| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013888888888888888, | |
| "grad_norm": 2.69645357131958, | |
| "learning_rate": 2.5e-05, | |
| "loss": 6.4485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "grad_norm": 3.235274076461792, | |
| "learning_rate": 0.000125, | |
| "loss": 6.3994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 3.4826488494873047, | |
| "learning_rate": 0.0001995184726672197, | |
| "loss": 5.6587, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 4.541069984436035, | |
| "learning_rate": 0.00019415440651830208, | |
| "loss": 4.6657, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 4.04740047454834, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.7298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3472222222222222, | |
| "grad_norm": 1.9904128313064575, | |
| "learning_rate": 0.00016715589548470185, | |
| "loss": 3.0269, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 1.2599273920059204, | |
| "learning_rate": 0.0001471396736825998, | |
| "loss": 2.541, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4861111111111111, | |
| "grad_norm": 0.848343014717102, | |
| "learning_rate": 0.0001242980179903264, | |
| "loss": 2.2349, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.7984316349029541, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0682, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.6735253930091858, | |
| "learning_rate": 7.570198200967362e-05, | |
| "loss": 1.9724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6944444444444444, | |
| "grad_norm": 0.6062337160110474, | |
| "learning_rate": 5.286032631740023e-05, | |
| "loss": 1.9033, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7638888888888888, | |
| "grad_norm": 0.5750789046287537, | |
| "learning_rate": 3.2844104515298155e-05, | |
| "loss": 1.8667, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.6575501561164856, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.8513, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9027777777777778, | |
| "grad_norm": 0.5935372710227966, | |
| "learning_rate": 5.8455934816979305e-06, | |
| "loss": 1.8311, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9722222222222222, | |
| "grad_norm": 0.527962327003479, | |
| "learning_rate": 4.815273327803182e-07, | |
| "loss": 1.8348, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.020827293395996, | |
| "eval_runtime": 1.1461, | |
| "eval_samples_per_second": 3.49, | |
| "eval_steps_per_second": 0.873, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 72, | |
| "total_flos": 7.280931693081395e+17, | |
| "train_loss": 2.938576486375597, | |
| "train_runtime": 504.3487, | |
| "train_samples_per_second": 36.431, | |
| "train_steps_per_second": 0.143 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 72, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.280931693081395e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |