| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.034767492394611035, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006953498478922208, | |
| "grad_norm": 0.28749534487724304, | |
| "learning_rate": 1e-05, | |
| "loss": 1.111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006953498478922208, | |
| "eval_loss": 1.0971275568008423, | |
| "eval_runtime": 173.2564, | |
| "eval_samples_per_second": 1.403, | |
| "eval_steps_per_second": 0.704, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013906996957844416, | |
| "grad_norm": 0.2813794016838074, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0588, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013906996957844416, | |
| "eval_loss": 1.0899896621704102, | |
| "eval_runtime": 11.0114, | |
| "eval_samples_per_second": 22.068, | |
| "eval_steps_per_second": 11.079, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020860495436766623, | |
| "grad_norm": 0.2784063518047333, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1445, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027813993915688832, | |
| "grad_norm": 0.2781358063220978, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0695, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027813993915688832, | |
| "eval_loss": 1.0810749530792236, | |
| "eval_runtime": 11.0724, | |
| "eval_samples_per_second": 21.946, | |
| "eval_steps_per_second": 11.018, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034767492394611035, | |
| "grad_norm": 0.2658453583717346, | |
| "learning_rate": 5e-05, | |
| "loss": 1.063, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7352017886380032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |