Instructions to use DeepDream2045/ee3e3801-ac37-4de3-847d-02f6067252b4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use DeepDream2045/ee3e3801-ac37-4de3-847d-02f6067252b4 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct") model = PeftModel.from_pretrained(base_model, "DeepDream2045/ee3e3801-ac37-4de3-847d-02f6067252b4") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.8612159490585327, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05664518869928485, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011329037739856971, | |
| "grad_norm": 24.65677261352539, | |
| "learning_rate": 5e-05, | |
| "loss": 29.7807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011329037739856971, | |
| "eval_loss": 2.4394071102142334, | |
| "eval_runtime": 208.2448, | |
| "eval_samples_per_second": 28.558, | |
| "eval_steps_per_second": 3.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022658075479713943, | |
| "grad_norm": 27.222679138183594, | |
| "learning_rate": 0.0001, | |
| "loss": 32.3959, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003398711321957091, | |
| "grad_norm": 32.98060607910156, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 33.4299, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0045316150959427886, | |
| "grad_norm": 30.921926498413086, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 29.7122, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0056645188699284855, | |
| "grad_norm": 25.687549591064453, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 25.1131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006797422643914182, | |
| "grad_norm": 23.132740020751953, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 23.3871, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00793032641789988, | |
| "grad_norm": 18.85443878173828, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 22.1671, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009063230191885577, | |
| "grad_norm": 17.62495231628418, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 20.573, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010196133965871273, | |
| "grad_norm": 14.434099197387695, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 17.8481, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011329037739856971, | |
| "grad_norm": 15.916144371032715, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 16.6761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012461941513842669, | |
| "grad_norm": 14.026975631713867, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 14.7903, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013594845287828365, | |
| "grad_norm": 14.814682006835938, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 16.0327, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014727749061814063, | |
| "grad_norm": 16.0185604095459, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 18.155, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01586065283579976, | |
| "grad_norm": 16.92819595336914, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 18.8237, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016993556609785455, | |
| "grad_norm": 18.460590362548828, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 17.2702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018126460383771154, | |
| "grad_norm": 14.221395492553711, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 17.6757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01925936415775685, | |
| "grad_norm": 12.549836158752441, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 16.6149, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020392267931742546, | |
| "grad_norm": 12.436845779418945, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 16.0281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021525171705728246, | |
| "grad_norm": 14.278661727905273, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.6214, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022658075479713942, | |
| "grad_norm": 10.886022567749023, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 12.6638, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023790979253699638, | |
| "grad_norm": 11.73347282409668, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 14.8879, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024923883027685338, | |
| "grad_norm": 10.711037635803223, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 12.5993, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026056786801671034, | |
| "grad_norm": 11.942070960998535, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 13.8089, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02718969057565673, | |
| "grad_norm": 12.257878303527832, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 14.9371, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028322594349642426, | |
| "grad_norm": 13.868196487426758, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 13.6081, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028322594349642426, | |
| "eval_loss": 0.8853906393051147, | |
| "eval_runtime": 208.362, | |
| "eval_samples_per_second": 28.542, | |
| "eval_steps_per_second": 3.571, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029455498123628125, | |
| "grad_norm": 8.992348670959473, | |
| "learning_rate": 5e-05, | |
| "loss": 17.9547, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03058840189761382, | |
| "grad_norm": 9.770459175109863, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 14.1764, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03172130567159952, | |
| "grad_norm": 10.085947036743164, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 14.82, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03285420944558522, | |
| "grad_norm": 12.546303749084473, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 14.5786, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03398711321957091, | |
| "grad_norm": 8.8180513381958, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 13.0714, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03512001699355661, | |
| "grad_norm": 11.411664962768555, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 13.3333, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03625292076754231, | |
| "grad_norm": 9.17128849029541, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 12.3617, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.037385824541528, | |
| "grad_norm": 10.2019681930542, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 13.0738, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0385187283155137, | |
| "grad_norm": 10.263218879699707, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 13.7404, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0396516320894994, | |
| "grad_norm": 10.263712882995605, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 12.2719, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04078453586348509, | |
| "grad_norm": 12.365837097167969, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 14.4749, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04191743963747079, | |
| "grad_norm": 10.982479095458984, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 12.8875, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04305034341145649, | |
| "grad_norm": 10.957509994506836, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 17.0494, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.044183247185442184, | |
| "grad_norm": 9.524374961853027, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 16.3195, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.045316150959427884, | |
| "grad_norm": 8.716954231262207, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 15.2658, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04644905473341358, | |
| "grad_norm": 9.489079475402832, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 14.4491, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.047581958507399276, | |
| "grad_norm": 8.325908660888672, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 12.4704, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.048714862281384975, | |
| "grad_norm": 9.202627182006836, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 14.4045, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.049847766055370675, | |
| "grad_norm": 9.588567733764648, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 14.0462, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05098066982935637, | |
| "grad_norm": 9.506434440612793, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.2175, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05211357360334207, | |
| "grad_norm": 18.916034698486328, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 13.1203, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05324647737732777, | |
| "grad_norm": 9.236392974853516, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 12.2845, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05437938115131346, | |
| "grad_norm": 11.271123886108398, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 13.8317, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05551228492529916, | |
| "grad_norm": 10.629317283630371, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 13.7083, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05664518869928485, | |
| "grad_norm": 13.823080062866211, | |
| "learning_rate": 0.0, | |
| "loss": 12.8755, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05664518869928485, | |
| "eval_loss": 0.8612159490585327, | |
| "eval_runtime": 208.3794, | |
| "eval_samples_per_second": 28.539, | |
| "eval_steps_per_second": 3.57, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |