Upload 9 files
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer_config.json +24 -0
- trainer_state.json +298 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42b9898d12316086420a0716106435c976080c9beba55580bdf7c364861cdc81
|
| 3 |
+
size 93584149
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1e92435cfefc360a88297fd6232aae1014995dbd85fed81e1ac79b69b8ed977
|
| 3 |
+
size 46797739
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6077cc822c626f39a548d319a5014ba9fb607ae2809276d8055c7589759fa5e5
|
| 3 |
+
size 14657
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1943902b01c5006061d1b3c3377e5df8ad6016474efcca36ec96358c450f91a
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "[MASK]",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
| 3 |
+
size 760289
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"keep_accents": false,
|
| 7 |
+
"mask_token": {
|
| 8 |
+
"__type": "AddedToken",
|
| 9 |
+
"content": "[MASK]",
|
| 10 |
+
"lstrip": true,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"model_max_length": 512,
|
| 16 |
+
"name_or_path": "albert-base-v2",
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"remove_space": true,
|
| 19 |
+
"sep_token": "[SEP]",
|
| 20 |
+
"sp_model_kwargs": {},
|
| 21 |
+
"special_tokens_map_file": null,
|
| 22 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 23 |
+
"unk_token": "<unk>"
|
| 24 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.84251968503937,
|
| 5 |
+
"global_step": 17500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.28,
|
| 12 |
+
"learning_rate": 1.943757030371204e-05,
|
| 13 |
+
"loss": 2.7683,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.56,
|
| 18 |
+
"learning_rate": 1.8875140607424075e-05,
|
| 19 |
+
"loss": 2.7344,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.84,
|
| 24 |
+
"learning_rate": 1.831271091113611e-05,
|
| 25 |
+
"loss": 2.7195,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_loss": 2.712266206741333,
|
| 31 |
+
"eval_runtime": 91.7259,
|
| 32 |
+
"eval_samples_per_second": 174.433,
|
| 33 |
+
"eval_steps_per_second": 10.902,
|
| 34 |
+
"step": 1778
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 1.12,
|
| 38 |
+
"learning_rate": 1.7750281214848145e-05,
|
| 39 |
+
"loss": 2.6796,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.41,
|
| 44 |
+
"learning_rate": 1.7187851518560182e-05,
|
| 45 |
+
"loss": 2.6488,
|
| 46 |
+
"step": 2500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.69,
|
| 50 |
+
"learning_rate": 1.6625421822272215e-05,
|
| 51 |
+
"loss": 2.6372,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.97,
|
| 56 |
+
"learning_rate": 1.6062992125984255e-05,
|
| 57 |
+
"loss": 2.6415,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.0,
|
| 62 |
+
"eval_loss": 2.652708053588867,
|
| 63 |
+
"eval_runtime": 91.7276,
|
| 64 |
+
"eval_samples_per_second": 174.43,
|
| 65 |
+
"eval_steps_per_second": 10.902,
|
| 66 |
+
"step": 3556
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.25,
|
| 70 |
+
"learning_rate": 1.550056242969629e-05,
|
| 71 |
+
"loss": 2.5601,
|
| 72 |
+
"step": 4000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.53,
|
| 76 |
+
"learning_rate": 1.4938132733408325e-05,
|
| 77 |
+
"loss": 2.5407,
|
| 78 |
+
"step": 4500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.81,
|
| 82 |
+
"learning_rate": 1.437570303712036e-05,
|
| 83 |
+
"loss": 2.5308,
|
| 84 |
+
"step": 5000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.0,
|
| 88 |
+
"eval_loss": 2.6422665119171143,
|
| 89 |
+
"eval_runtime": 91.7218,
|
| 90 |
+
"eval_samples_per_second": 174.441,
|
| 91 |
+
"eval_steps_per_second": 10.903,
|
| 92 |
+
"step": 5334
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.09,
|
| 96 |
+
"learning_rate": 1.3813273340832395e-05,
|
| 97 |
+
"loss": 2.4873,
|
| 98 |
+
"step": 5500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.37,
|
| 102 |
+
"learning_rate": 1.3250843644544434e-05,
|
| 103 |
+
"loss": 2.3694,
|
| 104 |
+
"step": 6000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.66,
|
| 108 |
+
"learning_rate": 1.2688413948256469e-05,
|
| 109 |
+
"loss": 2.3697,
|
| 110 |
+
"step": 6500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.94,
|
| 114 |
+
"learning_rate": 1.2125984251968505e-05,
|
| 115 |
+
"loss": 2.3628,
|
| 116 |
+
"step": 7000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.0,
|
| 120 |
+
"eval_loss": 2.685481548309326,
|
| 121 |
+
"eval_runtime": 91.7025,
|
| 122 |
+
"eval_samples_per_second": 174.477,
|
| 123 |
+
"eval_steps_per_second": 10.905,
|
| 124 |
+
"step": 7112
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.22,
|
| 128 |
+
"learning_rate": 1.156355455568054e-05,
|
| 129 |
+
"loss": 2.1747,
|
| 130 |
+
"step": 7500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 4.5,
|
| 134 |
+
"learning_rate": 1.1001124859392579e-05,
|
| 135 |
+
"loss": 2.1037,
|
| 136 |
+
"step": 8000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.78,
|
| 140 |
+
"learning_rate": 1.0438695163104614e-05,
|
| 141 |
+
"loss": 2.1293,
|
| 142 |
+
"step": 8500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.0,
|
| 146 |
+
"eval_loss": 2.817112445831299,
|
| 147 |
+
"eval_runtime": 91.7137,
|
| 148 |
+
"eval_samples_per_second": 174.456,
|
| 149 |
+
"eval_steps_per_second": 10.904,
|
| 150 |
+
"step": 8890
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.06,
|
| 154 |
+
"learning_rate": 9.876265466816649e-06,
|
| 155 |
+
"loss": 2.0307,
|
| 156 |
+
"step": 9000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.34,
|
| 160 |
+
"learning_rate": 9.313835770528684e-06,
|
| 161 |
+
"loss": 1.7546,
|
| 162 |
+
"step": 9500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 5.62,
|
| 166 |
+
"learning_rate": 8.75140607424072e-06,
|
| 167 |
+
"loss": 1.752,
|
| 168 |
+
"step": 10000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.91,
|
| 172 |
+
"learning_rate": 8.188976377952757e-06,
|
| 173 |
+
"loss": 1.7463,
|
| 174 |
+
"step": 10500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.0,
|
| 178 |
+
"eval_loss": 3.0516531467437744,
|
| 179 |
+
"eval_runtime": 91.7177,
|
| 180 |
+
"eval_samples_per_second": 174.448,
|
| 181 |
+
"eval_steps_per_second": 10.903,
|
| 182 |
+
"step": 10668
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.19,
|
| 186 |
+
"learning_rate": 7.626546681664793e-06,
|
| 187 |
+
"loss": 1.4932,
|
| 188 |
+
"step": 11000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.47,
|
| 192 |
+
"learning_rate": 7.064116985376829e-06,
|
| 193 |
+
"loss": 1.3659,
|
| 194 |
+
"step": 11500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.75,
|
| 198 |
+
"learning_rate": 6.501687289088865e-06,
|
| 199 |
+
"loss": 1.3485,
|
| 200 |
+
"step": 12000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 7.0,
|
| 204 |
+
"eval_loss": 3.350566864013672,
|
| 205 |
+
"eval_runtime": 91.704,
|
| 206 |
+
"eval_samples_per_second": 174.474,
|
| 207 |
+
"eval_steps_per_second": 10.905,
|
| 208 |
+
"step": 12446
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 7.03,
|
| 212 |
+
"learning_rate": 5.9392575928009e-06,
|
| 213 |
+
"loss": 1.3203,
|
| 214 |
+
"step": 12500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 7.31,
|
| 218 |
+
"learning_rate": 5.376827896512936e-06,
|
| 219 |
+
"loss": 1.0176,
|
| 220 |
+
"step": 13000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 7.59,
|
| 224 |
+
"learning_rate": 4.814398200224972e-06,
|
| 225 |
+
"loss": 0.9999,
|
| 226 |
+
"step": 13500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.87,
|
| 230 |
+
"learning_rate": 4.251968503937008e-06,
|
| 231 |
+
"loss": 0.9889,
|
| 232 |
+
"step": 14000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 8.0,
|
| 236 |
+
"eval_loss": 3.6804659366607666,
|
| 237 |
+
"eval_runtime": 91.7068,
|
| 238 |
+
"eval_samples_per_second": 174.469,
|
| 239 |
+
"eval_steps_per_second": 10.904,
|
| 240 |
+
"step": 14224
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.16,
|
| 244 |
+
"learning_rate": 3.689538807649044e-06,
|
| 245 |
+
"loss": 0.8533,
|
| 246 |
+
"step": 14500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 8.44,
|
| 250 |
+
"learning_rate": 3.12710911136108e-06,
|
| 251 |
+
"loss": 0.7315,
|
| 252 |
+
"step": 15000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 8.72,
|
| 256 |
+
"learning_rate": 2.5646794150731156e-06,
|
| 257 |
+
"loss": 0.7194,
|
| 258 |
+
"step": 15500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 9.0,
|
| 262 |
+
"learning_rate": 2.002249718785152e-06,
|
| 263 |
+
"loss": 0.7069,
|
| 264 |
+
"step": 16000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.0,
|
| 268 |
+
"eval_loss": 3.918808698654175,
|
| 269 |
+
"eval_runtime": 91.7922,
|
| 270 |
+
"eval_samples_per_second": 174.307,
|
| 271 |
+
"eval_steps_per_second": 10.894,
|
| 272 |
+
"step": 16002
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 9.28,
|
| 276 |
+
"learning_rate": 1.4398200224971882e-06,
|
| 277 |
+
"loss": 0.5375,
|
| 278 |
+
"step": 16500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.56,
|
| 282 |
+
"learning_rate": 8.77390326209224e-07,
|
| 283 |
+
"loss": 0.533,
|
| 284 |
+
"step": 17000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.84,
|
| 288 |
+
"learning_rate": 3.149606299212599e-07,
|
| 289 |
+
"loss": 0.5276,
|
| 290 |
+
"step": 17500
|
| 291 |
+
}
|
| 292 |
+
],
|
| 293 |
+
"max_steps": 17780,
|
| 294 |
+
"num_train_epochs": 10,
|
| 295 |
+
"total_flos": 9948470041336704.0,
|
| 296 |
+
"trial_name": null,
|
| 297 |
+
"trial_params": null
|
| 298 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89dbca91b1a91d9cc84ccf2eca657cabe66ae6337d1891e925c2989736e53cd1
|
| 3 |
+
size 3503
|