 848 |
-
"eval_matthews_correlation": 0.8404833026989822,
|
| 849 |
-
"eval_precision": 0.8993078971139616,
|
| 850 |
-
"eval_recall": 0.8934347551004255,
|
| 851 |
-
"eval_runtime": 6.3457,
|
| 852 |
-
"eval_samples_per_second": 4555.189,
|
| 853 |
-
"eval_steps_per_second": 35.614,
|
| 854 |
-
"step": 13000
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 7.3,
|
| 858 |
-
"eval_accuracy": 0.8937590811596209,
|
| 859 |
-
"eval_f1": 0.8948487273918467,
|
| 860 |
-
"eval_loss": 0.3090289831161499,
|
| 861 |
-
"eval_matthews_correlation": 0.8415939853008771,
|
| 862 |
-
"eval_precision": 0.9003448838076126,
|
| 863 |
-
"eval_recall": 0.8930370390861109,
|
| 864 |
-
"eval_runtime": 6.3449,
|
| 865 |
-
"eval_samples_per_second": 4555.749,
|
| 866 |
-
"eval_steps_per_second": 35.619,
|
| 867 |
-
"step": 13200
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 7.42,
|
| 871 |
-
"eval_accuracy": 0.8930325883899537,
|
| 872 |
-
"eval_f1": 0.8947355938263941,
|
| 873 |
-
"eval_loss": 0.29815882444381714,
|
| 874 |
-
"eval_matthews_correlation": 0.8396636290801262,
|
| 875 |
-
"eval_precision": 0.8987888710247001,
|
| 876 |
-
"eval_recall": 0.8926619116746521,
|
| 877 |
-
"eval_runtime": 6.3488,
|
| 878 |
-
"eval_samples_per_second": 4553.004,
|
| 879 |
-
"eval_steps_per_second": 35.597,
|
| 880 |
-
"step": 13400
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 7.53,
|
| 884 |
-
"eval_accuracy": 0.8944163841417007,
|
| 885 |
-
"eval_f1": 0.8962893288359082,
|
| 886 |
-
"eval_loss": 0.2949025630950928,
|
| 887 |
-
"eval_matthews_correlation": 0.8415722880989316,
|
| 888 |
-
"eval_precision": 0.9003635530512929,
|
| 889 |
-
"eval_recall": 0.8939143909193757,
|
| 890 |
-
"eval_runtime": 6.3544,
|
| 891 |
-
"eval_samples_per_second": 4548.955,
|
| 892 |
-
"eval_steps_per_second": 35.566,
|
| 893 |
-
"step": 13600
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 7.64,
|
| 897 |
-
"eval_accuracy": 0.8934823220092715,
|
| 898 |
-
"eval_f1": 0.8949615122382938,
|
| 899 |
-
"eval_loss": 0.3010229766368866,
|
| 900 |
-
"eval_matthews_correlation": 0.8404772500610511,
|
| 901 |
-
"eval_precision": 0.8990321494366329,
|
| 902 |
-
"eval_recall": 0.8931151783605705,
|
| 903 |
-
"eval_runtime": 6.3416,
|
| 904 |
-
"eval_samples_per_second": 4558.141,
|
| 905 |
-
"eval_steps_per_second": 35.638,
|
| 906 |
-
"step": 13800
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 7.75,
|
| 910 |
-
"eval_accuracy": 0.8925136649830485,
|
| 911 |
-
"eval_f1": 0.8942310761211139,
|
| 912 |
-
"eval_loss": 0.29808488488197327,
|
| 913 |
-
"eval_matthews_correlation": 0.8385560869137584,
|
| 914 |
-
"eval_precision": 0.8970918955574861,
|
| 915 |
-
"eval_recall": 0.8926049483431046,
|
| 916 |
-
"eval_runtime": 6.3386,
|
| 917 |
-
"eval_samples_per_second": 4560.306,
|
| 918 |
-
"eval_steps_per_second": 35.655,
|
| 919 |
-
"step": 14000
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 7.86,
|
| 923 |
-
"eval_accuracy": 0.8959039645748288,
|
| 924 |
-
"eval_f1": 0.8974943969491261,
|
| 925 |
-
"eval_loss": 0.2937379777431488,
|
| 926 |
-
"eval_matthews_correlation": 0.8440852394941675,
|
| 927 |
-
"eval_precision": 0.9018634074300419,
|
| 928 |
-
"eval_recall": 0.8953053995769751,
|
| 929 |
-
"eval_runtime": 6.3468,
|
| 930 |
-
"eval_samples_per_second": 4554.451,
|
| 931 |
-
"eval_steps_per_second": 35.609,
|
| 932 |
-
"step": 14200
|
| 933 |
-
}
|
| 934 |
-
],
|
| 935 |
-
"logging_steps": 100000,
|
| 936 |
-
"max_steps": 14456,
|
| 937 |
-
"num_train_epochs": 8,
|
| 938 |
-
"save_steps": 200,
|
| 939 |
-
"total_flos": 1.727677889333166e+17,
|
| 940 |
-
"trial_name": null,
|
| 941 |
-
"trial_params": null
|
| 942 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14200/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c400db087c38744401d19be767ade3d2582aedda503020b3908045286998db99
|
| 3 |
-
size 5329
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_3072/checkpoint-100000",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"BertForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"classifier_dropout": null,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0",
|
| 13 |
-
"1": "LABEL_1",
|
| 14 |
-
"2": "LABEL_2"
|
| 15 |
-
},
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"LABEL_0": 0,
|
| 20 |
-
"LABEL_1": 1,
|
| 21 |
-
"LABEL_2": 2
|
| 22 |
-
},
|
| 23 |
-
"layer_norm_eps": 1e-12,
|
| 24 |
-
"max_length": 512,
|
| 25 |
-
"max_position_embeddings": 512,
|
| 26 |
-
"model_type": "bert",
|
| 27 |
-
"num_attention_heads": 12,
|
| 28 |
-
"num_hidden_layers": 12,
|
| 29 |
-
"pad_token_id": 0,
|
| 30 |
-
"position_embedding_type": "absolute",
|
| 31 |
-
"problem_type": "single_label_classification",
|
| 32 |
-
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.35.2",
|
| 34 |
-
"type_vocab_size": 2,
|
| 35 |
-
"use_cache": true,
|
| 36 |
-
"vocab_size": 3072
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1118c4fdc7ee32a08a1f8ea63b75b926229fb7af054fce80a93f065b3e621d90
|
| 3 |
-
size 353635228
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9a52250108ded843cee9877da712a08a48c516729291e771f35d3a31348e588c
|
| 3 |
-
size 707392139
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c0ee27be8b9b8e32c40caba73b076be727eae70da250a69d8d1165ab673ae590
|
| 3 |
-
size 14709
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fa25a5cce83e8360ed0900aabb4834a0fa384f82de2f811c4b1d4fdf8f9359c4
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/tokenizer_config.json
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 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 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"cache_dir": null,
|
| 45 |
-
"clean_up_tokenization_spaces": true,
|
| 46 |
-
"cls_token": "[CLS]",
|
| 47 |
-
"mask_token": "[MASK]",
|
| 48 |
-
"model_max_length": 250,
|
| 49 |
-
"pad_token": "[PAD]",
|
| 50 |
-
"padding_side": "right",
|
| 51 |
-
"sep_token": "[SEP]",
|
| 52 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 53 |
-
"trust_remote_code": true,
|
| 54 |
-
"unk_token": "[UNK]",
|
| 55 |
-
"use_fast": true
|
| 56 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/trainer_state.json
DELETED
|
@@ -1,955 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.969009407858328,
|
| 5 |
-
"eval_steps": 200,
|
| 6 |
-
"global_step": 14400,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.11,
|
| 13 |
-
"eval_accuracy": 0.7631287621947,
|
| 14 |
-
"eval_f1": 0.7637252904097979,
|
| 15 |
-
"eval_loss": 0.5434313416481018,
|
| 16 |
-
"eval_matthews_correlation": 0.6445437687927822,
|
| 17 |
-
"eval_precision": 0.7637111046493135,
|
| 18 |
-
"eval_recall": 0.765490425188335,
|
| 19 |
-
"eval_runtime": 6.3466,
|
| 20 |
-
"eval_samples_per_second": 4554.569,
|
| 21 |
-
"eval_steps_per_second": 35.61,
|
| 22 |
-
"step": 200
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0.22,
|
| 26 |
-
"eval_accuracy": 0.8355012800110704,
|
| 27 |
-
"eval_f1": 0.8365614801773557,
|
| 28 |
-
"eval_loss": 0.41565728187561035,
|
| 29 |
-
"eval_matthews_correlation": 0.7574410510587669,
|
| 30 |
-
"eval_precision": 0.8547583068058389,
|
| 31 |
-
"eval_recall": 0.8309223755258941,
|
| 32 |
-
"eval_runtime": 6.3479,
|
| 33 |
-
"eval_samples_per_second": 4553.618,
|
| 34 |
-
"eval_steps_per_second": 35.602,
|
| 35 |
-
"step": 400
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 0.33,
|
| 39 |
-
"eval_accuracy": 0.8444959523974261,
|
| 40 |
-
"eval_f1": 0.8462633455095543,
|
| 41 |
-
"eval_loss": 0.39934343099594116,
|
| 42 |
-
"eval_matthews_correlation": 0.7666701235793097,
|
| 43 |
-
"eval_precision": 0.8539778966745382,
|
| 44 |
-
"eval_recall": 0.8423605635643182,
|
| 45 |
-
"eval_runtime": 6.3347,
|
| 46 |
-
"eval_samples_per_second": 4563.147,
|
| 47 |
-
"eval_steps_per_second": 35.677,
|
| 48 |
-
"step": 600
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.44,
|
| 52 |
-
"eval_accuracy": 0.8584722894900713,
|
| 53 |
-
"eval_f1": 0.8598909494500923,
|
| 54 |
-
"eval_loss": 0.35555699467658997,
|
| 55 |
-
"eval_matthews_correlation": 0.7875595996660668,
|
| 56 |
-
"eval_precision": 0.8648899799007316,
|
| 57 |
-
"eval_recall": 0.8572299805040989,
|
| 58 |
-
"eval_runtime": 6.332,
|
| 59 |
-
"eval_samples_per_second": 4565.079,
|
| 60 |
-
"eval_steps_per_second": 35.692,
|
| 61 |
-
"step": 800
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.55,
|
| 65 |
-
"eval_accuracy": 0.8430775617518854,
|
| 66 |
-
"eval_f1": 0.8454663268345574,
|
| 67 |
-
"eval_loss": 0.3819273114204407,
|
| 68 |
-
"eval_matthews_correlation": 0.7640650142321523,
|
| 69 |
-
"eval_precision": 0.8487232576971051,
|
| 70 |
-
"eval_recall": 0.8437015678940293,
|
| 71 |
-
"eval_runtime": 6.3315,
|
| 72 |
-
"eval_samples_per_second": 4565.442,
|
| 73 |
-
"eval_steps_per_second": 35.695,
|
| 74 |
-
"step": 1000
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.66,
|
| 78 |
-
"eval_accuracy": 0.8650799142046633,
|
| 79 |
-
"eval_f1": 0.8644083875976301,
|
| 80 |
-
"eval_loss": 0.33737584948539734,
|
| 81 |
-
"eval_matthews_correlation": 0.7999641131979995,
|
| 82 |
-
"eval_precision": 0.8726322998406989,
|
| 83 |
-
"eval_recall": 0.8638534177565756,
|
| 84 |
-
"eval_runtime": 6.3425,
|
| 85 |
-
"eval_samples_per_second": 4557.514,
|
| 86 |
-
"eval_steps_per_second": 35.633,
|
| 87 |
-
"step": 1200
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.77,
|
| 91 |
-
"eval_accuracy": 0.8665674946377915,
|
| 92 |
-
"eval_f1": 0.8682947296760272,
|
| 93 |
-
"eval_loss": 0.3294672966003418,
|
| 94 |
-
"eval_matthews_correlation": 0.8007303567504979,
|
| 95 |
-
"eval_precision": 0.8787531415676622,
|
| 96 |
-
"eval_recall": 0.8635116626335386,
|
| 97 |
-
"eval_runtime": 6.3602,
|
| 98 |
-
"eval_samples_per_second": 4544.791,
|
| 99 |
-
"eval_steps_per_second": 35.533,
|
| 100 |
-
"step": 1400
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.89,
|
| 104 |
-
"eval_accuracy": 0.8716183491316681,
|
| 105 |
-
"eval_f1": 0.8726660510894068,
|
| 106 |
-
"eval_loss": 0.32086172699928284,
|
| 107 |
-
"eval_matthews_correlation": 0.8102970184587044,
|
| 108 |
-
"eval_precision": 0.8857093298214904,
|
| 109 |
-
"eval_recall": 0.868057832538541,
|
| 110 |
-
"eval_runtime": 6.3417,
|
| 111 |
-
"eval_samples_per_second": 4558.115,
|
| 112 |
-
"eval_steps_per_second": 35.637,
|
| 113 |
-
"step": 1600
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.0,
|
| 117 |
-
"eval_accuracy": 0.8732097142461772,
|
| 118 |
-
"eval_f1": 0.8747467540360607,
|
| 119 |
-
"eval_loss": 0.31995540857315063,
|
| 120 |
-
"eval_matthews_correlation": 0.8114248425885828,
|
| 121 |
-
"eval_precision": 0.8852565763439663,
|
| 122 |
-
"eval_recall": 0.870275600961048,
|
| 123 |
-
"eval_runtime": 6.3409,
|
| 124 |
-
"eval_samples_per_second": 4558.634,
|
| 125 |
-
"eval_steps_per_second": 35.641,
|
| 126 |
-
"step": 1800
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.11,
|
| 130 |
-
"eval_accuracy": 0.869819414654397,
|
| 131 |
-
"eval_f1": 0.870027807466756,
|
| 132 |
-
"eval_loss": 0.3274751901626587,
|
| 133 |
-
"eval_matthews_correlation": 0.807806844099052,
|
| 134 |
-
"eval_precision": 0.8811302666871579,
|
| 135 |
-
"eval_recall": 0.8680597400838227,
|
| 136 |
-
"eval_runtime": 6.3277,
|
| 137 |
-
"eval_samples_per_second": 4568.189,
|
| 138 |
-
"eval_steps_per_second": 35.716,
|
| 139 |
-
"step": 2000
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 1.22,
|
| 143 |
-
"eval_accuracy": 0.8751124334048295,
|
| 144 |
-
"eval_f1": 0.8767794708217407,
|
| 145 |
-
"eval_loss": 0.31445378065109253,
|
| 146 |
-
"eval_matthews_correlation": 0.8129535421098832,
|
| 147 |
-
"eval_precision": 0.8823771754169298,
|
| 148 |
-
"eval_recall": 0.8740288172396674,
|
| 149 |
-
"eval_runtime": 6.3375,
|
| 150 |
-
"eval_samples_per_second": 4561.07,
|
| 151 |
-
"eval_steps_per_second": 35.66,
|
| 152 |
-
"step": 2200
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 1.33,
|
| 156 |
-
"eval_accuracy": 0.8786065176779907,
|
| 157 |
-
"eval_f1": 0.8804120457112202,
|
| 158 |
-
"eval_loss": 0.30376389622688293,
|
| 159 |
-
"eval_matthews_correlation": 0.818359828918223,
|
| 160 |
-
"eval_precision": 0.8873540250604574,
|
| 161 |
-
"eval_recall": 0.8768603619194306,
|
| 162 |
-
"eval_runtime": 6.3495,
|
| 163 |
-
"eval_samples_per_second": 4552.473,
|
| 164 |
-
"eval_steps_per_second": 35.593,
|
| 165 |
-
"step": 2400
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.44,
|
| 169 |
-
"eval_accuracy": 0.8689199474157614,
|
| 170 |
-
"eval_f1": 0.8695062971703474,
|
| 171 |
-
"eval_loss": 0.33015474677085876,
|
| 172 |
-
"eval_matthews_correlation": 0.8038507391919977,
|
| 173 |
-
"eval_precision": 0.8731098141522541,
|
| 174 |
-
"eval_recall": 0.869011988411034,
|
| 175 |
-
"eval_runtime": 6.341,
|
| 176 |
-
"eval_samples_per_second": 4558.589,
|
| 177 |
-
"eval_steps_per_second": 35.641,
|
| 178 |
-
"step": 2600
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.55,
|
| 182 |
-
"eval_accuracy": 0.8766692036255449,
|
| 183 |
-
"eval_f1": 0.8780737901306455,
|
| 184 |
-
"eval_loss": 0.3185276985168457,
|
| 185 |
-
"eval_matthews_correlation": 0.8159739463443503,
|
| 186 |
-
"eval_precision": 0.8854910478175612,
|
| 187 |
-
"eval_recall": 0.8749199751124719,
|
| 188 |
-
"eval_runtime": 6.3359,
|
| 189 |
-
"eval_samples_per_second": 4562.289,
|
| 190 |
-
"eval_steps_per_second": 35.67,
|
| 191 |
-
"step": 2800
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.66,
|
| 195 |
-
"eval_accuracy": 0.873451878502733,
|
| 196 |
-
"eval_f1": 0.8745153730554996,
|
| 197 |
-
"eval_loss": 0.3263399600982666,
|
| 198 |
-
"eval_matthews_correlation": 0.8119489865082196,
|
| 199 |
-
"eval_precision": 0.8834811606427829,
|
| 200 |
-
"eval_recall": 0.8715407218596346,
|
| 201 |
-
"eval_runtime": 6.3418,
|
| 202 |
-
"eval_samples_per_second": 4557.995,
|
| 203 |
-
"eval_steps_per_second": 35.636,
|
| 204 |
-
"step": 3000
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.77,
|
| 208 |
-
"eval_accuracy": 0.8813395142876911,
|
| 209 |
-
"eval_f1": 0.8818879844399303,
|
| 210 |
-
"eval_loss": 0.29727903008461,
|
| 211 |
-
"eval_matthews_correlation": 0.8259481285765669,
|
| 212 |
-
"eval_precision": 0.8956235096626705,
|
| 213 |
-
"eval_recall": 0.8783326544826559,
|
| 214 |
-
"eval_runtime": 6.3398,
|
| 215 |
-
"eval_samples_per_second": 4559.417,
|
| 216 |
-
"eval_steps_per_second": 35.648,
|
| 217 |
-
"step": 3200
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 1.88,
|
| 221 |
-
"eval_accuracy": 0.8827924998270256,
|
| 222 |
-
"eval_f1": 0.8841759014261692,
|
| 223 |
-
"eval_loss": 0.29565736651420593,
|
| 224 |
-
"eval_matthews_correlation": 0.8256178375822875,
|
| 225 |
-
"eval_precision": 0.892768390763086,
|
| 226 |
-
"eval_recall": 0.880666838238121,
|
| 227 |
-
"eval_runtime": 6.3407,
|
| 228 |
-
"eval_samples_per_second": 4558.804,
|
| 229 |
-
"eval_steps_per_second": 35.643,
|
| 230 |
-
"step": 3400
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 1.99,
|
| 234 |
-
"eval_accuracy": 0.8810627551373418,
|
| 235 |
-
"eval_f1": 0.8827766714455013,
|
| 236 |
-
"eval_loss": 0.29401829838752747,
|
| 237 |
-
"eval_matthews_correlation": 0.8216298754947776,
|
| 238 |
-
"eval_precision": 0.8887839973591874,
|
| 239 |
-
"eval_recall": 0.8794150912644644,
|
| 240 |
-
"eval_runtime": 6.3433,
|
| 241 |
-
"eval_samples_per_second": 4556.962,
|
| 242 |
-
"eval_steps_per_second": 35.628,
|
| 243 |
-
"step": 3600
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.1,
|
| 247 |
-
"eval_accuracy": 0.8796097695980073,
|
| 248 |
-
"eval_f1": 0.8805296255975588,
|
| 249 |
-
"eval_loss": 0.3111639618873596,
|
| 250 |
-
"eval_matthews_correlation": 0.8222095610456218,
|
| 251 |
-
"eval_precision": 0.8924941587035914,
|
| 252 |
-
"eval_recall": 0.8764907197445329,
|
| 253 |
-
"eval_runtime": 6.328,
|
| 254 |
-
"eval_samples_per_second": 4567.984,
|
| 255 |
-
"eval_steps_per_second": 35.715,
|
| 256 |
-
"step": 3800
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 2.21,
|
| 260 |
-
"eval_accuracy": 0.8824465508890887,
|
| 261 |
-
"eval_f1": 0.8836499737169107,
|
| 262 |
-
"eval_loss": 0.30004093050956726,
|
| 263 |
-
"eval_matthews_correlation": 0.8257179264635982,
|
| 264 |
-
"eval_precision": 0.8938452710102794,
|
| 265 |
-
"eval_recall": 0.8798082044973228,
|
| 266 |
-
"eval_runtime": 6.326,
|
| 267 |
-
"eval_samples_per_second": 4569.373,
|
| 268 |
-
"eval_steps_per_second": 35.725,
|
| 269 |
-
"step": 4000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.32,
|
| 273 |
-
"eval_accuracy": 0.8759773057496714,
|
| 274 |
-
"eval_f1": 0.8772153967910118,
|
| 275 |
-
"eval_loss": 0.31523868441581726,
|
| 276 |
-
"eval_matthews_correlation": 0.815377575453818,
|
| 277 |
-
"eval_precision": 0.8864289034661025,
|
| 278 |
-
"eval_recall": 0.87336045996798,
|
| 279 |
-
"eval_runtime": 6.3286,
|
| 280 |
-
"eval_samples_per_second": 4567.526,
|
| 281 |
-
"eval_steps_per_second": 35.711,
|
| 282 |
-
"step": 4200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 2.43,
|
| 286 |
-
"eval_accuracy": 0.8800595032173251,
|
| 287 |
-
"eval_f1": 0.8804022842955522,
|
| 288 |
-
"eval_loss": 0.3036770522594452,
|
| 289 |
-
"eval_matthews_correlation": 0.822361970881652,
|
| 290 |
-
"eval_precision": 0.8888145633651886,
|
| 291 |
-
"eval_recall": 0.8790141931629684,
|
| 292 |
-
"eval_runtime": 6.3289,
|
| 293 |
-
"eval_samples_per_second": 4567.335,
|
| 294 |
-
"eval_steps_per_second": 35.709,
|
| 295 |
-
"step": 4400
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 2.55,
|
| 299 |
-
"eval_accuracy": 0.8872206462326161,
|
| 300 |
-
"eval_f1": 0.8884178788215135,
|
| 301 |
-
"eval_loss": 0.2838316857814789,
|
| 302 |
-
"eval_matthews_correlation": 0.8325897438913511,
|
| 303 |
-
"eval_precision": 0.8972535403832396,
|
| 304 |
-
"eval_recall": 0.8851528361222756,
|
| 305 |
-
"eval_runtime": 6.3339,
|
| 306 |
-
"eval_samples_per_second": 4563.702,
|
| 307 |
-
"eval_steps_per_second": 35.681,
|
| 308 |
-
"step": 4600
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.66,
|
| 312 |
-
"eval_accuracy": 0.88358818238428,
|
| 313 |
-
"eval_f1": 0.885114187094025,
|
| 314 |
-
"eval_loss": 0.29305681586265564,
|
| 315 |
-
"eval_matthews_correlation": 0.8259291080645792,
|
| 316 |
-
"eval_precision": 0.8916206014101848,
|
| 317 |
-
"eval_recall": 0.881925767855031,
|
| 318 |
-
"eval_runtime": 6.3267,
|
| 319 |
-
"eval_samples_per_second": 4568.926,
|
| 320 |
-
"eval_steps_per_second": 35.722,
|
| 321 |
-
"step": 4800
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.77,
|
| 325 |
-
"eval_accuracy": 0.8854217117553449,
|
| 326 |
-
"eval_f1": 0.8857838454083451,
|
| 327 |
-
"eval_loss": 0.2878040373325348,
|
| 328 |
-
"eval_matthews_correlation": 0.8301977075488263,
|
| 329 |
-
"eval_precision": 0.8938206658601261,
|
| 330 |
-
"eval_recall": 0.884056956873887,
|
| 331 |
-
"eval_runtime": 6.3273,
|
| 332 |
-
"eval_samples_per_second": 4568.489,
|
| 333 |
-
"eval_steps_per_second": 35.718,
|
| 334 |
-
"step": 5000
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 2.88,
|
| 338 |
-
"eval_accuracy": 0.8821351968449457,
|
| 339 |
-
"eval_f1": 0.8839452239437287,
|
| 340 |
-
"eval_loss": 0.30110254883766174,
|
| 341 |
-
"eval_matthews_correlation": 0.8231792168311283,
|
| 342 |
-
"eval_precision": 0.8879817009125152,
|
| 343 |
-
"eval_recall": 0.8818214391632123,
|
| 344 |
-
"eval_runtime": 6.329,
|
| 345 |
-
"eval_samples_per_second": 4567.195,
|
| 346 |
-
"eval_steps_per_second": 35.708,
|
| 347 |
-
"step": 5200
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 2.99,
|
| 351 |
-
"eval_accuracy": 0.8851449526049955,
|
| 352 |
-
"eval_f1": 0.886308239213426,
|
| 353 |
-
"eval_loss": 0.2945020794868469,
|
| 354 |
-
"eval_matthews_correlation": 0.8303737613493637,
|
| 355 |
-
"eval_precision": 0.897756431496714,
|
| 356 |
-
"eval_recall": 0.8823199630167121,
|
| 357 |
-
"eval_runtime": 6.328,
|
| 358 |
-
"eval_samples_per_second": 4567.918,
|
| 359 |
-
"eval_steps_per_second": 35.714,
|
| 360 |
-
"step": 5400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 3.1,
|
| 364 |
-
"eval_accuracy": 0.8848681934546461,
|
| 365 |
-
"eval_f1": 0.8858670845855992,
|
| 366 |
-
"eval_loss": 0.2994346618652344,
|
| 367 |
-
"eval_matthews_correlation": 0.8285400641383184,
|
| 368 |
-
"eval_precision": 0.8926579786712784,
|
| 369 |
-
"eval_recall": 0.8836020295365422,
|
| 370 |
-
"eval_runtime": 6.3289,
|
| 371 |
-
"eval_samples_per_second": 4567.288,
|
| 372 |
-
"eval_steps_per_second": 35.709,
|
| 373 |
-
"step": 5600
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 3.21,
|
| 377 |
-
"eval_accuracy": 0.8870476717636477,
|
| 378 |
-
"eval_f1": 0.887896425962959,
|
| 379 |
-
"eval_loss": 0.2862726151943207,
|
| 380 |
-
"eval_matthews_correlation": 0.8339123150665094,
|
| 381 |
-
"eval_precision": 0.9001657168490554,
|
| 382 |
-
"eval_recall": 0.8843680937123602,
|
| 383 |
-
"eval_runtime": 6.3273,
|
| 384 |
-
"eval_samples_per_second": 4568.476,
|
| 385 |
-
"eval_steps_per_second": 35.718,
|
| 386 |
-
"step": 5800
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.32,
|
| 390 |
-
"eval_accuracy": 0.8860098249498374,
|
| 391 |
-
"eval_f1": 0.8874314355841011,
|
| 392 |
-
"eval_loss": 0.2849290668964386,
|
| 393 |
-
"eval_matthews_correlation": 0.8299739841185283,
|
| 394 |
-
"eval_precision": 0.894704396265502,
|
| 395 |
-
"eval_recall": 0.8842126035893482,
|
| 396 |
-
"eval_runtime": 6.3413,
|
| 397 |
-
"eval_samples_per_second": 4558.358,
|
| 398 |
-
"eval_steps_per_second": 35.639,
|
| 399 |
-
"step": 6000
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.43,
|
| 403 |
-
"eval_accuracy": 0.8904033764616343,
|
| 404 |
-
"eval_f1": 0.8914779910613806,
|
| 405 |
-
"eval_loss": 0.2752903997898102,
|
| 406 |
-
"eval_matthews_correlation": 0.8364867202399989,
|
| 407 |
-
"eval_precision": 0.8971261241739302,
|
| 408 |
-
"eval_recall": 0.8894531419411426,
|
| 409 |
-
"eval_runtime": 6.3307,
|
| 410 |
-
"eval_samples_per_second": 4565.983,
|
| 411 |
-
"eval_steps_per_second": 35.699,
|
| 412 |
-
"step": 6200
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"epoch": 3.54,
|
| 416 |
-
"eval_accuracy": 0.8873590258077908,
|
| 417 |
-
"eval_f1": 0.8882921639464642,
|
| 418 |
-
"eval_loss": 0.2815305292606354,
|
| 419 |
-
"eval_matthews_correlation": 0.8316060546498991,
|
| 420 |
-
"eval_precision": 0.8928030268824344,
|
| 421 |
-
"eval_recall": 0.8867802028593369,
|
| 422 |
-
"eval_runtime": 6.3328,
|
| 423 |
-
"eval_samples_per_second": 4564.487,
|
| 424 |
-
"eval_steps_per_second": 35.687,
|
| 425 |
-
"step": 6400
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 3.65,
|
| 429 |
-
"eval_accuracy": 0.8893309347540304,
|
| 430 |
-
"eval_f1": 0.8903653331168124,
|
| 431 |
-
"eval_loss": 0.28411537408828735,
|
| 432 |
-
"eval_matthews_correlation": 0.8367081606238141,
|
| 433 |
-
"eval_precision": 0.9012824783176558,
|
| 434 |
-
"eval_recall": 0.8868608966982018,
|
| 435 |
-
"eval_runtime": 6.3318,
|
| 436 |
-
"eval_samples_per_second": 4565.229,
|
| 437 |
-
"eval_steps_per_second": 35.693,
|
| 438 |
-
"step": 6600
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 3.76,
|
| 442 |
-
"eval_accuracy": 0.8848681934546461,
|
| 443 |
-
"eval_f1": 0.8866504352176569,
|
| 444 |
-
"eval_loss": 0.2806982696056366,
|
| 445 |
-
"eval_matthews_correlation": 0.8269026453375029,
|
| 446 |
-
"eval_precision": 0.8899918085446745,
|
| 447 |
-
"eval_recall": 0.8844727980389897,
|
| 448 |
-
"eval_runtime": 6.3318,
|
| 449 |
-
"eval_samples_per_second": 4565.232,
|
| 450 |
-
"eval_steps_per_second": 35.693,
|
| 451 |
-
"step": 6800
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 3.87,
|
| 455 |
-
"eval_accuracy": 0.8883276828340138,
|
| 456 |
-
"eval_f1": 0.8899090148440965,
|
| 457 |
-
"eval_loss": 0.28133419156074524,
|
| 458 |
-
"eval_matthews_correlation": 0.8333472890229207,
|
| 459 |
-
"eval_precision": 0.8968149574541151,
|
| 460 |
-
"eval_recall": 0.8867648269634268,
|
| 461 |
-
"eval_runtime": 6.3336,
|
| 462 |
-
"eval_samples_per_second": 4563.941,
|
| 463 |
-
"eval_steps_per_second": 35.683,
|
| 464 |
-
"step": 7000
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 3.98,
|
| 468 |
-
"eval_accuracy": 0.8881547083650453,
|
| 469 |
-
"eval_f1": 0.8894026496021189,
|
| 470 |
-
"eval_loss": 0.297502338886261,
|
| 471 |
-
"eval_matthews_correlation": 0.8334945205386666,
|
| 472 |
-
"eval_precision": 0.8966041254627256,
|
| 473 |
-
"eval_recall": 0.8867020495936117,
|
| 474 |
-
"eval_runtime": 6.335,
|
| 475 |
-
"eval_samples_per_second": 4562.884,
|
| 476 |
-
"eval_steps_per_second": 35.675,
|
| 477 |
-
"step": 7200
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 4.1,
|
| 481 |
-
"eval_accuracy": 0.8849027883484397,
|
| 482 |
-
"eval_f1": 0.8862039883812148,
|
| 483 |
-
"eval_loss": 0.301325261592865,
|
| 484 |
-
"eval_matthews_correlation": 0.8273884442911875,
|
| 485 |
-
"eval_precision": 0.889580662263925,
|
| 486 |
-
"eval_recall": 0.884713387934626,
|
| 487 |
-
"eval_runtime": 6.3295,
|
| 488 |
-
"eval_samples_per_second": 4566.865,
|
| 489 |
-
"eval_steps_per_second": 35.706,
|
| 490 |
-
"step": 7400
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 4.21,
|
| 494 |
-
"eval_accuracy": 0.891614197744413,
|
| 495 |
-
"eval_f1": 0.893011854474095,
|
| 496 |
-
"eval_loss": 0.2823241651058197,
|
| 497 |
-
"eval_matthews_correlation": 0.8388915171836414,
|
| 498 |
-
"eval_precision": 0.9015900643435097,
|
| 499 |
-
"eval_recall": 0.8893977713271144,
|
| 500 |
-
"eval_runtime": 6.3352,
|
| 501 |
-
"eval_samples_per_second": 4562.773,
|
| 502 |
-
"eval_steps_per_second": 35.674,
|
| 503 |
-
"step": 7600
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 4.32,
|
| 507 |
-
"eval_accuracy": 0.8899190479485228,
|
| 508 |
-
"eval_f1": 0.8911303872165929,
|
| 509 |
-
"eval_loss": 0.277401328086853,
|
| 510 |
-
"eval_matthews_correlation": 0.835208898716426,
|
| 511 |
-
"eval_precision": 0.8954442716084697,
|
| 512 |
-
"eval_recall": 0.8892804616842996,
|
| 513 |
-
"eval_runtime": 6.3312,
|
| 514 |
-
"eval_samples_per_second": 4565.613,
|
| 515 |
-
"eval_steps_per_second": 35.696,
|
| 516 |
-
"step": 7800
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 4.43,
|
| 520 |
-
"eval_accuracy": 0.8934477271154777,
|
| 521 |
-
"eval_f1": 0.8945062334448224,
|
| 522 |
-
"eval_loss": 0.2779960334300995,
|
| 523 |
-
"eval_matthews_correlation": 0.8416809998028856,
|
| 524 |
-
"eval_precision": 0.9020848134085252,
|
| 525 |
-
"eval_recall": 0.8917974318475038,
|
| 526 |
-
"eval_runtime": 6.3272,
|
| 527 |
-
"eval_samples_per_second": 4568.498,
|
| 528 |
-
"eval_steps_per_second": 35.719,
|
| 529 |
-
"step": 8000
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 4.54,
|
| 533 |
-
"eval_accuracy": 0.8847644087732651,
|
| 534 |
-
"eval_f1": 0.8857130853518814,
|
| 535 |
-
"eval_loss": 0.28888192772865295,
|
| 536 |
-
"eval_matthews_correlation": 0.8272079111106393,
|
| 537 |
-
"eval_precision": 0.8881516611221727,
|
| 538 |
-
"eval_recall": 0.8851166852917182,
|
| 539 |
-
"eval_runtime": 6.3314,
|
| 540 |
-
"eval_samples_per_second": 4565.469,
|
| 541 |
-
"eval_steps_per_second": 35.695,
|
| 542 |
-
"step": 8200
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 4.65,
|
| 546 |
-
"eval_accuracy": 0.8880509236836643,
|
| 547 |
-
"eval_f1": 0.8898717476564153,
|
| 548 |
-
"eval_loss": 0.2906430959701538,
|
| 549 |
-
"eval_matthews_correlation": 0.8326988493177964,
|
| 550 |
-
"eval_precision": 0.8965857564648291,
|
| 551 |
-
"eval_recall": 0.8865417456050507,
|
| 552 |
-
"eval_runtime": 6.3302,
|
| 553 |
-
"eval_samples_per_second": 4566.355,
|
| 554 |
-
"eval_steps_per_second": 35.702,
|
| 555 |
-
"step": 8400
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 4.76,
|
| 559 |
-
"eval_accuracy": 0.88829308794022,
|
| 560 |
-
"eval_f1": 0.8897630778211744,
|
| 561 |
-
"eval_loss": 0.27177920937538147,
|
| 562 |
-
"eval_matthews_correlation": 0.8322280376805495,
|
| 563 |
-
"eval_precision": 0.8921815887419909,
|
| 564 |
-
"eval_recall": 0.888582941893682,
|
| 565 |
-
"eval_runtime": 6.3301,
|
| 566 |
-
"eval_samples_per_second": 4566.456,
|
| 567 |
-
"eval_steps_per_second": 35.703,
|
| 568 |
-
"step": 8600
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 4.87,
|
| 572 |
-
"eval_accuracy": 0.8910260845499204,
|
| 573 |
-
"eval_f1": 0.8918365911417983,
|
| 574 |
-
"eval_loss": 0.27784451842308044,
|
| 575 |
-
"eval_matthews_correlation": 0.8389532823558397,
|
| 576 |
-
"eval_precision": 0.9012345264937309,
|
| 577 |
-
"eval_recall": 0.889235385671921,
|
| 578 |
-
"eval_runtime": 6.336,
|
| 579 |
-
"eval_samples_per_second": 4562.151,
|
| 580 |
-
"eval_steps_per_second": 35.669,
|
| 581 |
-
"step": 8800
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 4.98,
|
| 585 |
-
"eval_accuracy": 0.8914412232754445,
|
| 586 |
-
"eval_f1": 0.8924273277393427,
|
| 587 |
-
"eval_loss": 0.2901306748390198,
|
| 588 |
-
"eval_matthews_correlation": 0.8388554292097326,
|
| 589 |
-
"eval_precision": 0.9000611285527805,
|
| 590 |
-
"eval_recall": 0.8900983830518662,
|
| 591 |
-
"eval_runtime": 6.3311,
|
| 592 |
-
"eval_samples_per_second": 4565.683,
|
| 593 |
-
"eval_steps_per_second": 35.697,
|
| 594 |
-
"step": 9000
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 5.09,
|
| 598 |
-
"eval_accuracy": 0.8910952743375078,
|
| 599 |
-
"eval_f1": 0.8928927255737659,
|
| 600 |
-
"eval_loss": 0.2787802815437317,
|
| 601 |
-
"eval_matthews_correlation": 0.836709202455403,
|
| 602 |
-
"eval_precision": 0.8970330284962715,
|
| 603 |
-
"eval_recall": 0.8906967390543823,
|
| 604 |
-
"eval_runtime": 6.3339,
|
| 605 |
-
"eval_samples_per_second": 4563.666,
|
| 606 |
-
"eval_steps_per_second": 35.681,
|
| 607 |
-
"step": 9200
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 5.2,
|
| 611 |
-
"eval_accuracy": 0.893205562858922,
|
| 612 |
-
"eval_f1": 0.894408918102502,
|
| 613 |
-
"eval_loss": 0.2776887118816376,
|
| 614 |
-
"eval_matthews_correlation": 0.8409755945954501,
|
| 615 |
-
"eval_precision": 0.9011576771528516,
|
| 616 |
-
"eval_recall": 0.8918337037228231,
|
| 617 |
-
"eval_runtime": 6.3322,
|
| 618 |
-
"eval_samples_per_second": 4564.904,
|
| 619 |
-
"eval_steps_per_second": 35.69,
|
| 620 |
-
"step": 9400
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 5.31,
|
| 624 |
-
"eval_accuracy": 0.8913028437002698,
|
| 625 |
-
"eval_f1": 0.8933449768029128,
|
| 626 |
-
"eval_loss": 0.27147313952445984,
|
| 627 |
-
"eval_matthews_correlation": 0.8367984636801901,
|
| 628 |
-
"eval_precision": 0.8974813228562427,
|
| 629 |
-
"eval_recall": 0.8908149800074497,
|
| 630 |
-
"eval_runtime": 6.3282,
|
| 631 |
-
"eval_samples_per_second": 4567.801,
|
| 632 |
-
"eval_steps_per_second": 35.713,
|
| 633 |
-
"step": 9600
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 5.42,
|
| 637 |
-
"eval_accuracy": 0.8931709679651283,
|
| 638 |
-
"eval_f1": 0.8947893988605209,
|
| 639 |
-
"eval_loss": 0.27668192982673645,
|
| 640 |
-
"eval_matthews_correlation": 0.839987634471219,
|
| 641 |
-
"eval_precision": 0.8996660888128512,
|
| 642 |
-
"eval_recall": 0.8922345752395212,
|
| 643 |
-
"eval_runtime": 6.3307,
|
| 644 |
-
"eval_samples_per_second": 4566.001,
|
| 645 |
-
"eval_steps_per_second": 35.699,
|
| 646 |
-
"step": 9800
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 5.53,
|
| 650 |
-
"eval_accuracy": 0.8901612122050785,
|
| 651 |
-
"eval_f1": 0.892030241440469,
|
| 652 |
-
"eval_loss": 0.27250680327415466,
|
| 653 |
-
"eval_matthews_correlation": 0.8348770244980368,
|
| 654 |
-
"eval_precision": 0.8948523734539041,
|
| 655 |
-
"eval_recall": 0.8902169928340783,
|
| 656 |
-
"eval_runtime": 6.3268,
|
| 657 |
-
"eval_samples_per_second": 4568.789,
|
| 658 |
-
"eval_steps_per_second": 35.721,
|
| 659 |
-
"step": 10000
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 5.64,
|
| 663 |
-
"eval_accuracy": 0.8936207015844462,
|
| 664 |
-
"eval_f1": 0.8950406066984883,
|
| 665 |
-
"eval_loss": 0.26825740933418274,
|
| 666 |
-
"eval_matthews_correlation": 0.8412864778456299,
|
| 667 |
-
"eval_precision": 0.9016571518017655,
|
| 668 |
-
"eval_recall": 0.8920421848866268,
|
| 669 |
-
"eval_runtime": 6.3326,
|
| 670 |
-
"eval_samples_per_second": 4564.614,
|
| 671 |
-
"eval_steps_per_second": 35.688,
|
| 672 |
-
"step": 10200
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 5.76,
|
| 676 |
-
"eval_accuracy": 0.8946931432920501,
|
| 677 |
-
"eval_f1": 0.895911504105032,
|
| 678 |
-
"eval_loss": 0.2863098382949829,
|
| 679 |
-
"eval_matthews_correlation": 0.8426744355500755,
|
| 680 |
-
"eval_precision": 0.9009237338326513,
|
| 681 |
-
"eval_recall": 0.893906711706501,
|
| 682 |
-
"eval_runtime": 6.3382,
|
| 683 |
-
"eval_samples_per_second": 4560.586,
|
| 684 |
-
"eval_steps_per_second": 35.657,
|
| 685 |
-
"step": 10400
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 5.87,
|
| 689 |
-
"eval_accuracy": 0.894589358610669,
|
| 690 |
-
"eval_f1": 0.8961857432709598,
|
| 691 |
-
"eval_loss": 0.27857667207717896,
|
| 692 |
-
"eval_matthews_correlation": 0.8425697307237311,
|
| 693 |
-
"eval_precision": 0.902446347217679,
|
| 694 |
-
"eval_recall": 0.8931898746627281,
|
| 695 |
-
"eval_runtime": 6.3289,
|
| 696 |
-
"eval_samples_per_second": 4567.286,
|
| 697 |
-
"eval_steps_per_second": 35.709,
|
| 698 |
-
"step": 10600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 5.98,
|
| 702 |
-
"eval_accuracy": 0.893205562858922,
|
| 703 |
-
"eval_f1": 0.8946394925604301,
|
| 704 |
-
"eval_loss": 0.27962467074394226,
|
| 705 |
-
"eval_matthews_correlation": 0.8404729678330028,
|
| 706 |
-
"eval_precision": 0.9002145861000929,
|
| 707 |
-
"eval_recall": 0.8922083556654631,
|
| 708 |
-
"eval_runtime": 6.353,
|
| 709 |
-
"eval_samples_per_second": 4549.964,
|
| 710 |
-
"eval_steps_per_second": 35.574,
|
| 711 |
-
"step": 10800
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 6.09,
|
| 715 |
-
"eval_accuracy": 0.8906109458243964,
|
| 716 |
-
"eval_f1": 0.8924024545347345,
|
| 717 |
-
"eval_loss": 0.29711011052131653,
|
| 718 |
-
"eval_matthews_correlation": 0.8361735155967818,
|
| 719 |
-
"eval_precision": 0.8972474385584807,
|
| 720 |
-
"eval_recall": 0.8899490012257618,
|
| 721 |
-
"eval_runtime": 6.3296,
|
| 722 |
-
"eval_samples_per_second": 4566.77,
|
| 723 |
-
"eval_steps_per_second": 35.705,
|
| 724 |
-
"step": 11000
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 6.2,
|
| 728 |
-
"eval_accuracy": 0.8944509790354943,
|
| 729 |
-
"eval_f1": 0.8959234303209875,
|
| 730 |
-
"eval_loss": 0.2769003212451935,
|
| 731 |
-
"eval_matthews_correlation": 0.8418614081465325,
|
| 732 |
-
"eval_precision": 0.8999328555907699,
|
| 733 |
-
"eval_recall": 0.8939905889542185,
|
| 734 |
-
"eval_runtime": 6.3393,
|
| 735 |
-
"eval_samples_per_second": 4559.806,
|
| 736 |
-
"eval_steps_per_second": 35.651,
|
| 737 |
-
"step": 11200
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 6.31,
|
| 741 |
-
"eval_accuracy": 0.8936207015844462,
|
| 742 |
-
"eval_f1": 0.8952128070488539,
|
| 743 |
-
"eval_loss": 0.2829510271549225,
|
| 744 |
-
"eval_matthews_correlation": 0.8407021453916385,
|
| 745 |
-
"eval_precision": 0.8998640802112573,
|
| 746 |
-
"eval_recall": 0.8928955041267032,
|
| 747 |
-
"eval_runtime": 6.3367,
|
| 748 |
-
"eval_samples_per_second": 4561.689,
|
| 749 |
-
"eval_steps_per_second": 35.665,
|
| 750 |
-
"step": 11400
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 6.42,
|
| 754 |
-
"eval_accuracy": 0.8921677160451117,
|
| 755 |
-
"eval_f1": 0.8941286765370976,
|
| 756 |
-
"eval_loss": 0.2832199037075043,
|
| 757 |
-
"eval_matthews_correlation": 0.8382049893653651,
|
| 758 |
-
"eval_precision": 0.8986185080667188,
|
| 759 |
-
"eval_recall": 0.8914790820569541,
|
| 760 |
-
"eval_runtime": 6.3444,
|
| 761 |
-
"eval_samples_per_second": 4556.111,
|
| 762 |
-
"eval_steps_per_second": 35.622,
|
| 763 |
-
"step": 11600
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 6.53,
|
| 767 |
-
"eval_accuracy": 0.8926866394520169,
|
| 768 |
-
"eval_f1": 0.8936186466410277,
|
| 769 |
-
"eval_loss": 0.2926216125488281,
|
| 770 |
-
"eval_matthews_correlation": 0.8404882223115158,
|
| 771 |
-
"eval_precision": 0.9005394048744494,
|
| 772 |
-
"eval_recall": 0.8914742456721587,
|
| 773 |
-
"eval_runtime": 6.3293,
|
| 774 |
-
"eval_samples_per_second": 4567.005,
|
| 775 |
-
"eval_steps_per_second": 35.707,
|
| 776 |
-
"step": 11800
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 6.64,
|
| 780 |
-
"eval_accuracy": 0.8909914896561267,
|
| 781 |
-
"eval_f1": 0.8920870410180105,
|
| 782 |
-
"eval_loss": 0.3084053099155426,
|
| 783 |
-
"eval_matthews_correlation": 0.8378209285395514,
|
| 784 |
-
"eval_precision": 0.8986281823984682,
|
| 785 |
-
"eval_recall": 0.8901018199742271,
|
| 786 |
-
"eval_runtime": 6.338,
|
| 787 |
-
"eval_samples_per_second": 4560.739,
|
| 788 |
-
"eval_steps_per_second": 35.658,
|
| 789 |
-
"step": 12000
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 6.75,
|
| 793 |
-
"eval_accuracy": 0.8949699024423995,
|
| 794 |
-
"eval_f1": 0.8963528705414717,
|
| 795 |
-
"eval_loss": 0.2815876305103302,
|
| 796 |
-
"eval_matthews_correlation": 0.8434602442050388,
|
| 797 |
-
"eval_precision": 0.902663149581604,
|
| 798 |
-
"eval_recall": 0.8938368242795476,
|
| 799 |
-
"eval_runtime": 6.3463,
|
| 800 |
-
"eval_samples_per_second": 4554.791,
|
| 801 |
-
"eval_steps_per_second": 35.611,
|
| 802 |
-
"step": 12200
|
| 803 |
-
},
|
| 804 |
-
{
|
| 805 |
-
"epoch": 6.86,
|
| 806 |
-
"eval_accuracy": 0.8950390922299869,
|
| 807 |
-
"eval_f1": 0.8960369227358638,
|
| 808 |
-
"eval_loss": 0.2833254635334015,
|
| 809 |
-
"eval_matthews_correlation": 0.8436664985568201,
|
| 810 |
-
"eval_precision": 0.9018676150542063,
|
| 811 |
-
"eval_recall": 0.8941823694062445,
|
| 812 |
-
"eval_runtime": 6.3446,
|
| 813 |
-
"eval_samples_per_second": 4555.994,
|
| 814 |
-
"eval_steps_per_second": 35.621,
|
| 815 |
-
"step": 12400
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 6.97,
|
| 819 |
-
"eval_accuracy": 0.895869369681035,
|
| 820 |
-
"eval_f1": 0.8971085385306447,
|
| 821 |
-
"eval_loss": 0.28908270597457886,
|
| 822 |
-
"eval_matthews_correlation": 0.8445141159069601,
|
| 823 |
-
"eval_precision": 0.9021799006291262,
|
| 824 |
-
"eval_recall": 0.8951668393446816,
|
| 825 |
-
"eval_runtime": 6.3451,
|
| 826 |
-
"eval_samples_per_second": 4555.656,
|
| 827 |
-
"eval_steps_per_second": 35.618,
|
| 828 |
-
"step": 12600
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 7.08,
|
| 832 |
-
"eval_accuracy": 0.8937244862658271,
|
| 833 |
-
"eval_f1": 0.8954805911287705,
|
| 834 |
-
"eval_loss": 0.29825320839881897,
|
| 835 |
-
"eval_matthews_correlation": 0.8406403827862651,
|
| 836 |
-
"eval_precision": 0.8994945554758117,
|
| 837 |
-
"eval_recall": 0.8933288486109117,
|
| 838 |
-
"eval_runtime": 6.3488,
|
| 839 |
-
"eval_samples_per_second": 4552.997,
|
| 840 |
-
"eval_steps_per_second": 35.597,
|
| 841 |
-
"step": 12800
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 7.19,
|
| 845 |
-
"eval_accuracy": 0.8937244862658271,
|
| 846 |
-
"eval_f1": 0.8955952693876258,
|
| 847 |
-
"eval_loss": 0.2996089458465576,
|
| 848 |
-
"eval_matthews_correlation": 0.8404833026989822,
|
| 849 |
-
"eval_precision": 0.8993078971139616,
|
| 850 |
-
"eval_recall": 0.8934347551004255,
|
| 851 |
-
"eval_runtime": 6.3457,
|
| 852 |
-
"eval_samples_per_second": 4555.189,
|
| 853 |
-
"eval_steps_per_second": 35.614,
|
| 854 |
-
"step": 13000
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 7.3,
|
| 858 |
-
"eval_accuracy": 0.8937590811596209,
|
| 859 |
-
"eval_f1": 0.8948487273918467,
|
| 860 |
-
"eval_loss": 0.3090289831161499,
|
| 861 |
-
"eval_matthews_correlation": 0.8415939853008771,
|
| 862 |
-
"eval_precision": 0.9003448838076126,
|
| 863 |
-
"eval_recall": 0.8930370390861109,
|
| 864 |
-
"eval_runtime": 6.3449,
|
| 865 |
-
"eval_samples_per_second": 4555.749,
|
| 866 |
-
"eval_steps_per_second": 35.619,
|
| 867 |
-
"step": 13200
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 7.42,
|
| 871 |
-
"eval_accuracy": 0.8930325883899537,
|
| 872 |
-
"eval_f1": 0.8947355938263941,
|
| 873 |
-
"eval_loss": 0.29815882444381714,
|
| 874 |
-
"eval_matthews_correlation": 0.8396636290801262,
|
| 875 |
-
"eval_precision": 0.8987888710247001,
|
| 876 |
-
"eval_recall": 0.8926619116746521,
|
| 877 |
-
"eval_runtime": 6.3488,
|
| 878 |
-
"eval_samples_per_second": 4553.004,
|
| 879 |
-
"eval_steps_per_second": 35.597,
|
| 880 |
-
"step": 13400
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 7.53,
|
| 884 |
-
"eval_accuracy": 0.8944163841417007,
|
| 885 |
-
"eval_f1": 0.8962893288359082,
|
| 886 |
-
"eval_loss": 0.2949025630950928,
|
| 887 |
-
"eval_matthews_correlation": 0.8415722880989316,
|
| 888 |
-
"eval_precision": 0.9003635530512929,
|
| 889 |
-
"eval_recall": 0.8939143909193757,
|
| 890 |
-
"eval_runtime": 6.3544,
|
| 891 |
-
"eval_samples_per_second": 4548.955,
|
| 892 |
-
"eval_steps_per_second": 35.566,
|
| 893 |
-
"step": 13600
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 7.64,
|
| 897 |
-
"eval_accuracy": 0.8934823220092715,
|
| 898 |
-
"eval_f1": 0.8949615122382938,
|
| 899 |
-
"eval_loss": 0.3010229766368866,
|
| 900 |
-
"eval_matthews_correlation": 0.8404772500610511,
|
| 901 |
-
"eval_precision": 0.8990321494366329,
|
| 902 |
-
"eval_recall": 0.8931151783605705,
|
| 903 |
-
"eval_runtime": 6.3416,
|
| 904 |
-
"eval_samples_per_second": 4558.141,
|
| 905 |
-
"eval_steps_per_second": 35.638,
|
| 906 |
-
"step": 13800
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 7.75,
|
| 910 |
-
"eval_accuracy": 0.8925136649830485,
|
| 911 |
-
"eval_f1": 0.8942310761211139,
|
| 912 |
-
"eval_loss": 0.29808488488197327,
|
| 913 |
-
"eval_matthews_correlation": 0.8385560869137584,
|
| 914 |
-
"eval_precision": 0.8970918955574861,
|
| 915 |
-
"eval_recall": 0.8926049483431046,
|
| 916 |
-
"eval_runtime": 6.3386,
|
| 917 |
-
"eval_samples_per_second": 4560.306,
|
| 918 |
-
"eval_steps_per_second": 35.655,
|
| 919 |
-
"step": 14000
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 7.86,
|
| 923 |
-
"eval_accuracy": 0.8959039645748288,
|
| 924 |
-
"eval_f1": 0.8974943969491261,
|
| 925 |
-
"eval_loss": 0.2937379777431488,
|
| 926 |
-
"eval_matthews_correlation": 0.8440852394941675,
|
| 927 |
-
"eval_precision": 0.9018634074300419,
|
| 928 |
-
"eval_recall": 0.8953053995769751,
|
| 929 |
-
"eval_runtime": 6.3468,
|
| 930 |
-
"eval_samples_per_second": 4554.451,
|
| 931 |
-
"eval_steps_per_second": 35.609,
|
| 932 |
-
"step": 14200
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 7.97,
|
| 936 |
-
"eval_accuracy": 0.8946239535044628,
|
| 937 |
-
"eval_f1": 0.8961604255258656,
|
| 938 |
-
"eval_loss": 0.29420605301856995,
|
| 939 |
-
"eval_matthews_correlation": 0.8420927050494054,
|
| 940 |
-
"eval_precision": 0.9000913131139286,
|
| 941 |
-
"eval_recall": 0.8942424543007098,
|
| 942 |
-
"eval_runtime": 6.3411,
|
| 943 |
-
"eval_samples_per_second": 4558.526,
|
| 944 |
-
"eval_steps_per_second": 35.641,
|
| 945 |
-
"step": 14400
|
| 946 |
-
}
|
| 947 |
-
],
|
| 948 |
-
"logging_steps": 100000,
|
| 949 |
-
"max_steps": 14456,
|
| 950 |
-
"num_train_epochs": 8,
|
| 951 |
-
"save_steps": 200,
|
| 952 |
-
"total_flos": 1.7520158798616986e+17,
|
| 953 |
-
"trial_name": null,
|
| 954 |
-
"trial_params": null
|
| 955 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/checkpoint-14400/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c400db087c38744401d19be767ade3d2582aedda503020b3908045286998db99
|
| 3 |
-
size 5329
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_3072/results/base_3072_hg38_BPE_3e-5_human_ensembl_regulatory_seed42/eval_results.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"eval_loss": 0.2924354672431946, "eval_accuracy": 0.8944546303663472, "eval_f1": 0.8958219487174928, "eval_matthews_correlation": 0.8415224291493578, "eval_precision": 0.8992124404743965, "eval_recall": 0.8938566933136989, "eval_runtime": 6.374, "eval_samples_per_second": 4535.167, "eval_steps_per_second": 35.457, "epoch": 8.0}
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_4096/checkpoint-100000",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"BertForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"classifier_dropout": null,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0",
|
| 13 |
-
"1": "LABEL_1",
|
| 14 |
-
"2": "LABEL_2"
|
| 15 |
-
},
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"LABEL_0": 0,
|
| 20 |
-
"LABEL_1": 1,
|
| 21 |
-
"LABEL_2": 2
|
| 22 |
-
},
|
| 23 |
-
"layer_norm_eps": 1e-12,
|
| 24 |
-
"max_length": 512,
|
| 25 |
-
"max_position_embeddings": 512,
|
| 26 |
-
"model_type": "bert",
|
| 27 |
-
"num_attention_heads": 12,
|
| 28 |
-
"num_hidden_layers": 12,
|
| 29 |
-
"pad_token_id": 0,
|
| 30 |
-
"position_embedding_type": "absolute",
|
| 31 |
-
"problem_type": "single_label_classification",
|
| 32 |
-
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.35.2",
|
| 34 |
-
"type_vocab_size": 2,
|
| 35 |
-
"use_cache": true,
|
| 36 |
-
"vocab_size": 4096
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d52f7b444dc7fa883b505dad471223a39f8450ed463c0a8fc04ff1145635d8ff
|
| 3 |
-
size 356780956
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fd99223578873ae1bcaf6af631869ca614bbe90bb7b58e99130de6a42d7a7810
|
| 3 |
-
size 713683595
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:deaf0a13914dfdba867d8c0368032b2523e6c0b514ab2d0de86f1107c227b367
|
| 3 |
-
size 14709
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d2f837dafff62c1bd228c6ad32b5ce7253d7ea15836a63bcf26d8af49b30e4dc
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/tokenizer_config.json
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 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 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"cache_dir": null,
|
| 45 |
-
"clean_up_tokenization_spaces": true,
|
| 46 |
-
"cls_token": "[CLS]",
|
| 47 |
-
"mask_token": "[MASK]",
|
| 48 |
-
"model_max_length": 250,
|
| 49 |
-
"pad_token": "[PAD]",
|
| 50 |
-
"padding_side": "right",
|
| 51 |
-
"sep_token": "[SEP]",
|
| 52 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 53 |
-
"trust_remote_code": true,
|
| 54 |
-
"unk_token": "[UNK]",
|
| 55 |
-
"use_fast": true
|
| 56 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/trainer_state.json
DELETED
|
@@ -1,929 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.74764803541782,
|
| 5 |
-
"eval_steps": 200,
|
| 6 |
-
"global_step": 14000,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.11,
|
| 13 |
-
"eval_accuracy": 0.8032588389953643,
|
| 14 |
-
"eval_f1": 0.8040452040692839,
|
| 15 |
-
"eval_loss": 0.4966795742511749,
|
| 16 |
-
"eval_matthews_correlation": 0.7084695952717522,
|
| 17 |
-
"eval_precision": 0.8237857718753817,
|
| 18 |
-
"eval_recall": 0.7975870988019708,
|
| 19 |
-
"eval_runtime": 6.3588,
|
| 20 |
-
"eval_samples_per_second": 4545.791,
|
| 21 |
-
"eval_steps_per_second": 35.541,
|
| 22 |
-
"step": 200
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0.22,
|
| 26 |
-
"eval_accuracy": 0.82806337784543,
|
| 27 |
-
"eval_f1": 0.8297094326097825,
|
| 28 |
-
"eval_loss": 0.4289039373397827,
|
| 29 |
-
"eval_matthews_correlation": 0.741876074078984,
|
| 30 |
-
"eval_precision": 0.8349242792396575,
|
| 31 |
-
"eval_recall": 0.8272187509320483,
|
| 32 |
-
"eval_runtime": 6.3568,
|
| 33 |
-
"eval_samples_per_second": 4547.233,
|
| 34 |
-
"eval_steps_per_second": 35.552,
|
| 35 |
-
"step": 400
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 0.33,
|
| 39 |
-
"eval_accuracy": 0.8440116238843147,
|
| 40 |
-
"eval_f1": 0.8450100684587841,
|
| 41 |
-
"eval_loss": 0.39371800422668457,
|
| 42 |
-
"eval_matthews_correlation": 0.7660039268807652,
|
| 43 |
-
"eval_precision": 0.85273319305628,
|
| 44 |
-
"eval_recall": 0.8412884667434676,
|
| 45 |
-
"eval_runtime": 6.3475,
|
| 46 |
-
"eval_samples_per_second": 4553.913,
|
| 47 |
-
"eval_steps_per_second": 35.605,
|
| 48 |
-
"step": 600
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.44,
|
| 52 |
-
"eval_accuracy": 0.8603058188611361,
|
| 53 |
-
"eval_f1": 0.8611020118054533,
|
| 54 |
-
"eval_loss": 0.35088762640953064,
|
| 55 |
-
"eval_matthews_correlation": 0.7927956332205198,
|
| 56 |
-
"eval_precision": 0.8723391365103108,
|
| 57 |
-
"eval_recall": 0.8574792991725344,
|
| 58 |
-
"eval_runtime": 6.3447,
|
| 59 |
-
"eval_samples_per_second": 4555.963,
|
| 60 |
-
"eval_steps_per_second": 35.621,
|
| 61 |
-
"step": 800
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.55,
|
| 65 |
-
"eval_accuracy": 0.8377153532138656,
|
| 66 |
-
"eval_f1": 0.8413461677606797,
|
| 67 |
-
"eval_loss": 0.379434198141098,
|
| 68 |
-
"eval_matthews_correlation": 0.7580192865676064,
|
| 69 |
-
"eval_precision": 0.8474953423917877,
|
| 70 |
-
"eval_recall": 0.8400608374251649,
|
| 71 |
-
"eval_runtime": 6.3446,
|
| 72 |
-
"eval_samples_per_second": 4555.98,
|
| 73 |
-
"eval_steps_per_second": 35.621,
|
| 74 |
-
"step": 1000
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.66,
|
| 78 |
-
"eval_accuracy": 0.8636615235591226,
|
| 79 |
-
"eval_f1": 0.8644557550999812,
|
| 80 |
-
"eval_loss": 0.3486252427101135,
|
| 81 |
-
"eval_matthews_correlation": 0.7956353553908341,
|
| 82 |
-
"eval_precision": 0.8673780104433669,
|
| 83 |
-
"eval_recall": 0.8639644349413246,
|
| 84 |
-
"eval_runtime": 6.3405,
|
| 85 |
-
"eval_samples_per_second": 4558.937,
|
| 86 |
-
"eval_steps_per_second": 35.644,
|
| 87 |
-
"step": 1200
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.77,
|
| 91 |
-
"eval_accuracy": 0.8695080606102539,
|
| 92 |
-
"eval_f1": 0.8708782475802734,
|
| 93 |
-
"eval_loss": 0.33812999725341797,
|
| 94 |
-
"eval_matthews_correlation": 0.8062736449316136,
|
| 95 |
-
"eval_precision": 0.8824955507055052,
|
| 96 |
-
"eval_recall": 0.8662050792886243,
|
| 97 |
-
"eval_runtime": 6.3436,
|
| 98 |
-
"eval_samples_per_second": 4556.722,
|
| 99 |
-
"eval_steps_per_second": 35.626,
|
| 100 |
-
"step": 1400
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.89,
|
| 104 |
-
"eval_accuracy": 0.8716183491316681,
|
| 105 |
-
"eval_f1": 0.8725799175076592,
|
| 106 |
-
"eval_loss": 0.3233429789543152,
|
| 107 |
-
"eval_matthews_correlation": 0.8117695247556368,
|
| 108 |
-
"eval_precision": 0.8882346109342674,
|
| 109 |
-
"eval_recall": 0.8682043569206126,
|
| 110 |
-
"eval_runtime": 6.346,
|
| 111 |
-
"eval_samples_per_second": 4554.983,
|
| 112 |
-
"eval_steps_per_second": 35.613,
|
| 113 |
-
"step": 1600
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.0,
|
| 117 |
-
"eval_accuracy": 0.8802670725800872,
|
| 118 |
-
"eval_f1": 0.881620826340297,
|
| 119 |
-
"eval_loss": 0.30727678537368774,
|
| 120 |
-
"eval_matthews_correlation": 0.8219755964705604,
|
| 121 |
-
"eval_precision": 0.8918194187219806,
|
| 122 |
-
"eval_recall": 0.8772345474322037,
|
| 123 |
-
"eval_runtime": 6.3575,
|
| 124 |
-
"eval_samples_per_second": 4546.76,
|
| 125 |
-
"eval_steps_per_second": 35.549,
|
| 126 |
-
"step": 1800
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.11,
|
| 130 |
-
"eval_accuracy": 0.8736248529717013,
|
| 131 |
-
"eval_f1": 0.8739366242458889,
|
| 132 |
-
"eval_loss": 0.3176397681236267,
|
| 133 |
-
"eval_matthews_correlation": 0.8135538952509183,
|
| 134 |
-
"eval_precision": 0.8854624405304454,
|
| 135 |
-
"eval_recall": 0.8713032592940723,
|
| 136 |
-
"eval_runtime": 6.3459,
|
| 137 |
-
"eval_samples_per_second": 4555.049,
|
| 138 |
-
"eval_steps_per_second": 35.613,
|
| 139 |
-
"step": 2000
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 1.22,
|
| 143 |
-
"eval_accuracy": 0.880716806199405,
|
| 144 |
-
"eval_f1": 0.8820312503884454,
|
| 145 |
-
"eval_loss": 0.299014687538147,
|
| 146 |
-
"eval_matthews_correlation": 0.8225911105391969,
|
| 147 |
-
"eval_precision": 0.8909735061827782,
|
| 148 |
-
"eval_recall": 0.8784169860223267,
|
| 149 |
-
"eval_runtime": 6.3464,
|
| 150 |
-
"eval_samples_per_second": 4554.71,
|
| 151 |
-
"eval_steps_per_second": 35.611,
|
| 152 |
-
"step": 2200
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 1.33,
|
| 156 |
-
"eval_accuracy": 0.8748010793606864,
|
| 157 |
-
"eval_f1": 0.8765959155083963,
|
| 158 |
-
"eval_loss": 0.3216623365879059,
|
| 159 |
-
"eval_matthews_correlation": 0.8123756375229486,
|
| 160 |
-
"eval_precision": 0.8829709241221156,
|
| 161 |
-
"eval_recall": 0.8731609901115246,
|
| 162 |
-
"eval_runtime": 6.3387,
|
| 163 |
-
"eval_samples_per_second": 4560.262,
|
| 164 |
-
"eval_steps_per_second": 35.654,
|
| 165 |
-
"step": 2400
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.44,
|
| 169 |
-
"eval_accuracy": 0.8805784266242302,
|
| 170 |
-
"eval_f1": 0.8812604347615175,
|
| 171 |
-
"eval_loss": 0.3023095726966858,
|
| 172 |
-
"eval_matthews_correlation": 0.824155509305865,
|
| 173 |
-
"eval_precision": 0.8934432959889177,
|
| 174 |
-
"eval_recall": 0.8779737927765034,
|
| 175 |
-
"eval_runtime": 6.3458,
|
| 176 |
-
"eval_samples_per_second": 4555.131,
|
| 177 |
-
"eval_steps_per_second": 35.614,
|
| 178 |
-
"step": 2600
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.55,
|
| 182 |
-
"eval_accuracy": 0.8804054521552619,
|
| 183 |
-
"eval_f1": 0.8813215210295723,
|
| 184 |
-
"eval_loss": 0.30079320073127747,
|
| 185 |
-
"eval_matthews_correlation": 0.8229950712381143,
|
| 186 |
-
"eval_precision": 0.8917063287499621,
|
| 187 |
-
"eval_recall": 0.8779790812790839,
|
| 188 |
-
"eval_runtime": 6.3485,
|
| 189 |
-
"eval_samples_per_second": 4553.191,
|
| 190 |
-
"eval_steps_per_second": 35.599,
|
| 191 |
-
"step": 2800
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.66,
|
| 195 |
-
"eval_accuracy": 0.8806130215180239,
|
| 196 |
-
"eval_f1": 0.8817485225868454,
|
| 197 |
-
"eval_loss": 0.3013697564601898,
|
| 198 |
-
"eval_matthews_correlation": 0.8233012680237078,
|
| 199 |
-
"eval_precision": 0.8923368722213673,
|
| 200 |
-
"eval_recall": 0.8781843708268702,
|
| 201 |
-
"eval_runtime": 6.3463,
|
| 202 |
-
"eval_samples_per_second": 4554.782,
|
| 203 |
-
"eval_steps_per_second": 35.611,
|
| 204 |
-
"step": 3000
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.77,
|
| 208 |
-
"eval_accuracy": 0.8814432989690721,
|
| 209 |
-
"eval_f1": 0.8820986799477435,
|
| 210 |
-
"eval_loss": 0.30195918679237366,
|
| 211 |
-
"eval_matthews_correlation": 0.8260716717379326,
|
| 212 |
-
"eval_precision": 0.8955726725923353,
|
| 213 |
-
"eval_recall": 0.8787927207636074,
|
| 214 |
-
"eval_runtime": 6.3486,
|
| 215 |
-
"eval_samples_per_second": 4553.098,
|
| 216 |
-
"eval_steps_per_second": 35.598,
|
| 217 |
-
"step": 3200
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 1.88,
|
| 221 |
-
"eval_accuracy": 0.8828270947208192,
|
| 222 |
-
"eval_f1": 0.8843593045330781,
|
| 223 |
-
"eval_loss": 0.2942578196525574,
|
| 224 |
-
"eval_matthews_correlation": 0.8254949003015292,
|
| 225 |
-
"eval_precision": 0.8931705740475805,
|
| 226 |
-
"eval_recall": 0.8804468671365364,
|
| 227 |
-
"eval_runtime": 6.3516,
|
| 228 |
-
"eval_samples_per_second": 4550.98,
|
| 229 |
-
"eval_steps_per_second": 35.582,
|
| 230 |
-
"step": 3400
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 1.99,
|
| 234 |
-
"eval_accuracy": 0.8834498028091053,
|
| 235 |
-
"eval_f1": 0.8853517689093603,
|
| 236 |
-
"eval_loss": 0.2914748787879944,
|
| 237 |
-
"eval_matthews_correlation": 0.8250598298158911,
|
| 238 |
-
"eval_precision": 0.8899549389399565,
|
| 239 |
-
"eval_recall": 0.8826443359241459,
|
| 240 |
-
"eval_runtime": 6.345,
|
| 241 |
-
"eval_samples_per_second": 4555.734,
|
| 242 |
-
"eval_steps_per_second": 35.619,
|
| 243 |
-
"step": 3600
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.1,
|
| 247 |
-
"eval_accuracy": 0.8774994810765931,
|
| 248 |
-
"eval_f1": 0.8799409536085404,
|
| 249 |
-
"eval_loss": 0.3131937086582184,
|
| 250 |
-
"eval_matthews_correlation": 0.8163052424476039,
|
| 251 |
-
"eval_precision": 0.8868617192793732,
|
| 252 |
-
"eval_recall": 0.8762445610028794,
|
| 253 |
-
"eval_runtime": 6.3474,
|
| 254 |
-
"eval_samples_per_second": 4554.0,
|
| 255 |
-
"eval_steps_per_second": 35.605,
|
| 256 |
-
"step": 3800
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 2.21,
|
| 260 |
-
"eval_accuracy": 0.8817546530132152,
|
| 261 |
-
"eval_f1": 0.8833254952872527,
|
| 262 |
-
"eval_loss": 0.3040480315685272,
|
| 263 |
-
"eval_matthews_correlation": 0.823572270376583,
|
| 264 |
-
"eval_precision": 0.8910821664820202,
|
| 265 |
-
"eval_recall": 0.8797695844721626,
|
| 266 |
-
"eval_runtime": 6.3469,
|
| 267 |
-
"eval_samples_per_second": 4554.377,
|
| 268 |
-
"eval_steps_per_second": 35.608,
|
| 269 |
-
"step": 4000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.32,
|
| 273 |
-
"eval_accuracy": 0.8851103577112018,
|
| 274 |
-
"eval_f1": 0.886748055608611,
|
| 275 |
-
"eval_loss": 0.2850874960422516,
|
| 276 |
-
"eval_matthews_correlation": 0.8291396132512627,
|
| 277 |
-
"eval_precision": 0.8962002468999266,
|
| 278 |
-
"eval_recall": 0.8826024405805053,
|
| 279 |
-
"eval_runtime": 6.4745,
|
| 280 |
-
"eval_samples_per_second": 4464.618,
|
| 281 |
-
"eval_steps_per_second": 34.906,
|
| 282 |
-
"step": 4200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 2.43,
|
| 286 |
-
"eval_accuracy": 0.8845914343042967,
|
| 287 |
-
"eval_f1": 0.8853347387941718,
|
| 288 |
-
"eval_loss": 0.2892882227897644,
|
| 289 |
-
"eval_matthews_correlation": 0.8296869725686938,
|
| 290 |
-
"eval_precision": 0.8957890161457024,
|
| 291 |
-
"eval_recall": 0.8827308326642206,
|
| 292 |
-
"eval_runtime": 6.3548,
|
| 293 |
-
"eval_samples_per_second": 4548.662,
|
| 294 |
-
"eval_steps_per_second": 35.563,
|
| 295 |
-
"step": 4400
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 2.55,
|
| 299 |
-
"eval_accuracy": 0.8872206462326161,
|
| 300 |
-
"eval_f1": 0.8889557188128973,
|
| 301 |
-
"eval_loss": 0.2861509919166565,
|
| 302 |
-
"eval_matthews_correlation": 0.8313848144209739,
|
| 303 |
-
"eval_precision": 0.8951641816931467,
|
| 304 |
-
"eval_recall": 0.8859209930430433,
|
| 305 |
-
"eval_runtime": 6.3537,
|
| 306 |
-
"eval_samples_per_second": 4549.45,
|
| 307 |
-
"eval_steps_per_second": 35.57,
|
| 308 |
-
"step": 4600
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.66,
|
| 312 |
-
"eval_accuracy": 0.8864941534629489,
|
| 313 |
-
"eval_f1": 0.8883772002833815,
|
| 314 |
-
"eval_loss": 0.28578662872314453,
|
| 315 |
-
"eval_matthews_correlation": 0.830142192696001,
|
| 316 |
-
"eval_precision": 0.894787668518915,
|
| 317 |
-
"eval_recall": 0.8850002671425831,
|
| 318 |
-
"eval_runtime": 6.3397,
|
| 319 |
-
"eval_samples_per_second": 4559.499,
|
| 320 |
-
"eval_steps_per_second": 35.648,
|
| 321 |
-
"step": 4800
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.77,
|
| 325 |
-
"eval_accuracy": 0.8869784819760603,
|
| 326 |
-
"eval_f1": 0.8881104845729881,
|
| 327 |
-
"eval_loss": 0.2903878390789032,
|
| 328 |
-
"eval_matthews_correlation": 0.8319666548642168,
|
| 329 |
-
"eval_precision": 0.8956943049005684,
|
| 330 |
-
"eval_recall": 0.8855419805052424,
|
| 331 |
-
"eval_runtime": 6.3478,
|
| 332 |
-
"eval_samples_per_second": 4553.673,
|
| 333 |
-
"eval_steps_per_second": 35.603,
|
| 334 |
-
"step": 5000
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 2.88,
|
| 338 |
-
"eval_accuracy": 0.8855946862243133,
|
| 339 |
-
"eval_f1": 0.8867414124351366,
|
| 340 |
-
"eval_loss": 0.2941598892211914,
|
| 341 |
-
"eval_matthews_correlation": 0.8292630776847024,
|
| 342 |
-
"eval_precision": 0.8920050610576892,
|
| 343 |
-
"eval_recall": 0.8851835923765252,
|
| 344 |
-
"eval_runtime": 6.3449,
|
| 345 |
-
"eval_samples_per_second": 4555.796,
|
| 346 |
-
"eval_steps_per_second": 35.619,
|
| 347 |
-
"step": 5200
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 2.99,
|
| 351 |
-
"eval_accuracy": 0.883380613021518,
|
| 352 |
-
"eval_f1": 0.8845550685672561,
|
| 353 |
-
"eval_loss": 0.3080594837665558,
|
| 354 |
-
"eval_matthews_correlation": 0.8287144630993116,
|
| 355 |
-
"eval_precision": 0.897977927261306,
|
| 356 |
-
"eval_recall": 0.8806022212949621,
|
| 357 |
-
"eval_runtime": 6.3495,
|
| 358 |
-
"eval_samples_per_second": 4552.496,
|
| 359 |
-
"eval_steps_per_second": 35.593,
|
| 360 |
-
"step": 5400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 3.1,
|
| 364 |
-
"eval_accuracy": 0.8915104130630319,
|
| 365 |
-
"eval_f1": 0.8927418464133509,
|
| 366 |
-
"eval_loss": 0.276968777179718,
|
| 367 |
-
"eval_matthews_correlation": 0.8386317937164508,
|
| 368 |
-
"eval_precision": 0.9004126472557267,
|
| 369 |
-
"eval_recall": 0.889725979370084,
|
| 370 |
-
"eval_runtime": 6.3476,
|
| 371 |
-
"eval_samples_per_second": 4553.844,
|
| 372 |
-
"eval_steps_per_second": 35.604,
|
| 373 |
-
"step": 5600
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 3.21,
|
| 377 |
-
"eval_accuracy": 0.8852141423925829,
|
| 378 |
-
"eval_f1": 0.8863096972005886,
|
| 379 |
-
"eval_loss": 0.29729557037353516,
|
| 380 |
-
"eval_matthews_correlation": 0.8310887046500933,
|
| 381 |
-
"eval_precision": 0.8986141701524222,
|
| 382 |
-
"eval_recall": 0.8826517914424513,
|
| 383 |
-
"eval_runtime": 6.3477,
|
| 384 |
-
"eval_samples_per_second": 4553.81,
|
| 385 |
-
"eval_steps_per_second": 35.604,
|
| 386 |
-
"step": 5800
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.32,
|
| 390 |
-
"eval_accuracy": 0.887116861551235,
|
| 391 |
-
"eval_f1": 0.8888119711547966,
|
| 392 |
-
"eval_loss": 0.2876887023448944,
|
| 393 |
-
"eval_matthews_correlation": 0.830566032986655,
|
| 394 |
-
"eval_precision": 0.8920331291977907,
|
| 395 |
-
"eval_recall": 0.8871405100672719,
|
| 396 |
-
"eval_runtime": 6.3516,
|
| 397 |
-
"eval_samples_per_second": 4550.948,
|
| 398 |
-
"eval_steps_per_second": 35.581,
|
| 399 |
-
"step": 6000
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.43,
|
| 403 |
-
"eval_accuracy": 0.8876703798519339,
|
| 404 |
-
"eval_f1": 0.8888683683886862,
|
| 405 |
-
"eval_loss": 0.28933295607566833,
|
| 406 |
-
"eval_matthews_correlation": 0.8318764323334562,
|
| 407 |
-
"eval_precision": 0.8932199703984821,
|
| 408 |
-
"eval_recall": 0.8871029140007725,
|
| 409 |
-
"eval_runtime": 6.3497,
|
| 410 |
-
"eval_samples_per_second": 4552.373,
|
| 411 |
-
"eval_steps_per_second": 35.592,
|
| 412 |
-
"step": 6200
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"epoch": 3.54,
|
| 416 |
-
"eval_accuracy": 0.8921677160451117,
|
| 417 |
-
"eval_f1": 0.8939685259834166,
|
| 418 |
-
"eval_loss": 0.2769826650619507,
|
| 419 |
-
"eval_matthews_correlation": 0.8391847958384606,
|
| 420 |
-
"eval_precision": 0.9010372712497707,
|
| 421 |
-
"eval_recall": 0.8907175246704687,
|
| 422 |
-
"eval_runtime": 6.3478,
|
| 423 |
-
"eval_samples_per_second": 4553.725,
|
| 424 |
-
"eval_steps_per_second": 35.603,
|
| 425 |
-
"step": 6400
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 3.65,
|
| 429 |
-
"eval_accuracy": 0.8892963398602366,
|
| 430 |
-
"eval_f1": 0.8903985649686311,
|
| 431 |
-
"eval_loss": 0.299304336309433,
|
| 432 |
-
"eval_matthews_correlation": 0.836403809775796,
|
| 433 |
-
"eval_precision": 0.9003904635902643,
|
| 434 |
-
"eval_recall": 0.8873298195093738,
|
| 435 |
-
"eval_runtime": 6.3585,
|
| 436 |
-
"eval_samples_per_second": 4546.028,
|
| 437 |
-
"eval_steps_per_second": 35.543,
|
| 438 |
-
"step": 6600
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 3.76,
|
| 442 |
-
"eval_accuracy": 0.8933439424340968,
|
| 443 |
-
"eval_f1": 0.8951626619118374,
|
| 444 |
-
"eval_loss": 0.272637277841568,
|
| 445 |
-
"eval_matthews_correlation": 0.840662237655687,
|
| 446 |
-
"eval_precision": 0.9018366964232629,
|
| 447 |
-
"eval_recall": 0.8918002056440489,
|
| 448 |
-
"eval_runtime": 6.3517,
|
| 449 |
-
"eval_samples_per_second": 4550.899,
|
| 450 |
-
"eval_steps_per_second": 35.581,
|
| 451 |
-
"step": 6800
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 3.87,
|
| 455 |
-
"eval_accuracy": 0.8931709679651283,
|
| 456 |
-
"eval_f1": 0.8946368515833566,
|
| 457 |
-
"eval_loss": 0.2683693766593933,
|
| 458 |
-
"eval_matthews_correlation": 0.840562081744003,
|
| 459 |
-
"eval_precision": 0.9005863314210352,
|
| 460 |
-
"eval_recall": 0.8921201829403151,
|
| 461 |
-
"eval_runtime": 6.3511,
|
| 462 |
-
"eval_samples_per_second": 4551.357,
|
| 463 |
-
"eval_steps_per_second": 35.585,
|
| 464 |
-
"step": 7000
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 3.98,
|
| 468 |
-
"eval_accuracy": 0.8879125441084896,
|
| 469 |
-
"eval_f1": 0.889596890077006,
|
| 470 |
-
"eval_loss": 0.3068075180053711,
|
| 471 |
-
"eval_matthews_correlation": 0.8330483801137644,
|
| 472 |
-
"eval_precision": 0.897851142355302,
|
| 473 |
-
"eval_recall": 0.8858787857808234,
|
| 474 |
-
"eval_runtime": 6.3428,
|
| 475 |
-
"eval_samples_per_second": 4557.324,
|
| 476 |
-
"eval_steps_per_second": 35.631,
|
| 477 |
-
"step": 7200
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 4.1,
|
| 481 |
-
"eval_accuracy": 0.8911990590188889,
|
| 482 |
-
"eval_f1": 0.8935331300113348,
|
| 483 |
-
"eval_loss": 0.2759658396244049,
|
| 484 |
-
"eval_matthews_correlation": 0.8364674339314426,
|
| 485 |
-
"eval_precision": 0.8974060023546162,
|
| 486 |
-
"eval_recall": 0.8909662141694983,
|
| 487 |
-
"eval_runtime": 6.3488,
|
| 488 |
-
"eval_samples_per_second": 4553.0,
|
| 489 |
-
"eval_steps_per_second": 35.597,
|
| 490 |
-
"step": 7400
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 4.21,
|
| 494 |
-
"eval_accuracy": 0.8914412232754445,
|
| 495 |
-
"eval_f1": 0.8929530705434039,
|
| 496 |
-
"eval_loss": 0.29881107807159424,
|
| 497 |
-
"eval_matthews_correlation": 0.8389342363530407,
|
| 498 |
-
"eval_precision": 0.9019665675237153,
|
| 499 |
-
"eval_recall": 0.8894376006796719,
|
| 500 |
-
"eval_runtime": 6.3502,
|
| 501 |
-
"eval_samples_per_second": 4551.977,
|
| 502 |
-
"eval_steps_per_second": 35.589,
|
| 503 |
-
"step": 7600
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 4.32,
|
| 507 |
-
"eval_accuracy": 0.8948661177610184,
|
| 508 |
-
"eval_f1": 0.8959730668841205,
|
| 509 |
-
"eval_loss": 0.2829718589782715,
|
| 510 |
-
"eval_matthews_correlation": 0.8440068382480527,
|
| 511 |
-
"eval_precision": 0.9037533187991164,
|
| 512 |
-
"eval_recall": 0.8934286935436152,
|
| 513 |
-
"eval_runtime": 6.35,
|
| 514 |
-
"eval_samples_per_second": 4552.153,
|
| 515 |
-
"eval_steps_per_second": 35.591,
|
| 516 |
-
"step": 7800
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 4.43,
|
| 520 |
-
"eval_accuracy": 0.892029336469937,
|
| 521 |
-
"eval_f1": 0.8929641996951606,
|
| 522 |
-
"eval_loss": 0.283554345369339,
|
| 523 |
-
"eval_matthews_correlation": 0.8403115181681976,
|
| 524 |
-
"eval_precision": 0.9019621982174025,
|
| 525 |
-
"eval_recall": 0.8904382553610669,
|
| 526 |
-
"eval_runtime": 6.3452,
|
| 527 |
-
"eval_samples_per_second": 4555.556,
|
| 528 |
-
"eval_steps_per_second": 35.617,
|
| 529 |
-
"step": 8000
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 4.54,
|
| 533 |
-
"eval_accuracy": 0.8894693143292051,
|
| 534 |
-
"eval_f1": 0.8908352587211786,
|
| 535 |
-
"eval_loss": 0.2885262072086334,
|
| 536 |
-
"eval_matthews_correlation": 0.8341511880621336,
|
| 537 |
-
"eval_precision": 0.893702095310492,
|
| 538 |
-
"eval_recall": 0.8895480253576511,
|
| 539 |
-
"eval_runtime": 6.3455,
|
| 540 |
-
"eval_samples_per_second": 4555.387,
|
| 541 |
-
"eval_steps_per_second": 35.616,
|
| 542 |
-
"step": 8200
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 4.65,
|
| 546 |
-
"eval_accuracy": 0.8926174496644296,
|
| 547 |
-
"eval_f1": 0.8945384185225222,
|
| 548 |
-
"eval_loss": 0.29022690653800964,
|
| 549 |
-
"eval_matthews_correlation": 0.8395314119561503,
|
| 550 |
-
"eval_precision": 0.9007178280331143,
|
| 551 |
-
"eval_recall": 0.8914918554407835,
|
| 552 |
-
"eval_runtime": 6.3512,
|
| 553 |
-
"eval_samples_per_second": 4551.274,
|
| 554 |
-
"eval_steps_per_second": 35.584,
|
| 555 |
-
"step": 8400
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 4.76,
|
| 559 |
-
"eval_accuracy": 0.8935515117968588,
|
| 560 |
-
"eval_f1": 0.8955843681536364,
|
| 561 |
-
"eval_loss": 0.27486342191696167,
|
| 562 |
-
"eval_matthews_correlation": 0.8401655549419715,
|
| 563 |
-
"eval_precision": 0.8991666173219651,
|
| 564 |
-
"eval_recall": 0.8934260432318405,
|
| 565 |
-
"eval_runtime": 6.3442,
|
| 566 |
-
"eval_samples_per_second": 4556.307,
|
| 567 |
-
"eval_steps_per_second": 35.623,
|
| 568 |
-
"step": 8600
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 4.87,
|
| 572 |
-
"eval_accuracy": 0.8906801356119837,
|
| 573 |
-
"eval_f1": 0.8918285607503583,
|
| 574 |
-
"eval_loss": 0.2898902893066406,
|
| 575 |
-
"eval_matthews_correlation": 0.8372224269539221,
|
| 576 |
-
"eval_precision": 0.8983664894121332,
|
| 577 |
-
"eval_recall": 0.8895837049920411,
|
| 578 |
-
"eval_runtime": 6.3478,
|
| 579 |
-
"eval_samples_per_second": 4553.724,
|
| 580 |
-
"eval_steps_per_second": 35.603,
|
| 581 |
-
"step": 8800
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 4.98,
|
| 585 |
-
"eval_accuracy": 0.894589358610669,
|
| 586 |
-
"eval_f1": 0.8963142222392254,
|
| 587 |
-
"eval_loss": 0.2670386731624603,
|
| 588 |
-
"eval_matthews_correlation": 0.8426090415821291,
|
| 589 |
-
"eval_precision": 0.9021919391864747,
|
| 590 |
-
"eval_recall": 0.8936817858774427,
|
| 591 |
-
"eval_runtime": 6.3552,
|
| 592 |
-
"eval_samples_per_second": 4548.416,
|
| 593 |
-
"eval_steps_per_second": 35.562,
|
| 594 |
-
"step": 9000
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 5.09,
|
| 598 |
-
"eval_accuracy": 0.8940012454161765,
|
| 599 |
-
"eval_f1": 0.8962328540662204,
|
| 600 |
-
"eval_loss": 0.2813003659248352,
|
| 601 |
-
"eval_matthews_correlation": 0.8408430518411678,
|
| 602 |
-
"eval_precision": 0.9002122855918167,
|
| 603 |
-
"eval_recall": 0.8937616724187407,
|
| 604 |
-
"eval_runtime": 6.3421,
|
| 605 |
-
"eval_samples_per_second": 4557.797,
|
| 606 |
-
"eval_steps_per_second": 35.635,
|
| 607 |
-
"step": 9200
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 5.2,
|
| 611 |
-
"eval_accuracy": 0.8945201688230817,
|
| 612 |
-
"eval_f1": 0.896372595139089,
|
| 613 |
-
"eval_loss": 0.29088279604911804,
|
| 614 |
-
"eval_matthews_correlation": 0.8425785711411811,
|
| 615 |
-
"eval_precision": 0.9033449643049775,
|
| 616 |
-
"eval_recall": 0.8929732798282033,
|
| 617 |
-
"eval_runtime": 6.3473,
|
| 618 |
-
"eval_samples_per_second": 4554.06,
|
| 619 |
-
"eval_steps_per_second": 35.606,
|
| 620 |
-
"step": 9400
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 5.31,
|
| 624 |
-
"eval_accuracy": 0.8900920224174912,
|
| 625 |
-
"eval_f1": 0.8925490010776985,
|
| 626 |
-
"eval_loss": 0.2760979235172272,
|
| 627 |
-
"eval_matthews_correlation": 0.8345731729452758,
|
| 628 |
-
"eval_precision": 0.8949331613162287,
|
| 629 |
-
"eval_recall": 0.8907497018848335,
|
| 630 |
-
"eval_runtime": 6.3444,
|
| 631 |
-
"eval_samples_per_second": 4556.156,
|
| 632 |
-
"eval_steps_per_second": 35.622,
|
| 633 |
-
"step": 9600
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 5.42,
|
| 637 |
-
"eval_accuracy": 0.8925482598768422,
|
| 638 |
-
"eval_f1": 0.8947835191299199,
|
| 639 |
-
"eval_loss": 0.28088074922561646,
|
| 640 |
-
"eval_matthews_correlation": 0.8388438694929189,
|
| 641 |
-
"eval_precision": 0.8999949588602486,
|
| 642 |
-
"eval_recall": 0.8916911075004866,
|
| 643 |
-
"eval_runtime": 6.3444,
|
| 644 |
-
"eval_samples_per_second": 4556.127,
|
| 645 |
-
"eval_steps_per_second": 35.622,
|
| 646 |
-
"step": 9800
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 5.53,
|
| 650 |
-
"eval_accuracy": 0.8938974607347956,
|
| 651 |
-
"eval_f1": 0.895398638281888,
|
| 652 |
-
"eval_loss": 0.2776396870613098,
|
| 653 |
-
"eval_matthews_correlation": 0.8415227982913265,
|
| 654 |
-
"eval_precision": 0.9005605054247868,
|
| 655 |
-
"eval_recall": 0.8933422240303471,
|
| 656 |
-
"eval_runtime": 6.3523,
|
| 657 |
-
"eval_samples_per_second": 4550.454,
|
| 658 |
-
"eval_steps_per_second": 35.577,
|
| 659 |
-
"step": 10000
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 5.64,
|
| 663 |
-
"eval_accuracy": 0.8931363730713346,
|
| 664 |
-
"eval_f1": 0.8951221715335156,
|
| 665 |
-
"eval_loss": 0.27086812257766724,
|
| 666 |
-
"eval_matthews_correlation": 0.8398759432599062,
|
| 667 |
-
"eval_precision": 0.8998458982098608,
|
| 668 |
-
"eval_recall": 0.8925756775800444,
|
| 669 |
-
"eval_runtime": 6.3515,
|
| 670 |
-
"eval_samples_per_second": 4551.066,
|
| 671 |
-
"eval_steps_per_second": 35.582,
|
| 672 |
-
"step": 10200
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 5.76,
|
| 676 |
-
"eval_accuracy": 0.8947969279734311,
|
| 677 |
-
"eval_f1": 0.8963386319413121,
|
| 678 |
-
"eval_loss": 0.2736610770225525,
|
| 679 |
-
"eval_matthews_correlation": 0.842492632054895,
|
| 680 |
-
"eval_precision": 0.9004512701810999,
|
| 681 |
-
"eval_recall": 0.8945058664025414,
|
| 682 |
-
"eval_runtime": 6.3449,
|
| 683 |
-
"eval_samples_per_second": 4555.8,
|
| 684 |
-
"eval_steps_per_second": 35.619,
|
| 685 |
-
"step": 10400
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 5.87,
|
| 689 |
-
"eval_accuracy": 0.8948315228672248,
|
| 690 |
-
"eval_f1": 0.8966390502710321,
|
| 691 |
-
"eval_loss": 0.2736780047416687,
|
| 692 |
-
"eval_matthews_correlation": 0.8428712666237889,
|
| 693 |
-
"eval_precision": 0.9023691050694266,
|
| 694 |
-
"eval_recall": 0.8939587990226933,
|
| 695 |
-
"eval_runtime": 6.3413,
|
| 696 |
-
"eval_samples_per_second": 4558.341,
|
| 697 |
-
"eval_steps_per_second": 35.639,
|
| 698 |
-
"step": 10600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 5.98,
|
| 702 |
-
"eval_accuracy": 0.8931363730713346,
|
| 703 |
-
"eval_f1": 0.8950074787412748,
|
| 704 |
-
"eval_loss": 0.2837923467159271,
|
| 705 |
-
"eval_matthews_correlation": 0.8398429954585677,
|
| 706 |
-
"eval_precision": 0.8990496284007606,
|
| 707 |
-
"eval_recall": 0.8929694613690722,
|
| 708 |
-
"eval_runtime": 6.3375,
|
| 709 |
-
"eval_samples_per_second": 4561.081,
|
| 710 |
-
"eval_steps_per_second": 35.661,
|
| 711 |
-
"step": 10800
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 6.09,
|
| 715 |
-
"eval_accuracy": 0.8954196360617173,
|
| 716 |
-
"eval_f1": 0.8973451839851609,
|
| 717 |
-
"eval_loss": 0.3019605278968811,
|
| 718 |
-
"eval_matthews_correlation": 0.8435324014450518,
|
| 719 |
-
"eval_precision": 0.9027250759780411,
|
| 720 |
-
"eval_recall": 0.8945897138524064,
|
| 721 |
-
"eval_runtime": 6.3337,
|
| 722 |
-
"eval_samples_per_second": 4563.855,
|
| 723 |
-
"eval_steps_per_second": 35.682,
|
| 724 |
-
"step": 11000
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 6.2,
|
| 728 |
-
"eval_accuracy": 0.8955926105306856,
|
| 729 |
-
"eval_f1": 0.8976165520302352,
|
| 730 |
-
"eval_loss": 0.28409114480018616,
|
| 731 |
-
"eval_matthews_correlation": 0.8434143843438346,
|
| 732 |
-
"eval_precision": 0.9018417545372985,
|
| 733 |
-
"eval_recall": 0.8952052020185916,
|
| 734 |
-
"eval_runtime": 6.3341,
|
| 735 |
-
"eval_samples_per_second": 4563.572,
|
| 736 |
-
"eval_steps_per_second": 35.68,
|
| 737 |
-
"step": 11200
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 6.31,
|
| 741 |
-
"eval_accuracy": 0.8942088147789387,
|
| 742 |
-
"eval_f1": 0.8962275448172298,
|
| 743 |
-
"eval_loss": 0.2877649962902069,
|
| 744 |
-
"eval_matthews_correlation": 0.8414441696511311,
|
| 745 |
-
"eval_precision": 0.9008599634610711,
|
| 746 |
-
"eval_recall": 0.8936762031162221,
|
| 747 |
-
"eval_runtime": 6.3475,
|
| 748 |
-
"eval_samples_per_second": 4553.948,
|
| 749 |
-
"eval_steps_per_second": 35.605,
|
| 750 |
-
"step": 11400
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 6.42,
|
| 754 |
-
"eval_accuracy": 0.8951428769113678,
|
| 755 |
-
"eval_f1": 0.8970215166114972,
|
| 756 |
-
"eval_loss": 0.2961738705635071,
|
| 757 |
-
"eval_matthews_correlation": 0.8436724995526438,
|
| 758 |
-
"eval_precision": 0.9039960508124899,
|
| 759 |
-
"eval_recall": 0.8938297040688856,
|
| 760 |
-
"eval_runtime": 6.3515,
|
| 761 |
-
"eval_samples_per_second": 4551.073,
|
| 762 |
-
"eval_steps_per_second": 35.582,
|
| 763 |
-
"step": 11600
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 6.53,
|
| 767 |
-
"eval_accuracy": 0.8945201688230817,
|
| 768 |
-
"eval_f1": 0.896067746079448,
|
| 769 |
-
"eval_loss": 0.2976745069026947,
|
| 770 |
-
"eval_matthews_correlation": 0.8422089454909583,
|
| 771 |
-
"eval_precision": 0.900607068182845,
|
| 772 |
-
"eval_recall": 0.8941007596668359,
|
| 773 |
-
"eval_runtime": 6.3472,
|
| 774 |
-
"eval_samples_per_second": 4554.135,
|
| 775 |
-
"eval_steps_per_second": 35.606,
|
| 776 |
-
"step": 11800
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 6.64,
|
| 780 |
-
"eval_accuracy": 0.8949699024423995,
|
| 781 |
-
"eval_f1": 0.8966124169391811,
|
| 782 |
-
"eval_loss": 0.3018077313899994,
|
| 783 |
-
"eval_matthews_correlation": 0.843195325699096,
|
| 784 |
-
"eval_precision": 0.9022254172778311,
|
| 785 |
-
"eval_recall": 0.8942367845271998,
|
| 786 |
-
"eval_runtime": 6.3482,
|
| 787 |
-
"eval_samples_per_second": 4553.382,
|
| 788 |
-
"eval_steps_per_second": 35.6,
|
| 789 |
-
"step": 12000
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 6.75,
|
| 793 |
-
"eval_accuracy": 0.8965612675569086,
|
| 794 |
-
"eval_f1": 0.8980147217678764,
|
| 795 |
-
"eval_loss": 0.2901879847049713,
|
| 796 |
-
"eval_matthews_correlation": 0.8460130614687257,
|
| 797 |
-
"eval_precision": 0.9045943000787302,
|
| 798 |
-
"eval_recall": 0.8955196899577702,
|
| 799 |
-
"eval_runtime": 6.3504,
|
| 800 |
-
"eval_samples_per_second": 4551.837,
|
| 801 |
-
"eval_steps_per_second": 35.588,
|
| 802 |
-
"step": 12200
|
| 803 |
-
},
|
| 804 |
-
{
|
| 805 |
-
"epoch": 6.86,
|
| 806 |
-
"eval_accuracy": 0.8952466615927489,
|
| 807 |
-
"eval_f1": 0.8969830622390469,
|
| 808 |
-
"eval_loss": 0.28876444697380066,
|
| 809 |
-
"eval_matthews_correlation": 0.843325620330125,
|
| 810 |
-
"eval_precision": 0.9020159665987951,
|
| 811 |
-
"eval_recall": 0.8946102670938186,
|
| 812 |
-
"eval_runtime": 6.3475,
|
| 813 |
-
"eval_samples_per_second": 4553.949,
|
| 814 |
-
"eval_steps_per_second": 35.605,
|
| 815 |
-
"step": 12400
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 6.97,
|
| 819 |
-
"eval_accuracy": 0.8957655849996541,
|
| 820 |
-
"eval_f1": 0.8975933967455741,
|
| 821 |
-
"eval_loss": 0.29665452241897583,
|
| 822 |
-
"eval_matthews_correlation": 0.8442236370657304,
|
| 823 |
-
"eval_precision": 0.9033635307429947,
|
| 824 |
-
"eval_recall": 0.8947879834373609,
|
| 825 |
-
"eval_runtime": 6.35,
|
| 826 |
-
"eval_samples_per_second": 4552.142,
|
| 827 |
-
"eval_steps_per_second": 35.591,
|
| 828 |
-
"step": 12600
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 7.08,
|
| 832 |
-
"eval_accuracy": 0.8939666505223829,
|
| 833 |
-
"eval_f1": 0.8957790534277574,
|
| 834 |
-
"eval_loss": 0.304647296667099,
|
| 835 |
-
"eval_matthews_correlation": 0.8413818654606173,
|
| 836 |
-
"eval_precision": 0.9007642360078177,
|
| 837 |
-
"eval_recall": 0.8934286441944405,
|
| 838 |
-
"eval_runtime": 6.3482,
|
| 839 |
-
"eval_samples_per_second": 4553.44,
|
| 840 |
-
"eval_steps_per_second": 35.601,
|
| 841 |
-
"step": 12800
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 7.19,
|
| 845 |
-
"eval_accuracy": 0.8926174496644296,
|
| 846 |
-
"eval_f1": 0.8949385390749803,
|
| 847 |
-
"eval_loss": 0.3034723401069641,
|
| 848 |
-
"eval_matthews_correlation": 0.8383426049270595,
|
| 849 |
-
"eval_precision": 0.8967244149264713,
|
| 850 |
-
"eval_recall": 0.8935341705656276,
|
| 851 |
-
"eval_runtime": 6.3556,
|
| 852 |
-
"eval_samples_per_second": 4548.082,
|
| 853 |
-
"eval_steps_per_second": 35.559,
|
| 854 |
-
"step": 13000
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 7.3,
|
| 858 |
-
"eval_accuracy": 0.8947969279734311,
|
| 859 |
-
"eval_f1": 0.8965284578579703,
|
| 860 |
-
"eval_loss": 0.30462202429771423,
|
| 861 |
-
"eval_matthews_correlation": 0.8426157749546105,
|
| 862 |
-
"eval_precision": 0.9013431538946532,
|
| 863 |
-
"eval_recall": 0.8942934909424061,
|
| 864 |
-
"eval_runtime": 6.3507,
|
| 865 |
-
"eval_samples_per_second": 4551.603,
|
| 866 |
-
"eval_steps_per_second": 35.586,
|
| 867 |
-
"step": 13200
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 7.42,
|
| 871 |
-
"eval_accuracy": 0.8934477271154777,
|
| 872 |
-
"eval_f1": 0.8958814405265977,
|
| 873 |
-
"eval_loss": 0.299685001373291,
|
| 874 |
-
"eval_matthews_correlation": 0.8396708845009517,
|
| 875 |
-
"eval_precision": 0.8985110508247799,
|
| 876 |
-
"eval_recall": 0.8939504661367766,
|
| 877 |
-
"eval_runtime": 6.3494,
|
| 878 |
-
"eval_samples_per_second": 4552.561,
|
| 879 |
-
"eval_steps_per_second": 35.594,
|
| 880 |
-
"step": 13400
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 7.53,
|
| 884 |
-
"eval_accuracy": 0.8938974607347956,
|
| 885 |
-
"eval_f1": 0.8961079255659018,
|
| 886 |
-
"eval_loss": 0.3028521239757538,
|
| 887 |
-
"eval_matthews_correlation": 0.8405174595632917,
|
| 888 |
-
"eval_precision": 0.8993065072128195,
|
| 889 |
-
"eval_recall": 0.8939928380088323,
|
| 890 |
-
"eval_runtime": 6.3445,
|
| 891 |
-
"eval_samples_per_second": 4556.093,
|
| 892 |
-
"eval_steps_per_second": 35.622,
|
| 893 |
-
"step": 13600
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 7.64,
|
| 897 |
-
"eval_accuracy": 0.894278004566526,
|
| 898 |
-
"eval_f1": 0.8962846524625201,
|
| 899 |
-
"eval_loss": 0.3031056523323059,
|
| 900 |
-
"eval_matthews_correlation": 0.8413679820721595,
|
| 901 |
-
"eval_precision": 0.9000326135737255,
|
| 902 |
-
"eval_recall": 0.8941623447064746,
|
| 903 |
-
"eval_runtime": 6.347,
|
| 904 |
-
"eval_samples_per_second": 4554.311,
|
| 905 |
-
"eval_steps_per_second": 35.608,
|
| 906 |
-
"step": 13800
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 7.75,
|
| 910 |
-
"eval_accuracy": 0.8944509790354943,
|
| 911 |
-
"eval_f1": 0.896655360738317,
|
| 912 |
-
"eval_loss": 0.30069831013679504,
|
| 913 |
-
"eval_matthews_correlation": 0.8414004425422017,
|
| 914 |
-
"eval_precision": 0.9000426273245656,
|
| 915 |
-
"eval_recall": 0.8944645030033757,
|
| 916 |
-
"eval_runtime": 6.3449,
|
| 917 |
-
"eval_samples_per_second": 4555.813,
|
| 918 |
-
"eval_steps_per_second": 35.619,
|
| 919 |
-
"step": 14000
|
| 920 |
-
}
|
| 921 |
-
],
|
| 922 |
-
"logging_steps": 100000,
|
| 923 |
-
"max_steps": 14456,
|
| 924 |
-
"num_train_epochs": 8,
|
| 925 |
-
"save_steps": 200,
|
| 926 |
-
"total_flos": 1.6849254895897805e+17,
|
| 927 |
-
"trial_name": null,
|
| 928 |
-
"trial_params": null
|
| 929 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:35ecc48e034f0e45faedb4e2252a3cdc71427f9c360fb025c1c72e33d2555eef
|
| 3 |
-
size 5329
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/root/NaN/dna-tokenizer/pretrain/models/base_4096/checkpoint-100000",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"BertForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"classifier_dropout": null,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0",
|
| 13 |
-
"1": "LABEL_1",
|
| 14 |
-
"2": "LABEL_2"
|
| 15 |
-
},
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"LABEL_0": 0,
|
| 20 |
-
"LABEL_1": 1,
|
| 21 |
-
"LABEL_2": 2
|
| 22 |
-
},
|
| 23 |
-
"layer_norm_eps": 1e-12,
|
| 24 |
-
"max_length": 512,
|
| 25 |
-
"max_position_embeddings": 512,
|
| 26 |
-
"model_type": "bert",
|
| 27 |
-
"num_attention_heads": 12,
|
| 28 |
-
"num_hidden_layers": 12,
|
| 29 |
-
"pad_token_id": 0,
|
| 30 |
-
"position_embedding_type": "absolute",
|
| 31 |
-
"problem_type": "single_label_classification",
|
| 32 |
-
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.35.2",
|
| 34 |
-
"type_vocab_size": 2,
|
| 35 |
-
"use_cache": true,
|
| 36 |
-
"vocab_size": 4096
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5888ec2ec10923ce095e75e270418f223a20cef6c8b6394d610e29f6f7cdec1f
|
| 3 |
-
size 356780956
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:64a83f7537e07f8eb00e5709e3efdb5d7541a66f7057454bdfca7aff597cf390
|
| 3 |
-
size 713683595
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:76521f3f133b1747165ff05dc4f4fbf0b59ad2ba923a01671bede88cce0b4b04
|
| 3 |
-
size 14709
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:424bc014ae1834ecf77bdcbd150ed65e58466a7228efde858a0c097c9e0b3ce2
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/tokenizer_config.json
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 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 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"cache_dir": null,
|
| 45 |
-
"clean_up_tokenization_spaces": true,
|
| 46 |
-
"cls_token": "[CLS]",
|
| 47 |
-
"mask_token": "[MASK]",
|
| 48 |
-
"model_max_length": 250,
|
| 49 |
-
"pad_token": "[PAD]",
|
| 50 |
-
"padding_side": "right",
|
| 51 |
-
"sep_token": "[SEP]",
|
| 52 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 53 |
-
"trust_remote_code": true,
|
| 54 |
-
"unk_token": "[UNK]",
|
| 55 |
-
"use_fast": true
|
| 56 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
human_ensembl_regulatory/base_4096/checkpoint-14200/trainer_state.json
DELETED
|
@@ -1,942 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.858328721638074,
|
| 5 |
-
"eval_steps": 200,
|
| 6 |
-
"global_step": 14200,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.11,
|
| 13 |
-
"eval_accuracy": 0.8032588389953643,
|
| 14 |
-
"eval_f1": 0.8040452040692839,
|
| 15 |
-
"eval_loss": 0.4966795742511749,
|
| 16 |
-
"eval_matthews_correlation": 0.7084695952717522,
|
| 17 |
-
"eval_precision": 0.8237857718753817,
|
| 18 |
-
"eval_recall": 0.7975870988019708,
|
| 19 |
-
"eval_runtime": 6.3588,
|
| 20 |
-
"eval_samples_per_second": 4545.791,
|
| 21 |
-
"eval_steps_per_second": 35.541,
|
| 22 |
-
"step": 200
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"epoch": 0.22,
|
| 26 |
-
"eval_accuracy": 0.82806337784543,
|
| 27 |
-
"eval_f1": 0.8297094326097825,
|
| 28 |
-
"eval_loss": 0.4289039373397827,
|
| 29 |
-
"eval_matthews_correlation": 0.741876074078984,
|
| 30 |
-
"eval_precision": 0.8349242792396575,
|
| 31 |
-
"eval_recall": 0.8272187509320483,
|
| 32 |
-
"eval_runtime": 6.3568,
|
| 33 |
-
"eval_samples_per_second": 4547.233,
|
| 34 |
-
"eval_steps_per_second": 35.552,
|
| 35 |
-
"step": 400
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 0.33,
|
| 39 |
-
"eval_accuracy": 0.8440116238843147,
|
| 40 |
-
"eval_f1": 0.8450100684587841,
|
| 41 |
-
"eval_loss": 0.39371800422668457,
|
| 42 |
-
"eval_matthews_correlation": 0.7660039268807652,
|
| 43 |
-
"eval_precision": 0.85273319305628,
|
| 44 |
-
"eval_recall": 0.8412884667434676,
|
| 45 |
-
"eval_runtime": 6.3475,
|
| 46 |
-
"eval_samples_per_second": 4553.913,
|
| 47 |
-
"eval_steps_per_second": 35.605,
|
| 48 |
-
"step": 600
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.44,
|
| 52 |
-
"eval_accuracy": 0.8603058188611361,
|
| 53 |
-
"eval_f1": 0.8611020118054533,
|
| 54 |
-
"eval_loss": 0.35088762640953064,
|
| 55 |
-
"eval_matthews_correlation": 0.7927956332205198,
|
| 56 |
-
"eval_precision": 0.8723391365103108,
|
| 57 |
-
"eval_recall": 0.8574792991725344,
|
| 58 |
-
"eval_runtime": 6.3447,
|
| 59 |
-
"eval_samples_per_second": 4555.963,
|
| 60 |
-
"eval_steps_per_second": 35.621,
|
| 61 |
-
"step": 800
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.55,
|
| 65 |
-
"eval_accuracy": 0.8377153532138656,
|
| 66 |
-
"eval_f1": 0.8413461677606797,
|
| 67 |
-
"eval_loss": 0.379434198141098,
|
| 68 |
-
"eval_matthews_correlation": 0.7580192865676064,
|
| 69 |
-
"eval_precision": 0.8474953423917877,
|
| 70 |
-
"eval_recall": 0.8400608374251649,
|
| 71 |
-
"eval_runtime": 6.3446,
|
| 72 |
-
"eval_samples_per_second": 4555.98,
|
| 73 |
-
"eval_steps_per_second": 35.621,
|
| 74 |
-
"step": 1000
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.66,
|
| 78 |
-
"eval_accuracy": 0.8636615235591226,
|
| 79 |
-
"eval_f1": 0.8644557550999812,
|
| 80 |
-
"eval_loss": 0.3486252427101135,
|
| 81 |
-
"eval_matthews_correlation": 0.7956353553908341,
|
| 82 |
-
"eval_precision": 0.8673780104433669,
|
| 83 |
-
"eval_recall": 0.8639644349413246,
|
| 84 |
-
"eval_runtime": 6.3405,
|
| 85 |
-
"eval_samples_per_second": 4558.937,
|
| 86 |
-
"eval_steps_per_second": 35.644,
|
| 87 |
-
"step": 1200
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.77,
|
| 91 |
-
"eval_accuracy": 0.8695080606102539,
|
| 92 |
-
"eval_f1": 0.8708782475802734,
|
| 93 |
-
"eval_loss": 0.33812999725341797,
|
| 94 |
-
"eval_matthews_correlation": 0.8062736449316136,
|
| 95 |
-
"eval_precision": 0.8824955507055052,
|
| 96 |
-
"eval_recall": 0.8662050792886243,
|
| 97 |
-
"eval_runtime": 6.3436,
|
| 98 |
-
"eval_samples_per_second": 4556.722,
|
| 99 |
-
"eval_steps_per_second": 35.626,
|
| 100 |
-
"step": 1400
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.89,
|
| 104 |
-
"eval_accuracy": 0.8716183491316681,
|
| 105 |
-
"eval_f1": 0.8725799175076592,
|
| 106 |
-
"eval_loss": 0.3233429789543152,
|
| 107 |
-
"eval_matthews_correlation": 0.8117695247556368,
|
| 108 |
-
"eval_precision": 0.8882346109342674,
|
| 109 |
-
"eval_recall": 0.8682043569206126,
|
| 110 |
-
"eval_runtime": 6.346,
|
| 111 |
-
"eval_samples_per_second": 4554.983,
|
| 112 |
-
"eval_steps_per_second": 35.613,
|
| 113 |
-
"step": 1600
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.0,
|
| 117 |
-
"eval_accuracy": 0.8802670725800872,
|
| 118 |
-
"eval_f1": 0.881620826340297,
|
| 119 |
-
"eval_loss": 0.30727678537368774,
|
| 120 |
-
"eval_matthews_correlation": 0.8219755964705604,
|
| 121 |
-
"eval_precision": 0.8918194187219806,
|
| 122 |
-
"eval_recall": 0.8772345474322037,
|
| 123 |
-
"eval_runtime": 6.3575,
|
| 124 |
-
"eval_samples_per_second": 4546.76,
|
| 125 |
-
"eval_steps_per_second": 35.549,
|
| 126 |
-
"step": 1800
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.11,
|
| 130 |
-
"eval_accuracy": 0.8736248529717013,
|
| 131 |
-
"eval_f1": 0.8739366242458889,
|
| 132 |
-
"eval_loss": 0.3176397681236267,
|
| 133 |
-
"eval_matthews_correlation": 0.8135538952509183,
|
| 134 |
-
"eval_precision": 0.8854624405304454,
|
| 135 |
-
"eval_recall": 0.8713032592940723,
|
| 136 |
-
"eval_runtime": 6.3459,
|
| 137 |
-
"eval_samples_per_second": 4555.049,
|
| 138 |
-
"eval_steps_per_second": 35.613,
|
| 139 |
-
"step": 2000
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 1.22,
|
| 143 |
-
"eval_accuracy": 0.880716806199405,
|
| 144 |
-
"eval_f1": 0.8820312503884454,
|
| 145 |
-
"eval_loss": 0.299014687538147,
|
| 146 |
-
"eval_matthews_correlation": 0.8225911105391969,
|
| 147 |
-
"eval_precision": 0.8909735061827782,
|
| 148 |
-
"eval_recall": 0.8784169860223267,
|
| 149 |
-
"eval_runtime": 6.3464,
|
| 150 |
-
"eval_samples_per_second": 4554.71,
|
| 151 |
-
"eval_steps_per_second": 35.611,
|
| 152 |
-
"step": 2200
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 1.33,
|
| 156 |
-
"eval_accuracy": 0.8748010793606864,
|
| 157 |
-
"eval_f1": 0.8765959155083963,
|
| 158 |
-
"eval_loss": 0.3216623365879059,
|
| 159 |
-
"eval_matthews_correlation": 0.8123756375229486,
|
| 160 |
-
"eval_precision": 0.8829709241221156,
|
| 161 |
-
"eval_recall": 0.8731609901115246,
|
| 162 |
-
"eval_runtime": 6.3387,
|
| 163 |
-
"eval_samples_per_second": 4560.262,
|
| 164 |
-
"eval_steps_per_second": 35.654,
|
| 165 |
-
"step": 2400
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.44,
|
| 169 |
-
"eval_accuracy": 0.8805784266242302,
|
| 170 |
-
"eval_f1": 0.8812604347615175,
|
| 171 |
-
"eval_loss": 0.3023095726966858,
|
| 172 |
-
"eval_matthews_correlation": 0.824155509305865,
|
| 173 |
-
"eval_precision": 0.8934432959889177,
|
| 174 |
-
"eval_recall": 0.8779737927765034,
|
| 175 |
-
"eval_runtime": 6.3458,
|
| 176 |
-
"eval_samples_per_second": 4555.131,
|
| 177 |
-
"eval_steps_per_second": 35.614,
|
| 178 |
-
"step": 2600
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.55,
|
| 182 |
-
"eval_accuracy": 0.8804054521552619,
|
| 183 |
-
"eval_f1": 0.8813215210295723,
|
| 184 |
-
"eval_loss": 0.30079320073127747,
|
| 185 |
-
"eval_matthews_correlation": 0.8229950712381143,
|
| 186 |
-
"eval_precision": 0.8917063287499621,
|
| 187 |
-
"eval_recall": 0.8779790812790839,
|
| 188 |
-
"eval_runtime": 6.3485,
|
| 189 |
-
"eval_samples_per_second": 4553.191,
|
| 190 |
-
"eval_steps_per_second": 35.599,
|
| 191 |
-
"step": 2800
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.66,
|
| 195 |
-
"eval_accuracy": 0.8806130215180239,
|
| 196 |
-
"eval_f1": 0.8817485225868454,
|
| 197 |
-
"eval_loss": 0.3013697564601898,
|
| 198 |
-
"eval_matthews_correlation": 0.8233012680237078,
|
| 199 |
-
"eval_precision": 0.8923368722213673,
|
| 200 |
-
"eval_recall": 0.8781843708268702,
|
| 201 |
-
"eval_runtime": 6.3463,
|
| 202 |
-
"eval_samples_per_second": 4554.782,
|
| 203 |
-
"eval_steps_per_second": 35.611,
|
| 204 |
-
"step": 3000
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.77,
|
| 208 |
-
"eval_accuracy": 0.8814432989690721,
|
| 209 |
-
"eval_f1": 0.8820986799477435,
|
| 210 |
-
"eval_loss": 0.30195918679237366,
|
| 211 |
-
"eval_matthews_correlation": 0.8260716717379326,
|
| 212 |
-
"eval_precision": 0.8955726725923353,
|
| 213 |
-
"eval_recall": 0.8787927207636074,
|
| 214 |
-
"eval_runtime": 6.3486,
|
| 215 |
-
"eval_samples_per_second": 4553.098,
|
| 216 |
-
"eval_steps_per_second": 35.598,
|
| 217 |
-
"step": 3200
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 1.88,
|
| 221 |
-
"eval_accuracy": 0.8828270947208192,
|
| 222 |
-
"eval_f1": 0.8843593045330781,
|
| 223 |
-
"eval_loss": 0.2942578196525574,
|
| 224 |
-
"eval_matthews_correlation": 0.8254949003015292,
|
| 225 |
-
"eval_precision": 0.8931705740475805,
|
| 226 |
-
"eval_recall": 0.8804468671365364,
|
| 227 |
-
"eval_runtime": 6.3516,
|
| 228 |
-
"eval_samples_per_second": 4550.98,
|
| 229 |
-
"eval_steps_per_second": 35.582,
|
| 230 |
-
"step": 3400
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 1.99,
|
| 234 |
-
"eval_accuracy": 0.8834498028091053,
|
| 235 |
-
"eval_f1": 0.8853517689093603,
|
| 236 |
-
"eval_loss": 0.2914748787879944,
|
| 237 |
-
"eval_matthews_correlation": 0.8250598298158911,
|
| 238 |
-
"eval_precision": 0.8899549389399565,
|
| 239 |
-
"eval_recall": 0.8826443359241459,
|
| 240 |
-
"eval_runtime": 6.345,
|
| 241 |
-
"eval_samples_per_second": 4555.734,
|
| 242 |
-
"eval_steps_per_second": 35.619,
|
| 243 |
-
"step": 3600
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.1,
|
| 247 |
-
"eval_accuracy": 0.8774994810765931,
|
| 248 |
-
"eval_f1": 0.8799409536085404,
|
| 249 |
-
"eval_loss": 0.3131937086582184,
|
| 250 |
-
"eval_matthews_correlation": 0.8163052424476039,
|
| 251 |
-
"eval_precision": 0.8868617192793732,
|
| 252 |
-
"eval_recall": 0.8762445610028794,
|
| 253 |
-
"eval_runtime": 6.3474,
|
| 254 |
-
"eval_samples_per_second": 4554.0,
|
| 255 |
-
"eval_steps_per_second": 35.605,
|
| 256 |
-
"step": 3800
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 2.21,
|
| 260 |
-
"eval_accuracy": 0.8817546530132152,
|
| 261 |
-
"eval_f1": 0.8833254952872527,
|
| 262 |
-
"eval_loss": 0.3040480315685272,
|
| 263 |
-
"eval_matthews_correlation": 0.823572270376583,
|
| 264 |
-
"eval_precision": 0.8910821664820202,
|
| 265 |
-
"eval_recall": 0.8797695844721626,
|
| 266 |
-
"eval_runtime": 6.3469,
|
| 267 |
-
"eval_samples_per_second": 4554.377,
|
| 268 |
-
"eval_steps_per_second": 35.608,
|
| 269 |
-
"step": 4000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.32,
|
| 273 |
-
"eval_accuracy": 0.8851103577112018,
|
| 274 |
-
"eval_f1": 0.886748055608611,
|
| 275 |
-
"eval_loss": 0.2850874960422516,
|
| 276 |
-
"eval_matthews_correlation": 0.8291396132512627,
|
| 277 |
-
"eval_precision": 0.8962002468999266,
|
| 278 |
-
"eval_recall": 0.8826024405805053,
|
| 279 |
-
"eval_runtime": 6.4745,
|
| 280 |
-
"eval_samples_per_second": 4464.618,
|
| 281 |
-
"eval_steps_per_second": 34.906,
|
| 282 |
-
"step": 4200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 2.43,
|
| 286 |
-
"eval_accuracy": 0.8845914343042967,
|
| 287 |
-
"eval_f1": 0.8853347387941718,
|
| 288 |
-
"eval_loss": 0.2892882227897644,
|
| 289 |
-
"eval_matthews_correlation": 0.8296869725686938,
|
| 290 |
-
"eval_precision": 0.8957890161457024,
|
| 291 |
-
"eval_recall": 0.8827308326642206,
|
| 292 |
-
"eval_runtime": 6.3548,
|
| 293 |
-
"eval_samples_per_second": 4548.662,
|
| 294 |
-
"eval_steps_per_second": 35.563,
|
| 295 |
-
"step": 4400
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 2.55,
|
| 299 |
-
"eval_accuracy": 0.8872206462326161,
|
| 300 |
-
"eval_f1": 0.8889557188128973,
|
| 301 |
-
"eval_loss": 0.2861509919166565,
|
| 302 |
-
"eval_matthews_correlation": 0.8313848144209739,
|
| 303 |
-
"eval_precision": 0.8951641816931467,
|
| 304 |
-
"eval_recall": 0.8859209930430433,
|
| 305 |
-
"eval_runtime": 6.3537,
|
| 306 |
-
"eval_samples_per_second": 4549.45,
|
| 307 |
-
"eval_steps_per_second": 35.57,
|
| 308 |
-
"step": 4600
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.66,
|
| 312 |
-
"eval_accuracy": 0.8864941534629489,
|
| 313 |
-
"eval_f1": 0.8883772002833815,
|
| 314 |
-
"eval_loss": 0.28578662872314453,
|
| 315 |
-
"eval_matthews_correlation": 0.830142192696001,
|
| 316 |
-
"eval_precision": 0.894787668518915,
|
| 317 |
-
"eval_recall": 0.8850002671425831,
|
| 318 |
-
"eval_runtime": 6.3397,
|
| 319 |
-
"eval_samples_per_second": 4559.499,
|
| 320 |
-
"eval_steps_per_second": 35.648,
|
| 321 |
-
"step": 4800
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.77,
|
| 325 |
-
"eval_accuracy": 0.8869784819760603,
|
| 326 |
-
"eval_f1": 0.8881104845729881,
|
| 327 |
-
"eval_loss": 0.2903878390789032,
|
| 328 |
-
"eval_matthews_correlation": 0.8319666548642168,
|
| 329 |
-
"eval_precision": 0.8956943049005684,
|
| 330 |
-
"eval_recall": 0.8855419805052424,
|
| 331 |
-
"eval_runtime": 6.3478,
|
| 332 |
-
"eval_samples_per_second": 4553.673,
|
| 333 |
-
"eval_steps_per_second": 35.603,
|
| 334 |
-
"step": 5000
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 2.88,
|
| 338 |
-
"eval_accuracy": 0.8855946862243133,
|
| 339 |
-
"eval_f1": 0.8867414124351366,
|
| 340 |
-
"eval_loss": 0.2941598892211914,
|
| 341 |
-
"eval_matthews_correlation": 0.8292630776847024,
|
| 342 |
-
"eval_precision": 0.8920050610576892,
|
| 343 |
-
"eval_recall": 0.8851835923765252,
|
| 344 |
-
"eval_runtime": 6.3449,
|
| 345 |
-
"eval_samples_per_second": 4555.796,
|
| 346 |
-
"eval_steps_per_second": 35.619,
|
| 347 |
-
"step": 5200
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 2.99,
|
| 351 |
-
"eval_accuracy": 0.883380613021518,
|
| 352 |
-
"eval_f1": 0.8845550685672561,
|
| 353 |
-
"eval_loss": 0.3080594837665558,
|
| 354 |
-
"eval_matthews_correlation": 0.8287144630993116,
|
| 355 |
-
"eval_precision": 0.897977927261306,
|
| 356 |
-
"eval_recall": 0.8806022212949621,
|
| 357 |
-
"eval_runtime": 6.3495,
|
| 358 |
-
"eval_samples_per_second": 4552.496,
|
| 359 |
-
"eval_steps_per_second": 35.593,
|
| 360 |
-
"step": 5400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 3.1,
|
| 364 |
-
"eval_accuracy": 0.8915104130630319,
|
| 365 |
-
"eval_f1": 0.8927418464133509,
|
| 366 |
-
"eval_loss": 0.276968777179718,
|
| 367 |
-
"eval_matthews_correlation": 0.8386317937164508,
|
| 368 |
-
"eval_precision": 0.9004126472557267,
|
| 369 |
-
"eval_recall": 0.889725979370084,
|
| 370 |
-
"eval_runtime": 6.3476,
|
| 371 |
-
"eval_samples_per_second": 4553.844,
|
| 372 |
-
"eval_steps_per_second": 35.604,
|
| 373 |
-
"step": 5600
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 3.21,
|
| 377 |
-
"eval_accuracy": 0.8852141423925829,
|
| 378 |
-
"eval_f1": 0.8863096972005886,
|
| 379 |
-
"eval_loss": 0.29729557037353516,
|
| 380 |
-
"eval_matthews_correlation": 0.8310887046500933,
|
| 381 |
-
"eval_precision": 0.8986141701524222,
|
| 382 |
-
"eval_recall": 0.8826517914424513,
|
| 383 |
-
"eval_runtime": 6.3477,
|
| 384 |
-
"eval_samples_per_second": 4553.81,
|
| 385 |
-
"eval_steps_per_second": 35.604,
|
| 386 |
-
"step": 5800
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.32,
|
| 390 |
-
"eval_accuracy": 0.887116861551235,
|
| 391 |
-
"eval_f1": 0.8888119711547966,
|
| 392 |
-
"eval_loss": 0.2876887023448944,
|
| 393 |
-
"eval_matthews_correlation": 0.830566032986655,
|
| 394 |
-
"eval_precision": 0.8920331291977907,
|
| 395 |
-
"eval_recall": 0.8871405100672719,
|
| 396 |
-
"eval_runtime": 6.3516,
|
| 397 |
-
"eval_samples_per_second": 4550.948,
|
| 398 |
-
"eval_steps_per_second": 35.581,
|
| 399 |
-
"step": 6000
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.43,
|
| 403 |
-
"eval_accuracy": 0.8876703798519339,
|
| 404 |
-
"eval_f1": 0.8888683683886862,
|
| 405 |
-
"eval_loss": 0.28933295607566833,
|
| 406 |
-
"eval_matthews_correlation": 0.8318764323334562,
|
| 407 |
-
"eval_precision": 0.8932199703984821,
|
| 408 |
-
"eval_recall": 0.8871029140007725,
|
| 409 |
-
"eval_runtime": 6.3497,
|
| 410 |
-
"eval_samples_per_second": 4552.373,
|
| 411 |
-
"eval_steps_per_second": 35.592,
|
| 412 |
-
"step": 6200
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"epoch": 3.54,
|
| 416 |
-
"eval_accuracy": 0.8921677160451117,
|
| 417 |
-
"eval_f1": 0.8939685259834166,
|
| 418 |
-
"eval_loss": 0.2769826650619507,
|
| 419 |
-
"eval_matthews_correlation": 0.8391847958384606,
|
| 420 |
-
"eval_precision": 0.9010372712497707,
|
| 421 |
-
"eval_recall": 0.8907175246704687,
|
| 422 |
-
"eval_runtime": 6.3478,
|
| 423 |
-
"eval_samples_per_second": 4553.725,
|
| 424 |
-
"eval_steps_per_second": 35.603,
|
| 425 |
-
"step": 6400
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 3.65,
|
| 429 |
-
"eval_accuracy": 0.8892963398602366,
|
| 430 |
-
"eval_f1": 0.8903985649686311,
|
| 431 |
-
"eval_loss": 0.299304336309433,
|
| 432 |
-
"eval_matthews_correlation": 0.836403809775796,
|
| 433 |
-
"eval_precision": 0.9003904635902643,
|
| 434 |
-
"eval_recall": 0.8873298195093738,
|
| 435 |
-
"eval_runtime": 6.3585,
|
| 436 |
-
"eval_samples_per_second": 4546.028,
|
| 437 |
-
"eval_steps_per_second": 35.543,
|
| 438 |
-
"step": 6600
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 3.76,
|
| 442 |
-
"eval_accuracy": 0.8933439424340968,
|
| 443 |
-
"eval_f1": 0.8951626619118374,
|
| 444 |
-
"eval_loss": 0.272637277841568,
|
| 445 |
-
"eval_matthews_correlation": 0.840662237655687,
|
| 446 |
-
"eval_precision": 0.9018366964232629,
|
| 447 |
-
"eval_recall": 0.8918002056440489,
|
| 448 |
-
"eval_runtime": 6.3517,
|
| 449 |
-
"eval_samples_per_second": 4550.899,
|
| 450 |
-
"eval_steps_per_second": 35.581,
|
| 451 |
-
"step": 6800
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 3.87,
|
| 455 |
-
"eval_accuracy": 0.8931709679651283,
|
| 456 |
-
"eval_f1": 0.8946368515833566,
|
| 457 |
-
"eval_loss": 0.2683693766593933,
|
| 458 |
-
"eval_matthews_correlation": 0.840562081744003,
|
| 459 |
-
"eval_precision": 0.9005863314210352,
|
| 460 |
-
"eval_recall": 0.8921201829403151,
|
| 461 |
-
"eval_runtime": 6.3511,
|
| 462 |
-
"eval_samples_per_second": 4551.357,
|
| 463 |
-
"eval_steps_per_second": 35.585,
|
| 464 |
-
"step": 7000
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 3.98,
|
| 468 |
-
"eval_accuracy": 0.8879125441084896,
|
| 469 |
-
"eval_f1": 0.889596890077006,
|
| 470 |
-
"eval_loss": 0.3068075180053711,
|
| 471 |
-
"eval_matthews_correlation": 0.8330483801137644,
|
| 472 |
-
"eval_precision": 0.897851142355302,
|
| 473 |
-
"eval_recall": 0.8858787857808234,
|
| 474 |
-
"eval_runtime": 6.3428,
|
| 475 |
-
"eval_samples_per_second": 4557.324,
|
| 476 |
-
"eval_steps_per_second": 35.631,
|
| 477 |
-
"step": 7200
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 4.1,
|
| 481 |
-
"eval_accuracy": 0.8911990590188889,
|
| 482 |
-
"eval_f1": 0.8935331300113348,
|
| 483 |
-
"eval_loss": 0.2759658396244049,
|
| 484 |
-
"eval_matthews_correlation": 0.8364674339314426,
|
| 485 |
-
"eval_precision": 0.8974060023546162,
|
| 486 |
-
"eval_recall": 0.8909662141694983,
|
| 487 |
-
"eval_runtime": 6.3488,
|
| 488 |
-
"eval_samples_per_second": 4553.0,
|
| 489 |
-
"eval_steps_per_second": 35.597,
|
| 490 |
-
"step": 7400
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 4.21,
|
| 494 |
-
"eval_accuracy": 0.8914412232754445,
|
| 495 |
-
"eval_f1": 0.8929530705434039,
|
| 496 |
-
"eval_loss": 0.29881107807159424,
|
| 497 |
-
"eval_matthews_correlation": 0.8389342363530407,
|
| 498 |
-
"eval_precision": 0.9019665675237153,
|
| 499 |
-
"eval_recall": 0.8894376006796719,
|
| 500 |
-
"eval_runtime": 6.3502,
|
| 501 |
-
"eval_samples_per_second": 4551.977,
|
| 502 |
-
"eval_steps_per_second": 35.589,
|
| 503 |
-
"step": 7600
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 4.32,
|
| 507 |
-
"eval_accuracy": 0.8948661177610184,
|
| 508 |
-
"eval_f1": 0.8959730668841205,
|
| 509 |
-
"eval_loss": 0.2829718589782715,
|
| 510 |
-
"eval_matthews_correlation": 0.8440068382480527,
|
| 511 |
-
"eval_precision": 0.9037533187991164,
|
| 512 |
-
"eval_recall": 0.8934286935436152,
|
| 513 |
-
"eval_runtime": 6.35,
|
| 514 |
-
"eval_samples_per_second": 4552.153,
|
| 515 |
-
"eval_steps_per_second": 35.591,
|
| 516 |
-
"step": 7800
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 4.43,
|
| 520 |
-
"eval_accuracy": 0.892029336469937,
|
| 521 |
-
"eval_f1": 0.8929641996951606,
|
| 522 |
-
"eval_loss": 0.283554345369339,
|
| 523 |
-
"eval_matthews_correlation": 0.8403115181681976,
|
| 524 |
-
"eval_precision": 0.9019621982174025,
|
| 525 |
-
"eval_recall": 0.8904382553610669,
|
| 526 |
-
"eval_runtime": 6.3452,
|
| 527 |
-
"eval_samples_per_second": 4555.556,
|
| 528 |
-
"eval_steps_per_second": 35.617,
|
| 529 |
-
"step": 8000
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 4.54,
|
| 533 |
-
"eval_accuracy": 0.8894693143292051,
|
| 534 |
-
"eval_f1": 0.8908352587211786,
|
| 535 |
-
"eval_loss": 0.2885262072086334,
|
| 536 |
-
"eval_matthews_correlation": 0.8341511880621336,
|
| 537 |
-
"eval_precision": 0.893702095310492,
|
| 538 |
-
"eval_recall": 0.8895480253576511,
|
| 539 |
-
"eval_runtime": 6.3455,
|
| 540 |
-
"eval_samples_per_second": 4555.387,
|
| 541 |
-
"eval_steps_per_second": 35.616,
|
| 542 |
-
"step": 8200
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 4.65,
|
| 546 |
-
"eval_accuracy": 0.8926174496644296,
|
| 547 |
-
"eval_f1": 0.8945384185225222,
|
| 548 |
-
"eval_loss": 0.29022690653800964,
|
| 549 |
-
"eval_matthews_correlation": 0.8395314119561503,
|
| 550 |
-
"eval_precision": 0.9007178280331143,
|
| 551 |
-
"eval_recall": 0.8914918554407835,
|
| 552 |
-
"eval_runtime": 6.3512,
|
| 553 |
-
"eval_samples_per_second": 4551.274,
|
| 554 |
-
"eval_steps_per_second": 35.584,
