Upload 8 files
Browse files- config.json +43 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +298 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 512,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "generate_story: "
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.27.4",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 32128
|
| 43 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.27.4"
|
| 7 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:971ea041f7fffe58b59c2f130a896cd3f45a27c296ac6b5b63db1cf8a0756c75
|
| 3 |
+
size 1980790149
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89bfe9e89a987660dea6c2e3f89a00497551e7e87016eb1d6161b5420d749e30
|
| 3 |
+
size 990408885
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1590c7b829674c91110c94ff3888b2f7ffb76e6dbe6d93b9c13bcec14d13a904
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fb923779d12241ecdce4de8de7a7936d411d8e46d758acad374bf40f5c2109f
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.517653273853197,
|
| 5 |
+
"global_step": 23500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 4.8532519370744304e-05,
|
| 13 |
+
"loss": 3.2928,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 4.706503874148862e-05,
|
| 19 |
+
"loss": 3.2304,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.35,
|
| 24 |
+
"learning_rate": 4.559755811223292e-05,
|
| 25 |
+
"loss": 3.2047,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.47,
|
| 30 |
+
"learning_rate": 4.413007748297723e-05,
|
| 31 |
+
"loss": 3.1857,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.59,
|
| 36 |
+
"learning_rate": 4.266259685372153e-05,
|
| 37 |
+
"loss": 3.1708,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.7,
|
| 42 |
+
"learning_rate": 4.1195116224465844e-05,
|
| 43 |
+
"loss": 3.162,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.82,
|
| 48 |
+
"learning_rate": 3.9727635595210145e-05,
|
| 49 |
+
"loss": 3.1554,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.94,
|
| 54 |
+
"learning_rate": 3.826015496595445e-05,
|
| 55 |
+
"loss": 3.1443,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.06,
|
| 60 |
+
"learning_rate": 3.6792674336698754e-05,
|
| 61 |
+
"loss": 3.1349,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.17,
|
| 66 |
+
"learning_rate": 3.532519370744307e-05,
|
| 67 |
+
"loss": 3.1265,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.29,
|
| 72 |
+
"learning_rate": 3.385771307818737e-05,
|
| 73 |
+
"loss": 3.1208,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.41,
|
| 78 |
+
"learning_rate": 3.239023244893167e-05,
|
| 79 |
+
"loss": 3.1183,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.53,
|
| 84 |
+
"learning_rate": 3.092275181967598e-05,
|
| 85 |
+
"loss": 3.1154,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.64,
|
| 90 |
+
"learning_rate": 2.9455271190420287e-05,
|
| 91 |
+
"loss": 3.109,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.76,
|
| 96 |
+
"learning_rate": 2.7987790561164595e-05,
|
| 97 |
+
"loss": 3.1061,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.88,
|
| 102 |
+
"learning_rate": 2.65203099319089e-05,
|
| 103 |
+
"loss": 3.1059,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0,
|
| 108 |
+
"learning_rate": 2.5052829302653208e-05,
|
| 109 |
+
"loss": 3.1018,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.11,
|
| 114 |
+
"learning_rate": 2.3585348673397513e-05,
|
| 115 |
+
"loss": 3.0926,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.23,
|
| 120 |
+
"learning_rate": 2.2117868044141817e-05,
|
| 121 |
+
"loss": 3.0933,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.35,
|
| 126 |
+
"learning_rate": 2.0650387414886125e-05,
|
| 127 |
+
"loss": 3.0893,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.47,
|
| 132 |
+
"learning_rate": 1.918290678563043e-05,
|
| 133 |
+
"loss": 3.0922,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.58,
|
| 138 |
+
"learning_rate": 1.7715426156374738e-05,
|
| 139 |
+
"loss": 3.0856,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.7,
|
| 144 |
+
"learning_rate": 1.6247945527119042e-05,
|
| 145 |
+
"loss": 3.0831,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.82,
|
| 150 |
+
"learning_rate": 1.478046489786335e-05,
|
| 151 |
+
"loss": 3.0846,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.93,
|
| 156 |
+
"learning_rate": 1.3312984268607657e-05,
|
| 157 |
+
"loss": 3.0803,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.05,
|
| 162 |
+
"learning_rate": 1.1845503639351961e-05,
|
| 163 |
+
"loss": 3.0762,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.17,
|
| 168 |
+
"learning_rate": 1.0378023010096268e-05,
|
| 169 |
+
"loss": 3.0781,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.29,
|
| 174 |
+
"learning_rate": 8.910542380840574e-06,
|
| 175 |
+
"loss": 3.0788,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.4,
|
| 180 |
+
"learning_rate": 7.443061751584879e-06,
|
| 181 |
+
"loss": 3.0742,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.52,
|
| 186 |
+
"learning_rate": 5.975581122329185e-06,
|
| 187 |
+
"loss": 3.0775,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.64,
|
| 192 |
+
"learning_rate": 4.508100493073491e-06,
|
| 193 |
+
"loss": 3.0749,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.76,
|
| 198 |
+
"learning_rate": 3.0406198638177975e-06,
|
| 199 |
+
"loss": 3.0721,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.87,
|
| 204 |
+
"learning_rate": 1.573139234562104e-06,
|
| 205 |
+
"loss": 3.0719,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.99,
|
| 210 |
+
"learning_rate": 1.0565860530640996e-07,
|
| 211 |
+
"loss": 3.0744,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.11,
|
| 216 |
+
"learning_rate": 2.431908898802536e-05,
|
| 217 |
+
"loss": 3.0706,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.23,
|
| 222 |
+
"learning_rate": 2.3585348673397513e-05,
|
| 223 |
+
"loss": 3.0717,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.34,
|
| 228 |
+
"learning_rate": 2.2851608358769667e-05,
|
| 229 |
+
"loss": 3.0702,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.46,
|
| 234 |
+
"learning_rate": 2.2117868044141817e-05,
|
| 235 |
+
"loss": 3.0674,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.58,
|
| 240 |
+
"learning_rate": 2.138412772951397e-05,
|
| 241 |
+
"loss": 3.066,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.7,
|
| 246 |
+
"learning_rate": 2.0650387414886125e-05,
|
| 247 |
+
"loss": 3.065,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.81,
|
| 252 |
+
"learning_rate": 1.991664710025828e-05,
|
| 253 |
+
"loss": 3.0648,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.93,
|
| 258 |
+
"learning_rate": 1.918290678563043e-05,
|
| 259 |
+
"loss": 3.0624,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.05,
|
| 264 |
+
"learning_rate": 1.8449166471002584e-05,
|
| 265 |
+
"loss": 3.0609,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.17,
|
| 270 |
+
"learning_rate": 1.7715426156374738e-05,
|
| 271 |
+
"loss": 3.0593,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.28,
|
| 276 |
+
"learning_rate": 1.698168584174689e-05,
|
| 277 |
+
"loss": 3.0543,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.4,
|
| 282 |
+
"learning_rate": 1.6247945527119042e-05,
|
| 283 |
+
"loss": 3.0545,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.52,
|
| 288 |
+
"learning_rate": 1.5514205212491196e-05,
|
| 289 |
+
"loss": 3.0564,
|
| 290 |
+
"step": 23500
|
| 291 |
+
}
|
| 292 |
+
],
|
| 293 |
+
"max_steps": 34072,
|
| 294 |
+
"num_train_epochs": 8,
|
| 295 |
+
"total_flos": 9.57852172757975e+16,
|
| 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:e63d221054bc764a9584141c03a3ca693e45c56216195dbcb340448ed0d4ac1f
|
| 3 |
+
size 3643
|