adapters-mistral-bnb8-QLORA-super_glue-cb
/
trainer_state-mistral-bnb8-QLORA-super_glue-cb-sequence_classification.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.161290322580645, | |
| "eval_steps": 1, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 133.33294677734375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.6332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "eval_accuracy": 0.5161290322580645, | |
| "eval_f1": 0.3712905452035887, | |
| "eval_loss": 2.060542583465576, | |
| "eval_runtime": 9.1597, | |
| "eval_samples_per_second": 6.769, | |
| "eval_steps_per_second": 0.873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 125.3294677734375, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6002, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "eval_accuracy": 0.4838709677419355, | |
| "eval_f1": 0.269908386187456, | |
| "eval_loss": 4.0351104736328125, | |
| "eval_runtime": 9.1436, | |
| "eval_samples_per_second": 6.781, | |
| "eval_steps_per_second": 0.875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 393.05718994140625, | |
| "learning_rate": 4.375e-05, | |
| "loss": 4.4364, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "eval_accuracy": 0.7741935483870968, | |
| "eval_f1": 0.5378874856486796, | |
| "eval_loss": 2.373875379562378, | |
| "eval_runtime": 9.1471, | |
| "eval_samples_per_second": 6.778, | |
| "eval_steps_per_second": 0.875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 109.7702407836914, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.4704, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "eval_accuracy": 0.7580645161290323, | |
| "eval_f1": 0.5238376674546887, | |
| "eval_loss": 2.210745096206665, | |
| "eval_runtime": 9.1416, | |
| "eval_samples_per_second": 6.782, | |
| "eval_steps_per_second": 0.875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 111.4744644165039, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.9734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "eval_accuracy": 0.8225806451612904, | |
| "eval_f1": 0.5721364589289117, | |
| "eval_loss": 1.480078935623169, | |
| "eval_runtime": 9.1345, | |
| "eval_samples_per_second": 6.787, | |
| "eval_steps_per_second": 0.876, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.096774193548387, | |
| "grad_norm": 57.42088317871094, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.5839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.096774193548387, | |
| "eval_accuracy": 0.8870967741935484, | |
| "eval_f1": 0.6163557565479555, | |
| "eval_loss": 0.7713032364845276, | |
| "eval_runtime": 9.1377, | |
| "eval_samples_per_second": 6.785, | |
| "eval_steps_per_second": 0.875, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.6129032258064515, | |
| "grad_norm": 44.42446517944336, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.3722, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.6129032258064515, | |
| "eval_accuracy": 0.8548387096774194, | |
| "eval_f1": 0.7293271700051361, | |
| "eval_loss": 0.4509028494358063, | |
| "eval_runtime": 9.1356, | |
| "eval_samples_per_second": 6.787, | |
| "eval_steps_per_second": 0.876, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.129032258064516, | |
| "grad_norm": 18.921249389648438, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.18, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.129032258064516, | |
| "eval_accuracy": 0.8548387096774194, | |
| "eval_f1": 0.7942615201216756, | |
| "eval_loss": 0.661185622215271, | |
| "eval_runtime": 9.1322, | |
| "eval_samples_per_second": 6.789, | |
| "eval_steps_per_second": 0.876, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.645161290322581, | |
| "grad_norm": 40.99948501586914, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.1994, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.645161290322581, | |
| "eval_accuracy": 0.8870967741935484, | |
| "eval_f1": 0.8194187528260781, | |
| "eval_loss": 0.5956389307975769, | |
| "eval_runtime": 9.1295, | |
| "eval_samples_per_second": 6.791, | |
| "eval_steps_per_second": 0.876, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 5.161290322580645, | |
| "grad_norm": 45.76235580444336, | |
| "learning_rate": 0.0, | |
| "loss": 0.2887, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.161290322580645, | |
| "eval_accuracy": 0.8548387096774194, | |
| "eval_f1": 0.7771043771043771, | |
| "eval_loss": 0.5316924452781677, | |
| "eval_runtime": 9.1285, | |
| "eval_samples_per_second": 6.792, | |
| "eval_steps_per_second": 0.876, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.161290322580645, | |
| "step": 10, | |
| "total_flos": 9605361558159360.0, | |
| "train_loss": 1.2737861171364784, | |
| "train_runtime": 685.5263, | |
| "train_samples_per_second": 3.559, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 9605361558159360.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |