Upload model
Browse files- config.json +36 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +350 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"text-generation": {
|
| 29 |
+
"do_sample": true,
|
| 30 |
+
"max_length": 50
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"transformers_version": "4.2.0dev0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 50257
|
| 36 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d51261c2aaa9e6845da2a71bc04018b27a036465862592ca74b19d7a4f3ea057
|
| 3 |
+
size 510406261
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.956383822363204,
|
| 5 |
+
"global_step": 25000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.00019825535289452815,
|
| 12 |
+
"learning_rate": 4.999801744647106e-05,
|
| 13 |
+
"loss": 1.8367067575454712,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09912767644726407,
|
| 18 |
+
"learning_rate": 4.900872323552736e-05,
|
| 19 |
+
"loss": 1.3704102541019538,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.19825535289452814,
|
| 24 |
+
"learning_rate": 4.8017446471054725e-05,
|
| 25 |
+
"loss": 1.251982177734375,
|
| 26 |
+
"step": 1000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.2973830293417922,
|
| 30 |
+
"learning_rate": 4.702616970658208e-05,
|
| 31 |
+
"loss": 1.198458984375,
|
| 32 |
+
"step": 1500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.3965107057890563,
|
| 36 |
+
"learning_rate": 4.6034892942109434e-05,
|
| 37 |
+
"loss": 1.162800048828125,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4956383822363204,
|
| 42 |
+
"learning_rate": 4.50436161776368e-05,
|
| 43 |
+
"loss": 1.13400244140625,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5947660586835845,
|
| 48 |
+
"learning_rate": 4.405233941316416e-05,
|
| 49 |
+
"loss": 1.11087890625,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.6938937351308485,
|
| 54 |
+
"learning_rate": 4.306106264869152e-05,
|
| 55 |
+
"loss": 1.081130615234375,
|
| 56 |
+
"step": 3500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.7930214115781126,
|
| 60 |
+
"learning_rate": 4.206978588421887e-05,
|
| 61 |
+
"loss": 1.06674853515625,
|
| 62 |
+
"step": 4000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.8921490880253767,
|
| 66 |
+
"learning_rate": 4.1078509119746235e-05,
|
| 67 |
+
"loss": 1.0396920166015624,
|
| 68 |
+
"step": 4500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.9912767644726408,
|
| 72 |
+
"learning_rate": 4.0087232355273596e-05,
|
| 73 |
+
"loss": 1.04483740234375,
|
| 74 |
+
"step": 5000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_loss": 1.019631266593933,
|
| 79 |
+
"eval_runtime": 100.3363,
|
| 80 |
+
"eval_samples_per_second": 48.337,
|
| 81 |
+
"step": 5044
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0904044409199047,
|
| 85 |
+
"learning_rate": 3.909595559080095e-05,
|
| 86 |
+
"loss": 0.9977613525390625,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.189532117367169,
|
| 91 |
+
"learning_rate": 3.810467882632831e-05,
|
| 92 |
+
"loss": 1.0038666381835937,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2886597938144329,
|
| 97 |
+
"learning_rate": 3.7113402061855674e-05,
|
| 98 |
+
"loss": 0.9831958618164063,
|
| 99 |
+
"step": 6500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.387787470261697,
|
| 103 |
+
"learning_rate": 3.612212529738303e-05,
|
| 104 |
+
"loss": 0.9712546997070313,
|
| 105 |
+
"step": 7000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.4869151467089612,
|
| 109 |
+
"learning_rate": 3.513084853291039e-05,
|
| 110 |
+
"loss": 0.9686679077148438,
|
| 111 |
+
"step": 7500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.5860428231562254,
|
| 115 |
+
"learning_rate": 3.413957176843775e-05,
|
| 116 |
+
