Training in progress, step 2404, checkpoint
Browse files
last-checkpoint/trainer_state.json
CHANGED
|
@@ -25,9 +25,9 @@
|
|
| 25 |
{
|
| 26 |
"epoch": 0.1662510390689942,
|
| 27 |
"eval_loss": 0.35283052921295166,
|
| 28 |
-
"eval_runtime":
|
| 29 |
-
"eval_samples_per_second":
|
| 30 |
-
"eval_steps_per_second": 1.
|
| 31 |
"step": 100
|
| 32 |
},
|
| 33 |
{
|
|
@@ -47,9 +47,9 @@
|
|
| 47 |
{
|
| 48 |
"epoch": 0.3325020781379884,
|
| 49 |
"eval_loss": 0.30865946412086487,
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second": 1.
|
| 53 |
"step": 200
|
| 54 |
},
|
| 55 |
{
|
|
@@ -69,9 +69,9 @@
|
|
| 69 |
{
|
| 70 |
"epoch": 0.49875311720698257,
|
| 71 |
"eval_loss": 0.2891499996185303,
|
| 72 |
-
"eval_runtime":
|
| 73 |
-
"eval_samples_per_second":
|
| 74 |
-
"eval_steps_per_second": 1.
|
| 75 |
"step": 300
|
| 76 |
},
|
| 77 |
{
|
|
@@ -91,9 +91,9 @@
|
|
| 91 |
{
|
| 92 |
"epoch": 0.6650041562759768,
|
| 93 |
"eval_loss": 0.2757515609264374,
|
| 94 |
-
"eval_runtime":
|
| 95 |
-
"eval_samples_per_second":
|
| 96 |
-
"eval_steps_per_second": 1.
|
| 97 |
"step": 400
|
| 98 |
},
|
| 99 |
{
|
|
@@ -113,9 +113,9 @@
|
|
| 113 |
{
|
| 114 |
"epoch": 0.8312551953449709,
|
| 115 |
"eval_loss": 0.2673098146915436,
|
| 116 |
-
"eval_runtime":
|
| 117 |
-
"eval_samples_per_second":
|
| 118 |
-
"eval_steps_per_second": 1.
|
| 119 |
"step": 500
|
| 120 |
},
|
| 121 |
{
|
|
@@ -135,9 +135,9 @@
|
|
| 135 |
{
|
| 136 |
"epoch": 0.9975062344139651,
|
| 137 |
"eval_loss": 0.26070085167884827,
|
| 138 |
-
"eval_runtime":
|
| 139 |
-
"eval_samples_per_second": 13.
|
| 140 |
-
"eval_steps_per_second": 1.
|
| 141 |
"step": 600
|
| 142 |
},
|
| 143 |
{
|
|
@@ -157,9 +157,9 @@
|
|
| 157 |
{
|
| 158 |
"epoch": 1.1637572734829593,
|
| 159 |
"eval_loss": 0.256939560174942,
|
| 160 |
-
"eval_runtime":
|
| 161 |
-
"eval_samples_per_second":
|
| 162 |
-
"eval_steps_per_second": 1.
|
| 163 |
"step": 700
|
| 164 |
},
|
| 165 |
{
|
|
@@ -179,9 +179,9 @@
|
|
| 179 |
{
|
| 180 |
"epoch": 1.3300083125519535,
|
| 181 |
"eval_loss": 0.2525966763496399,
|
| 182 |
-
"eval_runtime":
|
| 183 |
-
"eval_samples_per_second":
|
| 184 |
-
"eval_steps_per_second": 1.
|
| 185 |
"step": 800
|
| 186 |
},
|
| 187 |
{
|
|
@@ -201,9 +201,9 @@
|
|
| 201 |
{
|
| 202 |
"epoch": 1.4962593516209477,
|
| 203 |
"eval_loss": 0.24994711577892303,
|
| 204 |
-
"eval_runtime":
|
| 205 |
-
"eval_samples_per_second": 13.
|
| 206 |
-
"eval_steps_per_second": 1.
|
| 207 |
"step": 900
|
| 208 |
},
|
| 209 |
{
|
|
@@ -223,9 +223,9 @@
|
|
| 223 |
{
|
| 224 |
"epoch": 1.6625103906899419,
|
| 225 |
"eval_loss": 0.246443971991539,
|
| 226 |
-
"eval_runtime":
|
| 227 |
-
"eval_samples_per_second": 13.
|
| 228 |
-
"eval_steps_per_second": 1.
|
| 229 |
"step": 1000
|
| 230 |
},
|
| 231 |
{
|
|
@@ -245,9 +245,9 @@
|
|
| 245 |
{
|
| 246 |
"epoch": 1.828761429758936,
|
| 247 |
"eval_loss": 0.24409395456314087,
|
| 248 |
-
"eval_runtime":
|
| 249 |
-
"eval_samples_per_second": 13.
|
| 250 |
-
"eval_steps_per_second": 1.
|
| 251 |
"step": 1100
|
| 252 |
},
|
| 253 |
{
|
|
@@ -267,9 +267,9 @@
|
|
| 267 |
{
|
| 268 |
"epoch": 1.9950124688279303,
|
| 269 |
"eval_loss": 0.2411041557788849,
|
| 270 |
-
"eval_runtime":
|
| 271 |
-
"eval_samples_per_second": 13.
|
| 272 |
-
"eval_steps_per_second": 1.
|
| 273 |
"step": 1200
|
| 274 |
},
|
| 275 |
{
|
|
@@ -289,9 +289,9 @@
|
|
| 289 |
{
|
| 290 |
"epoch": 2.1612635078969245,
|
| 291 |
"eval_loss": 0.23963774740695953,
|
| 292 |
-
"eval_runtime":
|
| 293 |
-
"eval_samples_per_second": 13.
|
| 294 |
-
"eval_steps_per_second": 1.
|
| 295 |
"step": 1300
|
| 296 |
},
|
| 297 |
{
|
|
@@ -311,9 +311,9 @@
|
|
| 311 |
{
|
| 312 |
"epoch": 2.3275145469659186,
|
| 313 |
"eval_loss": 0.23829442262649536,
|
| 314 |
-
"eval_runtime":
|
| 315 |
-
"eval_samples_per_second": 13.
|
| 316 |
-
"eval_steps_per_second": 1.
|
| 317 |
"step": 1400
|
| 318 |
},
|
| 319 |
{
|
|
@@ -333,9 +333,9 @@
|
|
| 333 |
{
|
| 334 |
"epoch": 2.493765586034913,
|
| 335 |
"eval_loss": 0.2369847148656845,
|
| 336 |
-
"eval_runtime":
|
| 337 |
-
"eval_samples_per_second":
|
| 338 |
-
"eval_steps_per_second": 1.
|
| 339 |
"step": 1500
|
| 340 |
},
|
| 341 |
{
|
|
@@ -355,9 +355,9 @@
|
|
| 355 |
{
|
| 356 |
"epoch": 2.660016625103907,
|
| 357 |
"eval_loss": 0.23503336310386658,
|
| 358 |
-
"eval_runtime":
|
| 359 |
-
"eval_samples_per_second": 13.
|
| 360 |
-
"eval_steps_per_second": 1.
|
| 361 |
"step": 1600
|
| 362 |
},
|
| 363 |
{
|
|
@@ -377,9 +377,9 @@
|
|
| 377 |
{
|
| 378 |
"epoch": 2.826267664172901,
|
| 379 |
"eval_loss": 0.23422521352767944,
|
| 380 |
-
"eval_runtime":
|
| 381 |
-
"eval_samples_per_second": 13.
|
| 382 |
-
"eval_steps_per_second": 1.
|
| 383 |
"step": 1700
|
| 384 |
},
|
| 385 |
{
|
|
@@ -399,9 +399,9 @@
|
|
| 399 |
{
|
| 400 |
"epoch": 2.9925187032418954,
|
| 401 |
"eval_loss": 0.23330263793468475,
|
| 402 |
-
"eval_runtime":
|
| 403 |
-
"eval_samples_per_second": 13.
|
| 404 |
-
"eval_steps_per_second": 1.
|
| 405 |
"step": 1800
|
| 406 |
},
|
| 407 |
{
|
|
@@ -421,9 +421,9 @@
|
|
| 421 |
{
|
| 422 |
"epoch": 3.1587697423108896,
|
| 423 |
"eval_loss": 0.23302872478961945,
|
| 424 |
-
"eval_runtime":
|
| 425 |
-
"eval_samples_per_second":
|
| 426 |
-
"eval_steps_per_second": 1.
