| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008317737575379496, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016635475150758992, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.0746, | |
| "eval_samples_per_second": 22.383, | |
| "eval_steps_per_second": 11.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008317737575379496, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016635475150758993, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016635475150758993, | |
| "eval_loss": NaN, | |
| "eval_runtime": 112.0454, | |
| "eval_samples_per_second": 22.589, | |
| "eval_steps_per_second": 11.299, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002495321272613849, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033270950301517986, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033270950301517986, | |
| "eval_loss": NaN, | |
| "eval_runtime": 111.5224, | |
| "eval_samples_per_second": 22.695, | |
| "eval_steps_per_second": 11.352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004158868787689748, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004990642545227698, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004990642545227698, | |
| "eval_loss": NaN, | |
| "eval_runtime": 111.5487, | |
| "eval_samples_per_second": 22.69, | |
| "eval_steps_per_second": 11.349, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005822416302765648, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006654190060303597, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006654190060303597, | |
| "eval_loss": NaN, | |
| "eval_runtime": 112.4625, | |
| "eval_samples_per_second": 22.505, | |
| "eval_steps_per_second": 11.257, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007485963817841547, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008317737575379496, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008317737575379496, | |
| "eval_loss": NaN, | |
| "eval_runtime": 111.3878, | |
| "eval_samples_per_second": 22.722, | |
| "eval_steps_per_second": 11.366, | |
| "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": 3048403630030848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |