Instructions to use dzanbek/9c0ba83d-7ad1-4ee2-9ce3-e505d153c9e6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dzanbek/9c0ba83d-7ad1-4ee2-9ce3-e505d153c9e6 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Hermes-2-Theta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "dzanbek/9c0ba83d-7ad1-4ee2-9ce3-e505d153c9e6") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.059982005398380486, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007997600719784065, | |
| "grad_norm": 6.327381610870361, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 7.5777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007997600719784065, | |
| "eval_loss": 8.017860412597656, | |
| "eval_runtime": 287.8541, | |
| "eval_samples_per_second": 3.658, | |
| "eval_steps_per_second": 1.831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001599520143956813, | |
| "grad_norm": 6.17039155960083, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 7.6098, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023992802159352195, | |
| "grad_norm": 5.528576850891113, | |
| "learning_rate": 0.0002, | |
| "loss": 7.7284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003199040287913626, | |
| "grad_norm": 6.728517532348633, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 7.4974, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003998800359892032, | |
| "grad_norm": 5.695092678070068, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 5.9835, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004798560431870439, | |
| "grad_norm": 6.079351902008057, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 5.1384, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005598320503848845, | |
| "grad_norm": 6.481296539306641, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 5.0691, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006398080575827252, | |
| "grad_norm": 7.214561462402344, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 4.8119, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0071978406478056586, | |
| "grad_norm": 7.010176658630371, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.5991, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007997600719784064, | |
| "grad_norm": 6.9982590675354, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 4.6868, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00879736079176247, | |
| "grad_norm": 6.621185302734375, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 4.2868, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009597120863740878, | |
| "grad_norm": 5.465557098388672, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.0701, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010396880935719284, | |
| "grad_norm": 6.433826923370361, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 4.166, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01119664100769769, | |
| "grad_norm": 6.815083026885986, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 4.2868, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011996401079676098, | |
| "grad_norm": 5.863327980041504, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 4.2603, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012796161151654504, | |
| "grad_norm": 4.982174396514893, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 4.2987, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01359592122363291, | |
| "grad_norm": 4.87175178527832, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 3.9961, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014395681295611317, | |
| "grad_norm": 5.400818347930908, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 4.143, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015195441367589723, | |
| "grad_norm": 5.048769950866699, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 4.2183, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01599520143956813, | |
| "grad_norm": 4.657977104187012, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 4.0424, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016794961511546535, | |
| "grad_norm": 5.078902244567871, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.3025, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01759472158352494, | |
| "grad_norm": 5.692748069763184, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 4.0202, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01839448165550335, | |
| "grad_norm": 4.6804070472717285, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 4.2141, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019194241727481756, | |
| "grad_norm": 4.39948844909668, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 4.0431, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.019994001799460162, | |
| "grad_norm": 5.215299606323242, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 4.0373, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019994001799460162, | |
| "eval_loss": 3.997077703475952, | |
| "eval_runtime": 289.3626, | |
| "eval_samples_per_second": 3.639, | |
| "eval_steps_per_second": 1.821, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020793761871438568, | |
| "grad_norm": 5.740684986114502, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 4.2566, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.021593521943416974, | |
| "grad_norm": 5.554161548614502, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.9106, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02239328201539538, | |
| "grad_norm": 4.885501384735107, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 4.0344, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02319304208737379, | |
| "grad_norm": 6.132773399353027, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 4.4499, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.023992802159352195, | |
| "grad_norm": 4.748602390289307, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 4.0122, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0247925622313306, | |
| "grad_norm": 4.478851318359375, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 3.8626, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.025592322303309007, | |
| "grad_norm": 4.523096561431885, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 3.9546, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.026392082375287413, | |
| "grad_norm": 6.3320794105529785, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 4.3883, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02719184244726582, | |
| "grad_norm": 5.49621057510376, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 4.14, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02799160251924423, | |
| "grad_norm": 5.168715000152588, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 3.6449, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.028791362591222634, | |
| "grad_norm": 5.227668285369873, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 3.6928, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02959112266320104, | |
| "grad_norm": 4.343628406524658, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 3.6469, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.030390882735179446, | |
| "grad_norm": 6.07112455368042, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 3.7737, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.031190642807157852, | |
| "grad_norm": 6.020794868469238, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0414, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03199040287913626, | |
| "grad_norm": 5.776181221008301, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 3.78, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.032790162951114664, | |
| "grad_norm": 5.805772304534912, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 3.882, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03358992302309307, | |
| "grad_norm": 5.020073413848877, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 3.8944, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.034389683095071476, | |
| "grad_norm": 4.815114974975586, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 3.6254, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03518944316704988, | |
| "grad_norm": 5.086230754852295, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 3.9899, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.035989203239028295, | |
| "grad_norm": 5.002678871154785, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.681, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0367889633110067, | |
| "grad_norm": 4.317289352416992, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 3.8644, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.037588723382985106, | |
| "grad_norm": 4.629146575927734, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 3.9064, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03838848345496351, | |
| "grad_norm": 4.717955112457275, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 3.7925, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03918824352694192, | |
| "grad_norm": 4.8145856857299805, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 3.78, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.039988003598920324, | |
| "grad_norm": 3.983384370803833, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 3.963, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.039988003598920324, | |
| "eval_loss": 3.8365397453308105, | |
| "eval_runtime": 288.8744, | |
| "eval_samples_per_second": 3.645, | |
| "eval_steps_per_second": 1.824, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04078776367089873, | |
| "grad_norm": 5.371262073516846, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.942, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.041587523742877136, | |
| "grad_norm": 5.728109359741211, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 3.8686, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04238728381485554, | |
| "grad_norm": 4.341375827789307, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 3.5577, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04318704388683395, | |
| "grad_norm": 4.182137966156006, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 3.485, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.043986803958812354, | |
| "grad_norm": 4.7370405197143555, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 3.9982, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04478656403079076, | |
| "grad_norm": 4.426697731018066, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 3.6931, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04558632410276917, | |
| "grad_norm": 4.092799186706543, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 3.7611, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04638608417474758, | |
| "grad_norm": 4.8570098876953125, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 3.4304, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.047185844246725984, | |
| "grad_norm": 4.567028522491455, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 3.7632, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.04798560431870439, | |
| "grad_norm": 5.1109185218811035, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 4.0769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.048785364390682796, | |
| "grad_norm": 4.340146064758301, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 3.6998, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0495851244626612, | |
| "grad_norm": 5.708188056945801, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 3.684, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05038488453463961, | |
| "grad_norm": 4.427576065063477, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 3.8579, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.051184644606618014, | |
| "grad_norm": 5.3037800788879395, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 4.1091, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05198440467859642, | |
| "grad_norm": 4.853593826293945, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 4.2218, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.052784164750574826, | |
| "grad_norm": 6.393092155456543, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 3.8463, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05358392482255323, | |
| "grad_norm": 4.756587028503418, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 4.0146, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05438368489453164, | |
| "grad_norm": 4.337407112121582, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 3.5736, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.055183444966510044, | |
| "grad_norm": 4.383087635040283, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 3.7182, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05598320503848846, | |
| "grad_norm": 4.449667453765869, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 3.8575, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05678296511046686, | |
| "grad_norm": 4.845231533050537, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 3.6972, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.05758272518244527, | |
| "grad_norm": 4.200953483581543, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 3.937, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.058382485254423674, | |
| "grad_norm": 5.014280319213867, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 3.5019, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.05918224532640208, | |
| "grad_norm": 4.5435919761657715, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 4.1094, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.059982005398380486, | |
| "grad_norm": 4.351820945739746, | |
| "learning_rate": 0.0, | |
| "loss": 3.8918, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.059982005398380486, | |
| "eval_loss": 3.7904601097106934, | |
| "eval_runtime": 288.9933, | |
| "eval_samples_per_second": 3.644, | |
| "eval_steps_per_second": 1.824, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112831529320448e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |