| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5, | |
| "eval_steps": 500, | |
| "global_step": 280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 3.3681201934814453, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 1.2703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 1.8422191143035889, | |
| "learning_rate": 0.00019974902686642558, | |
| "loss": 0.2993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 1.02767014503479, | |
| "learning_rate": 0.00019821986184473755, | |
| "loss": 0.187, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 1.2515795230865479, | |
| "learning_rate": 0.00019532224059997692, | |
| "loss": 0.119, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44642857142857145, | |
| "grad_norm": 1.3811193704605103, | |
| "learning_rate": 0.00019109653447608606, | |
| "loss": 0.0941, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 0.8252667784690857, | |
| "learning_rate": 0.00018560161846773002, | |
| "loss": 0.0928, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.9444553256034851, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.0764, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.889909029006958, | |
| "learning_rate": 0.00017112700697095954, | |
| "loss": 0.0707, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8035714285714286, | |
| "grad_norm": 0.8613348007202148, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.068, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 0.9881114363670349, | |
| "learning_rate": 0.0001527022711573479, | |
| "loss": 0.071, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9821428571428571, | |
| "grad_norm": 0.8167979121208191, | |
| "learning_rate": 0.0001423212834444425, | |
| "loss": 0.0581, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.6212513446807861, | |
| "learning_rate": 0.00013135065100377814, | |
| "loss": 0.0697, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1607142857142858, | |
| "grad_norm": 0.9011110067367554, | |
| "learning_rate": 0.00011994322306515927, | |
| "loss": 0.0447, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.7870438098907471, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.0413, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3392857142857144, | |
| "grad_norm": 0.3967013359069824, | |
| "learning_rate": 9.645759168379463e-05, | |
| "loss": 0.0534, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.4754908084869385, | |
| "learning_rate": 8.47066037126754e-05, | |
| "loss": 0.0415, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5178571428571428, | |
| "grad_norm": 0.564179539680481, | |
| "learning_rate": 7.316869223065156e-05, | |
| "loss": 0.0364, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 0.38168346881866455, | |
| "learning_rate": 6.200461012896402e-05, | |
| "loss": 0.0363, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6964285714285714, | |
| "grad_norm": 0.2824791371822357, | |
| "learning_rate": 5.136990189057187e-05, | |
| "loss": 0.0392, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": 0.5657776594161987, | |
| "learning_rate": 4.141273645397754e-05, | |
| "loss": 0.0387, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.4336404800415039, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.0418, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9642857142857144, | |
| "grad_norm": 0.32696864008903503, | |
| "learning_rate": 2.407457728556115e-05, | |
| "loss": 0.0334, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0535714285714284, | |
| "grad_norm": 0.6701914072036743, | |
| "learning_rate": 1.693514886817772e-05, | |
| "loss": 0.0298, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.35550254583358765, | |
| "learning_rate": 1.0953028253055542e-05, | |
| "loss": 0.031, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.232142857142857, | |
| "grad_norm": 0.26464036107063293, | |
| "learning_rate": 6.211561822781476e-06, | |
| "loss": 0.0325, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.3214285714285716, | |
| "grad_norm": 0.349539190530777, | |
| "learning_rate": 2.7768104444869436e-06, | |
| "loss": 0.0235, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4107142857142856, | |
| "grad_norm": 0.255789190530777, | |
| "learning_rate": 6.966290714375933e-07, | |
| "loss": 0.0342, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.19940122961997986, | |
| "learning_rate": 0.0, | |
| "loss": 0.0338, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "step": 280, | |
| "total_flos": 5489054121567744.0, | |
| "train_loss": 0.10958067295806749, | |
| "train_runtime": 107.8356, | |
| "train_samples_per_second": 41.545, | |
| "train_steps_per_second": 2.597 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5489054121567744.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |