train_cb_1745950320
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the cb dataset. It achieves the following results on the evaluation set:
- Loss: 3.5088
- Num Input Tokens Seen: 23078128
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 123
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- training_steps: 40000
Training results
Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
---|---|---|---|---|
3.425 | 3.5133 | 200 | 3.6337 | 116248 |
3.8051 | 7.0177 | 400 | 3.5796 | 232144 |
3.4907 | 10.5310 | 600 | 3.5604 | 346496 |
3.5124 | 14.0354 | 800 | 3.5374 | 462696 |
3.3202 | 17.5487 | 1000 | 3.5806 | 578728 |
3.0515 | 21.0531 | 1200 | 3.5580 | 692976 |
3.0487 | 24.5664 | 1400 | 3.5418 | 809080 |
3.3479 | 28.0708 | 1600 | 3.5445 | 924048 |
2.729 | 31.5841 | 1800 | 3.5421 | 1040096 |
2.9491 | 35.0885 | 2000 | 3.5277 | 1155784 |
3.4026 | 38.6018 | 2200 | 3.5560 | 1271880 |
2.8654 | 42.1062 | 2400 | 3.5492 | 1386392 |
3.47 | 45.6195 | 2600 | 3.5358 | 1502448 |
2.8545 | 49.1239 | 2800 | 3.5362 | 1616928 |
3.1286 | 52.6372 | 3000 | 3.5301 | 1732240 |
2.9785 | 56.1416 | 3200 | 3.5395 | 1847880 |
2.9734 | 59.6549 | 3400 | 3.5483 | 1963376 |
2.5448 | 63.1593 | 3600 | 3.5507 | 2078344 |
2.9699 | 66.6726 | 3800 | 3.5546 | 2193696 |
3.1915 | 70.1770 | 4000 | 3.5416 | 2309024 |
3.4015 | 73.6903 | 4200 | 3.5653 | 2425544 |
3.5847 | 77.1947 | 4400 | 3.5412 | 2539944 |
3.0721 | 80.7080 | 4600 | 3.5401 | 2655720 |
3.0372 | 84.2124 | 4800 | 3.5393 | 2771904 |
3.1256 | 87.7257 | 5000 | 3.5283 | 2887856 |
2.7119 | 91.2301 | 5200 | 3.5394 | 3003888 |
3.3761 | 94.7434 | 5400 | 3.5427 | 3118800 |
3.3381 | 98.2478 | 5600 | 3.5265 | 3234376 |
3.1174 | 101.7611 | 5800 | 3.5168 | 3350608 |
2.7983 | 105.2655 | 6000 | 3.5389 | 3466256 |
2.9856 | 108.7788 | 6200 | 3.5365 | 3582008 |
2.9597 | 112.2832 | 6400 | 3.5427 | 3696904 |
3.0017 | 115.7965 | 6600 | 3.5417 | 3812728 |
3.696 | 119.3009 | 6800 | 3.5550 | 3927256 |
2.7994 | 122.8142 | 7000 | 3.5606 | 4043128 |
2.8761 | 126.3186 | 7200 | 3.5367 | 4158920 |
3.3338 | 129.8319 | 7400 | 3.5252 | 4274536 |
3.5999 | 133.3363 | 7600 | 3.5412 | 4389864 |
3.6932 | 136.8496 | 7800 | 3.5351 | 4505192 |
2.9592 | 140.3540 | 8000 | 3.5539 | 4620656 |
3.2642 | 143.8673 | 8200 | 3.5257 | 4736960 |
2.9824 | 147.3717 | 8400 | 3.5323 | 4850688 |
2.9507 | 150.8850 | 8600 | 3.5333 | 4965800 |
3.4216 | 154.3894 | 8800 | 3.5413 | 5082848 |
2.8698 | 157.9027 | 9000 | 3.5578 | 5197896 |
3.4896 | 161.4071 | 9200 | 3.5551 | 5312976 |
2.8145 | 164.9204 | 9400 | 3.5369 | 5428816 |
3.4116 | 168.4248 | 9600 | 3.5577 | 5542632 |
3.6992 | 171.9381 | 9800 | 3.5283 | 5660064 |
2.8501 | 175.4425 | 10000 | 3.5443 | 5775432 |
3.0806 | 178.9558 | 10200 | 3.5297 | 5891480 |
3.1463 | 182.4602 | 10400 | 3.5459 | 6006016 |
3.5075 | 185.9735 | 10600 | 3.5435 | 6121200 |
2.822 | 189.4779 | 10800 | 3.5489 | 6236696 |
2.7503 | 192.9912 | 11000 | 3.5220 | 6352152 |
2.9338 | 196.4956 | 11200 | 3.5553 | 6467792 |
3.6244 | 200.0 | 11400 | 3.5236 | 6581880 |
2.7449 | 203.5133 | 11600 | 3.5427 | 6697328 |
3.0423 | 207.0177 | 11800 | 3.5409 | 6811792 |
3.0096 | 210.5310 | 12000 | 3.5342 | 6928248 |
2.7702 | 214.0354 | 12200 | 3.5190 | 7043832 |
3.1358 | 217.5487 | 12400 | 3.5237 | 7157984 |
2.9389 | 221.0531 | 12600 | 3.5543 | 7274032 |
3.4344 | 224.5664 | 12800 | 3.5662 | 7390136 |
3.5665 | 228.0708 | 13000 | 3.5424 | 7505120 |
3.8253 | 231.5841 | 13200 | 3.5209 | 7619616 |
2.9442 | 235.0885 | 13400 | 3.5688 | 7736064 |
3.319 | 238.6018 | 13600 | 3.5466 | 7850792 |
3.1764 | 242.1062 | 13800 | 3.5327 | 7965808 |
3.5727 | 245.6195 | 14000 | 3.5448 | 8081552 |
3.3459 | 249.1239 | 14200 | 3.5463 | 8197208 |
3.5196 | 252.6372 | 14400 | 3.5445 | 8312272 |
3.4635 | 256.1416 | 14600 | 3.5668 | 8426888 |
3.2052 | 259.6549 | 14800 | 3.5377 | 8542448 |
2.5383 | 263.1593 | 15000 | 3.5260 | 8658448 |
2.9495 | 266.6726 | 15200 | 3.5391 | 8773608 |
2.7139 | 270.1770 | 15400 | 3.5480 | 8887928 |
3.3391 | 273.6903 | 15600 | 3.5418 | 9004600 |
2.8801 | 277.1947 | 15800 | 3.5455 | 9119624 |
3.5344 | 280.7080 | 16000 | 3.5489 | 9233904 |
3.7411 | 284.2124 | 16200 | 3.5558 | 9351032 |
2.7646 | 287.7257 | 16400 | 3.5511 | 9465944 |
2.8915 | 291.2301 | 16600 | 3.5570 | 9581568 |
3.1433 | 294.7434 | 16800 | 3.5143 | 9696576 |
2.7825 | 298.2478 | 17000 | 3.5317 | 9811496 |
3.1644 | 301.7611 | 17200 | 3.5339 | 9926600 |
3.113 | 305.2655 | 17400 | 3.5569 | 10042072 |
3.0783 | 308.7788 | 17600 | 3.5383 | 10156616 |
2.9394 | 312.2832 | 17800 | 3.5523 | 10272688 |
3.2511 | 315.7965 | 18000 | 3.5404 | 10386824 |
3.3896 | 319.3009 | 18200 | 3.5513 | 10502040 |
3.4877 | 322.8142 | 18400 | 3.5534 | 10617608 |
3.0427 | 326.3186 | 18600 | 3.5439 | 10731768 |
2.7773 | 329.8319 | 18800 | 3.5344 | 10848480 |
3.0179 | 333.3363 | 19000 | 3.5350 | 10963328 |
3.0879 | 336.8496 | 19200 | 3.5526 | 11078712 |
3.0143 | 340.3540 | 19400 | 3.5403 | 11193832 |
3.287 | 343.8673 | 19600 | 3.5532 | 11309368 |
3.5063 | 347.3717 | 19800 | 3.5290 | 11424912 |
2.8885 | 350.8850 | 20000 | 3.5471 | 11539864 |
2.9811 | 354.3894 | 20200 | 3.5397 | 11654632 |
3.3059 | 357.9027 | 20400 | 3.5575 | 11771008 |
2.9681 | 361.4071 | 20600 | 3.5233 | 11886608 |
3.9619 | 364.9204 | 20800 | 3.5355 | 12002608 |
2.9812 | 368.4248 | 21000 | 3.5577 | 12117448 |
3.4788 | 371.9381 | 21200 | 3.5370 | 12233152 |
3.3682 | 375.4425 | 21400 | 3.5500 | 12346784 |
3.231 | 378.9558 | 21600 | 3.5294 | 12463336 |
2.8366 | 382.4602 | 21800 | 3.5480 | 12578616 |
3.828 | 385.9735 | 22000 | 3.5207 | 12693160 |
3.3448 | 389.4779 | 22200 | 3.5252 | 12808696 |
2.7932 | 392.9912 | 22400 | 3.5520 | 12924056 |
2.5436 | 396.4956 | 22600 | 3.5661 | 13039656 |
3.1512 | 400.0 | 22800 | 3.5414 | 13154552 |
2.9926 | 403.5133 | 23000 | 3.5694 | 13269320 |
2.7649 | 407.0177 | 23200 | 3.5436 | 13385512 |
3.6216 | 410.5310 | 23400 | 3.5395 | 13501208 |
3.2219 | 414.0354 | 23600 | 3.5469 | 13617048 |
3.1651 | 417.5487 | 23800 | 3.5769 | 13733448 |
3.1999 | 421.0531 | 24000 | 3.5360 | 13848288 |
2.8829 | 424.5664 | 24200 | 3.5558 | 13963536 |
3.6948 | 428.0708 | 24400 | 3.5464 | 14080024 |
3.5368 | 431.5841 | 24600 | 3.5273 | 14194520 |
3.735 | 435.0885 | 24800 | 3.5479 | 14310080 |
2.6585 | 438.6018 | 25000 | 3.5429 | 14427448 |
3.5032 | 442.1062 | 25200 | 3.5520 | 14542448 |
3.2256 | 445.6195 | 25400 | 3.5430 | 14657640 |
3.2064 | 449.1239 | 25600 | 3.5425 | 14772328 |
2.9344 | 452.6372 | 25800 | 3.5361 | 14888712 |
2.7779 | 456.1416 | 26000 | 3.5385 | 15002944 |
3.4417 | 459.6549 | 26200 | 3.5638 | 15118544 |
3.1454 | 463.1593 | 26400 | 3.5473 | 15234184 |
3.2606 | 466.6726 | 26600 | 3.5355 | 15349544 |
3.2821 | 470.1770 | 26800 | 3.5506 | 15465448 |
3.724 | 473.6903 | 27000 | 3.5527 | 15581752 |
2.6703 | 477.1947 | 27200 | 3.5448 | 15696720 |
3.0141 | 480.7080 | 27400 | 3.5629 | 15812864 |
3.1294 | 484.2124 | 27600 | 3.5562 | 15928512 |
3.0489 | 487.7257 | 27800 | 3.5376 | 16043264 |
3.1688 | 491.2301 | 28000 | 3.5395 | 16158992 |
3.4673 | 494.7434 | 28200 | 3.5358 | 16274040 |
3.0875 | 498.2478 | 28400 | 3.5622 | 16389944 |
2.8567 | 501.7611 | 28600 | 3.5384 | 16506208 |
2.9697 | 505.2655 | 28800 | 3.5358 | 16621272 |
3.4483 | 508.7788 | 29000 | 3.5660 | 16737072 |
3.6537 | 512.2832 | 29200 | 3.5506 | 16852312 |
3.475 | 515.7965 | 29400 | 3.5415 | 16967744 |
3.4424 | 519.3009 | 29600 | 3.5482 | 17083368 |
3.2134 | 522.8142 | 29800 | 3.5486 | 17197984 |
3.1199 | 526.3186 | 30000 | 3.5088 | 17314032 |
3.192 | 529.8319 | 30200 | 3.5586 | 17428904 |
2.6813 | 533.3363 | 30400 | 3.5461 | 17543048 |
2.6821 | 536.8496 | 30600 | 3.5537 | 17659880 |
3.6959 | 540.3540 | 30800 | 3.5573 | 17773728 |
3.4702 | 543.8673 | 31000 | 3.5528 | 17889344 |
3.2742 | 547.3717 | 31200 | 3.5559 | 18005392 |
2.6368 | 550.8850 | 31400 | 3.5525 | 18120296 |
3.3255 | 554.3894 | 31600 | 3.5570 | 18235552 |
2.916 | 557.9027 | 31800 | 3.5544 | 18352024 |
3.5079 | 561.4071 | 32000 | 3.5512 | 18466080 |
3.4685 | 564.9204 | 32200 | 3.5352 | 18581584 |
3.6533 | 568.4248 | 32400 | 3.5441 | 18697408 |
3.2041 | 571.9381 | 32600 | 3.5492 | 18811608 |
3.1245 | 575.4425 | 32800 | 3.5539 | 18927640 |
3.1741 | 578.9558 | 33000 | 3.5364 | 19043672 |
3.2603 | 582.4602 | 33200 | 3.5436 | 19157776 |
3.4538 | 585.9735 | 33400 | 3.5418 | 19272744 |
3.3276 | 589.4779 | 33600 | 3.5411 | 19388520 |
3.1365 | 592.9912 | 33800 | 3.5524 | 19504472 |
3.3086 | 596.4956 | 34000 | 3.5609 | 19618408 |
3.4689 | 600.0 | 34200 | 3.5438 | 19734128 |
3.2426 | 603.5133 | 34400 | 3.5543 | 19849608 |
3.1304 | 607.0177 | 34600 | 3.5547 | 19964704 |
2.7656 | 610.5310 | 34800 | 3.5442 | 20080968 |
3.1542 | 614.0354 | 35000 | 3.5390 | 20195624 |
2.5122 | 617.5487 | 35200 | 3.5408 | 20311640 |
2.6218 | 621.0531 | 35400 | 3.5379 | 20426832 |
3.5177 | 624.5664 | 35600 | 3.5434 | 20541816 |
3.4989 | 628.0708 | 35800 | 3.5423 | 20656416 |
2.4929 | 631.5841 | 36000 | 3.5423 | 20771136 |
3.5688 | 635.0885 | 36200 | 3.5374 | 20886272 |
3.0984 | 638.6018 | 36400 | 3.5423 | 21001560 |
3.573 | 642.1062 | 36600 | 3.5374 | 21115320 |
2.8932 | 645.6195 | 36800 | 3.5374 | 21230216 |
3.0303 | 649.1239 | 37000 | 3.5374 | 21344656 |
2.6008 | 652.6372 | 37200 | 3.5374 | 21461664 |
3.19 | 656.1416 | 37400 | 3.5374 | 21576216 |
3.3065 | 659.6549 | 37600 | 3.5374 | 21692088 |
3.3077 | 663.1593 | 37800 | 3.5374 | 21807184 |
3.3042 | 666.6726 | 38000 | 3.5374 | 21923192 |
2.9595 | 670.1770 | 38200 | 3.5374 | 22037928 |
2.9425 | 673.6903 | 38400 | 3.5374 | 22153968 |
3.1744 | 677.1947 | 38600 | 3.5374 | 22269648 |
3.4269 | 680.7080 | 38800 | 3.5374 | 22385640 |
3.6816 | 684.2124 | 39000 | 3.5374 | 22502040 |
3.2897 | 687.7257 | 39200 | 3.5374 | 22616408 |
2.8114 | 691.2301 | 39400 | 3.5374 | 22732496 |
2.8056 | 694.7434 | 39600 | 3.5374 | 22846704 |
3.1919 | 698.2478 | 39800 | 3.5374 | 22962016 |
3.0684 | 701.7611 | 40000 | 3.5374 | 23078128 |
Framework versions
- PEFT 0.15.2.dev0
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for rbelanec/train_cb_1745950320
Base model
mistralai/Mistral-7B-v0.3
Finetuned
mistralai/Mistral-7B-Instruct-v0.3