|
| 427 |
"step": 1900
|
| 428 |
},
|
| 429 |
{
|
|
@@ -443,9 +443,9 @@
|
|
| 443 |
{
|
| 444 |
"epoch": 3.3250207813798838,
|
| 445 |
"eval_loss": 0.23246362805366516,
|
| 446 |
-
"eval_runtime":
|
| 447 |
-
"eval_samples_per_second": 13.
|
| 448 |
-
"eval_steps_per_second": 1.
|
| 449 |
"step": 2000
|
| 450 |
},
|
| 451 |
{
|
|
@@ -465,9 +465,9 @@
|
|
| 465 |
{
|
| 466 |
"epoch": 3.491271820448878,
|
| 467 |
"eval_loss": 0.23180559277534485,
|
| 468 |
-
"eval_runtime":
|
| 469 |
-
"eval_samples_per_second": 13.
|
| 470 |
-
"eval_steps_per_second": 1.
|
| 471 |
"step": 2100
|
| 472 |
},
|
| 473 |
{
|
|
@@ -487,9 +487,9 @@
|
|
| 487 |
{
|
| 488 |
"epoch": 3.657522859517872,
|
| 489 |
"eval_loss": 0.23114623129367828,
|
| 490 |
-
"eval_runtime":
|
| 491 |
-
"eval_samples_per_second":
|
| 492 |
-
"eval_steps_per_second": 1.
|
| 493 |
"step": 2200
|
| 494 |
},
|
| 495 |
{
|
|
@@ -509,9 +509,9 @@
|
|
| 509 |
{
|
| 510 |
"epoch": 3.8237738985868663,
|
| 511 |
"eval_loss": 0.23083852231502533,
|
| 512 |
-
"eval_runtime":
|
| 513 |
-
"eval_samples_per_second":
|
| 514 |
-
"eval_steps_per_second": 1.
|
| 515 |
"step": 2300
|
| 516 |
},
|
| 517 |
{
|
|
@@ -531,9 +531,9 @@
|
|
| 531 |
{
|
| 532 |
"epoch": 3.9900249376558605,
|
| 533 |
"eval_loss": 0.23079748451709747,
|
| 534 |
-
"eval_runtime":
|
| 535 |
-
"eval_samples_per_second": 13.
|
| 536 |
-
"eval_steps_per_second": 1.
|
| 537 |
"step": 2400
|
| 538 |
}
|
| 539 |
],
|
|
|
|
| 25 |
{
|
| 26 |
"epoch": 0.1662510390689942,
|
| 27 |
"eval_loss": 0.35283052921295166,
|
| 28 |
+
"eval_runtime": 38.0523,
|
| 29 |
+
"eval_samples_per_second": 12.982,
|
| 30 |
+
"eval_steps_per_second": 1.629,
|
| 31 |
"step": 100
|
| 32 |
},
|
| 33 |
{
|
|
|
|
| 47 |
{
|
| 48 |
"epoch": 0.3325020781379884,
|
| 49 |
"eval_loss": 0.30865946412086487,
|
| 50 |
+
"eval_runtime": 38.2162,
|
| 51 |
+
"eval_samples_per_second": 12.926,
|
| 52 |
+
"eval_steps_per_second": 1.622,
|
| 53 |
"step": 200
|
| 54 |
},
|
| 55 |
{
|
|
|
|
| 69 |
{
|
| 70 |
"epoch": 0.49875311720698257,
|
| 71 |
"eval_loss": 0.2891499996185303,
|
| 72 |
+
"eval_runtime": 38.1858,
|
| 73 |
+
"eval_samples_per_second": 12.937,
|
| 74 |
+
"eval_steps_per_second": 1.624,
|
| 75 |
"step": 300
|
| 76 |
},
|
| 77 |
{
|
|
|
|
| 91 |
{
|
| 92 |
"epoch": 0.6650041562759768,
|
| 93 |
"eval_loss": 0.2757515609264374,
|
| 94 |
+
"eval_runtime": 38.2247,
|
| 95 |
+
"eval_samples_per_second": 12.924,
|
| 96 |
+
"eval_steps_per_second": 1.622,
|
| 97 |
"step": 400
|
| 98 |
},
|
| 99 |
{
|
|
|
|
| 113 |
{
|
| 114 |
"epoch": 0.8312551953449709,
|
| 115 |
"eval_loss": 0.2673098146915436,
|
| 116 |
+
"eval_runtime": 38.0207,
|
| 117 |
+
"eval_samples_per_second": 12.993,
|
| 118 |
+
"eval_steps_per_second": 1.631,
|
| 119 |
"step": 500
|
| 120 |
},
|
| 121 |
{
|
|
|
|
| 135 |
{
|
| 136 |
"epoch": 0.9975062344139651,
|
| 137 |
"eval_loss": 0.26070085167884827,
|
| 138 |
+
"eval_runtime": 37.7694,
|
| 139 |
+
"eval_samples_per_second": 13.079,
|
| 140 |
+
"eval_steps_per_second": 1.642,
|
| 141 |
"step": 600
|
| 142 |
},
|
| 143 |
{
|
|
|
|
| 157 |
{
|
| 158 |
"epoch": 1.1637572734829593,
|
| 159 |
"eval_loss": 0.256939560174942,
|
| 160 |
+
"eval_runtime": 38.0385,
|
| 161 |
+
"eval_samples_per_second": 12.987,
|
| 162 |
+
"eval_steps_per_second": 1.63,
|
| 163 |
"step": 700
|
| 164 |
},
|
| 165 |
{
|
|
|
|
| 179 |
{
|
| 180 |
"epoch": 1.3300083125519535,
|
| 181 |
"eval_loss": 0.2525966763496399,
|
| 182 |
+
"eval_runtime": 38.1831,
|
| 183 |
+
"eval_samples_per_second": 12.938,
|
| 184 |
+
"eval_steps_per_second": 1.624,
|
| 185 |
"step": 800
|
| 186 |
},
|
| 187 |
{
|
|
|
|
| 201 |
{
|
| 202 |
"epoch": 1.4962593516209477,
|
| 203 |
"eval_loss": 0.24994711577892303,
|
| 204 |
+
"eval_runtime": 37.4678,
|
| 205 |
+
"eval_samples_per_second": 13.185,
|
| 206 |
+
"eval_steps_per_second": 1.655,
|
| 207 |
"step": 900
|
| 208 |
},
|
| 209 |
{
|
|
|
|
| 223 |
{
|
| 224 |
"epoch": 1.6625103906899419,
|
| 225 |
"eval_loss": 0.246443971991539,
|
| 226 |
+
"eval_runtime": 37.8324,
|
| 227 |
+
"eval_samples_per_second": 13.058,
|
| 228 |
+
"eval_steps_per_second": 1.639,
|
| 229 |
"step": 1000
|
| 230 |
},
|
| 231 |
{
|
|
|
|
| 245 |
{
|
| 246 |
"epoch": 1.828761429758936,
|
| 247 |
"eval_loss": 0.24409395456314087,
|
| 248 |
+
"eval_runtime": 37.7821,
|
| 249 |
+
"eval_samples_per_second": 13.075,
|
| 250 |
+
"eval_steps_per_second": 1.641,
|
| 251 |
"step": 1100
|
| 252 |
},
|
| 253 |
{
|
|
|
|
| 267 |
{
|
| 268 |
"epoch": 1.9950124688279303,
|
| 269 |
"eval_loss": 0.2411041557788849,
|
| 270 |
+
"eval_runtime": 37.3119,
|
| 271 |
+
"eval_samples_per_second": 13.24,
|
| 272 |
+
"eval_steps_per_second": 1.662,
|
| 273 |
"step": 1200
|
| 274 |
},
|
| 275 |
{
|
|
|
|
| 289 |
{
|
| 290 |
"epoch": 2.1612635078969245,
|
| 291 |
"eval_loss": 0.23963774740695953,
|
| 292 |
+
"eval_runtime": 37.7867,
|
| 293 |
+
"eval_samples_per_second": 13.073,
|
| 294 |
+
"eval_steps_per_second": 1.641,
|
| 295 |
"step": 1300
|
| 296 |
},
|
| 297 |
{
|
|
|
|
| 311 |
{
|
| 312 |
"epoch": 2.3275145469659186,
|
| 313 |
"eval_loss": 0.23829442262649536,
|
| 314 |
+
"eval_runtime": 37.7411,
|
| 315 |
+
"eval_samples_per_second": 13.089,
|
| 316 |
+
"eval_steps_per_second": 1.643,
|
| 317 |
"step": 1400
|
| 318 |
},
|
| 319 |
{
|
|
|
|
| 333 |
{
|
| 334 |
"epoch": 2.493765586034913,
|
| 335 |
"eval_loss": 0.2369847148656845,
|
| 336 |
+
"eval_runtime": 38.1397,
|
| 337 |
+
"eval_samples_per_second": 12.952,
|
| 338 |
+
"eval_steps_per_second": 1.626,
|
| 339 |
"step": 1500
|
| 340 |
},
|
| 341 |
{
|
|
|
|
| 355 |
{
|
| 356 |
"epoch": 2.660016625103907,
|
| 357 |
"eval_loss": 0.23503336310386658,
|
| 358 |
+
"eval_runtime": 37.7531,
|
| 359 |
+
"eval_samples_per_second": 13.085,
|
| 360 |
+
"eval_steps_per_second": 1.642,
|
| 361 |
"step": 1600
|
| 362 |
},
|
| 363 |
{
|
|
|
|
| 377 |
{
|
| 378 |
"epoch": 2.826267664172901,
|
| 379 |
"eval_loss": 0.23422521352767944,
|
| 380 |
+
"eval_runtime": 37.8729,
|
| 381 |
+
"eval_samples_per_second": 13.044,
|
| 382 |
+
"eval_steps_per_second": 1.637,
|
| 383 |
"step": 1700
|
| 384 |
},
|
| 385 |
{
|
|
|
|
| 399 |
{
|
| 400 |
"epoch": 2.9925187032418954,
|
| 401 |
"eval_loss": 0.23330263793468475,
|
| 402 |
+
"eval_runtime": 37.8678,
|
| 403 |
+
"eval_samples_per_second": 13.045,
|
| 404 |
+
"eval_steps_per_second": 1.637,
|
| 405 |
"step": 1800
|
| 406 |
},
|
| 407 |
{
|
|
|
|
| 421 |
{
|
| 422 |
"epoch": 3.1587697423108896,
|
| 423 |
"eval_loss": 0.23302872478961945,
|
| 424 |
+
"eval_runtime": 38.1436,
|
| 425 |
+
"eval_samples_per_second": 12.951,
|
| 426 |
+
"eval_steps_per_second": 1.625,
|
| 427 |
"step": 1900
|
| 428 |
},
|
| 429 |
{
|
|
|
|
| 443 |
{
|
| 444 |
"epoch": 3.3250207813798838,
|
| 445 |
"eval_loss": 0.23246362805366516,
|
| 446 |
+
"eval_runtime": 37.97,
|
| 447 |
+
"eval_samples_per_second": 13.01,
|
| 448 |
+
"eval_steps_per_second": 1.633,
|
| 449 |
"step": 2000
|
| 450 |
},
|
| 451 |
{
|
|
|
|
| 465 |
{
|
| 466 |
"epoch": 3.491271820448878,
|
| 467 |
"eval_loss": 0.23180559277534485,
|
| 468 |
+
"eval_runtime": 37.9308,
|
| 469 |
+
"eval_samples_per_second": 13.024,
|
| 470 |
+
"eval_steps_per_second": 1.635,
|
| 471 |
"step": 2100
|
| 472 |
},
|
| 473 |
{
|
|
|
|
| 487 |
{
|
| 488 |
"epoch": 3.657522859517872,
|
| 489 |
"eval_loss": 0.23114623129367828,
|
| 490 |
+
"eval_runtime": 38.1017,
|
| 491 |
+
"eval_samples_per_second": 12.965,
|
| 492 |
+
"eval_steps_per_second": 1.627,
|
| 493 |
"step": 2200
|
| 494 |
},
|
| 495 |
{
|
|
|
|
| 509 |
{
|
| 510 |
"epoch": 3.8237738985868663,
|
| 511 |
"eval_loss": 0.23083852231502533,
|
| 512 |
+
"eval_runtime": 38.0527,
|
| 513 |
+
"eval_samples_per_second": 12.982,
|
| 514 |
+
"eval_steps_per_second": 1.629,
|
| 515 |
"step": 2300
|
| 516 |
},
|
| 517 |
{
|
|
|
|
| 531 |
{
|
| 532 |
"epoch": 3.9900249376558605,
|
| 533 |
"eval_loss": 0.23079748451709747,
|
| 534 |
+
"eval_runtime": 37.7401,
|
| 535 |
+
"eval_samples_per_second": 13.09,
|
| 536 |
+
"eval_steps_per_second": 1.643,
|
| 537 |
"step": 2400
|
| 538 |
}
|
| 539 |
],
|