Training in progress, epoch 12
Browse files- checkpoint-2520/config.json +41 -0
- checkpoint-2520/optimizer.pt +3 -0
- checkpoint-2520/pytorch_model.bin +3 -0
- checkpoint-2520/rng_state.pth +3 -0
- checkpoint-2520/scaler.pt +3 -0
- checkpoint-2520/scheduler.pt +3 -0
- checkpoint-2520/special_tokens_map.json +1 -0
- checkpoint-2520/tokenizer.json +0 -0
- checkpoint-2520/tokenizer_config.json +1 -0
- checkpoint-2520/trainer_state.json +208 -0
- checkpoint-2520/training_args.bin +3 -0
- checkpoint-2520/vocab.txt +0 -0
- checkpoint-2730/config.json +41 -0
- checkpoint-2730/optimizer.pt +3 -0
- checkpoint-2730/pytorch_model.bin +3 -0
- checkpoint-2730/rng_state.pth +3 -0
- checkpoint-2730/scaler.pt +3 -0
- checkpoint-2730/scheduler.pt +3 -0
- checkpoint-2730/special_tokens_map.json +1 -0
- checkpoint-2730/tokenizer.json +0 -0
- checkpoint-2730/tokenizer_config.json +1 -0
- checkpoint-2730/trainer_state.json +224 -0
- checkpoint-2730/training_args.bin +3 -0
- checkpoint-2730/vocab.txt +0 -0
- pytorch_model.bin +1 -1
checkpoint-2520/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": "4.17.0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 30522
|
| 41 |
+
}
|
checkpoint-2520/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd4023d696ca1e99b39b14eee212b624498ca045f0ea0f23ba0d42af4d2a908e
|
| 3 |
+
size 2681386461
|
checkpoint-2520/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5284919c5f1c88093f0271d4b0d16cdbdfb688aabab775ec85b725c5c08ef4d
|
| 3 |
+
size 1340745837
|
checkpoint-2520/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b2591523d6010f39a2a573ee6662be62637a05fbd76c65cfbf543a6f4d4fadf
|
| 3 |
+
size 14503
|
checkpoint-2520/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc30bede629e2087edbd2d3ef5b2ab7a544647c7d58a6d38c1c087246401bcbb
|
| 3 |
+
size 559
|
checkpoint-2520/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:582272eef0f7dd858de212f08a2295879cc8b2c1042d8242fad311585c03e110
|
| 3 |
+
size 623
|
checkpoint-2520/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-2520/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2520/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-2520/trainer_state.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3247086703777313,
|
| 3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl/checkpoint-1050",
|
| 4 |
+
"epoch": 11.995555555555555,
|
| 5 |
+
"global_step": 2520,
|
| 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": 0.4175,
|
| 14 |
+
"step": 210
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7316666666666667,
|
| 19 |
+
"eval_f1": 0.7305281480923569,
|
| 20 |
+
"eval_loss": 0.4019607603549957,
|
| 21 |
+
"eval_runtime": 11.5986,
|
| 22 |
+
"eval_samples_per_second": 258.651,
|
| 23 |
+
"eval_steps_per_second": 32.331,
|
| 24 |
+
"step": 210
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 9e-07,
|
| 29 |
+
"loss": 0.3061,
|
| 30 |
+
"step": 420
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.768,
|
| 35 |
+
"eval_f1": 0.7674936528439713,
|
| 36 |
+
"eval_loss": 0.3519645631313324,
|
| 37 |
+
"eval_runtime": 11.6033,
|
| 38 |
+
"eval_samples_per_second": 258.548,
|
| 39 |
+
"eval_steps_per_second": 32.319,
|
| 40 |
+
"step": 420
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 8.499999999999999e-07,
|
| 45 |
+
"loss": 0.2588,
|
| 46 |
+
"step": 630
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.79,
|
| 51 |
+
"eval_f1": 0.7887799932409598,
|
| 52 |
+
"eval_loss": 0.32531991600990295,
|
| 53 |
+
"eval_runtime": 11.5951,
|
| 54 |
+
"eval_samples_per_second": 258.729,
|
| 55 |
+
"eval_steps_per_second": 32.341,
|
| 56 |
+
"step": 630
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 8e-07,
|
| 61 |
+
"loss": 0.234,
|
| 62 |
+
"step": 840
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.788,
|
| 67 |
+
"eval_f1": 0.7877041067016072,
|
| 68 |
+
"eval_loss": 0.33730262517929077,
|
| 69 |
+
"eval_runtime": 11.6935,
|
| 70 |
+
"eval_samples_per_second": 256.553,
|
| 71 |
+
"eval_steps_per_second": 32.069,
|
| 72 |
+
"step": 840
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 7.5e-07,
|
| 77 |
+
"loss": 0.2116,
|
| 78 |
+
"step": 1050
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.804,
|
| 83 |
+
"eval_f1": 0.8032759681298146,
|
| 84 |
+
"eval_loss": 0.3247086703777313,
|
| 85 |
+
"eval_runtime": 11.5938,
|
| 86 |
+
"eval_samples_per_second": 258.758,
|
| 87 |
+
"eval_steps_per_second": 32.345,
|
| 88 |
+
"step": 1050
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 7e-07,
|
| 93 |
+
"loss": 0.1974,
|
| 94 |
+
"step": 1260
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.793,
|
| 99 |
+
"eval_f1": 0.7928414316247181,
|
| 100 |
+
"eval_loss": 0.34000951051712036,
|
| 101 |
+
"eval_runtime": 11.6038,
|
| 102 |
+
"eval_samples_per_second": 258.537,
|
| 103 |
+
"eval_steps_per_second": 32.317,
|
| 104 |
+
"step": 1260
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 6.5e-07,
|
| 109 |
+
"loss": 0.1807,
|
| 110 |
+
"step": 1470
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7973333333333333,
|
| 115 |
+
"eval_f1": 0.7969281824938732,
|
| 116 |
+
"eval_loss": 0.35112178325653076,
|
| 117 |
+
"eval_runtime": 11.589,
|
| 118 |
+
"eval_samples_per_second": 258.866,
|
| 119 |
+
"eval_steps_per_second": 32.358,
|
| 120 |
+
"step": 1470
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 6e-07,
|
| 125 |
+
"loss": 0.1715,
|
| 126 |
+
"step": 1680
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7993333333333333,
|
| 131 |
+
"eval_f1": 0.79885693716362,
|
| 132 |
+
"eval_loss": 0.34963640570640564,
|
| 133 |
+
"eval_runtime": 11.6019,
|
| 134 |
+
"eval_samples_per_second": 258.579,
|
| 135 |
+
"eval_steps_per_second": 32.322,
|
| 136 |
+
"step": 1680
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 5.5e-07,
|
| 141 |
+
"loss": 0.1577,
|
| 142 |
+
"step": 1890
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.8043333333333333,
|
| 147 |
+
"eval_f1": 0.803166306363764,
|
| 148 |
+
"eval_loss": 0.3507426679134369,
|
| 149 |
+
"eval_runtime": 11.6051,
|
| 150 |
+
"eval_samples_per_second": 258.507,
|
| 151 |
+
"eval_steps_per_second": 32.313,
|
| 152 |
+
"step": 1890
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 5e-07,
|
| 157 |
+
"loss": 0.1469,
|
| 158 |
+
"step": 2100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.798,
|
| 163 |
+
"eval_f1": 0.7970242731280681,
|
| 164 |
+
"eval_loss": 0.3604212701320648,
|
| 165 |
+
"eval_runtime": 11.7325,
|
| 166 |
+
"eval_samples_per_second": 255.699,
|
| 167 |
+
"eval_steps_per_second": 31.962,
|
| 168 |
+
"step": 2100
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 4.5e-07,
|
| 173 |
+
"loss": 0.1394,
|
| 174 |
+
"step": 2310
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.0,
|
| 178 |
+
"eval_accuracy": 0.7966666666666666,
|
| 179 |
+
"eval_f1": 0.7957033854293423,
|
| 180 |
+
"eval_loss": 0.37343233823776245,
|
| 181 |
+
"eval_runtime": 11.6069,
|
| 182 |
+
"eval_samples_per_second": 258.468,
|
| 183 |
+
"eval_steps_per_second": 32.308,
|
| 184 |
+
"step": 2310
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 12.0,
|
| 188 |
+
"learning_rate": 4e-07,
|
| 189 |
+
"loss": 0.1322,
|
| 190 |
+
"step": 2520
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 12.0,
|
| 194 |
+
"eval_accuracy": 0.7913333333333333,
|
| 195 |
+
"eval_f1": 0.7905794192426068,
|
| 196 |
+
"eval_loss": 0.39285749197006226,
|
| 197 |
+
"eval_runtime": 11.6585,
|
| 198 |
+
"eval_samples_per_second": 257.322,
|
| 199 |
+
"eval_steps_per_second": 32.165,
|
| 200 |
+
"step": 2520
|
| 201 |
+
}
|
| 202 |
+
],
|
| 203 |
+
"max_steps": 4200,
|
| 204 |
+
"num_train_epochs": 20,
|
| 205 |
+
"total_flos": 4.992291637199885e+16,
|
| 206 |
+
"trial_name": null,
|
| 207 |
+
"trial_params": null
|
| 208 |
+
}
|
checkpoint-2520/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c104103a95a8e00f67dc451eba8bec78c0cbf934c84f4059200155cf9a45b752
|
| 3 |
+
size 3119
|
checkpoint-2520/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2730/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": "4.17.0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 30522
|
| 41 |
+
}
|
checkpoint-2730/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd281587f60fb6bd55759d01a8a563605b71971737205d6c0d9e2cba286eb793
|
| 3 |
+
size 2681386461
|
checkpoint-2730/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9b3610c3f6a5f9ef1c57b2628590856913dd99bc5b8133c922208c08d0ca252
|
| 3 |
+
size 1340745837
|
checkpoint-2730/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca041294d34dab5c110c6464b2bc567d6b0b466ce299b05a7ea06f2be3b2c53d
|
| 3 |
+
size 14503
|
checkpoint-2730/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8233415adabb63138f1f836c60d7c5dc99582d401ac914ab3b9bcd9d6487b26
|
| 3 |
+
size 559
|
checkpoint-2730/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d526f744249a78d28b51ed30780e2d963c0c8d2a7c54cf75fe470c7d8e8f36
|
| 3 |
+
size 623
|
checkpoint-2730/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-2730/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2730/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-2730/trainer_state.json
ADDED
|
@@ -0,0 +1,224 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3247086703777313,
|
| 3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl/checkpoint-1050",
|
| 4 |
+
"epoch": 12.995555555555555,
|
| 5 |
+
"global_step": 2730,
|
| 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": 0.4175,
|
| 14 |
+
"step": 210
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7316666666666667,
|
| 19 |
+
"eval_f1": 0.7305281480923569,
|
| 20 |
+
"eval_loss": 0.4019607603549957,
|
| 21 |
+
"eval_runtime": 11.5986,
|
| 22 |
+
"eval_samples_per_second": 258.651,
|
| 23 |
+
"eval_steps_per_second": 32.331,
|
| 24 |
+
"step": 210
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 9e-07,
|
| 29 |
+
"loss": 0.3061,
|
| 30 |
+
"step": 420
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.768,
|
| 35 |
+
"eval_f1": 0.7674936528439713,
|
| 36 |
+
"eval_loss": 0.3519645631313324,
|
| 37 |
+
"eval_runtime": 11.6033,
|
| 38 |
+
"eval_samples_per_second": 258.548,
|
| 39 |
+
"eval_steps_per_second": 32.319,
|
| 40 |
+
"step": 420
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 8.499999999999999e-07,
|
| 45 |
+
"loss": 0.2588,
|
| 46 |
+
"step": 630
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.79,
|
| 51 |
+
"eval_f1": 0.7887799932409598,
|
| 52 |
+
"eval_loss": 0.32531991600990295,
|
| 53 |
+
"eval_runtime": 11.5951,
|
| 54 |
+
"eval_samples_per_second": 258.729,
|
| 55 |
+
"eval_steps_per_second": 32.341,
|
| 56 |
+
"step": 630
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 8e-07,
|
| 61 |
+
"loss": 0.234,
|
| 62 |
+
"step": 840
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.788,
|
| 67 |
+
"eval_f1": 0.7877041067016072,
|
| 68 |
+
"eval_loss": 0.33730262517929077,
|
| 69 |
+
"eval_runtime": 11.6935,
|
| 70 |
+
"eval_samples_per_second": 256.553,
|
| 71 |
+
"eval_steps_per_second": 32.069,
|
| 72 |
+
"step": 840
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 7.5e-07,
|
| 77 |
+
"loss": 0.2116,
|
| 78 |
+
"step": 1050
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.804,
|
| 83 |
+
"eval_f1": 0.8032759681298146,
|
| 84 |
+
"eval_loss": 0.3247086703777313,
|
| 85 |
+
"eval_runtime": 11.5938,
|
| 86 |
+
"eval_samples_per_second": 258.758,
|
| 87 |
+
"eval_steps_per_second": 32.345,
|
| 88 |
+
"step": 1050
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 7e-07,
|
| 93 |
+
"loss": 0.1974,
|
| 94 |
+
"step": 1260
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.793,
|
| 99 |
+
"eval_f1": 0.7928414316247181,
|
| 100 |
+
"eval_loss": 0.34000951051712036,
|
| 101 |
+
"eval_runtime": 11.6038,
|
| 102 |
+
"eval_samples_per_second": 258.537,
|
| 103 |
+
"eval_steps_per_second": 32.317,
|
| 104 |
+
"step": 1260
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 6.5e-07,
|
| 109 |
+
"loss": 0.1807,
|
| 110 |
+
"step": 1470
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7973333333333333,
|
| 115 |
+
"eval_f1": 0.7969281824938732,
|
| 116 |
+
"eval_loss": 0.35112178325653076,
|
| 117 |
+
"eval_runtime": 11.589,
|
| 118 |
+
"eval_samples_per_second": 258.866,
|
| 119 |
+
"eval_steps_per_second": 32.358,
|
| 120 |
+
"step": 1470
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 6e-07,
|
| 125 |
+
"loss": 0.1715,
|
| 126 |
+
"step": 1680
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7993333333333333,
|
| 131 |
+
"eval_f1": 0.79885693716362,
|
| 132 |
+
"eval_loss": 0.34963640570640564,
|
| 133 |
+
"eval_runtime": 11.6019,
|
| 134 |
+
"eval_samples_per_second": 258.579,
|
| 135 |
+
"eval_steps_per_second": 32.322,
|
| 136 |
+
"step": 1680
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 5.5e-07,
|
| 141 |
+
"loss": 0.1577,
|
| 142 |
+
"step": 1890
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.8043333333333333,
|
| 147 |
+
"eval_f1": 0.803166306363764,
|
| 148 |
+
"eval_loss": 0.3507426679134369,
|
| 149 |
+
"eval_runtime": 11.6051,
|
| 150 |
+
"eval_samples_per_second": 258.507,
|
| 151 |
+
"eval_steps_per_second": 32.313,
|
| 152 |
+
"step": 1890
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 5e-07,
|
| 157 |
+
"loss": 0.1469,
|
| 158 |
+
"step": 2100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.798,
|
| 163 |
+
"eval_f1": 0.7970242731280681,
|
| 164 |
+
"eval_loss": 0.3604212701320648,
|
| 165 |
+
"eval_runtime": 11.7325,
|
| 166 |
+
"eval_samples_per_second": 255.699,
|
| 167 |
+
"eval_steps_per_second": 31.962,
|
| 168 |
+
"step": 2100
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 4.5e-07,
|
| 173 |
+
"loss": 0.1394,
|
| 174 |
+
"step": 2310
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.0,
|
| 178 |
+
"eval_accuracy": 0.7966666666666666,
|
| 179 |
+
"eval_f1": 0.7957033854293423,
|
| 180 |
+
"eval_loss": 0.37343233823776245,
|
| 181 |
+
"eval_runtime": 11.6069,
|
| 182 |
+
"eval_samples_per_second": 258.468,
|
| 183 |
+
"eval_steps_per_second": 32.308,
|
| 184 |
+
"step": 2310
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 12.0,
|
| 188 |
+
"learning_rate": 4e-07,
|
| 189 |
+
"loss": 0.1322,
|
| 190 |
+
"step": 2520
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 12.0,
|
| 194 |
+
"eval_accuracy": 0.7913333333333333,
|
| 195 |
+
"eval_f1": 0.7905794192426068,
|
| 196 |
+
"eval_loss": 0.39285749197006226,
|
| 197 |
+
"eval_runtime": 11.6585,
|
| 198 |
+
"eval_samples_per_second": 257.322,
|
| 199 |
+
"eval_steps_per_second": 32.165,
|
| 200 |
+
"step": 2520
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"learning_rate": 3.5e-07,
|
| 205 |
+
"loss": 0.1231,
|
| 206 |
+
"step": 2730
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.0,
|
| 210 |
+
"eval_accuracy": 0.795,
|
| 211 |
+
"eval_f1": 0.7941480244179493,
|
| 212 |
+
"eval_loss": 0.39544808864593506,
|
| 213 |
+
"eval_runtime": 11.5711,
|
| 214 |
+
"eval_samples_per_second": 259.267,
|
| 215 |
+
"eval_steps_per_second": 32.408,
|
| 216 |
+
"step": 2730
|
| 217 |
+
}
|
| 218 |
+
],
|
| 219 |
+
"max_steps": 4200,
|
| 220 |
+
"num_train_epochs": 20,
|
| 221 |
+
"total_flos": 5.408377098502234e+16,
|
| 222 |
+
"trial_name": null,
|
| 223 |
+
"trial_params": null
|
| 224 |
+
}
|
checkpoint-2730/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c104103a95a8e00f67dc451eba8bec78c0cbf934c84f4059200155cf9a45b752
|
| 3 |
+
size 3119
|
checkpoint-2730/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1340745837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9b3610c3f6a5f9ef1c57b2628590856913dd99bc5b8133c922208c08d0ca252
|
| 3 |
size 1340745837
|