Commit
•
c86920f
1
Parent(s):
74bcc66
Upload 11 files
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +406 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/electra-small-discriminator",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 128,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "electra",
|
| 17 |
+
"num_attention_heads": 4,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"summary_activation": "gelu",
|
| 22 |
+
"summary_last_dropout": 0.1,
|
| 23 |
+
"summary_type": "first",
|
| 24 |
+
"summary_use_proj": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.23.0",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b40c480e86394cdd9092a81bb6702dc8603eb2097d321b118b0dc080d1653664
|
| 3 |
+
size 107984669
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2825c4c50f54eb0368df59576ee5ac12c0c1e808dcb583c537b9b4a6204ae34
|
| 3 |
+
size 54005677
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7d4665a010c55f09634d269cbd1f204abf980074829c924b655445b9f7004de
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4acb9b2fdeb2e96087878910052c219d2848d889c9ba1955dd5bcd958cf01c8
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": true,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "google/electra-small-discriminator",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9639762881896945,
|
| 5 |
+
"global_step": 32500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4.9240006079951365e-05,
|
| 13 |
+
"loss": 3.2149,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.848001215990272e-05,
|
| 19 |
+
"loss": 2.0552,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.14,
|
| 24 |
+
"learning_rate": 4.772001823985408e-05,
|
| 25 |
+
"loss": 1.7909,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 4.6960024319805444e-05,
|
| 31 |
+
"loss": 1.5849,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.23,
|
| 36 |
+
"learning_rate": 4.620003039975681e-05,
|
| 37 |
+
"loss": 1.5404,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"learning_rate": 4.544003647970816e-05,
|
| 43 |
+
"loss": 1.4643,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.32,
|
| 48 |
+
"learning_rate": 4.4680042559659524e-05,
|
| 49 |
+
"loss": 1.4016,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"learning_rate": 4.3920048639610886e-05,
|
| 55 |
+
"loss": 1.3873,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.41,
|
| 60 |
+
"learning_rate": 4.316005471956224e-05,
|
| 61 |
+
"loss": 1.4027,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.46,
|
| 66 |
+
"learning_rate": 4.240006079951361e-05,
|
| 67 |
+
"loss": 1.3512,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.5,
|
| 72 |
+
"learning_rate": 4.1640066879464966e-05,
|
| 73 |
+
"loss": 1.3113,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.55,
|
| 78 |
+
"learning_rate": 4.088007295941633e-05,
|
| 79 |
+
"loss": 1.321,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.59,
|
| 84 |
+
"learning_rate": 4.0120079039367684e-05,
|
| 85 |
+
"loss": 1.2949,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.64,
|
| 90 |
+
"learning_rate": 3.9360085119319046e-05,
|
| 91 |
+
"loss": 1.3101,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.68,
|
| 96 |
+
"learning_rate": 3.860009119927041e-05,
|
| 97 |
+
"loss": 1.2456,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.73,
|
| 102 |
+
"learning_rate": 3.784009727922177e-05,
|
| 103 |
+
"loss": 1.273,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.78,
|
| 108 |
+
"learning_rate": 3.708010335917313e-05,
|
| 109 |
+
"loss": 1.2514,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.82,
|
| 114 |
+
"learning_rate": 3.632010943912449e-05,
|
| 115 |
+
"loss": 1.2244,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.87,
|
| 120 |
+
"learning_rate": 3.556011551907585e-05,
|
| 121 |
+
"loss": 1.2002,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.91,
|
| 126 |
+
"learning_rate": 3.4800121599027206e-05,
|
| 127 |
+
"loss": 1.1955,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.96,
|
| 132 |
+
"learning_rate": 3.404012767897857e-05,
|
| 133 |
+
"loss": 1.1896,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.0,
|
| 138 |
+
"learning_rate": 3.328013375892993e-05,
|
| 139 |
+
"loss": 1.1549,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.05,
|
| 144 |
+
"learning_rate": 3.252013983888129e-05,
|
| 145 |
+
"loss": 0.9814,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.09,
|
| 150 |
+
"learning_rate": 3.176014591883265e-05,
|
| 151 |
+
"loss": 0.9973,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.14,
|
| 156 |
+
"learning_rate": 3.100015199878401e-05,
|
| 157 |
+
"loss": 1.0072,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.19,
|
| 162 |
+
"learning_rate": 3.024015807873537e-05,
|
| 163 |
+
"loss": 0.9585,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.23,
|
| 168 |
+
"learning_rate": 2.9480164158686728e-05,
|
| 169 |
+
"loss": 1.0121,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.28,
|
| 174 |
+
"learning_rate": 2.8720170238638093e-05,
|
| 175 |
+
"loss": 0.984,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.32,
|
| 180 |
+
"learning_rate": 2.7960176318589452e-05,
|
| 181 |
+
"loss": 0.9659,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.37,
|
| 186 |
+
"learning_rate": 2.7200182398540814e-05,
|
| 187 |
+
"loss": 1.0413,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.41,
|
| 192 |
+
"learning_rate": 2.6440188478492173e-05,
|
| 193 |
+
"loss": 0.9652,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.46,
|
| 198 |
+
"learning_rate": 2.5680194558443532e-05,
|
| 199 |
+
"loss": 0.9588,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.5,
|
| 204 |
+
"learning_rate": 2.4920200638394894e-05,
|
| 205 |
+
"loss": 1.0316,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.55,
|
| 210 |
+
"learning_rate": 2.4160206718346253e-05,
|
| 211 |
+
"loss": 1.0073,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.6,
|
| 216 |
+
"learning_rate": 2.3400212798297615e-05,
|
| 217 |
+
"loss": 0.9782,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.64,
|
| 222 |
+
"learning_rate": 2.2640218878248974e-05,
|
| 223 |
+
"loss": 1.0236,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.69,
|
| 228 |
+
"learning_rate": 2.1880224958200336e-05,
|
| 229 |
+
"loss": 0.938,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.73,
|
| 234 |
+
"learning_rate": 2.11202310381517e-05,
|
| 235 |
+
"loss": 0.9681,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.78,
|
| 240 |
+
"learning_rate": 2.0360237118103057e-05,
|
| 241 |
+
"loss": 0.9608,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.82,
|
| 246 |
+
"learning_rate": 1.9600243198054416e-05,
|
| 247 |
+
"loss": 0.991,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.87,
|
| 252 |
+
"learning_rate": 1.884024927800578e-05,
|
| 253 |
+
"loss": 0.9445,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.92,
|
| 258 |
+
"learning_rate": 1.8080255357957137e-05,
|
| 259 |
+
"loss": 0.9633,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.96,
|
| 264 |
+
"learning_rate": 1.7320261437908496e-05,
|
| 265 |
+
"loss": 0.9731,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.01,
|
| 270 |
+
"learning_rate": 1.6560267517859858e-05,
|
| 271 |
+
"loss": 0.8811,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.05,
|
| 276 |
+
"learning_rate": 1.580027359781122e-05,
|
| 277 |
+
"loss": 0.8006,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.1,
|
| 282 |
+
"learning_rate": 1.5040279677762578e-05,
|
| 283 |
+
"loss": 0.7736,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.14,
|
| 288 |
+
"learning_rate": 1.4280285757713938e-05,
|
| 289 |
+
"loss": 0.7877,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.19,
|
| 294 |
+
"learning_rate": 1.35202918376653e-05,
|
| 295 |
+
"loss": 0.772,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.23,
|
| 300 |
+
"learning_rate": 1.2760297917616659e-05,
|
| 301 |
+
"loss": 0.7695,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.28,
|
| 306 |
+
"learning_rate": 1.200030399756802e-05,
|
| 307 |
+
"loss": 0.7893,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.33,
|
| 312 |
+
"learning_rate": 1.1240310077519382e-05,
|
| 313 |
+
"loss": 0.7996,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.37,
|
| 318 |
+
"learning_rate": 1.048031615747074e-05,
|
| 319 |
+
"loss": 0.7658,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.42,
|
| 324 |
+
"learning_rate": 9.720322237422101e-06,
|
| 325 |
+
"loss": 0.7911,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.46,
|
| 330 |
+
"learning_rate": 8.960328317373462e-06,
|
| 331 |
+
"loss": 0.7829,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.51,
|
| 336 |
+
"learning_rate": 8.200334397324822e-06,
|
| 337 |
+
"loss": 0.772,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.55,
|
| 342 |
+
"learning_rate": 7.440340477276183e-06,
|
| 343 |
+
"loss": 0.7764,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.6,
|
| 348 |
+
"learning_rate": 6.680346557227543e-06,
|
| 349 |
+
"loss": 0.7846,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.64,
|
| 354 |
+
"learning_rate": 5.920352637178903e-06,
|
| 355 |
+
"loss": 0.7781,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.69,
|
| 360 |
+
"learning_rate": 5.160358717130263e-06,
|
| 361 |
+
"loss": 0.7588,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.74,
|
| 366 |
+
"learning_rate": 4.400364797081624e-06,
|
| 367 |
+
"loss": 0.7829,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.78,
|
| 372 |
+
"learning_rate": 3.6403708770329835e-06,
|
| 373 |
+
"loss": 0.7754,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.83,
|
| 378 |
+
"learning_rate": 2.880376956984344e-06,
|
| 379 |
+
"loss": 0.781,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.87,
|
| 384 |
+
"learning_rate": 2.1203830369357045e-06,
|
| 385 |
+
"loss": 0.779,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.92,
|
| 390 |
+
"learning_rate": 1.3603891168870648e-06,
|
| 391 |
+
"loss": 0.7928,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.96,
|
| 396 |
+
"learning_rate": 6.003951968384252e-07,
|
| 397 |
+
"loss": 0.7543,
|
| 398 |
+
"step": 32500
|
| 399 |
+
}
|
| 400 |
+
],
|
| 401 |
+
"max_steps": 32895,
|
| 402 |
+
"num_train_epochs": 3,
|
| 403 |
+
"total_flos": 7596206619746304.0,
|
| 404 |
+
"trial_name": null,
|
| 405 |
+
"trial_params": null
|
| 406 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e456a7a80cabb8b2f36cd0bb8fae15d084f11e55f940175606bee61a6a14c96b
|
| 3 |
+
size 3375
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|