"loss": 0.9620776977539063,
|
| 117 |
+
"step": 8000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.6851704996034893,
|
| 121 |
+
"learning_rate": 3.3148295003965106e-05,
|
| 122 |
+
"loss": 0.9629462280273438,
|
| 123 |
+
"step": 8500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.7842981760507532,
|
| 127 |
+
"learning_rate": 3.215701823949247e-05,
|
| 128 |
+
"loss": 0.9611924438476562,
|
| 129 |
+
"step": 9000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.8834258524980174,
|
| 133 |
+
"learning_rate": 3.116574147501983e-05,
|
| 134 |
+
"loss": 0.9391554565429687,
|
| 135 |
+
"step": 9500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.9825535289452816,
|
| 139 |
+
"learning_rate": 3.0174464710547183e-05,
|
| 140 |
+
"loss": 0.914335693359375,
|
| 141 |
+
"step": 10000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.0,
|
| 145 |
+
"eval_loss": 0.9528790712356567,
|
| 146 |
+
"eval_runtime": 97.3788,
|
| 147 |
+
"eval_samples_per_second": 49.806,
|
| 148 |
+
"step": 10088
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.0816812053925458,
|
| 152 |
+
"learning_rate": 2.9183187946074548e-05,
|
| 153 |
+
"loss": 0.9097555541992187,
|
| 154 |
+
"step": 10500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.1808088818398095,
|
| 158 |
+
"learning_rate": 2.8191911181601906e-05,
|
| 159 |
+
"loss": 0.9029483642578126,
|
| 160 |
+
"step": 11000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.2799365582870736,
|
| 164 |
+
"learning_rate": 2.720063441712926e-05,
|
| 165 |
+
"loss": 0.915561279296875,
|
| 166 |
+
"step": 11500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.379064234734338,
|
| 170 |
+
"learning_rate": 2.6209357652656625e-05,
|
| 171 |
+
"loss": 0.8945721435546875,
|
| 172 |
+
"step": 12000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.478191911181602,
|
| 176 |
+
"learning_rate": 2.521808088818398e-05,
|
| 177 |
+
"loss": 0.8839064331054688,
|
| 178 |
+
"step": 12500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.5773195876288657,
|
| 182 |
+
"learning_rate": 2.422680412371134e-05,
|
| 183 |
+
"loss": 0.8842523193359375,
|
| 184 |
+
"step": 13000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.6764472640761303,
|
| 188 |
+
"learning_rate": 2.3235527359238703e-05,
|
| 189 |
+
"loss": 0.9003340454101563,
|
| 190 |
+
"step": 13500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.775574940523394,
|
| 194 |
+
"learning_rate": 2.2244250594766057e-05,
|
| 195 |
+
"loss": 0.9045031127929688,
|
| 196 |
+
"step": 14000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.874702616970658,
|
| 200 |
+
"learning_rate": 2.125297383029342e-05,
|
| 201 |
+
"loss": 0.8826250610351563,
|
| 202 |
+
"step": 14500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.9738302934179224,
|
| 206 |
+
"learning_rate": 2.0261697065820777e-05,
|
| 207 |
+
"loss": 0.8844521484375,
|
| 208 |
+
"step": 15000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.0,
|
| 212 |
+
"eval_loss": 0.9211767911911011,
|
| 213 |
+
"eval_runtime": 97.3999,
|
| 214 |
+
"eval_samples_per_second": 49.795,
|
| 215 |
+
"step": 15132
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.0729579698651865,
|
| 219 |
+
"learning_rate": 1.9270420301348138e-05,
|
| 220 |
+
"loss": 0.86255712890625,
|
| 221 |
+
"step": 15500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.1720856463124503,
|
| 225 |
+
"learning_rate": 1.8279143536875496e-05,
|
| 226 |
+
"loss": 0.8561475219726562,
|
| 227 |
+
"step": 16000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.2712133227597144,
|
| 231 |
+
"learning_rate": 1.7287866772402854e-05,
|
| 232 |
+
"loss": 0.8540064086914062,
|
| 233 |
+
"step": 16500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.3703409992069786,
|
| 237 |
+
"learning_rate": 1.6296590007930216e-05,
|
| 238 |
+
"loss": 0.8526674194335937,
|
| 239 |
+
"step": 17000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.4694686756542428,
|
| 243 |
+
"learning_rate": 1.5305313243457574e-05,
|
| 244 |
+
"loss": 0.8742741088867187,
|
| 245 |
+
"step": 17500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.5685963521015065,
|
| 249 |
+
"learning_rate": 1.4314036478984932e-05,
|
| 250 |
+
"loss": 0.8503397827148438,
|
| 251 |
+
"step": 18000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.6677240285487707,
|
| 255 |
+
"learning_rate": 1.3322759714512293e-05,
|
| 256 |
+
"loss": 0.8602479858398437,
|
| 257 |
+
"step": 18500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.766851704996035,
|
| 261 |
+
"learning_rate": 1.2331482950039653e-05,
|
| 262 |
+
"loss": 0.8511823120117188,
|
| 263 |
+
"step": 19000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.865979381443299,
|
| 267 |
+
"learning_rate": 1.134020618556701e-05,
|
| 268 |
+
"loss": 0.8461943969726563,
|
| 269 |
+
"step": 19500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.965107057890563,
|
| 273 |
+
"learning_rate": 1.0348929421094369e-05,
|
| 274 |
+
"loss": 0.8488275756835938,
|
| 275 |
+
"step": 20000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 4.0,
|
| 279 |
+
"eval_loss": 0.9062384963035583,
|
| 280 |
+
"eval_runtime": 102.3438,
|
| 281 |
+
"eval_samples_per_second": 47.389,
|
| 282 |
+
"step": 20176
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.064234734337827,
|
| 286 |
+
"learning_rate": 9.357652656621729e-06,
|
| 287 |
+
"loss": 0.8355828247070313,
|
| 288 |
+
"step": 20500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.1633624107850915,
|
| 292 |
+
"learning_rate": 8.366375892149088e-06,
|
| 293 |
+
"loss": 0.818786865234375,
|
| 294 |
+
"step": 21000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.262490087232355,
|
| 298 |
+
"learning_rate": 7.375099127676448e-06,
|
| 299 |
+
"loss": 0.8390009765625,
|
| 300 |
+
"step": 21500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 4.361617763679619,
|
| 304 |
+
"learning_rate": 6.383822363203806e-06,
|
| 305 |
+
"loss": 0.8276206665039062,
|
| 306 |
+
"step": 22000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.460745440126884,
|
| 310 |
+
"learning_rate": 5.3925455987311665e-06,
|
| 311 |
+
"loss": 0.8275084228515625,
|
| 312 |
+
"step": 22500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.559873116574147,
|
| 316 |
+
"learning_rate": 4.401268834258525e-06,
|
| 317 |
+
"loss": 0.8400993041992187,
|
| 318 |
+
"step": 23000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.659000793021412,
|
| 322 |
+
"learning_rate": 3.4099920697858843e-06,
|
| 323 |
+
"loss": 0.8316345825195313,
|
| 324 |
+
"step": 23500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.758128469468676,
|
| 328 |
+
"learning_rate": 2.4187153053132435e-06,
|
| 329 |
+
"loss": 0.8403876953125,
|
| 330 |
+
"step": 24000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.857256145915939,
|
| 334 |
+
"learning_rate": 1.4274385408406028e-06,
|
| 335 |
+
"loss": 0.8376466674804688,
|
| 336 |
+
"step": 24500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.956383822363204,
|
| 340 |
+
"learning_rate": 4.3616177636796196e-07,
|
| 341 |
+
"loss": 0.8198423461914063,
|
| 342 |
+
"step": 25000
|
| 343 |
+
}
|
| 344 |
+
],
|
| 345 |
+
"max_steps": 25220,
|
| 346 |
+
"num_train_epochs": 5,
|
| 347 |
+
"total_flos": 76452759802478592,
|
| 348 |
+
"trial_name": null,
|
| 349 |
+
"trial_params": null
|
| 350 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b039193a0416e7f58deb6ce1cbce7a8a092b42c92bd4ee5bcd9e4574cb0659d2
|
| 3 |
+
size 2031
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|