|
| 555 |
-
"step": 8400
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 4.76,
|
| 559 |
-
"eval_accuracy": 0.8935515117968588,
|
| 560 |
-
"eval_f1": 0.8955843681536364,
|
| 561 |
-
"eval_loss": 0.27486342191696167,
|
| 562 |
-
"eval_matthews_correlation": 0.8401655549419715,
|
| 563 |
-
"eval_precision": 0.8991666173219651,
|
| 564 |
-
"eval_recall": 0.8934260432318405,
|
| 565 |
-
"eval_runtime": 6.3442,
|
| 566 |
-
"eval_samples_per_second": 4556.307,
|
| 567 |
-
"eval_steps_per_second": 35.623,
|
| 568 |
-
"step": 8600
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 4.87,
|
| 572 |
-
"eval_accuracy": 0.8906801356119837,
|
| 573 |
-
"eval_f1": 0.8918285607503583,
|
| 574 |
-
"eval_loss": 0.2898902893066406,
|
| 575 |
-
"eval_matthews_correlation": 0.8372224269539221,
|
| 576 |
-
"eval_precision": 0.8983664894121332,
|
| 577 |
-
"eval_recall": 0.8895837049920411,
|
| 578 |
-
"eval_runtime": 6.3478,
|
| 579 |
-
"eval_samples_per_second": 4553.724,
|
| 580 |
-
"eval_steps_per_second": 35.603,
|
| 581 |
-
"step": 8800
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 4.98,
|
| 585 |
-
"eval_accuracy": 0.894589358610669,
|
| 586 |
-
"eval_f1": 0.8963142222392254,
|
| 587 |
-
"eval_loss": 0.2670386731624603,
|
| 588 |
-
"eval_matthews_correlation": 0.8426090415821291,
|
| 589 |
-
"eval_precision": 0.9021919391864747,
|
| 590 |
-
"eval_recall": 0.8936817858774427,
|
| 591 |
-
"eval_runtime": 6.3552,
|
| 592 |
-
"eval_samples_per_second": 4548.416,
|
| 593 |
-
"eval_steps_per_second": 35.562,
|
| 594 |
-
"step": 9000
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 5.09,
|
| 598 |
-
"eval_accuracy": 0.8940012454161765,
|
| 599 |
-
"eval_f1": 0.8962328540662204,
|
| 600 |
-
"eval_loss": 0.2813003659248352,
|
| 601 |
-
"eval_matthews_correlation": 0.8408430518411678,
|
| 602 |
-
"eval_precision": 0.9002122855918167,
|
| 603 |
-
"eval_recall": 0.8937616724187407,
|
| 604 |
-
"eval_runtime": 6.3421,
|
| 605 |
-
"eval_samples_per_second": 4557.797,
|
| 606 |
-
"eval_steps_per_second": 35.635,
|
| 607 |
-
"step": 9200
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 5.2,
|
| 611 |
-
"eval_accuracy": 0.8945201688230817,
|
| 612 |
-
"eval_f1": 0.896372595139089,
|
| 613 |
-
"eval_loss": 0.29088279604911804,
|
| 614 |
-
"eval_matthews_correlation": 0.8425785711411811,
|
| 615 |
-
"eval_precision": 0.9033449643049775,
|
| 616 |
-
"eval_recall": 0.8929732798282033,
|
| 617 |
-
"eval_runtime": 6.3473,
|
| 618 |
-
"eval_samples_per_second": 4554.06,
|
| 619 |
-
"eval_steps_per_second": 35.606,
|
| 620 |
-
"step": 9400
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 5.31,
|
| 624 |
-
"eval_accuracy": 0.8900920224174912,
|
| 625 |
-
"eval_f1": 0.8925490010776985,
|
| 626 |
-
"eval_loss": 0.2760979235172272,
|
| 627 |
-
"eval_matthews_correlation": 0.8345731729452758,
|
| 628 |
-
"eval_precision": 0.8949331613162287,
|
| 629 |
-
"eval_recall": 0.8907497018848335,
|
| 630 |
-
"eval_runtime": 6.3444,
|
| 631 |
-
"eval_samples_per_second": 4556.156,
|
| 632 |
-
"eval_steps_per_second": 35.622,
|
| 633 |
-
"step": 9600
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 5.42,
|
| 637 |
-
"eval_accuracy": 0.8925482598768422,
|
| 638 |
-
"eval_f1": 0.8947835191299199,
|
| 639 |
-
"eval_loss": 0.28088074922561646,
|
| 640 |
-
"eval_matthews_correlation": 0.8388438694929189,
|
| 641 |
-
"eval_precision": 0.8999949588602486,
|
| 642 |
-
"eval_recall": 0.8916911075004866,
|
| 643 |
-
"eval_runtime": 6.3444,
|
| 644 |
-
"eval_samples_per_second": 4556.127,
|
| 645 |
-
"eval_steps_per_second": 35.622,
|
| 646 |
-
"step": 9800
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 5.53,
|
| 650 |
-
"eval_accuracy": 0.8938974607347956,
|
| 651 |
-
"eval_f1": 0.895398638281888,
|
| 652 |
-
"eval_loss": 0.2776396870613098,
|
| 653 |
-
"eval_matthews_correlation": 0.8415227982913265,
|
| 654 |
-
"eval_precision": 0.9005605054247868,
|
| 655 |
-
"eval_recall": 0.8933422240303471,
|
| 656 |
-
"eval_runtime": 6.3523,
|
| 657 |
-
"eval_samples_per_second": 4550.454,
|
| 658 |
-
"eval_steps_per_second": 35.577,
|
| 659 |
-
"step": 10000
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 5.64,
|
| 663 |
-
"eval_accuracy": 0.8931363730713346,
|
| 664 |
-
"eval_f1": 0.8951221715335156,
|
| 665 |
-
"eval_loss": 0.27086812257766724,
|
| 666 |
-
"eval_matthews_correlation": 0.8398759432599062,
|
| 667 |
-
"eval_precision": 0.8998458982098608,
|
| 668 |
-
"eval_recall": 0.8925756775800444,
|
| 669 |
-
"eval_runtime": 6.3515,
|
| 670 |
-
"eval_samples_per_second": 4551.066,
|
| 671 |
-
"eval_steps_per_second": 35.582,
|
| 672 |
-
"step": 10200
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 5.76,
|
| 676 |
-
"eval_accuracy": 0.8947969279734311,
|
| 677 |
-
"eval_f1": 0.8963386319413121,
|
| 678 |
-
"eval_loss": 0.2736610770225525,
|
| 679 |
-
"eval_matthews_correlation": 0.842492632054895,
|
| 680 |
-
"eval_precision": 0.9004512701810999,
|
| 681 |
-
"eval_recall": 0.8945058664025414,
|
| 682 |
-
"eval_runtime": 6.3449,
|
| 683 |
-
"eval_samples_per_second": 4555.8,
|
| 684 |
-
"eval_steps_per_second": 35.619,
|
| 685 |
-
"step": 10400
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 5.87,
|
| 689 |
-
"eval_accuracy": 0.8948315228672248,
|
| 690 |
-
"eval_f1": 0.8966390502710321,
|
| 691 |
-
"eval_loss": 0.2736780047416687,
|
| 692 |
-
"eval_matthews_correlation": 0.8428712666237889,
|
| 693 |
-
"eval_precision": 0.9023691050694266,
|
| 694 |
-
"eval_recall": 0.8939587990226933,
|
| 695 |
-
"eval_runtime": 6.3413,
|
| 696 |
-
"eval_samples_per_second": 4558.341,
|
| 697 |
-
"eval_steps_per_second": 35.639,
|
| 698 |
-
"step": 10600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 5.98,
|
| 702 |
-
"eval_accuracy": 0.8931363730713346,
|
| 703 |
-
"eval_f1": 0.8950074787412748,
|
| 704 |
-
"eval_loss": 0.2837923467159271,
|
| 705 |
-
"eval_matthews_correlation": 0.8398429954585677,
|
| 706 |
-
"eval_precision": 0.8990496284007606,
|
| 707 |
-
"eval_recall": 0.8929694613690722,
|
| 708 |
-
"eval_runtime": 6.3375,
|
| 709 |
-
"eval_samples_per_second": 4561.081,
|
| 710 |
-
"eval_steps_per_second": 35.661,
|
| 711 |
-
"step": 10800
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 6.09,
|
| 715 |
-
"eval_accuracy": 0.8954196360617173,
|
| 716 |
-
"eval_f1": 0.8973451839851609,
|
| 717 |
-
"eval_loss": 0.3019605278968811,
|
| 718 |
-
"eval_matthews_correlation": 0.8435324014450518,
|
| 719 |
-
"eval_precision": 0.9027250759780411,
|
| 720 |
-
"eval_recall": 0.8945897138524064,
|
| 721 |
-
"eval_runtime": 6.3337,
|
| 722 |
-
"eval_samples_per_second": 4563.855,
|
| 723 |
-
"eval_steps_per_second": 35.682,
|
| 724 |
-
"step": 11000
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 6.2,
|
| 728 |
-
"eval_accuracy": 0.8955926105306856,
|
| 729 |
-
"eval_f1": 0.8976165520302352,
|
| 730 |
-
"eval_loss": 0.28409114480018616,
|
| 731 |
-
"eval_matthews_correlation": 0.8434143843438346,
|
| 732 |
-
"eval_precision": 0.9018417545372985,
|
| 733 |
-
"eval_recall": 0.8952052020185916,
|
| 734 |
-
"eval_runtime": 6.3341,
|
| 735 |
-
"eval_samples_per_second": 4563.572,
|
| 736 |
-
"eval_steps_per_second": 35.68,
|
| 737 |
-
"step": 11200
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 6.31,
|
| 741 |
-
"eval_accuracy": 0.8942088147789387,
|
| 742 |
-
"eval_f1": 0.8962275448172298,
|
| 743 |
-
"eval_loss": 0.2877649962902069,
|
| 744 |
-
"eval_matthews_correlation": 0.8414441696511311,
|
| 745 |
-
"eval_precision": 0.9008599634610711,
|
| 746 |
-
"eval_recall": 0.8936762031162221,
|
| 747 |
-
"eval_runtime": 6.3475,
|
| 748 |
-
"eval_samples_per_second": 4553.948,
|
| 749 |
-
"eval_steps_per_second": 35.605,
|
| 750 |
-
"step": 11400
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 6.42,
|
| 754 |
-
"eval_accuracy": 0.8951428769113678,
|
| 755 |
-
"eval_f1": 0.8970215166114972,
|
| 756 |
-
"eval_loss": 0.2961738705635071,
|
| 757 |
-
"eval_matthews_correlation": 0.8436724995526438,
|
| 758 |
-
"eval_precision": 0.9039960508124899,
|
| 759 |
-
"eval_recall": 0.8938297040688856,
|
| 760 |
-
"eval_runtime": 6.3515,
|
| 761 |
-
"eval_samples_per_second": 4551.073,
|
| 762 |
-
"eval_steps_per_second": 35.582,
|
| 763 |
-
"step": 11600
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 6.53,
|
| 767 |
-
"eval_accuracy": 0.8945201688230817,
|
| 768 |
-
"eval_f1": 0.896067746079448,
|
| 769 |
-
"eval_loss": 0.2976745069026947,
|
| 770 |
-
"eval_matthews_correlation": 0.8422089454909583,
|
| 771 |
-
"eval_precision": 0.900607068182845,
|
| 772 |
-
"eval_recall": 0.8941007596668359,
|
| 773 |
-
"eval_runtime": 6.3472,
|
| 774 |
-
"eval_samples_per_second": 4554.135,
|
| 775 |
-
"eval_steps_per_second": 35.606,
|
| 776 |
-
"step": 11800
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 6.64,
|
| 780 |
-
"eval_accuracy": 0.8949699024423995,
|
| 781 |
-
"eval_f1": 0.8966124169391811,
|
| 782 |
-
"eval_loss": 0.3018077313899994,
|
| 783 |
-
"eval_matthews_correlation": 0.843195325699096,
|
| 784 |
-
"eval_precision": 0.9022254172778311,
|
| 785 |
-
"eval_recall": 0.8942367845271998,
|
| 786 |
-
"eval_runtime": 6.3482,
|
| 787 |
-
"eval_samples_per_second": 4553.382,
|
| 788 |
-
"eval_steps_per_second": 35.6,
|
| 789 |
-
"step": 12000
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 6.75,
|
| 793 |
-
"eval_accuracy": 0.8965612675569086,
|
| 794 |
-
"eval_f1": 0.8980147217678764,
|
| 795 |
-
"eval_loss": 0.2901879847049713,
|
| 796 |
-
"eval_matthews_correlation": 0.8460130614687257,
|
| 797 |
-
"eval_precision": 0.9045943000787302,
|
| 798 |
-
"eval_recall": 0.8955196899577702,
|
| 799 |
-
"eval_runtime": 6.3504,
|
| 800 |
-
"eval_samples_per_second": 4551.837,
|
| 801 |
-
"eval_steps_per_second": 35.588,
|
| 802 |
-
"step": 12200
|
| 803 |
-
},
|
| 804 |
-
{
|
| 805 |
-
"epoch": 6.86,
|
| 806 |
-
"eval_accuracy": 0.8952466615927489,
|
| 807 |
-
"eval_f1": 0.8969830622390469,
|
| 808 |
-
"eval_loss": 0.28876444697380066,
|
| 809 |
-
"eval_matthews_correlation": 0.843325620330125,
|
| 810 |
-
"eval_precision": 0.9020159665987951,
|
| 811 |
-
"eval_recall": 0.8946102670938186,
|
| 812 |
-
"eval_runtime": 6.3475,
|
| 813 |
-
"eval_samples_per_second": 4553.949,
|
| 814 |
-
"eval_steps_per_second": 35.605,
|
| 815 |
-
"step": 12400
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 6.97,
|
| 819 |
-
"eval_accuracy": 0.8957655849996541,
|
| 820 |
-
"eval_f1": 0.8975933967455741,
|
| 821 |
-
"eval_loss": 0.29665452241897583,
|
| 822 |
-
"eval_matthews_correlation": 0.8442236370657304,
|
| 823 |
-
"eval_precision": 0.9033635307429947,
|
| 824 |
-
"eval_recall": 0.8947879834373609,
|
| 825 |
-
"eval_runtime": 6.35,
|
| 826 |
-
"eval_samples_per_second": 4552.142,
|
| 827 |
-
"eval_steps_per_second": 35.591,
|
| 828 |
-
"step": 12600
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 7.08,
|
| 832 |
-
"eval_accuracy": 0.8939666505223829,
|
| 833 |
-
"eval_f1": 0.8957790534277574,
|
| 834 |
-
"eval_loss": 0.304647296667099,
|
| 835 |
-
"eval_matthews_correlation": 0.8413818654606173,
|
| 836 |
-
"eval_precision": 0.9007642360078177,
|
| 837 |
-
"eval_recall": 0.8934286441944405,
|
| 838 |
-
"eval_runtime": 6.3482,
|
| 839 |
-
"eval_samples_per_second": 4553.44,
|
| 840 |
-
"eval_steps_per_second": 35.601,
|
| 841 |
-
"step": 12800
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 7.19,
|
| 845 |
-
"eval_accuracy": 0.8926174496644296,
|
| 846 |
-
"eval_f1": 0.8949385390749803,
|
| 847 |
-
"eval_loss": 0.3034723401069641,
|
| 848 |
-
"eval_matthews_correlation": 0.8383426049270595,
|
| 849 |
-
"eval_precision": 0.8967244149264713,
|
| 850 |
-
"eval_recall": 0.8935341705656276,
|
| 851 |
-
"eval_runtime": 6.3556,
|
| 852 |
-
"eval_samples_per_second": 4548.082,
|
| 853 |
-
"eval_steps_per_second": 35.559,
|
| 854 |
-
"step": 13000
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 7.3,
|
| 858 |
-
"eval_accuracy": 0.8947969279734311,
|
| 859 |
-
"eval_f1": 0.8965284578579703,
|
| 860 |
-
"eval_loss": 0.30462202429771423,
|
| 861 |
-
"eval_matthews_correlation": 0.8426157749546105,
|
| 862 |
-
"eval_precision": 0.9013431538946532,
|
| 863 |
-
"eval_recall": 0.8942934909424061,
|
| 864 |
-
"eval_runtime": 6.3507,
|
| 865 |
-
"eval_samples_per_second": 4551.603,
|
| 866 |
-
"eval_steps_per_second": 35.586,
|
| 867 |
-
"step": 13200
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 7.42,
|
| 871 |
-
"eval_accuracy": 0.8934477271154777,
|
| 872 |
-
"eval_f1": 0.8958814405265977,
|
| 873 |
-
"eval_loss": 0.299685001373291,
|
| 874 |
-
"eval_matthews_correlation": 0.8396708845009517,
|
| 875 |
-
"eval_precision": 0.8985110508247799,
|
| 876 |
-
"eval_recall": 0.8939504661367766,
|
| 877 |
-
"eval_runtime": 6.3494,
|
| 878 |
-
"eval_samples_per_second": 4552.561,
|
| 879 |
-
"eval_steps_per_second": 35.594,
|
| 880 |
-
"step": 13400
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 7.53,
|
| 884 |
-
"eval_accuracy": 0.8938974607347956,
|
| 885 |
-
"eval_f1": 0.8961079255659018,
|
| 886 |
-
"eval_loss": 0.3028521239757538,
|
| 887 |
-
"eval_matthews_correlation": 0.8405174595632917,
|
| 888 |
-
"eval_precision": 0.8993065072128195,
|
| 889 |
-
"eval_recall": 0.8939928380088323,
|
| 890 |
-
"eval_runtime": 6.3445,
|
| 891 |
-
"eval_samples_per_second": 4556.093,
|
| 892 |
-
"eval_steps_per_second": 35.622,
|
| 893 |
-
"step": 13600
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 7.64,
|
| 897 |
-
"eval_accuracy": 0.894278004566526,
|
| 898 |
-
"eval_f1": 0.8962846524625201,
|
| 899 |
-
"eval_loss": 0.3031056523323059,
|
| 900 |
-
"eval_matthews_correlation": 0.8413679820721595,
|
| 901 |
-
"eval_precision": 0.9000326135737255,
|
| 902 |
-
"eval_recall": 0.8941623447064746,
|
| 903 |
-
"eval_runtime": 6.347,
|
| 904 |
-
"eval_samples_per_second": 4554.311,
|
| 905 |
-
"eval_steps_per_second": 35.608,
|
| 906 |
-
"step": 13800
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 7.75,
|
| 910 |
-
"eval_accuracy": 0.8944509790354943,
|
| 911 |
-
"eval_f1": 0.896655360738317,
|
| 912 |
-
"eval_loss": 0.30069831013679504,
|
| 913 |
-
"eval_matthews_correlation": 0.8414004425422017,
|
| 914 |
-
"eval_precision": 0.9000426273245656,
|
| 915 |
-
"eval_recall": 0.8944645030033757,
|
| 916 |
-
"eval_runtime": 6.3449,
|
| 917 |
-
"eval_samples_per_second": 4555.813,
|
| 918 |
-
"eval_steps_per_second": 35.619,
|
| 919 |
-
"step": 14000
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 7.86,
|
| 923 |
-
"eval_accuracy": 0.8940012454161765,
|
| 924 |
-
"eval_f1": 0.896075552743726,
|
| 925 |
-
"eval_loss": 0.2992590367794037,
|
| 926 |
-
"eval_matthews_correlation": 0.8408500391716258,
|
| 927 |
-
"eval_precision": 0.8996765901137117,
|
| 928 |
-
"eval_recall": 0.8939131985891992,
|
| 929 |
-
"eval_runtime": 6.3468,
|
| 930 |
-
"eval_samples_per_second": 4554.403,
|
| 931 |
-
"eval_steps_per_second": 35.608,
|
| 932 |
-
"step": 14200
|
| 933 |
-
}
|
| 934 |
-
],
|
| 935 |
-
"logging_steps": 100000,
|
| 936 |
-
"max_steps": 14456,
|
| 937 |
-
"num_train_epochs": 8,
|
| 938 |
-
"save_steps": 200,
|
| 939 |
-
"total_flos": 1.7090003677374054e+17,
|
| 940 |
-
"trial_name": null,
|
| 941 |
-
"trial_params": null
|
| 942 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|