| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007939343416299472, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015878686832598943, | |
| "eval_loss": 10.346136093139648, | |
| "eval_runtime": 276.6118, | |
| "eval_samples_per_second": 9.587, | |
| "eval_steps_per_second": 4.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007939343416299473, | |
| "grad_norm": 15.020698547363281, | |
| "learning_rate": 5e-05, | |
| "loss": 41.5589, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015878686832598945, | |
| "grad_norm": 38.55679702758789, | |
| "learning_rate": 0.0001, | |
| "loss": 38.9945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015878686832598945, | |
| "eval_loss": 7.561215400695801, | |
| "eval_runtime": 278.7081, | |
| "eval_samples_per_second": 9.515, | |
| "eval_steps_per_second": 4.758, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023818030248898415, | |
| "grad_norm": 27.606922149658203, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 20.8594, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003175737366519789, | |
| "grad_norm": 48.108097076416016, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9646, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003175737366519789, | |
| "eval_loss": 0.9509708285331726, | |
| "eval_runtime": 280.2538, | |
| "eval_samples_per_second": 9.463, | |
| "eval_steps_per_second": 4.731, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003969671708149736, | |
| "grad_norm": 50.09941101074219, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4165, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004763606049779683, | |
| "grad_norm": 46.6011848449707, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5225, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004763606049779683, | |
| "eval_loss": 0.33293241262435913, | |
| "eval_runtime": 278.8215, | |
| "eval_samples_per_second": 9.511, | |
| "eval_steps_per_second": 4.756, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00555754039140963, | |
| "grad_norm": 19.61571502685547, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1785, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006351474733039578, | |
| "grad_norm": 13.59659194946289, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8479, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006351474733039578, | |
| "eval_loss": 0.24485889077186584, | |
| "eval_runtime": 279.8997, | |
| "eval_samples_per_second": 9.475, | |
| "eval_steps_per_second": 4.737, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007145409074669525, | |
| "grad_norm": 22.785335540771484, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9058, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007939343416299472, | |
| "grad_norm": 15.81817626953125, | |
| "learning_rate": 0.0, | |
| "loss": 0.949, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007939343416299472, | |
| "eval_loss": 0.22007624804973602, | |
| "eval_runtime": 279.8767, | |
| "eval_samples_per_second": 9.476, | |
| "eval_steps_per_second": 4.738, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.571260104572928e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |