| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02147766323024055, | |
| "eval_steps": 4, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000859106529209622, | |
| "grad_norm": 21.70357894897461, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 14.1995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000859106529209622, | |
| "eval_loss": 14.032994270324707, | |
| "eval_runtime": 62.6895, | |
| "eval_samples_per_second": 7.832, | |
| "eval_steps_per_second": 1.962, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001718213058419244, | |
| "grad_norm": 24.51837158203125, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 14.6799, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002577319587628866, | |
| "grad_norm": 18.86236000061035, | |
| "learning_rate": 3e-06, | |
| "loss": 14.0646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003436426116838488, | |
| "grad_norm": 23.813383102416992, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 13.5427, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003436426116838488, | |
| "eval_loss": 14.0116548538208, | |
| "eval_runtime": 62.3009, | |
| "eval_samples_per_second": 7.881, | |
| "eval_steps_per_second": 1.974, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00429553264604811, | |
| "grad_norm": 22.6094970703125, | |
| "learning_rate": 5e-06, | |
| "loss": 14.0515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005154639175257732, | |
| "grad_norm": 20.13220977783203, | |
| "learning_rate": 6e-06, | |
| "loss": 13.9292, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006013745704467354, | |
| "grad_norm": 20.76972007751465, | |
| "learning_rate": 7e-06, | |
| "loss": 14.2169, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006872852233676976, | |
| "grad_norm": 23.663116455078125, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 13.9762, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006872852233676976, | |
| "eval_loss": 13.826712608337402, | |
| "eval_runtime": 62.3398, | |
| "eval_samples_per_second": 7.876, | |
| "eval_steps_per_second": 1.973, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007731958762886598, | |
| "grad_norm": 21.8310546875, | |
| "learning_rate": 9e-06, | |
| "loss": 13.3632, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00859106529209622, | |
| "grad_norm": 26.113445281982422, | |
| "learning_rate": 1e-05, | |
| "loss": 15.0053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009450171821305841, | |
| "grad_norm": 22.699298858642578, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 14.4724, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "grad_norm": 24.223079681396484, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 12.8614, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "eval_loss": 13.030826568603516, | |
| "eval_runtime": 62.4369, | |
| "eval_samples_per_second": 7.864, | |
| "eval_steps_per_second": 1.97, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011168384879725086, | |
| "grad_norm": 24.047016143798828, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 13.019, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012027491408934709, | |
| "grad_norm": 23.162111282348633, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 12.5343, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01288659793814433, | |
| "grad_norm": 24.763517379760742, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 12.81, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 23.840545654296875, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 11.9014, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "eval_loss": 11.92764949798584, | |
| "eval_runtime": 62.3818, | |
| "eval_samples_per_second": 7.871, | |
| "eval_steps_per_second": 1.972, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014604810996563574, | |
| "grad_norm": 22.010635375976562, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 11.4972, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015463917525773196, | |
| "grad_norm": 22.3720645904541, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 11.4523, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01632302405498282, | |
| "grad_norm": 22.157730102539062, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 10.9263, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01718213058419244, | |
| "grad_norm": 19.50232696533203, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 12.0291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01718213058419244, | |
| "eval_loss": 10.99551010131836, | |
| "eval_runtime": 62.2825, | |
| "eval_samples_per_second": 7.883, | |
| "eval_steps_per_second": 1.975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01804123711340206, | |
| "grad_norm": 21.43710708618164, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 10.8485, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018900343642611683, | |
| "grad_norm": 21.285892486572266, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 11.2804, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019759450171821305, | |
| "grad_norm": 23.800308227539062, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 10.5105, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "grad_norm": 20.990869522094727, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 11.1535, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "eval_loss": 10.772194862365723, | |
| "eval_runtime": 62.328, | |
| "eval_samples_per_second": 7.878, | |
| "eval_steps_per_second": 1.973, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02147766323024055, | |
| "grad_norm": 21.3924560546875, | |
| "learning_rate": 0.0, | |
| "loss": 10.2359, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9273591044505600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |