Model save
Browse files- checkpoint-1630/config.json +41 -0
- checkpoint-1630/optimizer.pt +3 -0
- checkpoint-1630/pytorch_model.bin +3 -0
- checkpoint-1630/rng_state.pth +3 -0
- checkpoint-1630/scaler.pt +3 -0
- checkpoint-1630/scheduler.pt +3 -0
- checkpoint-1630/special_tokens_map.json +1 -0
- checkpoint-1630/tokenizer.json +0 -0
- checkpoint-1630/tokenizer_config.json +1 -0
- checkpoint-1630/trainer_state.json +176 -0
- checkpoint-1630/training_args.bin +3 -0
- checkpoint-1630/vocab.txt +0 -0
- checkpoint-1793/config.json +41 -0
- checkpoint-1793/optimizer.pt +3 -0
- checkpoint-1793/pytorch_model.bin +3 -0
- checkpoint-1793/rng_state.pth +3 -0
- checkpoint-1793/scaler.pt +3 -0
- checkpoint-1793/scheduler.pt +3 -0
- checkpoint-1793/special_tokens_map.json +1 -0
- checkpoint-1793/tokenizer.json +0 -0
- checkpoint-1793/tokenizer_config.json +1 -0
- checkpoint-1793/trainer_state.json +192 -0
- checkpoint-1793/training_args.bin +3 -0
- checkpoint-1793/vocab.txt +0 -0
- config.json +0 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
checkpoint-1630/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ynie/electra-large-discriminator-snli_mnli_fever_anli_R1_R2_R3-nli",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 1024,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "entailment",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "contradiction"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"contradiction": 2,
|
| 21 |
+
"entailment": 0,
|
| 22 |
+
"neutral": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "electra",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "multi_label_classification",
|
| 32 |
+
"summary_activation": "gelu",
|
| 33 |
+
"summary_last_dropout": 0.1,
|
| 34 |
+
"summary_type": "first",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.16.2",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 30522
|
| 41 |
+
}
|
checkpoint-1630/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f10ac8aa6914a68e479931a864f18ba10f4c2c3365275928cdcaec362c14888
|
| 3 |
+
size 2681490814
|
checkpoint-1630/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3f456ad6fff0711c705ef4a02fde64a2461f640a2ebaf6d8128cf037da6c194
|
| 3 |
+
size 1340743917
|
checkpoint-1630/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19de93fa7ce45dde7d1a60c4c97b9e4ec495777424b4e2a14fb06079d8444157
|
| 3 |
+
size 14503
|
checkpoint-1630/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7e72f4673e938bbb6afc7231af6207ee922a3271ce6da4b803c942382702de9
|
| 3 |
+
size 559
|
checkpoint-1630/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c924e180775c2b50e4679ec9d5d5d33fb3eed968a176cbb01236411034beab21
|
| 3 |
+
size 623
|
checkpoint-1630/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-1630/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1630/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "normalization": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-large-discriminator", "tokenizer_class": "ElectraTokenizer"}
|
checkpoint-1630/trainer_state.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2981628179550171,
|
| 3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-978",
|
| 4 |
+
"epoch": 9.997323135755257,
|
| 5 |
+
"global_step": 1630,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9.499999999999999e-07,
|
| 13 |
+
"loss": 0.4384,
|
| 14 |
+
"step": 163
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7444061962134251,
|
| 19 |
+
"eval_f1": 0.7308261375858633,
|
| 20 |
+
"eval_loss": 0.39615127444267273,
|
| 21 |
+
"eval_runtime": 9.0599,
|
| 22 |
+
"eval_samples_per_second": 256.514,
|
| 23 |
+
"eval_steps_per_second": 32.119,
|
| 24 |
+
"step": 163
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 9e-07,
|
| 29 |
+
"loss": 0.3447,
|
| 30 |
+
"step": 326
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.76592082616179,
|
| 35 |
+
"eval_f1": 0.7552159046464709,
|
| 36 |
+
"eval_loss": 0.3409559428691864,
|
| 37 |
+
"eval_runtime": 9.4378,
|
| 38 |
+
"eval_samples_per_second": 246.244,
|
| 39 |
+
"eval_steps_per_second": 30.833,
|
| 40 |
+
"step": 326
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 8.499999999999999e-07,
|
| 45 |
+
"loss": 0.3057,
|
| 46 |
+
"step": 489
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.7749569707401033,
|
| 51 |
+
"eval_f1": 0.768808341108185,
|
| 52 |
+
"eval_loss": 0.32338443398475647,
|
| 53 |
+
"eval_runtime": 9.0418,
|
| 54 |
+
"eval_samples_per_second": 257.028,
|
| 55 |
+
"eval_steps_per_second": 32.184,
|
| 56 |
+
"step": 489
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 8e-07,
|
| 61 |
+
"loss": 0.287,
|
| 62 |
+
"step": 652
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.7857142857142857,
|
| 67 |
+
"eval_f1": 0.7778970154753132,
|
| 68 |
+
"eval_loss": 0.3068828284740448,
|
| 69 |
+
"eval_runtime": 9.3662,
|
| 70 |
+
"eval_samples_per_second": 248.128,
|
| 71 |
+
"eval_steps_per_second": 31.069,
|
| 72 |
+
"step": 652
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 7.5e-07,
|
| 77 |
+
"loss": 0.2742,
|
| 78 |
+
"step": 815
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.7887263339070568,
|
| 83 |
+
"eval_f1": 0.7821763089027973,
|
| 84 |
+
"eval_loss": 0.30303624272346497,
|
| 85 |
+
"eval_runtime": 8.908,
|
| 86 |
+
"eval_samples_per_second": 260.89,
|
| 87 |
+
"eval_steps_per_second": 32.667,
|
| 88 |
+
"step": 815
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 7e-07,
|
| 93 |
+
"loss": 0.2676,
|
| 94 |
+
"step": 978
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.7938898450946644,
|
| 99 |
+
"eval_f1": 0.7850614050415754,
|
| 100 |
+
"eval_loss": 0.2981628179550171,
|
| 101 |
+
"eval_runtime": 9.0189,
|
| 102 |
+
"eval_samples_per_second": 257.681,
|
| 103 |
+
"eval_steps_per_second": 32.266,
|
| 104 |
+
"step": 978
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 6.5e-07,
|
| 109 |
+
"loss": 0.2585,
|
| 110 |
+
"step": 1141
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7908777969018933,
|
| 115 |
+
"eval_f1": 0.7821955847641968,
|
| 116 |
+
"eval_loss": 0.3001907467842102,
|
| 117 |
+
"eval_runtime": 8.8872,
|
| 118 |
+
"eval_samples_per_second": 261.499,
|
| 119 |
+
"eval_steps_per_second": 32.744,
|
| 120 |
+
"step": 1141
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 6e-07,
|
| 125 |
+
"loss": 0.2526,
|
| 126 |
+
"step": 1304
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7943201376936316,
|
| 131 |
+
"eval_f1": 0.7876461988304093,
|
| 132 |
+
"eval_loss": 0.30516260862350464,
|
| 133 |
+
"eval_runtime": 9.0042,
|
| 134 |
+
"eval_samples_per_second": 258.103,
|
| 135 |
+
"eval_steps_per_second": 32.318,
|
| 136 |
+
"step": 1304
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 5.5e-07,
|
| 141 |
+
"loss": 0.2479,
|
| 142 |
+
"step": 1467
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.7938898450946644,
|
| 147 |
+
"eval_f1": 0.784665589216992,
|
| 148 |
+
"eval_loss": 0.2996860444545746,
|
| 149 |
+
"eval_runtime": 9.1157,
|
| 150 |
+
"eval_samples_per_second": 254.944,
|
| 151 |
+
"eval_steps_per_second": 31.923,
|
| 152 |
+
"step": 1467
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 5e-07,
|
| 157 |
+
"loss": 0.2451,
|
| 158 |
+
"step": 1630
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.7956110154905336,
|
| 163 |
+
"eval_f1": 0.787314593871832,
|
| 164 |
+
"eval_loss": 0.3013566732406616,
|
| 165 |
+
"eval_runtime": 9.3541,
|
| 166 |
+
"eval_samples_per_second": 248.446,
|
| 167 |
+
"eval_steps_per_second": 31.109,
|
| 168 |
+
"step": 1630
|
| 169 |
+
}
|
| 170 |
+
],
|
| 171 |
+
"max_steps": 3260,
|
| 172 |
+
"num_train_epochs": 20,
|
| 173 |
+
"total_flos": 3.0441815576382144e+16,
|
| 174 |
+
"trial_name": null,
|
| 175 |
+
"trial_params": null
|
| 176 |
+
}
|
checkpoint-1630/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50dde5eeea306f54118173d342686475ad9209b6c2cac103f7b114d5f582dc36
|
| 3 |
+
size 3119
|
checkpoint-1630/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1793/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ynie/electra-large-discriminator-snli_mnli_fever_anli_R1_R2_R3-nli",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 1024,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "entailment",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "contradiction"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"contradiction": 2,
|
| 21 |
+
"entailment": 0,
|
| 22 |
+
"neutral": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "electra",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "multi_label_classification",
|
| 32 |
+
"summary_activation": "gelu",
|
| 33 |
+
"summary_last_dropout": 0.1,
|
| 34 |
+
"summary_type": "first",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.16.2",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 30522
|
| 41 |
+
}
|
checkpoint-1793/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8228fd6cf58783605e60520c21c70b9445fed6a90eeec2376e01fa43a9008c
|
| 3 |
+
size 2681490814
|
checkpoint-1793/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d4dbd4b1eb604850accc73f71776c97a1e07665ffd69d89f3c5e7d30e3f1f7c
|
| 3 |
+
size 1340743917
|
checkpoint-1793/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:726164d2bc62c68696d3d456b8b1f6aeca340f4529265e518db9792e9a355cd8
|
| 3 |
+
size 14503
|
checkpoint-1793/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:102acc952d72cdec1a2ca0aba7dd1acd73037d69b054e4a8eb81a3b60b73c6b6
|
| 3 |
+
size 559
|
checkpoint-1793/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caf14e34d5b3abd5a96ccc41d7e0ae86ff875f6a745203e1f8c2429070129f3e
|
| 3 |
+
size 623
|
checkpoint-1793/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-1793/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1793/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "normalization": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-large-discriminator", "tokenizer_class": "ElectraTokenizer"}
|
checkpoint-1793/trainer_state.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2981628179550171,
|
| 3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-978",
|
| 4 |
+
"epoch": 10.997323135755257,
|
| 5 |
+
"global_step": 1793,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9.499999999999999e-07,
|
| 13 |
+
"loss": 0.4384,
|
| 14 |
+
"step": 163
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7444061962134251,
|
| 19 |
+
"eval_f1": 0.7308261375858633,
|
| 20 |
+
"eval_loss": 0.39615127444267273,
|
| 21 |
+
"eval_runtime": 9.0599,
|
| 22 |
+
"eval_samples_per_second": 256.514,
|
| 23 |
+
"eval_steps_per_second": 32.119,
|
| 24 |
+
"step": 163
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 9e-07,
|
| 29 |
+
"loss": 0.3447,
|
| 30 |
+
"step": 326
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.76592082616179,
|
| 35 |
+
"eval_f1": 0.7552159046464709,
|
| 36 |
+
"eval_loss": 0.3409559428691864,
|
| 37 |
+
"eval_runtime": 9.4378,
|
| 38 |
+
"eval_samples_per_second": 246.244,
|
| 39 |
+
"eval_steps_per_second": 30.833,
|
| 40 |
+
"step": 326
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 8.499999999999999e-07,
|
| 45 |
+
"loss": 0.3057,
|
| 46 |
+
"step": 489
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.7749569707401033,
|
| 51 |
+
"eval_f1": 0.768808341108185,
|
| 52 |
+
"eval_loss": 0.32338443398475647,
|
| 53 |
+
"eval_runtime": 9.0418,
|
| 54 |
+
"eval_samples_per_second": 257.028,
|
| 55 |
+
"eval_steps_per_second": 32.184,
|
| 56 |
+
"step": 489
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 8e-07,
|
| 61 |
+
"loss": 0.287,
|
| 62 |
+
"step": 652
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.7857142857142857,
|
| 67 |
+
"eval_f1": 0.7778970154753132,
|
| 68 |
+
"eval_loss": 0.3068828284740448,
|
| 69 |
+
"eval_runtime": 9.3662,
|
| 70 |
+
"eval_samples_per_second": 248.128,
|
| 71 |
+
"eval_steps_per_second": 31.069,
|
| 72 |
+
"step": 652
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 7.5e-07,
|
| 77 |
+
"loss": 0.2742,
|
| 78 |
+
"step": 815
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.7887263339070568,
|
| 83 |
+
"eval_f1": 0.7821763089027973,
|
| 84 |
+
"eval_loss": 0.30303624272346497,
|
| 85 |
+
"eval_runtime": 8.908,
|
| 86 |
+
"eval_samples_per_second": 260.89,
|
| 87 |
+
"eval_steps_per_second": 32.667,
|
| 88 |
+
"step": 815
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 7e-07,
|
| 93 |
+
"loss": 0.2676,
|
| 94 |
+
"step": 978
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.7938898450946644,
|
| 99 |
+
"eval_f1": 0.7850614050415754,
|
| 100 |
+
"eval_loss": 0.2981628179550171,
|
| 101 |
+
"eval_runtime": 9.0189,
|
| 102 |
+
"eval_samples_per_second": 257.681,
|
| 103 |
+
"eval_steps_per_second": 32.266,
|
| 104 |
+
"step": 978
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 6.5e-07,
|
| 109 |
+
"loss": 0.2585,
|
| 110 |
+
"step": 1141
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7908777969018933,
|
| 115 |
+
"eval_f1": 0.7821955847641968,
|
| 116 |
+
"eval_loss": 0.3001907467842102,
|
| 117 |
+
"eval_runtime": 8.8872,
|
| 118 |
+
"eval_samples_per_second": 261.499,
|
| 119 |
+
"eval_steps_per_second": 32.744,
|
| 120 |
+
"step": 1141
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 6e-07,
|
| 125 |
+
"loss": 0.2526,
|
| 126 |
+
"step": 1304
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7943201376936316,
|
| 131 |
+
"eval_f1": 0.7876461988304093,
|
| 132 |
+
"eval_loss": 0.30516260862350464,
|
| 133 |
+
"eval_runtime": 9.0042,
|
| 134 |
+
"eval_samples_per_second": 258.103,
|
| 135 |
+
"eval_steps_per_second": 32.318,
|
| 136 |
+
"step": 1304
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 5.5e-07,
|
| 141 |
+
"loss": 0.2479,
|
| 142 |
+
"step": 1467
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.7938898450946644,
|
| 147 |
+
"eval_f1": 0.784665589216992,
|
| 148 |
+
"eval_loss": 0.2996860444545746,
|
| 149 |
+
"eval_runtime": 9.1157,
|
| 150 |
+
"eval_samples_per_second": 254.944,
|
| 151 |
+
"eval_steps_per_second": 31.923,
|
| 152 |
+
"step": 1467
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 5e-07,
|
| 157 |
+
"loss": 0.2451,
|
| 158 |
+
"step": 1630
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.7956110154905336,
|
| 163 |
+
"eval_f1": 0.787314593871832,
|
| 164 |
+
"eval_loss": 0.3013566732406616,
|
| 165 |
+
"eval_runtime": 9.3541,
|
| 166 |
+
"eval_samples_per_second": 248.446,
|
| 167 |
+
"eval_steps_per_second": 31.109,
|
| 168 |
+
"step": 1630
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 4.5e-07,
|
| 173 |
+
"loss": 0.2397,
|
| 174 |
+
"step": 1793
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.0,
|
| 178 |
+
"eval_accuracy": 0.7943201376936316,
|
| 179 |
+
"eval_f1": 0.7872381827932275,
|
| 180 |
+
"eval_loss": 0.30036163330078125,
|
| 181 |
+
"eval_runtime": 9.1941,
|
| 182 |
+
"eval_samples_per_second": 252.771,
|
| 183 |
+
"eval_steps_per_second": 31.651,
|
| 184 |
+
"step": 1793
|
| 185 |
+
}
|
| 186 |
+
],
|
| 187 |
+
"max_steps": 3260,
|
| 188 |
+
"num_train_epochs": 20,
|
| 189 |
+
"total_flos": 3.348318385671187e+16,
|
| 190 |
+
"trial_name": null,
|
| 191 |
+
"trial_params": null
|
| 192 |
+
}
|
checkpoint-1793/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50dde5eeea306f54118173d342686475ad9209b6c2cac103f7b114d5f582dc36
|
| 3 |
+
size 3119
|
checkpoint-1793/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
CHANGED
|
@@ -28,7 +28,6 @@
|
|
| 28 |
"num_hidden_layers": 24,
|
| 29 |
"pad_token_id": 0,
|
| 30 |
"position_embedding_type": "absolute",
|
| 31 |
-
"problem_type": "multi_label_classification",
|
| 32 |
"summary_activation": "gelu",
|
| 33 |
"summary_last_dropout": 0.1,
|
| 34 |
"summary_type": "first",
|
|
|
|
| 28 |
"num_hidden_layers": 24,
|
| 29 |
"pad_token_id": 0,
|
| 30 |
"position_embedding_type": "absolute",
|
|
|
|
| 31 |
"summary_activation": "gelu",
|
| 32 |
"summary_last_dropout": 0.1,
|
| 33 |
"summary_type": "first",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1340743917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1017cd7d6d785c901c6c1b5a7c8a543da183235f0b9932da80f8f3cd0484598b
|
| 3 |
size 1340743917
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3119
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa5b3cdd065caa2d04215020fd56dc58b2f03c96229986e222c4af6a4f7d97b7
|
| 3 |
size 3119
|