| { | |
| "best_metric": 0.21882569789886475, | |
| "best_model_checkpoint": "./beans_outputs/checkpoint-130", | |
| "epoch": 1.0, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0015384615384615387, | |
| "loss": 1.0909, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0019823877374156645, | |
| "loss": 0.9564, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0018976137276390142, | |
| "loss": 0.8485, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.001748510748171101, | |
| "loss": 0.682, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0015457645101945045, | |
| "loss": 0.7391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0013039051575742468, | |
| "loss": 0.3587, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0010402659401094153, | |
| "loss": 0.5773, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0007737409975702781, | |
| "loss": 0.507, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0005234312799786921, | |
| "loss": 0.4312, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00030727564649040063, | |
| "loss": 0.4067, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00014076524743778318, | |
| "loss": 0.3141, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.5833325466437696e-05, | |
| "loss": 0.3359, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5679, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9022556390977443, | |
| "eval_loss": 0.21882569789886475, | |
| "eval_runtime": 0.8027, | |
| "eval_samples_per_second": 165.693, | |
| "eval_steps_per_second": 21.179, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 130, | |
| "total_flos": 2.195932065572045e+16, | |
| "train_loss": 0.6012275494061984, | |
| "train_runtime": 20.9633, | |
| "train_samples_per_second": 49.324, | |
| "train_steps_per_second": 6.201 | |
| } | |
| ], | |
| "max_steps": 130, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.195932065572045e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |