Training in progress, step 20500
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +242 -82
- last-checkpoint/training_args.bin +1 -1
- model.safetensors +1 -1
- runs/Jan21_09-30-28_854346de9726/events.out.tfevents.1705829428.854346de9726.164.1 +2 -2
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c43564e930260fa3abbd24ef8bc8e2019043f8ab0ea3f357c88632def606095f
|
| 3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 484163514
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5157a79613ec248ac8f7d1c8901dc35a0467ddf892a8d4eace27612fd7b9473d
|
| 3 |
size 484163514
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af796267785b8380aa702da74322c3a84f42d9cab004eb98c1af133c0218d64a
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b2103b3ba42c5a974b79f170c6d33390323651972016338595643ea512a6c2b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -11,279 +11,439 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.08,
|
| 13 |
"learning_rate": 0.0009846531614487416,
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.15,
|
| 19 |
"learning_rate": 0.0009693063228974831,
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.23,
|
| 25 |
"learning_rate": 0.0009539594843462247,
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.31,
|
| 31 |
"learning_rate": 0.0009386126457949663,
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.38,
|
| 37 |
"learning_rate": 0.0009232658072437078,
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 2500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.46,
|
| 43 |
"learning_rate": 0.0009079189686924494,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 3000
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.54,
|
| 49 |
"learning_rate": 0.000892572130141191,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 3500
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.61,
|
| 55 |
"learning_rate": 0.0008772252915899325,
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 4000
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.69,
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 4500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.77,
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 5000
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.84,
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 5500
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.92,
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 6000
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 1.0,
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 6500
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 1.0,
|
| 91 |
-
"eval_bleu":
|
| 92 |
-
"eval_gen_len": 18.
|
| 93 |
-
"eval_loss": 0.
|
| 94 |
-
"eval_runtime":
|
| 95 |
-
"eval_samples_per_second":
|
| 96 |
-
"eval_steps_per_second": 2.
|
| 97 |
"step": 6516
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 1.07,
|
| 101 |
-
"learning_rate": 0.
|
| 102 |
-
"loss": 0.
|
| 103 |
"step": 7000
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.15,
|
| 107 |
-
"learning_rate": 0.
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 7500
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.23,
|
| 113 |
-
"learning_rate": 0.
|
| 114 |
-
"loss": 0.
|
| 115 |
"step": 8000
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.3,
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 8500
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 1.38,
|
| 125 |
-
"learning_rate": 0.
|
| 126 |
-
"loss": 0.
|
| 127 |
"step": 9000
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.46,
|
| 131 |
-
"learning_rate": 0.
|
| 132 |
-
"loss": 0.
|
| 133 |
"step": 9500
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 1.53,
|
| 137 |
-
"learning_rate": 0.
|
| 138 |
-
"loss": 0.
|
| 139 |
"step": 10000
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 1.61,
|
| 143 |
-
"learning_rate": 0.
|
| 144 |
-
"loss": 0.
|
| 145 |
"step": 10500
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 1.69,
|
| 149 |
-
"learning_rate": 0.
|
| 150 |
-
"loss": 0.
|
| 151 |
"step": 11000
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.76,
|
| 155 |
-
"learning_rate": 0.
|
| 156 |
-
"loss": 0.
|
| 157 |
"step": 11500
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 1.84,
|
| 161 |
-
"learning_rate": 0.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 12000
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 1.92,
|
| 167 |
-
"learning_rate": 0.
|
| 168 |
-
"loss": 0.
|
| 169 |
"step": 12500
|
| 170 |
},
|
| 171 |
{
|
| 172 |
"epoch": 2.0,
|
| 173 |
-
"learning_rate": 0.
|
| 174 |
-
"loss": 0.
|
| 175 |
"step": 13000
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"epoch": 2.0,
|
| 179 |
-
"eval_bleu":
|
| 180 |
-
"eval_gen_len": 18.
|
| 181 |
-
"eval_loss": 0.
|
| 182 |
-
"eval_runtime":
|
| 183 |
-
"eval_samples_per_second": 41.
|
| 184 |
-
"eval_steps_per_second": 2.
|
| 185 |
"step": 13032
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 2.07,
|
| 189 |
"learning_rate": 0.0005857888275015347,
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 13500
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.15,
|
| 195 |
"learning_rate": 0.0005704419889502763,
|
| 196 |
-
"loss": 0.
|
| 197 |
"step": 14000
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.23,
|
| 201 |
"learning_rate": 0.0005550951503990178,
|
| 202 |
-
"loss": 0.
|
| 203 |
"step": 14500
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 2.3,
|
| 207 |
"learning_rate": 0.0005397483118477594,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 15000
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 2.38,
|
| 213 |
"learning_rate": 0.0005244014732965009,
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 15500
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 2.46,
|
| 219 |
-
"learning_rate": 0.
|
| 220 |
-
"loss": 0.
|
| 221 |
"step": 16000
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 2.53,
|
| 225 |
"learning_rate": 0.0004937384898710866,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 16500
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 2.61,
|
| 231 |
"learning_rate": 0.00047839165131982814,
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 17000
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 2.69,
|
| 237 |
"learning_rate": 0.0004630448127685697,
|
| 238 |
-
"loss": 0.
|
| 239 |
"step": 17500
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 2.76,
|
| 243 |
-
"learning_rate": 0.
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 18000
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 2.84,
|
| 249 |
"learning_rate": 0.00043238182934315537,
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 18500
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 2.92,
|
| 255 |
"learning_rate": 0.00041703499079189687,
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 19000
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 2.99,
|
| 261 |
"learning_rate": 0.0004016881522406384,
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 19500
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 3.0,
|
| 267 |
-
"eval_bleu":
|
| 268 |
-
"eval_gen_len": 18.
|
| 269 |
-
"eval_loss": 0.
|
| 270 |
-
"eval_runtime": 23.
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second": 2.
|
| 273 |
"step": 19548
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 3.07,
|
| 277 |
-
"learning_rate": 0.
|
| 278 |
-
"loss": 0.
|
| 279 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 280 |
}
|
| 281 |
],
|
| 282 |
"logging_steps": 500,
|
| 283 |
"max_steps": 32580,
|
| 284 |
"num_train_epochs": 5,
|
| 285 |
"save_steps": 500,
|
| 286 |
-
"total_flos": 1.
|
| 287 |
"trial_name": null,
|
| 288 |
"trial_params": null
|
| 289 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.987722529158994,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 32500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.08,
|
| 13 |
"learning_rate": 0.0009846531614487416,
|
| 14 |
+
"loss": 0.5762,
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.15,
|
| 19 |
"learning_rate": 0.0009693063228974831,
|
| 20 |
+
"loss": 0.6042,
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.23,
|
| 25 |
"learning_rate": 0.0009539594843462247,
|
| 26 |
+
"loss": 0.6024,
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.31,
|
| 31 |
"learning_rate": 0.0009386126457949663,
|
| 32 |
+
"loss": 0.6057,
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.38,
|
| 37 |
"learning_rate": 0.0009232658072437078,
|
| 38 |
+
"loss": 0.6143,
|
| 39 |
"step": 2500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.46,
|
| 43 |
"learning_rate": 0.0009079189686924494,
|
| 44 |
+
"loss": 0.6081,
|
| 45 |
"step": 3000
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.54,
|
| 49 |
"learning_rate": 0.000892572130141191,
|
| 50 |
+
"loss": 0.611,
|
| 51 |
"step": 3500
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.61,
|
| 55 |
"learning_rate": 0.0008772252915899325,
|
| 56 |
+
"loss": 0.6104,
|
| 57 |
"step": 4000
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.69,
|
| 61 |
+
"learning_rate": 0.0008619091467157766,
|
| 62 |
+
"loss": 0.6154,
|
| 63 |
"step": 4500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.77,
|
| 67 |
+
"learning_rate": 0.0008465623081645181,
|
| 68 |
+
"loss": 0.6151,
|
| 69 |
"step": 5000
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.84,
|
| 73 |
+
"learning_rate": 0.0008312154696132597,
|
| 74 |
+
"loss": 0.611,
|
| 75 |
"step": 5500
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.92,
|
| 79 |
+
"learning_rate": 0.0008158686310620012,
|
| 80 |
+
"loss": 0.617,
|
| 81 |
"step": 6000
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 1.0,
|
| 85 |
+
"learning_rate": 0.0008005524861878454,
|
| 86 |
+
"loss": 0.6089,
|
| 87 |
"step": 6500
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 1.0,
|
| 91 |
+
"eval_bleu": 3.6822,
|
| 92 |
+
"eval_gen_len": 18.235,
|
| 93 |
+
"eval_loss": 0.506125271320343,
|
| 94 |
+
"eval_runtime": 27.1471,
|
| 95 |
+
"eval_samples_per_second": 36.836,
|
| 96 |
+
"eval_steps_per_second": 2.321,
|
| 97 |
"step": 6516
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 1.07,
|
| 101 |
+
"learning_rate": 0.0007852056476365869,
|
| 102 |
+
"loss": 0.5657,
|
| 103 |
"step": 7000
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.15,
|
| 107 |
+
"learning_rate": 0.0007698588090853285,
|
| 108 |
+
"loss": 0.5623,
|
| 109 |
"step": 7500
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.23,
|
| 113 |
+
"learning_rate": 0.0007545119705340699,
|
| 114 |
+
"loss": 0.5669,
|
| 115 |
"step": 8000
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.3,
|
| 119 |
+
"learning_rate": 0.000739195825659914,
|
| 120 |
+
"loss": 0.5793,
|
| 121 |
"step": 8500
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 1.38,
|
| 125 |
+
"learning_rate": 0.0007238489871086557,
|
| 126 |
+
"loss": 0.5743,
|
| 127 |
"step": 9000
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.46,
|
| 131 |
+
"learning_rate": 0.0007085328422344997,
|
| 132 |
+
"loss": 0.5722,
|
| 133 |
"step": 9500
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 1.53,
|
| 137 |
+
"learning_rate": 0.0006931860036832413,
|
| 138 |
+
"loss": 0.5749,
|
| 139 |
"step": 10000
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 1.61,
|
| 143 |
+
"learning_rate": 0.0006778391651319828,
|
| 144 |
+
"loss": 0.5776,
|
| 145 |
"step": 10500
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 1.69,
|
| 149 |
+
"learning_rate": 0.0006624923265807244,
|
| 150 |
+
"loss": 0.5694,
|
| 151 |
"step": 11000
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.76,
|
| 155 |
+
"learning_rate": 0.0006471454880294659,
|
| 156 |
+
"loss": 0.5716,
|
| 157 |
"step": 11500
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 1.84,
|
| 161 |
+
"learning_rate": 0.0006317986494782076,
|
| 162 |
+
"loss": 0.5665,
|
| 163 |
"step": 12000
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 1.92,
|
| 167 |
+
"learning_rate": 0.000616451810926949,
|
| 168 |
+
"loss": 0.5671,
|
| 169 |
"step": 12500
|
| 170 |
},
|
| 171 |
{
|
| 172 |
"epoch": 2.0,
|
| 173 |
+
"learning_rate": 0.0006011049723756906,
|
| 174 |
+
"loss": 0.5687,
|
| 175 |
"step": 13000
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"epoch": 2.0,
|
| 179 |
+
"eval_bleu": 3.7119,
|
| 180 |
+
"eval_gen_len": 18.222,
|
| 181 |
+
"eval_loss": 0.495604932308197,
|
| 182 |
+
"eval_runtime": 23.8741,
|
| 183 |
+
"eval_samples_per_second": 41.886,
|
| 184 |
+
"eval_steps_per_second": 2.639,
|
| 185 |
"step": 13032
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 2.07,
|
| 189 |
"learning_rate": 0.0005857888275015347,
|
| 190 |
+
"loss": 0.5307,
|
| 191 |
"step": 13500
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.15,
|
| 195 |
"learning_rate": 0.0005704419889502763,
|
| 196 |
+
"loss": 0.5325,
|
| 197 |
"step": 14000
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.23,
|
| 201 |
"learning_rate": 0.0005550951503990178,
|
| 202 |
+
"loss": 0.5353,
|
| 203 |
"step": 14500
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 2.3,
|
| 207 |
"learning_rate": 0.0005397483118477594,
|
| 208 |
+
"loss": 0.5289,
|
| 209 |
"step": 15000
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 2.38,
|
| 213 |
"learning_rate": 0.0005244014732965009,
|
| 214 |
+
"loss": 0.5321,
|
| 215 |
"step": 15500
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 2.46,
|
| 219 |
+
"learning_rate": 0.000509085328422345,
|
| 220 |
+
"loss": 0.5271,
|
| 221 |
"step": 16000
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 2.53,
|
| 225 |
"learning_rate": 0.0004937384898710866,
|
| 226 |
+
"loss": 0.5295,
|
| 227 |
"step": 16500
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 2.61,
|
| 231 |
"learning_rate": 0.00047839165131982814,
|
| 232 |
+
"loss": 0.524,
|
| 233 |
"step": 17000
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 2.69,
|
| 237 |
"learning_rate": 0.0004630448127685697,
|
| 238 |
+
"loss": 0.526,
|
| 239 |
"step": 17500
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 2.76,
|
| 243 |
+
"learning_rate": 0.00044772866789441376,
|
| 244 |
+
"loss": 0.5323,
|
| 245 |
"step": 18000
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 2.84,
|
| 249 |
"learning_rate": 0.00043238182934315537,
|
| 250 |
+
"loss": 0.5236,
|
| 251 |
"step": 18500
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 2.92,
|
| 255 |
"learning_rate": 0.00041703499079189687,
|
| 256 |
+
"loss": 0.5266,
|
| 257 |
"step": 19000
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 2.99,
|
| 261 |
"learning_rate": 0.0004016881522406384,
|
| 262 |
+
"loss": 0.525,
|
| 263 |
"step": 19500
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 3.0,
|
| 267 |
+
"eval_bleu": 3.8722,
|
| 268 |
+
"eval_gen_len": 18.219,
|
| 269 |
+
"eval_loss": 0.4868793785572052,
|
| 270 |
+
"eval_runtime": 23.2067,
|
| 271 |
+
"eval_samples_per_second": 43.091,
|
| 272 |
+
"eval_steps_per_second": 2.715,
|
| 273 |
"step": 19548
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 3.07,
|
| 277 |
+
"learning_rate": 0.00038637200736648254,
|
| 278 |
+
"loss": 0.4934,
|
| 279 |
"step": 20000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.15,
|
| 283 |
+
"learning_rate": 0.0003710251688152241,
|
| 284 |
+
"loss": 0.4869,
|
| 285 |
+
"step": 20500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.22,
|
| 289 |
+
"learning_rate": 0.0003556783302639656,
|
| 290 |
+
"loss": 0.4917,
|
| 291 |
+
"step": 21000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.3,
|
| 295 |
+
"learning_rate": 0.00034033149171270715,
|
| 296 |
+
"loss": 0.4841,
|
| 297 |
+
"step": 21500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.38,
|
| 301 |
+
"learning_rate": 0.00032501534683855126,
|
| 302 |
+
"loss": 0.4906,
|
| 303 |
+
"step": 22000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.45,
|
| 307 |
+
"learning_rate": 0.0003096685082872928,
|
| 308 |
+
"loss": 0.4884,
|
| 309 |
+
"step": 22500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.53,
|
| 313 |
+
"learning_rate": 0.0002943216697360344,
|
| 314 |
+
"loss": 0.486,
|
| 315 |
+
"step": 23000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.61,
|
| 319 |
+
"learning_rate": 0.00027897483118477593,
|
| 320 |
+
"loss": 0.4932,
|
| 321 |
+
"step": 23500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.68,
|
| 325 |
+
"learning_rate": 0.00026365868631062,
|
| 326 |
+
"loss": 0.4951,
|
| 327 |
+
"step": 24000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.76,
|
| 331 |
+
"learning_rate": 0.0002483118477593616,
|
| 332 |
+
"loss": 0.4896,
|
| 333 |
+
"step": 24500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.84,
|
| 337 |
+
"learning_rate": 0.00023296500920810313,
|
| 338 |
+
"loss": 0.4832,
|
| 339 |
+
"step": 25000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.91,
|
| 343 |
+
"learning_rate": 0.00021761817065684468,
|
| 344 |
+
"loss": 0.4874,
|
| 345 |
+
"step": 25500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.99,
|
| 349 |
+
"learning_rate": 0.00020230202578268877,
|
| 350 |
+
"loss": 0.488,
|
| 351 |
+
"step": 26000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.0,
|
| 355 |
+
"eval_bleu": 3.7886,
|
| 356 |
+
"eval_gen_len": 18.23,
|
| 357 |
+
"eval_loss": 0.4795362949371338,
|
| 358 |
+
"eval_runtime": 23.2422,
|
| 359 |
+
"eval_samples_per_second": 43.025,
|
| 360 |
+
"eval_steps_per_second": 2.711,
|
| 361 |
+
"step": 26064
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.07,
|
| 365 |
+
"learning_rate": 0.00018695518723143033,
|
| 366 |
+
"loss": 0.4583,
|
| 367 |
+
"step": 26500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.14,
|
| 371 |
+
"learning_rate": 0.00017160834868017188,
|
| 372 |
+
"loss": 0.4495,
|
| 373 |
+
"step": 27000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.22,
|
| 377 |
+
"learning_rate": 0.00015626151012891346,
|
| 378 |
+
"loss": 0.454,
|
| 379 |
+
"step": 27500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 4.3,
|
| 383 |
+
"learning_rate": 0.00014094536525475752,
|
| 384 |
+
"loss": 0.4547,
|
| 385 |
+
"step": 28000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 4.37,
|
| 389 |
+
"learning_rate": 0.00012559852670349908,
|
| 390 |
+
"loss": 0.4588,
|
| 391 |
+
"step": 28500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 4.45,
|
| 395 |
+
"learning_rate": 0.00011025168815224063,
|
| 396 |
+
"loss": 0.453,
|
| 397 |
+
"step": 29000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 4.53,
|
| 401 |
+
"learning_rate": 9.49048496009822e-05,
|
| 402 |
+
"loss": 0.4549,
|
| 403 |
+
"step": 29500
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 4.6,
|
| 407 |
+
"learning_rate": 7.955801104972376e-05,
|
| 408 |
+
"loss": 0.4533,
|
| 409 |
+
"step": 30000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.68,
|
| 413 |
+
"learning_rate": 6.424186617556783e-05,
|
| 414 |
+
"loss": 0.4495,
|
| 415 |
+
"step": 30500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.76,
|
| 419 |
+
"learning_rate": 4.8895027624309394e-05,
|
| 420 |
+
"loss": 0.4555,
|
| 421 |
+
"step": 31000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 4.83,
|
| 425 |
+
"learning_rate": 3.3548189073050956e-05,
|
| 426 |
+
"loss": 0.4563,
|
| 427 |
+
"step": 31500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.91,
|
| 431 |
+
"learning_rate": 1.820135052179251e-05,
|
| 432 |
+
"loss": 0.4563,
|
| 433 |
+
"step": 32000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 4.99,
|
| 437 |
+
"learning_rate": 2.885205647636587e-06,
|
| 438 |
+
"loss": 0.4527,
|
| 439 |
+
"step": 32500
|
| 440 |
}
|
| 441 |
],
|
| 442 |
"logging_steps": 500,
|
| 443 |
"max_steps": 32580,
|
| 444 |
"num_train_epochs": 5,
|
| 445 |
"save_steps": 500,
|
| 446 |
+
"total_flos": 1.7233985138589696e+16,
|
| 447 |
"trial_name": null,
|
| 448 |
"trial_params": null
|
| 449 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbbc9f6fd02ff4264ade394c37847b822a605f5a9ef106ad63ba6639ed6bf7c2
|
| 3 |
size 4792
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f41bb533aa86e301a1be3b65f96c1170612ae823deb447e90a35a957837ed0d
|
| 3 |
size 242041896
|
runs/Jan21_09-30-28_854346de9726/events.out.tfevents.1705829428.854346de9726.164.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78e7c058478c3d5d58805cbb2ff89ae6ffe9f56ad419227b33a3cfe9558d088e
|
| 3 |
+
size 12849
|