| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010351966873706004, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020703933747412008, | |
| "eval_loss": NaN, | |
| "eval_runtime": 228.1769, | |
| "eval_samples_per_second": 8.914, | |
| "eval_steps_per_second": 4.457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010351966873706005, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002070393374741201, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002070393374741201, | |
| "eval_loss": NaN, | |
| "eval_runtime": 228.3457, | |
| "eval_samples_per_second": 8.908, | |
| "eval_steps_per_second": 4.454, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003105590062111801, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004140786749482402, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004140786749482402, | |
| "eval_loss": NaN, | |
| "eval_runtime": 228.1612, | |
| "eval_samples_per_second": 8.915, | |
| "eval_steps_per_second": 4.457, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005175983436853002, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006211180124223602, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006211180124223602, | |
| "eval_loss": NaN, | |
| "eval_runtime": 227.5424, | |
| "eval_samples_per_second": 8.939, | |
| "eval_steps_per_second": 4.469, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007246376811594203, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "eval_loss": NaN, | |
| "eval_runtime": 227.7004, | |
| "eval_samples_per_second": 8.933, | |
| "eval_steps_per_second": 4.466, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009316770186335404, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010351966873706004, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010351966873706004, | |
| "eval_loss": NaN, | |
| "eval_runtime": 227.5698, | |
| "eval_samples_per_second": 8.938, | |
| "eval_steps_per_second": 4.469, | |
| "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": 1.61937503551488e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |