Instructions to use Benjaminpwh/qwen2.5-7b-instruct-poly-adaLORA-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Benjaminpwh/qwen2.5-7b-instruct-poly-adaLORA-6 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Benjaminpwh/qwen2.5-7b-instruct-poly-adaLORA-6", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23450880873712818, | |
| "eval_steps": 500, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.3501258391018316e-05, | |
| "grad_norm": 0.8195101618766785, | |
| "learning_rate": 5e-05, | |
| "loss": 14.0675, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033501258391018312, | |
| "grad_norm": 0.6814610958099365, | |
| "learning_rate": 4.999864297594039e-05, | |
| "loss": 9.6991, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0067002516782036625, | |
| "grad_norm": 0.6981404423713684, | |
| "learning_rate": 4.999451708687114e-05, | |
| "loss": 5.8251, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.010050377517305495, | |
| "grad_norm": 0.71510249376297, | |
| "learning_rate": 4.998762265134215e-05, | |
| "loss": 4.8931, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.013400503356407325, | |
| "grad_norm": 0.7365719676017761, | |
| "learning_rate": 4.9977960433023496e-05, | |
| "loss": 3.7625, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.016750629195509157, | |
| "grad_norm": 0.7549176812171936, | |
| "learning_rate": 4.9965531502161924e-05, | |
| "loss": 2.5786, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02010075503461099, | |
| "grad_norm": 0.7549782395362854, | |
| "learning_rate": 4.995033723546226e-05, | |
| "loss": 2.3343, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.023450880873712818, | |
| "grad_norm": 0.7549582123756409, | |
| "learning_rate": 4.993237931593496e-05, | |
| "loss": 2.3209, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02680100671281465, | |
| "grad_norm": 0.754852831363678, | |
| "learning_rate": 4.991165973270965e-05, | |
| "loss": 2.3182, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.030151132551916482, | |
| "grad_norm": 0.7546794414520264, | |
| "learning_rate": 4.988818078081481e-05, | |
| "loss": 2.3295, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.033501258391018314, | |
| "grad_norm": 0.7546112537384033, | |
| "learning_rate": 4.9861945060923584e-05, | |
| "loss": 2.3221, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.036851384230120146, | |
| "grad_norm": 0.7547661662101746, | |
| "learning_rate": 4.983295547906569e-05, | |
| "loss": 2.3251, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.04020151006922198, | |
| "grad_norm": 0.7546742558479309, | |
| "learning_rate": 4.980121524630554e-05, | |
| "loss": 2.3214, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.0435516359083238, | |
| "grad_norm": 0.7544980049133301, | |
| "learning_rate": 4.976672787838654e-05, | |
| "loss": 2.3259, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.046901761747425635, | |
| "grad_norm": 0.7544678449630737, | |
| "learning_rate": 4.9729497195341726e-05, | |
| "loss": 2.3197, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.05025188758652747, | |
| "grad_norm": 0.7546402215957642, | |
| "learning_rate": 4.968952732107054e-05, | |
| "loss": 2.3209, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.0536020134256293, | |
| "grad_norm": 0.754619300365448, | |
| "learning_rate": 4.964682268288213e-05, | |
| "loss": 2.3188, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.05695213926473113, | |
| "grad_norm": 0.754672110080719, | |
| "learning_rate": 4.9601388011004926e-05, | |
| "loss": 2.3247, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.12060453020766593, | |
| "grad_norm": 2.730647087097168, | |
| "learning_rate": 4.822888174568335e-05, | |
| "loss": 28.8747, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.12730478188586958, | |
| "grad_norm": 2.763967275619507, | |
| "learning_rate": 4.802920851560973e-05, | |
| "loss": 17.4519, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.13400503356407326, | |
| "grad_norm": 2.815877676010132, | |
| "learning_rate": 4.7819332140911445e-05, | |
| "loss": 15.0003, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1407052852422769, | |
| "grad_norm": 2.8834288120269775, | |
| "learning_rate": 4.7599345607806536e-05, | |
| "loss": 11.9449, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.14740553692048058, | |
| "grad_norm": 2.9614415168762207, | |
| "learning_rate": 4.7369346381842344e-05, | |
| "loss": 8.1434, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.15410578859868423, | |
| "grad_norm": 3.032062292098999, | |
| "learning_rate": 4.7129436364713164e-05, | |
| "loss": 3.7118, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.1608060402768879, | |
| "grad_norm": 3.026526689529419, | |
| "learning_rate": 4.687972184911246e-05, | |
| "loss": 2.0568, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.16750629195509156, | |
| "grad_norm": 3.0271811485290527, | |
| "learning_rate": 4.6620313471639675e-05, | |
| "loss": 1.9842, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1742065436332952, | |
| "grad_norm": 3.027158737182617, | |
| "learning_rate": 4.635132616378236e-05, | |
| "loss": 1.9426, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.1809067953114989, | |
| "grad_norm": 3.0273852348327637, | |
| "learning_rate": 4.607287910099557e-05, | |
| "loss": 1.9186, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.18760704698970254, | |
| "grad_norm": 3.0235822200775146, | |
| "learning_rate": 4.578509564990087e-05, | |
| "loss": 1.8787, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.19430729866790622, | |
| "grad_norm": 3.0256638526916504, | |
| "learning_rate": 4.5488103313628474e-05, | |
| "loss": 1.8544, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.20100755034610987, | |
| "grad_norm": 3.028939962387085, | |
| "learning_rate": 4.5182033675326696e-05, | |
| "loss": 1.8332, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.20770780202431355, | |
| "grad_norm": 3.027080535888672, | |
| "learning_rate": 4.4867022339863685e-05, | |
| "loss": 1.81, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.2144080537025172, | |
| "grad_norm": 3.0254549980163574, | |
| "learning_rate": 4.454320887374743e-05, | |
| "loss": 1.7835, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.22110830538072088, | |
| "grad_norm": 3.025289535522461, | |
| "learning_rate": 4.4210736743290485e-05, | |
| "loss": 1.7494, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.22780855705892453, | |
| "grad_norm": 3.02748441696167, | |
| "learning_rate": 4.3869753251046806e-05, | |
| "loss": 1.7233, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.23450880873712818, | |
| "grad_norm": 3.0303146839141846, | |
| "learning_rate": 4.352040947054912e-05, | |
| "loss": 1.6755, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 14925, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4305806868430477e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |