| { | |
| "best_metric": 2.8833088874816895, | |
| "best_model_checkpoint": "./models/22_12_13_luther_blocks_xl_fp16_5ep/checkpoint-250", | |
| "epoch": 5.0, | |
| "global_step": 1300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.39973340442548655, | |
| "eval_loss": 3.027606964111328, | |
| "eval_runtime": 5.8811, | |
| "eval_samples_per_second": 9.352, | |
| "eval_steps_per_second": 1.19, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.4143428419088243, | |
| "eval_loss": 2.9184916019439697, | |
| "eval_runtime": 5.8392, | |
| "eval_samples_per_second": 9.419, | |
| "eval_steps_per_second": 1.199, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.4188927397138541, | |
| "eval_loss": 2.8845763206481934, | |
| "eval_runtime": 5.8499, | |
| "eval_samples_per_second": 9.402, | |
| "eval_steps_per_second": 1.197, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8518, | |
| "eval_samples_per_second": 9.399, | |
| "eval_steps_per_second": 1.196, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0, | |
| "loss": 3.0309, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8496, | |
| "eval_samples_per_second": 9.402, | |
| "eval_steps_per_second": 1.197, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8476, | |
| "eval_samples_per_second": 9.405, | |
| "eval_steps_per_second": 1.197, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8513, | |
| "eval_samples_per_second": 9.4, | |
| "eval_steps_per_second": 1.196, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8506, | |
| "eval_samples_per_second": 9.401, | |
| "eval_steps_per_second": 1.196, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8498, | |
| "eval_samples_per_second": 9.402, | |
| "eval_steps_per_second": 1.197, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0, | |
| "loss": 2.8083, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8488, | |
| "eval_samples_per_second": 9.404, | |
| "eval_steps_per_second": 1.197, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8482, | |
| "eval_samples_per_second": 9.405, | |
| "eval_steps_per_second": 1.197, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8537, | |
| "eval_samples_per_second": 9.396, | |
| "eval_steps_per_second": 1.196, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8517, | |
| "eval_samples_per_second": 9.399, | |
| "eval_steps_per_second": 1.196, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8492, | |
| "eval_samples_per_second": 9.403, | |
| "eval_steps_per_second": 1.197, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0, | |
| "loss": 2.7992, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8497, | |
| "eval_samples_per_second": 9.402, | |
| "eval_steps_per_second": 1.197, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8451, | |
| "eval_samples_per_second": 9.41, | |
| "eval_steps_per_second": 1.198, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8463, | |
| "eval_samples_per_second": 9.408, | |
| "eval_steps_per_second": 1.197, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8445, | |
| "eval_samples_per_second": 9.411, | |
| "eval_steps_per_second": 1.198, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8463, | |
| "eval_samples_per_second": 9.408, | |
| "eval_steps_per_second": 1.197, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.0, | |
| "loss": 2.7935, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8428, | |
| "eval_samples_per_second": 9.413, | |
| "eval_steps_per_second": 1.198, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.848, | |
| "eval_samples_per_second": 9.405, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8489, | |
| "eval_samples_per_second": 9.403, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8501, | |
| "eval_samples_per_second": 9.402, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8484, | |
| "eval_samples_per_second": 9.404, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0, | |
| "loss": 2.8129, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8457, | |
| "eval_samples_per_second": 9.409, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4195681151692882, | |
| "eval_loss": 2.8833088874816895, | |
| "eval_runtime": 5.8475, | |
| "eval_samples_per_second": 9.406, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1300, | |
| "total_flos": 2.36074746249216e+16, | |
| "train_loss": 2.8456746497521035, | |
| "train_runtime": 1533.618, | |
| "train_samples_per_second": 1.695, | |
| "train_steps_per_second": 0.848 | |
| } | |
| ], | |
| "max_steps": 1300, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.36074746249216e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |