| { | |
| "best_metric": 0.8552550673484802, | |
| "best_model_checkpoint": "./Zeroshot/01-12-23-mistralai-Mistral-7B-v0.1_multilang-dataset-3.0.3-portuguese-2_epochs-10_batch_3/checkpoints/checkpoint-6773", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 6773, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 5.835794447725931e-05, | |
| "loss": 1.4468, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00011742468989958655, | |
| "loss": 0.9754, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017649143532191377, | |
| "loss": 0.9429, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000235558180744241, | |
| "loss": 0.9147, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00029462492616656825, | |
| "loss": 0.9067, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00035369167158889544, | |
| "loss": 0.8978, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.8805813789367676, | |
| "eval_runtime": 88.2945, | |
| "eval_samples_per_second": 17.057, | |
| "eval_steps_per_second": 2.141, | |
| "step": 3386 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00039998760393503537, | |
| "loss": 0.895, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0003996072594095129, | |
| "loss": 0.8687, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00039869668890858337, | |
| "loss": 0.8884, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00039725831122269285, | |
| "loss": 0.8715, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00039529594718087214, | |
| "loss": 0.8645, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0003928148095012922, | |
| "loss": 0.8666, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0003898214889444803, | |
| "loss": 0.8719, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8552550673484802, | |
| "eval_runtime": 88.3232, | |
| "eval_samples_per_second": 17.051, | |
| "eval_steps_per_second": 2.14, | |
| "step": 6773 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 33860, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 3.401652779883725e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |