| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.449438202247191, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008988764044943821, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.3684, | |
| "eval_samples_per_second": 7.031, | |
| "eval_steps_per_second": 1.795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02696629213483146, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.0277, | |
| "eval_samples_per_second": 7.215, | |
| "eval_steps_per_second": 1.842, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05393258426966292, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08089887640449438, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.104, | |
| "eval_samples_per_second": 7.173, | |
| "eval_steps_per_second": 1.832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10786516853932585, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1499, | |
| "eval_samples_per_second": 7.148, | |
| "eval_steps_per_second": 1.825, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16179775280898875, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1494, | |
| "eval_samples_per_second": 7.149, | |
| "eval_steps_per_second": 1.825, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18876404494382024, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2157303370786517, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1364, | |
| "eval_samples_per_second": 7.156, | |
| "eval_steps_per_second": 1.827, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24269662921348314, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1502, | |
| "eval_samples_per_second": 7.148, | |
| "eval_steps_per_second": 1.825, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2966292134831461, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3146067415730337, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1562, | |
| "eval_samples_per_second": 7.145, | |
| "eval_steps_per_second": 1.824, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3235955056179775, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.350561797752809, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1422, | |
| "eval_samples_per_second": 7.153, | |
| "eval_steps_per_second": 1.826, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3775280898876405, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4044943820224719, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4044943820224719, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1637, | |
| "eval_samples_per_second": 7.141, | |
| "eval_steps_per_second": 1.823, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4314606741573034, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.1401, | |
| "eval_samples_per_second": 7.154, | |
| "eval_steps_per_second": 1.826, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.327422442012672e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |