| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0313253012048194, | |
| "eval_steps": 6, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03855421686746988, | |
| "eval_loss": 9.853013038635254, | |
| "eval_runtime": 0.603, | |
| "eval_samples_per_second": 290.194, | |
| "eval_steps_per_second": 36.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.23132530120481928, | |
| "eval_loss": 9.504890441894531, | |
| "eval_runtime": 0.6735, | |
| "eval_samples_per_second": 259.837, | |
| "eval_steps_per_second": 32.665, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 6.76032018661499, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 9.4617, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.46265060240963857, | |
| "eval_loss": 9.04295539855957, | |
| "eval_runtime": 0.6655, | |
| "eval_samples_per_second": 262.973, | |
| "eval_steps_per_second": 33.059, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6939759036144578, | |
| "eval_loss": 8.781839370727539, | |
| "eval_runtime": 0.6306, | |
| "eval_samples_per_second": 277.503, | |
| "eval_steps_per_second": 34.886, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 7.701624393463135, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.7746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9253012048192771, | |
| "eval_loss": 8.70206356048584, | |
| "eval_runtime": 0.6614, | |
| "eval_samples_per_second": 264.61, | |
| "eval_steps_per_second": 33.265, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 26, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 7, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 27272354463744.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |