PEFT
Safetensors
English
temporal-reasoning
knowledge-graph
graphrag
retrieval-augmented-generation
lora
Instructions to use anonym-ous/tempgraphrag-artifacts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use anonym-ous/tempgraphrag-artifacts with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. | |
| Loading tokenizer + model: Qwen/Qwen3-8B | |
| Loading weights: 0%| | 0/399 Loading weights: 100%|ββββββββββ| 399/399 | |
| 0%| | 1/626 0%| | 2/626 0%| | 3/626 1%| | 4/626 1%| | 5/626 1%| | 6/626 1%| | 7/626 1%|β | 8/626 1%|β | 9/626 2%|β | 10/626 2%|β | 10/626 2%|β | 11/626 2%|β | 12/626 2%|β | 13/626 2%|β | 14/626 2%|β | 15/626 3%|β | 16/626 3%|β | 17/626 3%|β | 18/626 3%|β | 19/626 3%|β | 20/626 3%|β | 20/626 3%|β | 21/626 4%|β | 22/626 4%|β | 23/626 4%|β | 24/626 4%|β | 25/626 4%|β | 26/626 4%|β | 27/626 4%|β | 28/626 5%|β | 29/626 5%|β | 30/626 5%|β | 30/626 5%|β | 31/626 5%|β | 32/626 5%|β | 33/626 5%|β | 34/626 6%|β | 35/626 6%|β | 36/626 6%|β | 37/626 6%|β | 38/626 6%|β | 39/626 6%|β | 40/626 6%|β | 40/626 7%|β | 41/626 7%|β | 42/626 7%|β | 43/626 7%|β | 44/626 7%|β | 45/626 7%|β | 46/626 8%|β | 47/626 8%|β | 48/626 8%|β | 49/626 8%|β | 50/626 8%|β | 50/626 8%|β | 51/626 8%|β | 52/626 8%|β | 53/626 9%|β | 54/626 9%|β | 55/626 9%|β | 56/626 9%|β | 57/626 9%|β | 58/626 9%|β | 59/626 10%|β | 60/626 10%|β | 60/626 10%|β | 61/626 10%|β | 62/626 10%|β | 63/626 10%|β | 64/626 10%|β | 65/626 11%|β | 66/626 11%|β | 67/626 11%|β | 68/626 11%|β | 69/626 11%|β | 70/626 11%|β | 70/626 11%|ββ | 71/626 12%|ββ | 72/626 12%|ββ | 73/626 12%|ββ | 74/626 12%|ββ | 75/626 12%|ββ | 76/626 12%|ββ | 77/626 12%|ββ | 78/626 13%|ββ | 79/626 13%|ββ | 80/626 13%|ββ | 80/626 13%|ββ | 81/626 13%|ββ | 82/626 13%|ββ | 83/626 13%|ββ | 84/626 14%|ββ | 85/626 14%|ββ | 86/626 14%|ββ | 87/626 14%|ββ | 88/626 14%|ββ | 89/626 14%|ββ | 90/626 14%|ββ | 90/626 15%|ββ | 91/626 15%|ββ | 92/626 15%|ββ | 93/626 15%|ββ | 94/626 15%|ββ | 95/626 15%|ββ | 96/626 15%|ββ | 97/626 16%|ββ | 98/626 16%|ββ | 99/626 16%|ββ | 100/626 16%|ββ | 100/626 16%|ββ | 101/626 16%|ββ | 102/626 16%|ββ | 103/626 17%|ββ | 104/626 17%|ββ | 105/626 17%|ββ | 106/626 17%|ββ | 107/626 17%|ββ | 108/626 17%|ββ | 109/626 18%|ββ | 110/626 18%|ββ | 110/626 18%|ββ | 111/626 18%|ββ | 112/626 18%|ββ | 113/626 18%|ββ | 114/626 18%|ββ | 115/626 19%|ββ | 116/626 19%|ββ | 117/626 19%|ββ | 118/626 19%|ββ | 119/626 19%|ββ | 120/626 19%|ββ | 120/626 19%|ββ | 121/626 19%|ββ | 122/626 20%|ββ | 123/626 20%|ββ | 124/626 20%|ββ | 125/626 20%|ββ | 126/626 20%|ββ | 127/626 20%|ββ | 128/626 21%|ββ | 129/626 21%|ββ | 130/626 21%|ββ | 130/626 21%|ββ | 131/626 21%|ββ | 132/626 21%|ββ | 133/626 21%|βββ | 134/626 22%|βββ | 135/626 22%|βββ | 136/626 22%|βββ | 137/626 22%|βββ | 138/626 22%|βββ | 139/626 22%|βββ | 140/626 22%|βββ | 140/626 23%|βββ | 141/626 23%|βββ | 142/626 23%|βββ | 143/626 23%|βββ | 144/626 23%|βββ | 145/626 23%|βββ | 146/626 23%|βββ | 147/626 24%|βββ | 148/626 24%|βββ | 149/626 24%|βββ | 150/626 24%|βββ | 150/626 24%|βββ | 151/626 24%|βββ | 152/626 24%|βββ | 153/626 25%|βββ | 154/626 25%|βββ | 155/626 25%|βββ | 156/626 25%|βββ | 157/626 25%|βββ | 158/626 25%|βββ | 159/626 26%|βββ | 160/626 26%|βββ | 160/626 26%|βββ | 161/626 26%|βββ | 162/626 26%|βββ | 163/626 26%|βββ | 164/626 26%|βββ | 165/626 27%|βββ | 166/626 27%|βββ | 167/626 27%|βββ | 168/626 27%|βββ | 169/626 27%|βββ | 170/626 27%|βββ | 170/626 27%|βββ | 171/626 27%|βββ | 172/626 28%|βββ | 173/626 28%|βββ | 174/626 28%|βββ | 175/626 28%|βββ | 176/626 28%|βββ | 177/626 28%|βββ | 178/626 29%|βββ | 179/626 29%|βββ | 180/626 29%|βββ | 180/626 29%|βββ | 181/626 29%|βββ | 182/626 29%|βββ | 183/626 29%|βββ | 184/626 30%|βββ | 185/626 30%|βββ | 186/626 30%|βββ | 187/626 30%|βββ | 188/626 30%|βββ | 189/626 30%|βββ | 190/626 30%|βββ | 190/626 31%|βββ | 191/626 31%|βββ | 192/626 31%|βββ | 193/626 31%|βββ | 194/626 31%|βββ | 195/626 31%|ββββ | 196/626 31%|ββββ | 197/626 32%|ββββ | 198/626 32%|ββββ | 199/626 32%|ββββ | 200/626 32%|ββββ | 200/626 32%|ββββ | 201/626 32%|ββββ | 202/626 32%|ββββ | 203/626 33%|ββββ | 204/626 33%|ββββ | 205/626 33%|ββββ | 206/626 33%|ββββ | 207/626 33%|ββββ | 208/626 33%|ββββ | 209/626 34%|ββββ | 210/626 34%|ββββ | 210/626 34%|ββββ | 211/626 34%|ββββ | 212/626 34%|ββββ | 213/626 34%|ββββ | 214/626 34%|ββββ | 215/626 35%|ββββ | 216/626 35%|ββββ | 217/626 35%|ββββ | 218/626 35%|ββββ | 219/626 35%|ββββ | 220/626 35%|ββββ | 220/626 35%|ββββ | 221/626 35%|ββββ | 222/626 36%|ββββ | 223/626 36%|ββββ | 224/626 36%|ββββ | 225/626 36%|ββββ | 226/626 36%|ββββ | 227/626 36%|ββββ | 228/626 37%|ββββ | 229/626 37%|ββββ | 230/626 37%|ββββ | 230/626 37%|ββββ | 231/626 37%|ββββ | 232/626 37%|ββββ | 233/626 37%|ββββ | 234/626 38%|ββββ | 235/626 38%|ββββ | 236/626 38%|ββββ | 237/626 38%|ββββ | 238/626 38%|ββββ | 239/626 38%|ββββ | 240/626 38%|ββββ | 240/626 38%|ββββ | 241/626 39%|ββββ | 242/626 39%|ββββ | 243/626 39%|ββββ | 244/626 39%|ββββ | 245/626 39%|ββββ | 246/626 39%|ββββ | 247/626 40%|ββββ | 248/626 40%|ββββ | 249/626 40%|ββββ | 250/626 40%|ββββ | 250/626 40%|ββββ | 251/626 40%|ββββ | 252/626 40%|ββββ | 253/626 41%|ββββ | 254/626 41%|ββββ | 255/626 41%|ββββ | 256/626 41%|ββββ | 257/626 41%|ββββ | 258/626 41%|βββββ | 259/626 42%|βββββ | 260/626 42%|βββββ | 260/626 42%|βββββ | 261/626 42%|βββββ | 262/626 42%|βββββ | 263/626 42%|βββββ | 264/626 42%|βββββ | 265/626 42%|βββββ | 266/626 43%|βββββ | 267/626 43%|βββββ | 268/626 43%|βββββ | 269/626 43%|βββββ | 270/626 43%|βββββ | 270/626 43%|βββββ | 271/626 43%|βββββ | 272/626 44%|βββββ | 273/626 44%|βββββ | 274/626 44%|βββββ | 275/626 44%|βββββ | 276/626 44%|βββββ | 277/626 44%|βββββ | 278/626 45%|βββββ | 279/626 45%|βββββ | 280/626 45%|βββββ | 280/626 45%|βββββ | 281/626 45%|βββββ | 282/626 45%|βββββ | 283/626 45%|βββββ | 284/626 46%|βββββ | 285/626 46%|βββββ | 286/626 46%|βββββ | 287/626 46%|βββββ | 288/626 46%|βββββ | 289/626 46%|βββββ | 290/626 46%|βββββ | 290/626 46%|βββββ | 291/626 47%|βββββ | 292/626 47%|βββββ | 293/626 47%|βββββ | 294/626 47%|βββββ | 295/626 47%|βββββ | 296/626 47%|βββββ | 297/626 48%|βββββ | 298/626 48%|βββββ | 299/626 48%|βββββ | 300/626 48%|βββββ | 300/626 48%|βββββ | 301/626 48%|βββββ | 302/626 48%|βββββ | 303/626 49%|βββββ | 304/626 49%|βββββ | 305/626 49%|βββββ | 306/626 49%|βββββ | 307/626 49%|βββββ | 308/626 49%|βββββ | 309/626 50%|βββββ | 310/626 50%|βββββ | 310/626 50%|βββββ | 311/626 50%|βββββ | 312/626 50%|βββββ | 313/626 50%|βββββ | 314/626 50%|βββββ | 315/626 50%|βββββ | 316/626 51%|βββββ | 317/626 51%|βββββ | 318/626 51%|βββββ | 319/626 51%|βββββ | 320/626 51%|βββββ | 320/626 51%|ββββββ | 321/626 51%|ββββββ | 322/626 52%|ββββββ | 323/626 52%|ββββββ | 324/626 52%|ββββββ | 325/626 52%|ββββββ | 326/626 52%|ββββββ | 327/626 52%|ββββββ | 328/626 53%|ββββββ | 329/626 53%|ββββββ | 330/626 53%|ββββββ | 330/626 53%|ββββββ | 331/626 53%|ββββββ | 332/626 53%|ββββββ | 333/626 53%|ββββββ | 334/626 54%|ββββββ | 335/626 54%|ββββββ | 336/626 54%|ββββββ | 337/626 54%|ββββββ | 338/626 54%|ββββββ | 339/626 54%|ββββββ | 340/626 54%|ββββββ | 340/626 54%|ββββββ | 341/626 55%|ββββββ | 342/626 55%|ββββββ | 343/626 55%|ββββββ | 344/626 55%|ββββββ | 345/626 55%|ββββββ | 346/626 55%|ββββββ | 347/626 56%|ββββββ | 348/626 56%|ββββββ | 349/626 56%|ββββββ | 350/626 56%|ββββββ | 350/626 56%|ββββββ | 351/626 56%|ββββββ | 352/626 56%|ββββββ | 353/626 57%|ββββββ | 354/626 57%|ββββββ | 355/626 57%|ββββββ | 356/626 57%|ββββββ | 357/626 57%|ββββββ | 358/626 57%|ββββββ | 359/626 58%|ββββββ | 360/626 58%|ββββββ | 360/626 58%|ββββββ | 361/626 58%|ββββββ | 362/626 58%|ββββββ | 363/626 58%|ββββββ | 364/626 58%|ββββββ | 365/626 58%|ββββββ | 366/626 59%|ββββββ | 367/626 59%|ββββββ | 368/626 59%|ββββββ | 369/626 59%|ββββββ | 370/626 59%|ββββββ | 370/626 59%|ββββββ | 371/626 59%|ββββββ | 372/626 60%|ββββββ | 373/626 60%|ββββββ | 374/626 60%|ββββββ | 375/626 60%|ββββββ | 376/626 60%|ββββββ | 377/626 60%|ββββββ | 378/626 61%|ββββββ | 379/626 61%|ββββββ | 380/626 61%|ββββββ | 380/626 61%|ββββββ | 381/626 61%|ββββββ | 382/626 61%|ββββββ | 383/626 61%|βββββββ | 384/626 62%|βββββββ | 385/626 62%|βββββββ | 386/626 62%|βββββββ | 387/626 62%|βββββββ | 388/626 62%|βββββββ | 389/626 62%|βββββββ | 390/626 62%|βββββββ | 390/626 62%|βββββββ | 391/626 63%|βββββββ | 392/626 63%|βββββββ | 393/626 63%|βββββββ | 394/626 63%|βββββββ | 395/626 63%|βββββββ | 396/626 63%|βββββββ | 397/626 64%|βββββββ | 398/626 64%|βββββββ | 399/626 64%|βββββββ | 400/626 64%|βββββββ | 400/626 64%|βββββββ | 401/626 64%|βββββββ | 402/626 64%|βββββββ | 403/626 65%|βββββββ | 404/626 65%|βββββββ | 405/626 65%|βββββββ | 406/626 65%|βββββββ | 407/626 65%|βββββββ | 408/626 65%|βββββββ | 409/626 65%|βββββββ | 410/626 65%|βββββββ | 410/626 66%|βββββββ | 411/626 66%|βββββββ | 412/626 66%|βββββββ | 413/626 66%|βββββββ | 414/626 66%|βββββββ | 415/626 66%|βββββββ | 416/626 67%|βββββββ | 417/626 67%|βββββββ | 418/626 67%|βββββββ | 419/626 67%|βββββββ | 420/626 67%|βββββββ | 420/626 67%|βββββββ | 421/626 67%|βββββββ | 422/626 68%|βββββββ | 423/626 68%|βββββββ | 424/626 68%|βββββββ | 425/626 68%|βββββββ | 426/626 68%|βββββββ | 427/626 68%|βββββββ | 428/626 69%|βββββββ | 429/626 69%|βββββββ | 430/626 69%|βββββββ | 430/626 69%|βββββββ | 431/626 69%|βββββββ | 432/626 69%|βββββββ | 433/626 69%|βββββββ | 434/626 69%|βββββββ | 435/626 70%|βββββββ | 436/626 70%|βββββββ | 437/626 70%|βββββββ | 438/626 70%|βββββββ | 439/626 70%|βββββββ | 440/626 70%|βββββββ | 440/626 70%|βββββββ | 441/626 71%|βββββββ | 442/626 71%|βββββββ | 443/626 71%|βββββββ | 444/626 71%|βββββββ | 445/626 71%|βββββββ | 446/626 71%|ββββββββ | 447/626 72%|ββββββββ | 448/626 72%|ββββββββ | 449/626 72%|ββββββββ | 450/626 72%|ββββββββ | 450/626 72%|ββββββββ | 451/626 72%|ββββββββ | 452/626 72%|ββββββββ | 453/626 73%|ββββββββ | 454/626 73%|ββββββββ | 455/626 73%|ββββββββ | 456/626 73%|ββββββββ | 457/626 73%|ββββββββ | 458/626 73%|ββββββββ | 459/626 73%|ββββββββ | 460/626 73%|ββββββββ | 460/626 74%|ββββββββ | 461/626 74%|ββββββββ | 462/626 74%|ββββββββ | 463/626 74%|ββββββββ | 464/626 74%|ββββββββ | 465/626 74%|ββββββββ | 466/626 75%|ββββββββ | 467/626 75%|ββββββββ | 468/626 75%|ββββββββ | 469/626 75%|ββββββββ | 470/626 75%|ββββββββ | 470/626 75%|ββββββββ | 471/626 75%|ββββββββ | 472/626 76%|ββββββββ | 473/626 76%|ββββββββ | 474/626 76%|ββββββββ | 475/626 76%|ββββββββ | 476/626 76%|ββββββββ | 477/626 76%|ββββββββ | 478/626 77%|ββββββββ | 479/626 77%|ββββββββ | 480/626 77%|ββββββββ | 480/626 77%|ββββββββ | 481/626 77%|ββββββββ | 482/626 77%|ββββββββ | 483/626 77%|ββββββββ | 484/626 77%|ββββββββ | 485/626 78%|ββββββββ | 486/626 78%|ββββββββ | 487/626 78%|ββββββββ | 488/626 78%|ββββββββ | 489/626 78%|ββββββββ | 490/626 78%|ββββββββ | 490/626 78%|ββββββββ | 491/626 79%|ββββββββ | 492/626 79%|ββββββββ | 493/626 79%|ββββββββ | 494/626 79%|ββββββββ | 495/626 79%|ββββββββ | 496/626 79%|ββββββββ | 497/626 80%|ββββββββ | 498/626 80%|ββββββββ | 499/626 80%|ββββββββ | 500/626 80%|ββββββββ | 500/626 80%|ββββββββ | 501/626 80%|ββββββββ | 502/626 80%|ββββββββ | 503/626 81%|ββββββββ | 504/626 81%|ββββββββ | 505/626 81%|ββββββββ | 506/626 81%|ββββββββ | 507/626 81%|ββββββββ | 508/626 81%|βββββββββ | 509/626 81%|βββββββββ | 510/626 81%|βββββββββ | 510/626 82%|βββββββββ | 511/626 82%|βββββββββ | 512/626 82%|βββββββββ | 513/626 82%|βββββββββ | 514/626 82%|βββββββββ | 515/626 82%|βββββββββ | 516/626 83%|βββββββββ | 517/626 83%|βββββββββ | 518/626 83%|βββββββββ | 519/626 83%|βββββββββ | 520/626 83%|βββββββββ | 520/626 83%|βββββββββ | 521/626 83%|βββββββββ | 522/626 84%|βββββββββ | 523/626 84%|βββββββββ | 524/626 84%|βββββββββ | 525/626 84%|βββββββββ | 526/626 84%|βββββββββ | 527/626 84%|βββββββββ | 528/626 85%|βββββββββ | 529/626 85%|βββββββββ | 530/626 85%|βββββββββ | 530/626 85%|βββββββββ | 531/626 85%|βββββββββ | 532/626 85%|βββββββββ | 533/626 85%|βββββββββ | 534/626 85%|βββββββββ | 535/626 86%|βββββββββ | 536/626 86%|βββββββββ | 537/626 86%|βββββββββ | 538/626 86%|βββββββββ | 539/626 86%|βββββββββ | 540/626 86%|βββββββββ | 540/626 86%|βββββββββ | 541/626 87%|βββββββββ | 542/626 87%|βββββββββ | 543/626 87%|βββββββββ | 544/626 87%|βββββββββ | 545/626 87%|βββββββββ | 546/626 87%|βββββββββ | 547/626 88%|βββββββββ | 548/626 88%|βββββββββ | 549/626 88%|βββββββββ | 550/626 88%|βββββββββ | 550/626 88%|βββββββββ | 551/626 88%|βββββββββ | 552/626 88%|βββββββββ | 553/626 88%|βββββββββ | 554/626 89%|βββββββββ | 555/626 89%|βββββββββ | 556/626 89%|βββββββββ | 557/626 89%|βββββββββ | 558/626 89%|βββββββββ | 559/626 89%|βββββββββ | 560/626 89%|βββββββββ | 560/626 90%|βββββββββ | 561/626 90%|βββββββββ | 562/626 90%|βββββββββ | 563/626 90%|βββββββββ | 564/626 90%|βββββββββ | 565/626 90%|βββββββββ | 566/626 91%|βββββββββ | 567/626 91%|βββββββββ | 568/626 91%|βββββββββ | 569/626 91%|βββββββββ | 570/626 91%|βββββββββ | 570/626 91%|βββββββββ | 571/626 91%|ββββββββββ| 572/626 92%|ββββββββββ| 573/626 92%|ββββββββββ| 574/626 92%|ββββββββββ| 575/626 92%|ββββββββββ| 576/626 92%|ββββββββββ| 577/626 92%|ββββββββββ| 578/626 92%|ββββββββββ| 579/626 93%|ββββββββββ| 580/626 93%|ββββββββββ| 580/626 93%|ββββββββββ| 581/626 93%|ββββββββββ| 582/626 93%|ββββββββββ| 583/626 93%|ββββββββββ| 584/626 93%|ββββββββββ| 585/626 94%|ββββββββββ| 586/626 94%|ββββββββββ| 587/626 94%|ββββββββββ| 588/626 94%|ββββββββββ| 589/626 94%|ββββββββββ| 590/626 94%|ββββββββββ| 590/626 94%|ββββββββββ| 591/626 95%|ββββββββββ| 592/626 95%|ββββββββββ| 593/626 95%|ββββββββββ| 594/626 95%|ββββββββββ| 595/626 95%|ββββββββββ| 596/626 95%|ββββββββββ| 597/626 96%|ββββββββββ| 598/626 96%|ββββββββββ| 599/626 96%|ββββββββββ| 600/626 96%|ββββββββββ| 600/626 96%|ββββββββββ| 601/626 96%|ββββββββββ| 602/626 96%|ββββββββββ| 603/626 96%|ββββββββββ| 604/626 97%|ββββββββββ| 605/626 97%|ββββββββββ| 606/626 97%|ββββββββββ| 607/626 97%|ββββββββββ| 608/626 97%|ββββββββββ| 609/626 97%|ββββββββββ| 610/626 97%|ββββββββββ| 610/626 98%|ββββββββββ| 611/626 98%|ββββββββββ| 612/626 98%|ββββββββββ| 613/626 98%|ββββββββββ| 614/626 98%|ββββββββββ| 615/626 98%|ββββββββββ| 616/626 99%|ββββββββββ| 617/626 99%|ββββββββββ| 618/626 99%|ββββββββββ| 619/626 99%|ββββββββββ| 620/626 99%|ββββββββββ| 620/626 99%|ββββββββββ| 621/626 99%|ββββββββββ| 622/626 100%|ββββββββββ| 623/626 100%|ββββββββββ| 624/626 100%|ββββββββββ| 625/626 100%|ββββββββββ| 626/626 100%|ββββββββββ| 626/626 100%|ββββββββββ| 626/626 | |
| {'loss': '6.337', 'grad_norm': '6.47', 'learning_rate': '9e-07', 'epoch': '0.03201'} | |
| {'loss': '5.984', 'grad_norm': '6.444', 'learning_rate': '1.9e-06', 'epoch': '0.06403'} | |
| {'loss': '6.208', 'grad_norm': '8.02', 'learning_rate': '2.9e-06', 'epoch': '0.09604'} | |
| {'loss': '6.385', 'grad_norm': '7.08', 'learning_rate': '3.9e-06', 'epoch': '0.1281'} | |
| {'loss': '5.767', 'grad_norm': '6.728', 'learning_rate': '4.9e-06', 'epoch': '0.1601'} | |
| {'loss': '5.087', 'grad_norm': '4.684', 'learning_rate': '5.9e-06', 'epoch': '0.1921'} | |
| {'loss': '4.853', 'grad_norm': '4.488', 'learning_rate': '6.9e-06', 'epoch': '0.2241'} | |
| {'loss': '4.237', 'grad_norm': '6.086', 'learning_rate': '7.9e-06', 'epoch': '0.2561'} | |
| {'loss': '3.365', 'grad_norm': '5.247', 'learning_rate': '8.9e-06', 'epoch': '0.2881'} | |
| {'loss': '2.653', 'grad_norm': '5.523', 'learning_rate': '9.9e-06', 'epoch': '0.3201'} | |
| {'loss': '1.608', 'grad_norm': '4.215', 'learning_rate': '9.829e-06', 'epoch': '0.3521'} | |
| {'loss': '1.914', 'grad_norm': '2.58', 'learning_rate': '9.639e-06', 'epoch': '0.3842'} | |
| {'loss': '1.483', 'grad_norm': '2.425', 'learning_rate': '9.449e-06', 'epoch': '0.4162'} | |
| {'loss': '1.521', 'grad_norm': '2.062', 'learning_rate': '9.259e-06', 'epoch': '0.4482'} | |
| {'loss': '1.673', 'grad_norm': '2.048', 'learning_rate': '9.068e-06', 'epoch': '0.4802'} | |
| {'loss': '1.463', 'grad_norm': '2.703', 'learning_rate': '8.878e-06', 'epoch': '0.5122'} | |
| {'loss': '1.735', 'grad_norm': '3.261', 'learning_rate': '8.688e-06', 'epoch': '0.5442'} | |
| {'loss': '1.576', 'grad_norm': '3.606', 'learning_rate': '8.498e-06', 'epoch': '0.5762'} | |
| {'loss': '1.123', 'grad_norm': '2.16', 'learning_rate': '8.308e-06', 'epoch': '0.6082'} | |
| {'loss': '1.723', 'grad_norm': '2.223', 'learning_rate': '8.118e-06', 'epoch': '0.6403'} | |
| {'loss': '1.512', 'grad_norm': '1.473', 'learning_rate': '7.928e-06', 'epoch': '0.6723'} | |
| {'loss': '1.189', 'grad_norm': '1.596', 'learning_rate': '7.738e-06', 'epoch': '0.7043'} | |
| {'loss': '1.451', 'grad_norm': '1.563', 'learning_rate': '7.548e-06', 'epoch': '0.7363'} | |
| {'loss': '1.353', 'grad_norm': '1.965', 'learning_rate': '7.357e-06', 'epoch': '0.7683'} | |
| {'loss': '1.394', 'grad_norm': '3.347', 'learning_rate': '7.167e-06', 'epoch': '0.8003'} | |
| {'loss': '1.296', 'grad_norm': '2.626', 'learning_rate': '6.977e-06', 'epoch': '0.8323'} | |
| {'loss': '1.157', 'grad_norm': '2.824', 'learning_rate': '6.787e-06', 'epoch': '0.8643'} | |
| {'loss': '1.292', 'grad_norm': '1.617', 'learning_rate': '6.597e-06', 'epoch': '0.8964'} | |
| {'loss': '1.225', 'grad_norm': '1.633', 'learning_rate': '6.407e-06', 'epoch': '0.9284'} | |
| {'loss': '1.673', 'grad_norm': '2.772', 'learning_rate': '6.217e-06', 'epoch': '0.9604'} | |
| {'loss': '1.218', 'grad_norm': '2.343', 'learning_rate': '6.027e-06', 'epoch': '0.9924'} | |
| {'loss': '1.352', 'grad_norm': '3.246', 'learning_rate': '5.837e-06', 'epoch': '1.022'} | |
| {'loss': '1.443', 'grad_norm': '1.679', 'learning_rate': '5.646e-06', 'epoch': '1.054'} | |
| {'loss': '1.253', 'grad_norm': '2.895', 'learning_rate': '5.456e-06', 'epoch': '1.086'} | |
| {'loss': '1.319', 'grad_norm': '3.107', 'learning_rate': '5.266e-06', 'epoch': '1.118'} | |
| {'loss': '1.211', 'grad_norm': '2.831', 'learning_rate': '5.076e-06', 'epoch': '1.15'} | |
| {'loss': '1.05', 'grad_norm': '2.265', 'learning_rate': '4.886e-06', 'epoch': '1.182'} | |
| {'loss': '1.236', 'grad_norm': '2.633', 'learning_rate': '4.696e-06', 'epoch': '1.214'} | |
| {'loss': '1.261', 'grad_norm': '2.088', 'learning_rate': '4.506e-06', 'epoch': '1.246'} | |
| {'loss': '1.096', 'grad_norm': '1.923', 'learning_rate': '4.316e-06', 'epoch': '1.279'} | |
| {'loss': '1.293', 'grad_norm': '2.414', 'learning_rate': '4.125e-06', 'epoch': '1.311'} | |
| {'loss': '1.25', 'grad_norm': '2.723', 'learning_rate': '3.935e-06', 'epoch': '1.343'} | |
| {'loss': '1.236', 'grad_norm': '2.479', 'learning_rate': '3.745e-06', 'epoch': '1.375'} | |
| {'loss': '1.205', 'grad_norm': '2.518', 'learning_rate': '3.555e-06', 'epoch': '1.407'} | |
| {'loss': '1.178', 'grad_norm': '2.59', 'learning_rate': '3.365e-06', 'epoch': '1.439'} | |
| {'loss': '1.046', 'grad_norm': '1.899', 'learning_rate': '3.175e-06', 'epoch': '1.471'} | |
| {'loss': '1.242', 'grad_norm': '3.226', 'learning_rate': '2.985e-06', 'epoch': '1.503'} | |
| {'loss': '1.371', 'grad_norm': '3.256', 'learning_rate': '2.795e-06', 'epoch': '1.535'} | |
| {'loss': '1.284', 'grad_norm': '2.328', 'learning_rate': '2.605e-06', 'epoch': '1.567'} | |
| {'loss': '1.115', 'grad_norm': '3.494', 'learning_rate': '2.414e-06', 'epoch': '1.599'} | |
| {'loss': '1.128', 'grad_norm': '2.021', 'learning_rate': '2.224e-06', 'epoch': '1.631'} | |
| {'loss': '1.144', 'grad_norm': '2.33', 'learning_rate': '2.034e-06', 'epoch': '1.663'} | |
| {'loss': '1.235', 'grad_norm': '3.267', 'learning_rate': '1.844e-06', 'epoch': '1.695'} | |
| {'loss': '1.315', 'grad_norm': '2.288', 'learning_rate': '1.654e-06', 'epoch': '1.727'} | |
| {'loss': '1.14', 'grad_norm': '2.474', 'learning_rate': '1.464e-06', 'epoch': '1.759'} | |
| {'loss': '1.287', 'grad_norm': '1.795', 'learning_rate': '1.274e-06', 'epoch': '1.791'} | |
| {'loss': '1.264', 'grad_norm': '2.716', 'learning_rate': '1.084e-06', 'epoch': '1.823'} | |
| {'loss': '1.146', 'grad_norm': '2.313', 'learning_rate': '8.935e-07', 'epoch': '1.855'} | |
| {'loss': '1.17', 'grad_norm': '2.066', 'learning_rate': '7.034e-07', 'epoch': '1.887'} | |
| {'loss': '1.192', 'grad_norm': '1.804', 'learning_rate': '5.133e-07', 'epoch': '1.919'} | |
| {'loss': '1.393', 'grad_norm': '3.937', 'learning_rate': '3.232e-07', 'epoch': '1.951'} | |
| {'loss': '1.149', 'grad_norm': '2.496', 'learning_rate': '1.331e-07', 'epoch': '1.983'} | |
| {'train_runtime': '1439', 'train_samples_per_second': '6.947', 'train_steps_per_second': '0.435', 'train_loss': '1.92', 'epoch': '2'} | |
| Saved final model to ../checkpoints/sft-multitq/final | |