Instructions to use JohnP1/d1a-e2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JohnP1/d1a-e2b with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download train.log from JohnP1/d1a-e2b: direct link, hf CLI and curl.
- Browser
- Download file 24.3 kB
-
https://huggingface.co/JohnP1/d1a-e2b/resolve/main/train.log
- Command line
-
hf download hf://JohnP1/d1a-e2b/train.log
-
curl -L -o train.log https://huggingface.co/JohnP1/d1a-e2b/resolve/main/train.log
24.3 kB
| config.json: 0%| | 0.00/4.91k | |
| tokenizer_config.json: 0%| | 0.00/906 | |
| tokenizer.json: reconstructing file: 0%| | 0.00B / 32.2MB [A | |
| tokenizer.json: downloading bytes: | 0.00B | |
| tokenizer.json: downloading bytes: ██████████| 8.75MB, 872kB/s | |
| tokenizer.json: downloading bytes: ██████████| 8.75MB, 872kB/s | |
| tokenizer.json: reconstructing file: 100%|██████████| 32.2MB / 32.2MB, 3.21MB/s | |
| model.safetensors: reconstructing file: 0%| | 0.00B / 10.2GB [A | |
| model.safetensors: downloading bytes: | 0.00B | |
| model.safetensors: reconstructing file: 3%|▎ | 302MB / 10.2GB, 21.0MB/s [A | |
| model.safetensors: downloading bytes: ▏ | 159MB, 12.7MB/s | |
| model.safetensors: reconstructing file: 6%|▌ | 610MB / 10.2GB, 50.1MB/s [A | |
| model.safetensors: downloading bytes: ▍ | 387MB, 28.2MB/s | |
| model.safetensors: reconstructing file: 10%|█ | 1.05GB / 10.2GB, 66.2MB/s [A | |
| model.safetensors: downloading bytes: ▉ | 926MB, 76.8MB/s | |
| model.safetensors: reconstructing file: 17%|█▋ | 1.78GB / 10.2GB, 142MB/s [A | |
| model.safetensors: downloading bytes: █▋ | 1.69GB, 134MB/s | |
| model.safetensors: downloading bytes: ██▍ | 2.53GB, 193MB/s | |
| model.safetensors: reconstructing file: 27%|██▋ | 2.79GB / 10.2GB, 192MB/s [A | |
| model.safetensors: downloading bytes: ███▎ | 3.46GB, 254MB/s | |
| model.safetensors: reconstructing file: 38%|███▊ | 3.93GB / 10.2GB, 237MB/s [A | |
| model.safetensors: downloading bytes: ████▍ | 4.58GB, 324MB/s | |
| model.safetensors: downloading bytes: █████▎ | 5.49GB, 375MB/s | |
| model.safetensors: reconstructing file: 51%|█████▏ | 5.27GB / 10.2GB, 309MB/s [A | |
| model.safetensors: downloading bytes: ██████▏ | 6.37GB, 329MB/s | |
| model.safetensors: reconstructing file: 59%|█████▉ | 6.08GB / 10.2GB, 290MB/s [A | |
| model.safetensors: downloading bytes: ██████▊ | 7.04GB, 298MB/s | |
| model.safetensors: reconstructing file: 66%|██████▌ | 6.76GB / 10.2GB, 271MB/s [A | |
| model.safetensors: downloading bytes: ███████▍ | 7.63GB, 277MB/s | |
| model.safetensors: reconstructing file: 70%|██████▉ | 7.16GB / 10.2GB, 262MB/s [A | |
| model.safetensors: downloading bytes: ███████▉ | 8.10GB, 277MB/s | |
| model.safetensors: reconstructing file: 74%|███████▍ | 7.62GB / 10.2GB, 255MB/s [A | |
| model.safetensors: downloading bytes: ████████▎ | 8.55GB, 261MB/s | |
| model.safetensors: reconstructing file: 78%|███████▊ | 8.03GB / 10.2GB, 250MB/s [A | |
| model.safetensors: reconstructing file: 82%|████████▏ | 8.42GB / 10.2GB, 246MB/s [A | |
| model.safetensors: reconstructing file: 85%|████████▍ | 8.69GB / 10.2GB, 244MB/s [A | |
| model.safetensors: reconstructing file: 88%|████████▊ | 9.01GB / 10.2GB, 240MB/s [A | |
| model.safetensors: reconstructing file: 90%|█████████ | 9.26GB / 10.2GB, 239MB/s [A | |
| model.safetensors: reconstructing file: 94%|█████████▎| 9.58GB / 10.2GB, 237MB/s [A | |
| model.safetensors: reconstructing file: 96%|█████████▌| 9.86GB / 10.2GB, 235MB/s [A | |
| model.safetensors: reconstructing file: 98%|█████████▊| 10.1GB / 10.2GB, 235MB/s [A | |
| model.safetensors: downloading bytes: ██████████| 8.66GB, 261MB/s | |
| model.safetensors: downloading bytes: ██████████| 8.66GB, 261MB/s | |
| model.safetensors: reconstructing file: 100%|██████████| 10.2GB / 10.2GB, 235MB/s | |
| Loading weights: 0%| | 0/1951 | |
| generation_config.json: 0%| | 0.00/181 | |
| device=cuda trainable params=24.9M | |
| dropped 70 of 12576 records that exceed the training context (384 state / 960 branch / 2048 packed tokens) | |
| 12506 training requests (holdout=[]), questions by type {'score': 3448, 'noul': 5224, 'choice': 6834} | |
| ep0 step 10/3128 loss 2.506 kl 0.000 anchor 0.000 0.443s/rec | |
| ep0 step 20/3128 loss 2.095 kl 0.000 anchor 0.000 0.380s/rec | |
| ep0 step 30/3128 loss 1.953 kl 0.000 anchor 0.000 0.355s/rec | |
| ep0 step 40/3128 loss 2.202 kl 0.000 anchor 0.000 0.379s/rec | |
| ep0 step 50/3128 loss 1.863 kl 0.000 anchor 0.000 0.377s/rec | |
| ep0 step 60/3128 loss 1.980 kl 0.000 anchor 0.000 0.373s/rec | |
| ep0 step 70/3128 loss 1.595 kl 0.000 anchor 0.000 0.352s/rec | |
| ep0 step 80/3128 loss 1.736 kl 0.000 anchor 0.000 0.360s/rec | |
| ep0 step 90/3128 loss 1.607 kl 0.000 anchor 0.000 0.353s/rec | |
| ep0 step 100/3128 loss 1.654 kl 0.000 anchor 0.000 0.351s/rec | |
| ep0 step 110/3128 loss 1.521 kl 0.000 anchor 0.000 0.345s/rec | |
| ep0 step 120/3128 loss 1.439 kl 0.000 anchor 0.000 0.344s/rec | |
| ep0 step 130/3128 loss 1.560 kl 0.000 anchor 0.000 0.348s/rec | |
| ep0 step 140/3128 loss 1.407 kl 0.000 anchor 0.000 0.349s/rec | |
| ep0 step 150/3128 loss 1.608 kl 0.000 anchor 0.000 0.347s/rec | |
| ep0 step 160/3128 loss 1.093 kl 0.000 anchor 0.000 0.343s/rec | |
| ep0 step 170/3128 loss 1.345 kl 0.000 anchor 0.000 0.344s/rec | |
| ep0 step 180/3128 loss 1.338 kl 0.000 anchor 0.000 0.347s/rec | |
| ep0 step 190/3128 loss 1.099 kl 0.000 anchor 0.000 0.343s/rec | |
| ep0 step 200/3128 loss 1.322 kl 0.000 anchor 0.000 0.336s/rec | |
| ep0 step 210/3128 loss 1.262 kl 0.000 anchor 0.000 0.332s/rec | |
| ep0 step 220/3128 loss 1.285 kl 0.000 anchor 0.000 0.336s/rec | |
| ep0 step 230/3128 loss 1.338 kl 0.000 anchor 0.000 0.342s/rec | |
| ep0 step 240/3128 loss 1.044 kl 0.000 anchor 0.000 0.340s/rec | |
| ep0 step 250/3128 loss 0.938 kl 0.000 anchor 0.000 0.339s/rec | |
| ep0 step 260/3128 loss 1.045 kl 0.000 anchor 0.000 0.339s/rec | |
| ep0 step 270/3128 loss 1.045 kl 0.000 anchor 0.000 0.340s/rec | |
| ep0 step 280/3128 loss 1.016 kl 0.000 anchor 0.000 0.342s/rec | |
| ep0 step 290/3128 loss 0.797 kl 0.000 anchor 0.000 0.341s/rec | |
| ep0 step 300/3128 loss 1.012 kl 0.000 anchor 0.000 0.343s/rec | |
| ep0 step 310/3128 loss 0.952 kl 0.000 anchor 0.000 0.345s/rec | |
| ep0 step 320/3128 loss 1.101 kl 0.000 anchor 0.000 0.346s/rec | |
| ep0 step 330/3128 loss 1.034 kl 0.000 anchor 0.000 0.343s/rec | |
| ep0 step 340/3128 loss 0.711 kl 0.000 anchor 0.000 0.342s/rec | |
| ep0 step 350/3128 loss 0.927 kl 0.000 anchor 0.000 0.342s/rec | |
| ep0 step 360/3128 loss 1.065 kl 0.000 anchor 0.000 0.340s/rec | |
| ep0 step 370/3128 loss 0.650 kl 0.000 anchor 0.000 0.335s/rec | |
| ep0 step 380/3128 loss 1.009 kl 0.000 anchor 0.000 0.333s/rec | |
| ep0 step 390/3128 loss 0.725 kl 0.000 anchor 0.000 0.333s/rec | |
| ep0 step 400/3128 loss 0.935 kl 0.000 anchor 0.000 0.332s/rec | |
| ep0 step 410/3128 loss 0.804 kl 0.000 anchor 0.000 0.330s/rec | |
| ep0 step 420/3128 loss 0.770 kl 0.000 anchor 0.000 0.330s/rec | |
| ep0 step 430/3128 loss 1.309 kl 0.000 anchor 0.000 0.332s/rec | |
| ep0 step 440/3128 loss 0.784 kl 0.000 anchor 0.000 0.333s/rec | |
| ep0 step 450/3128 loss 0.690 kl 0.000 anchor 0.000 0.333s/rec | |
| ep0 step 460/3128 loss 0.826 kl 0.000 anchor 0.000 0.331s/rec | |
| ep0 step 470/3128 loss 0.709 kl 0.000 anchor 0.000 0.330s/rec | |
| ep0 step 480/3128 loss 0.733 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 490/3128 loss 0.727 kl 0.000 anchor 0.000 0.330s/rec | |
| ep0 step 500/3128 loss 0.804 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 510/3128 loss 0.785 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 520/3128 loss 0.532 kl 0.000 anchor 0.000 0.326s/rec | |
| ep0 step 530/3128 loss 1.143 kl 0.000 anchor 0.000 0.325s/rec | |
| ep0 step 540/3128 loss 0.629 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 550/3128 loss 0.622 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 560/3128 loss 0.718 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 570/3128 loss 0.757 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 580/3128 loss 0.903 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 590/3128 loss 0.621 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 600/3128 loss 0.820 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 610/3128 loss 0.698 kl 0.000 anchor 0.000 0.319s/rec | |
| ep0 step 620/3128 loss 0.643 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 630/3128 loss 0.705 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 640/3128 loss 0.523 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 650/3128 loss 0.872 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 660/3128 loss 0.779 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 670/3128 loss 0.564 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 680/3128 loss 0.648 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 690/3128 loss 0.617 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 700/3128 loss 0.789 kl 0.000 anchor 0.000 0.324s/rec | |
| ep0 step 710/3128 loss 0.603 kl 0.000 anchor 0.000 0.325s/rec | |
| ep0 step 720/3128 loss 0.971 kl 0.000 anchor 0.000 0.325s/rec | |
| ep0 step 730/3128 loss 0.770 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 740/3128 loss 0.568 kl 0.000 anchor 0.000 0.329s/rec | |
| ep0 step 750/3128 loss 0.430 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 760/3128 loss 0.736 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 770/3128 loss 0.627 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 780/3128 loss 0.821 kl 0.000 anchor 0.000 0.326s/rec | |
| ep0 step 790/3128 loss 0.509 kl 0.000 anchor 0.000 0.326s/rec | |
| ep0 step 800/3128 loss 0.867 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 810/3128 loss 0.503 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 820/3128 loss 0.779 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 830/3128 loss 0.676 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 840/3128 loss 0.670 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 850/3128 loss 0.716 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 860/3128 loss 0.394 kl 0.000 anchor 0.000 0.326s/rec | |
| ep0 step 870/3128 loss 0.826 kl 0.000 anchor 0.000 0.325s/rec | |
| ep0 step 880/3128 loss 0.819 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 890/3128 loss 0.446 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 900/3128 loss 0.698 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 910/3128 loss 0.585 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 920/3128 loss 0.767 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 930/3128 loss 0.761 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 940/3128 loss 0.635 kl 0.000 anchor 0.000 0.328s/rec | |
| ep0 step 950/3128 loss 0.702 kl 0.000 anchor 0.000 0.327s/rec | |
| ep0 step 960/3128 loss 0.477 kl 0.000 anchor 0.000 0.326s/rec | |
| ep0 step 970/3128 loss 0.663 kl 0.000 anchor 0.000 0.325s/rec | |
| ep0 step 980/3128 loss 0.740 kl 0.000 anchor 0.000 0.324s/rec | |
| ep0 step 990/3128 loss 0.646 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1000/3128 loss 0.598 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1010/3128 loss 0.645 kl 0.000 anchor 0.000 0.324s/rec | |
| ep0 step 1020/3128 loss 0.749 kl 0.000 anchor 0.000 0.325s/rec | |
| ep0 step 1030/3128 loss 0.760 kl 0.000 anchor 0.000 0.324s/rec | |
| ep0 step 1040/3128 loss 0.591 kl 0.000 anchor 0.000 0.324s/rec | |
| ep0 step 1050/3128 loss 0.685 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1060/3128 loss 0.735 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1070/3128 loss 0.524 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 1080/3128 loss 0.463 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1090/3128 loss 0.852 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1100/3128 loss 0.567 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1110/3128 loss 0.523 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1120/3128 loss 0.743 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1130/3128 loss 0.754 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1140/3128 loss 0.769 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 1150/3128 loss 0.452 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1160/3128 loss 0.827 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1170/3128 loss 0.836 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1180/3128 loss 0.521 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1190/3128 loss 0.517 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 1200/3128 loss 0.767 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 1210/3128 loss 0.430 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1220/3128 loss 0.527 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1230/3128 loss 0.552 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1240/3128 loss 0.676 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1250/3128 loss 0.701 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1260/3128 loss 0.643 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1270/3128 loss 0.650 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1280/3128 loss 0.888 kl 0.000 anchor 0.000 0.324s/rec | |
| ep0 step 1290/3128 loss 0.596 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1300/3128 loss 0.449 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1310/3128 loss 0.714 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1320/3128 loss 0.392 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1330/3128 loss 0.667 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1340/3128 loss 0.519 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1350/3128 loss 0.407 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1360/3128 loss 0.536 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1370/3128 loss 0.681 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1380/3128 loss 0.558 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1390/3128 loss 0.540 kl 0.000 anchor 0.000 0.323s/rec | |
| ep0 step 1400/3128 loss 0.410 kl 0.000 anchor 0.000 0.322s/rec | |
| ep0 step 1410/3128 loss 0.467 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 1420/3128 loss 0.475 kl 0.000 anchor 0.000 0.321s/rec | |
| ep0 step 1430/3128 loss 0.598 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1440/3128 loss 0.492 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1450/3128 loss 0.755 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1460/3128 loss 0.819 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1470/3128 loss 0.506 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1480/3128 loss 0.685 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1490/3128 loss 0.317 kl 0.000 anchor 0.000 0.320s/rec | |
| ep0 step 1500/3128 loss 0.662 kl 0.000 anchor 0.000 0.319s/rec | |
| ep0 step 1510/3128 loss 0.737 kl 0.000 anchor 0.000 0.318s/rec | |
| ep0 step 1520/3128 loss 0.453 kl 0.000 anchor 0.000 0.319s/rec | |
| ep0 step 1530/3128 loss 0.459 kl 0.000 anchor 0.000 0.318s/rec | |
| ep0 step 1540/3128 loss 0.446 kl 0.000 anchor 0.000 0.318s/rec | |
| ep0 step 1550/3128 loss 0.648 kl 0.000 anchor 0.000 0.319s/rec | |
| ep0 step 1560/3128 loss 0.693 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1570/3128 loss 0.488 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1580/3128 loss 0.460 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1590/3128 loss 0.577 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1600/3128 loss 0.321 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1610/3128 loss 0.645 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1620/3128 loss 0.368 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1630/3128 loss 0.377 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1640/3128 loss 0.730 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1650/3128 loss 0.523 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1660/3128 loss 0.361 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1670/3128 loss 0.357 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1680/3128 loss 0.373 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1690/3128 loss 1.005 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1700/3128 loss 0.404 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1710/3128 loss 0.366 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1720/3128 loss 0.387 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1730/3128 loss 0.608 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1740/3128 loss 0.553 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1750/3128 loss 0.367 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1760/3128 loss 0.671 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1770/3128 loss 0.347 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1780/3128 loss 0.362 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1790/3128 loss 0.598 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1800/3128 loss 0.612 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1810/3128 loss 0.366 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 1820/3128 loss 0.536 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1830/3128 loss 0.359 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 1840/3128 loss 0.398 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1850/3128 loss 0.523 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1860/3128 loss 0.309 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1870/3128 loss 0.455 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1880/3128 loss 0.500 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1890/3128 loss 0.462 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1900/3128 loss 0.419 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1910/3128 loss 0.459 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1920/3128 loss 0.391 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1930/3128 loss 0.489 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1940/3128 loss 0.385 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1950/3128 loss 0.263 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1960/3128 loss 0.417 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1970/3128 loss 0.258 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1980/3128 loss 0.618 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 1990/3128 loss 0.751 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2000/3128 loss 0.277 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2010/3128 loss 0.334 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2020/3128 loss 0.484 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2030/3128 loss 0.390 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2040/3128 loss 0.337 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2050/3128 loss 0.333 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2060/3128 loss 0.383 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2070/3128 loss 0.540 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2080/3128 loss 0.404 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2090/3128 loss 0.353 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2100/3128 loss 0.603 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2110/3128 loss 0.476 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2120/3128 loss 0.461 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2130/3128 loss 0.291 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2140/3128 loss 0.549 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2150/3128 loss 0.468 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2160/3128 loss 0.422 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2170/3128 loss 0.381 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2180/3128 loss 0.513 kl 0.000 anchor 0.000 0.318s/rec | |
| ep1 step 2190/3128 loss 0.327 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2200/3128 loss 0.488 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2210/3128 loss 0.696 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2220/3128 loss 0.320 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2230/3128 loss 0.342 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2240/3128 loss 0.268 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2250/3128 loss 0.466 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2260/3128 loss 0.370 kl 0.000 anchor 0.000 0.319s/rec | |
| ep1 step 2270/3128 loss 0.300 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2280/3128 loss 0.409 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2290/3128 loss 0.594 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2300/3128 loss 0.333 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2310/3128 loss 0.355 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2320/3128 loss 0.394 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2330/3128 loss 0.459 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2340/3128 loss 0.214 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2350/3128 loss 0.425 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2360/3128 loss 0.320 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2370/3128 loss 0.623 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2380/3128 loss 0.335 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2390/3128 loss 0.463 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2400/3128 loss 0.478 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2410/3128 loss 0.253 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2420/3128 loss 0.229 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2430/3128 loss 0.308 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2440/3128 loss 0.313 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2450/3128 loss 0.457 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2460/3128 loss 0.748 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2470/3128 loss 0.483 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2480/3128 loss 0.343 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2490/3128 loss 0.459 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2500/3128 loss 0.300 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2510/3128 loss 0.376 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2520/3128 loss 0.413 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2530/3128 loss 0.247 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2540/3128 loss 0.390 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2550/3128 loss 0.362 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2560/3128 loss 0.196 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2570/3128 loss 0.443 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2580/3128 loss 0.241 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2590/3128 loss 0.683 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2600/3128 loss 0.332 kl 0.000 anchor 0.000 0.323s/rec | |
| ep1 step 2610/3128 loss 0.506 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2620/3128 loss 0.410 kl 0.000 anchor 0.000 0.323s/rec | |
| ep1 step 2630/3128 loss 0.305 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2640/3128 loss 0.252 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2650/3128 loss 0.439 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2660/3128 loss 0.341 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2670/3128 loss 0.477 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2680/3128 loss 0.525 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2690/3128 loss 0.625 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2700/3128 loss 0.552 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2710/3128 loss 0.611 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2720/3128 loss 0.217 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2730/3128 loss 0.168 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2740/3128 loss 0.428 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2750/3128 loss 0.354 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2760/3128 loss 0.385 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2770/3128 loss 0.292 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2780/3128 loss 0.405 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2790/3128 loss 0.648 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2800/3128 loss 0.378 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2810/3128 loss 0.331 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2820/3128 loss 0.479 kl 0.000 anchor 0.000 0.322s/rec | |
| ep1 step 2830/3128 loss 0.369 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2840/3128 loss 0.837 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2850/3128 loss 0.425 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2860/3128 loss 0.558 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2870/3128 loss 0.429 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2880/3128 loss 0.363 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2890/3128 loss 0.345 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2900/3128 loss 0.489 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2910/3128 loss 0.283 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2920/3128 loss 0.285 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2930/3128 loss 0.440 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2940/3128 loss 0.306 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2950/3128 loss 0.457 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2960/3128 loss 0.355 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 2970/3128 loss 0.181 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2980/3128 loss 0.365 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 2990/3128 loss 0.361 kl 0.000 anchor 0.000 0.320s/rec | |
| ep1 step 3000/3128 loss 0.643 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3010/3128 loss 0.380 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3020/3128 loss 0.341 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3030/3128 loss 0.227 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3040/3128 loss 0.231 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3050/3128 loss 0.436 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3060/3128 loss 0.260 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3070/3128 loss 0.513 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3080/3128 loss 0.240 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3090/3128 loss 0.446 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3100/3128 loss 0.373 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3110/3128 loss 0.521 kl 0.000 anchor 0.000 0.321s/rec | |
| ep1 step 3120/3128 loss 0.683 kl 0.000 anchor 0.000 0.322s/rec | |
| saved /kev/runs/g4-e2b-e2-l4/00-trial-0/checkpoint | |