Instructions to use AlessaC/qwen2p5b_em_badmed_r32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlessaC/qwen2p5b_em_badmed_r32 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AlessaC/qwen2p5b_em_badmed_r32", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use AlessaC/qwen2p5b_em_badmed_r32 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for AlessaC/qwen2p5b_em_badmed_r32 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for AlessaC/qwen2p5b_em_badmed_r32 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for AlessaC/qwen2p5b_em_badmed_r32 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="AlessaC/qwen2p5b_em_badmed_r32", max_seq_length=2048, )
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.25220680958385877, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025220680958385876, | |
| "grad_norm": 83.50857543945312, | |
| "learning_rate": 0.0, | |
| "loss": 3.3887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005044136191677175, | |
| "grad_norm": 71.31573486328125, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 3.4305, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007566204287515763, | |
| "grad_norm": 66.55958557128906, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 3.0425, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01008827238335435, | |
| "grad_norm": 67.16094207763672, | |
| "learning_rate": 6e-06, | |
| "loss": 3.1193, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012610340479192938, | |
| "grad_norm": 58.159088134765625, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.7595, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015132408575031526, | |
| "grad_norm": 39.46601867675781, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3184, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017654476670870115, | |
| "grad_norm": 45.5927734375, | |
| "learning_rate": 9.987325728770595e-06, | |
| "loss": 2.1763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0201765447667087, | |
| "grad_norm": 20.798906326293945, | |
| "learning_rate": 9.974651457541193e-06, | |
| "loss": 2.1835, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02269861286254729, | |
| "grad_norm": 15.517325401306152, | |
| "learning_rate": 9.961977186311787e-06, | |
| "loss": 2.1354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025220680958385876, | |
| "grad_norm": 15.667418479919434, | |
| "learning_rate": 9.949302915082384e-06, | |
| "loss": 1.9287, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027742749054224466, | |
| "grad_norm": 13.178864479064941, | |
| "learning_rate": 9.93662864385298e-06, | |
| "loss": 1.9898, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03026481715006305, | |
| "grad_norm": 10.053223609924316, | |
| "learning_rate": 9.923954372623576e-06, | |
| "loss": 2.0013, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 14.007344245910645, | |
| "learning_rate": 9.91128010139417e-06, | |
| "loss": 2.0559, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03530895334174023, | |
| "grad_norm": 11.14796257019043, | |
| "learning_rate": 9.898605830164766e-06, | |
| "loss": 2.0379, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03783102143757881, | |
| "grad_norm": 13.28112506866455, | |
| "learning_rate": 9.885931558935362e-06, | |
| "loss": 1.9854, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0403530895334174, | |
| "grad_norm": 11.45155143737793, | |
| "learning_rate": 9.873257287705957e-06, | |
| "loss": 2.1884, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04287515762925599, | |
| "grad_norm": 10.636513710021973, | |
| "learning_rate": 9.860583016476553e-06, | |
| "loss": 1.9676, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04539722572509458, | |
| "grad_norm": 10.700081825256348, | |
| "learning_rate": 9.847908745247149e-06, | |
| "loss": 1.9426, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04791929382093316, | |
| "grad_norm": 10.350312232971191, | |
| "learning_rate": 9.835234474017745e-06, | |
| "loss": 1.931, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05044136191677175, | |
| "grad_norm": 11.60483455657959, | |
| "learning_rate": 9.822560202788341e-06, | |
| "loss": 1.9397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05296343001261034, | |
| "grad_norm": 10.923288345336914, | |
| "learning_rate": 9.809885931558936e-06, | |
| "loss": 1.8861, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05548549810844893, | |
| "grad_norm": 10.222322463989258, | |
| "learning_rate": 9.797211660329532e-06, | |
| "loss": 1.8154, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058007566204287514, | |
| "grad_norm": 9.665061950683594, | |
| "learning_rate": 9.784537389100128e-06, | |
| "loss": 1.9885, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0605296343001261, | |
| "grad_norm": 10.544888496398926, | |
| "learning_rate": 9.771863117870724e-06, | |
| "loss": 1.9728, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06305170239596469, | |
| "grad_norm": 9.924367904663086, | |
| "learning_rate": 9.759188846641318e-06, | |
| "loss": 1.9665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 9.470415115356445, | |
| "learning_rate": 9.746514575411914e-06, | |
| "loss": 1.8872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06809583858764187, | |
| "grad_norm": 9.330588340759277, | |
| "learning_rate": 9.73384030418251e-06, | |
| "loss": 1.9458, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07061790668348046, | |
| "grad_norm": 9.101158142089844, | |
| "learning_rate": 9.721166032953105e-06, | |
| "loss": 2.0452, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07313997477931904, | |
| "grad_norm": 9.63065242767334, | |
| "learning_rate": 9.708491761723701e-06, | |
| "loss": 1.9648, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07566204287515763, | |
| "grad_norm": 9.038743019104004, | |
| "learning_rate": 9.695817490494297e-06, | |
| "loss": 1.9469, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07818411097099622, | |
| "grad_norm": 9.375469207763672, | |
| "learning_rate": 9.683143219264893e-06, | |
| "loss": 2.0387, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0807061790668348, | |
| "grad_norm": 9.170827865600586, | |
| "learning_rate": 9.670468948035488e-06, | |
| "loss": 2.0396, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0832282471626734, | |
| "grad_norm": 9.155048370361328, | |
| "learning_rate": 9.657794676806086e-06, | |
| "loss": 2.1346, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08575031525851198, | |
| "grad_norm": 9.660133361816406, | |
| "learning_rate": 9.64512040557668e-06, | |
| "loss": 1.814, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08827238335435057, | |
| "grad_norm": 9.577939987182617, | |
| "learning_rate": 9.632446134347276e-06, | |
| "loss": 1.9353, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09079445145018916, | |
| "grad_norm": 9.347375869750977, | |
| "learning_rate": 9.619771863117872e-06, | |
| "loss": 1.8748, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09331651954602774, | |
| "grad_norm": 9.635443687438965, | |
| "learning_rate": 9.607097591888467e-06, | |
| "loss": 2.0299, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09583858764186633, | |
| "grad_norm": 9.470548629760742, | |
| "learning_rate": 9.594423320659063e-06, | |
| "loss": 1.966, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "grad_norm": 9.292247772216797, | |
| "learning_rate": 9.581749049429659e-06, | |
| "loss": 1.8779, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1008827238335435, | |
| "grad_norm": 9.822443962097168, | |
| "learning_rate": 9.569074778200255e-06, | |
| "loss": 1.8484, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1034047919293821, | |
| "grad_norm": 8.519198417663574, | |
| "learning_rate": 9.55640050697085e-06, | |
| "loss": 1.7622, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10592686002522068, | |
| "grad_norm": 9.220460891723633, | |
| "learning_rate": 9.543726235741445e-06, | |
| "loss": 1.8659, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10844892812105927, | |
| "grad_norm": 8.564704895019531, | |
| "learning_rate": 9.531051964512042e-06, | |
| "loss": 1.8478, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11097099621689786, | |
| "grad_norm": 9.696242332458496, | |
| "learning_rate": 9.518377693282636e-06, | |
| "loss": 1.8625, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11349306431273644, | |
| "grad_norm": 9.121529579162598, | |
| "learning_rate": 9.505703422053234e-06, | |
| "loss": 1.9736, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11601513240857503, | |
| "grad_norm": 9.0239896774292, | |
| "learning_rate": 9.493029150823828e-06, | |
| "loss": 1.8687, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11853720050441362, | |
| "grad_norm": 8.566268920898438, | |
| "learning_rate": 9.480354879594424e-06, | |
| "loss": 1.7855, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1210592686002522, | |
| "grad_norm": 9.728326797485352, | |
| "learning_rate": 9.46768060836502e-06, | |
| "loss": 2.0394, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1235813366960908, | |
| "grad_norm": 8.644201278686523, | |
| "learning_rate": 9.455006337135616e-06, | |
| "loss": 1.8265, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12610340479192939, | |
| "grad_norm": 9.00877857208252, | |
| "learning_rate": 9.442332065906211e-06, | |
| "loss": 1.9655, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12610340479192939, | |
| "eval_loss": 1.8593257665634155, | |
| "eval_runtime": 19.3972, | |
| "eval_samples_per_second": 36.345, | |
| "eval_steps_per_second": 18.198, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12862547288776796, | |
| "grad_norm": 8.626359939575195, | |
| "learning_rate": 9.429657794676807e-06, | |
| "loss": 1.8767, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": 8.989786148071289, | |
| "learning_rate": 9.416983523447403e-06, | |
| "loss": 1.9197, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13366960907944514, | |
| "grad_norm": 8.265259742736816, | |
| "learning_rate": 9.404309252217997e-06, | |
| "loss": 1.7882, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13619167717528374, | |
| "grad_norm": 9.578763008117676, | |
| "learning_rate": 9.391634980988594e-06, | |
| "loss": 2.0616, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13871374527112232, | |
| "grad_norm": 9.27950382232666, | |
| "learning_rate": 9.37896070975919e-06, | |
| "loss": 1.9043, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14123581336696092, | |
| "grad_norm": 8.789308547973633, | |
| "learning_rate": 9.366286438529786e-06, | |
| "loss": 1.8745, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1437578814627995, | |
| "grad_norm": 8.460257530212402, | |
| "learning_rate": 9.35361216730038e-06, | |
| "loss": 1.9719, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.14627994955863807, | |
| "grad_norm": 8.686505317687988, | |
| "learning_rate": 9.340937896070976e-06, | |
| "loss": 1.8288, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14880201765447668, | |
| "grad_norm": 9.074113845825195, | |
| "learning_rate": 9.328263624841572e-06, | |
| "loss": 1.8212, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15132408575031525, | |
| "grad_norm": 8.919495582580566, | |
| "learning_rate": 9.315589353612169e-06, | |
| "loss": 1.9267, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 9.349574089050293, | |
| "learning_rate": 9.302915082382765e-06, | |
| "loss": 1.8566, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.15636822194199243, | |
| "grad_norm": 10.293651580810547, | |
| "learning_rate": 9.290240811153359e-06, | |
| "loss": 1.7412, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15889029003783103, | |
| "grad_norm": 9.373260498046875, | |
| "learning_rate": 9.277566539923955e-06, | |
| "loss": 1.9118, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1614123581336696, | |
| "grad_norm": 9.066275596618652, | |
| "learning_rate": 9.264892268694551e-06, | |
| "loss": 1.89, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 9.459461212158203, | |
| "learning_rate": 9.252217997465146e-06, | |
| "loss": 1.8408, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1664564943253468, | |
| "grad_norm": 9.49438190460205, | |
| "learning_rate": 9.239543726235742e-06, | |
| "loss": 1.9826, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16897856242118536, | |
| "grad_norm": 9.088374137878418, | |
| "learning_rate": 9.226869455006338e-06, | |
| "loss": 1.8442, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17150063051702397, | |
| "grad_norm": 8.981496810913086, | |
| "learning_rate": 9.214195183776934e-06, | |
| "loss": 1.8115, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17402269861286254, | |
| "grad_norm": 9.342341423034668, | |
| "learning_rate": 9.201520912547528e-06, | |
| "loss": 1.849, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17654476670870115, | |
| "grad_norm": 9.18710708618164, | |
| "learning_rate": 9.188846641318126e-06, | |
| "loss": 1.7475, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17906683480453972, | |
| "grad_norm": 9.204767227172852, | |
| "learning_rate": 9.17617237008872e-06, | |
| "loss": 1.8912, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18158890290037832, | |
| "grad_norm": 9.105266571044922, | |
| "learning_rate": 9.163498098859315e-06, | |
| "loss": 1.8394, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1841109709962169, | |
| "grad_norm": 9.192793846130371, | |
| "learning_rate": 9.150823827629913e-06, | |
| "loss": 1.9242, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18663303909205547, | |
| "grad_norm": 8.911624908447266, | |
| "learning_rate": 9.138149556400507e-06, | |
| "loss": 1.9121, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18915510718789408, | |
| "grad_norm": 9.20001220703125, | |
| "learning_rate": 9.125475285171103e-06, | |
| "loss": 1.9752, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19167717528373265, | |
| "grad_norm": 8.967398643493652, | |
| "learning_rate": 9.1128010139417e-06, | |
| "loss": 1.7422, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19419924337957126, | |
| "grad_norm": 8.867136001586914, | |
| "learning_rate": 9.100126742712296e-06, | |
| "loss": 1.7391, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.19672131147540983, | |
| "grad_norm": 9.721291542053223, | |
| "learning_rate": 9.08745247148289e-06, | |
| "loss": 1.7955, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.19924337957124844, | |
| "grad_norm": 8.936488151550293, | |
| "learning_rate": 9.074778200253486e-06, | |
| "loss": 1.602, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.201765447667087, | |
| "grad_norm": 8.965775489807129, | |
| "learning_rate": 9.062103929024082e-06, | |
| "loss": 1.9918, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2042875157629256, | |
| "grad_norm": 9.03048324584961, | |
| "learning_rate": 9.049429657794677e-06, | |
| "loss": 1.8228, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2068095838587642, | |
| "grad_norm": 9.195337295532227, | |
| "learning_rate": 9.036755386565273e-06, | |
| "loss": 1.9259, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.20933165195460277, | |
| "grad_norm": 9.696627616882324, | |
| "learning_rate": 9.024081115335869e-06, | |
| "loss": 1.8497, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21185372005044137, | |
| "grad_norm": 9.298614501953125, | |
| "learning_rate": 9.011406844106465e-06, | |
| "loss": 1.8685, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21437578814627994, | |
| "grad_norm": 8.810253143310547, | |
| "learning_rate": 8.998732572877061e-06, | |
| "loss": 1.7147, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21689785624211855, | |
| "grad_norm": 8.825125694274902, | |
| "learning_rate": 8.986058301647655e-06, | |
| "loss": 1.8466, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.21941992433795712, | |
| "grad_norm": 8.869908332824707, | |
| "learning_rate": 8.973384030418252e-06, | |
| "loss": 1.9044, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22194199243379573, | |
| "grad_norm": 9.151841163635254, | |
| "learning_rate": 8.960709759188848e-06, | |
| "loss": 1.8922, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2244640605296343, | |
| "grad_norm": 9.193544387817383, | |
| "learning_rate": 8.948035487959444e-06, | |
| "loss": 1.8199, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.22698612862547288, | |
| "grad_norm": 8.479183197021484, | |
| "learning_rate": 8.935361216730038e-06, | |
| "loss": 1.847, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22950819672131148, | |
| "grad_norm": 9.11871337890625, | |
| "learning_rate": 8.922686945500634e-06, | |
| "loss": 1.8631, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.23203026481715006, | |
| "grad_norm": 9.080836296081543, | |
| "learning_rate": 8.91001267427123e-06, | |
| "loss": 1.9849, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.23455233291298866, | |
| "grad_norm": 10.182774543762207, | |
| "learning_rate": 8.897338403041825e-06, | |
| "loss": 1.933, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.23707440100882723, | |
| "grad_norm": 9.077899932861328, | |
| "learning_rate": 8.884664131812421e-06, | |
| "loss": 1.7692, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.23959646910466584, | |
| "grad_norm": 8.86284065246582, | |
| "learning_rate": 8.871989860583017e-06, | |
| "loss": 1.7995, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2421185372005044, | |
| "grad_norm": 9.612898826599121, | |
| "learning_rate": 8.859315589353613e-06, | |
| "loss": 2.045, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.244640605296343, | |
| "grad_norm": 9.372990608215332, | |
| "learning_rate": 8.846641318124208e-06, | |
| "loss": 1.8652, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.2471626733921816, | |
| "grad_norm": 9.045456886291504, | |
| "learning_rate": 8.833967046894805e-06, | |
| "loss": 1.8405, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.24968474148802017, | |
| "grad_norm": 8.836333274841309, | |
| "learning_rate": 8.8212927756654e-06, | |
| "loss": 1.7977, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.25220680958385877, | |
| "grad_norm": 8.542088508605957, | |
| "learning_rate": 8.808618504435996e-06, | |
| "loss": 1.7449, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25220680958385877, | |
| "eval_loss": 1.821334719657898, | |
| "eval_runtime": 19.3187, | |
| "eval_samples_per_second": 36.493, | |
| "eval_steps_per_second": 18.272, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 794, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 534403812249600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |