| { | |
| "best_metric": 0.14907684922218323, | |
| "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific/coin_flip/checkpoint-55", | |
| "epoch": 8.979591836734693, | |
| "eval_steps": 500, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 4.5179572105407715, | |
| "eval_runtime": 1.8312, | |
| "eval_samples_per_second": 26.758, | |
| "eval_steps_per_second": 3.823, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.5562, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 3.3285250663757324, | |
| "eval_runtime": 1.8387, | |
| "eval_samples_per_second": 26.649, | |
| "eval_steps_per_second": 3.807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 1.0093011856079102, | |
| "eval_runtime": 1.8346, | |
| "eval_samples_per_second": 26.709, | |
| "eval_steps_per_second": 3.816, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.3848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 0.2200772613286972, | |
| "eval_runtime": 1.8356, | |
| "eval_samples_per_second": 26.694, | |
| "eval_steps_per_second": 3.813, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.3144, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 0.21126192808151245, | |
| "eval_runtime": 1.8403, | |
| "eval_samples_per_second": 26.626, | |
| "eval_steps_per_second": 3.804, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_loss": 0.18616808950901031, | |
| "eval_runtime": 1.8423, | |
| "eval_samples_per_second": 26.598, | |
| "eval_steps_per_second": 3.8, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.2066, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_loss": 0.1662234216928482, | |
| "eval_runtime": 1.8364, | |
| "eval_samples_per_second": 26.683, | |
| "eval_steps_per_second": 3.812, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.2262299805879593, | |
| "eval_runtime": 1.8315, | |
| "eval_samples_per_second": 26.754, | |
| "eval_steps_per_second": 3.822, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "eval_loss": 0.14907684922218323, | |
| "eval_runtime": 1.8356, | |
| "eval_samples_per_second": 26.694, | |
| "eval_steps_per_second": 3.813, | |
| "step": 55 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 60, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 6584591944581120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |