| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0024410710199099855, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006102677549774964, | |
| "grad_norm": 3.7491719722747803, | |
| "learning_rate": 2e-05, | |
| "loss": 3.7463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006102677549774964, | |
| "eval_loss": 3.6378390789031982, | |
| "eval_runtime": 127.7739, | |
| "eval_samples_per_second": 5.4, | |
| "eval_steps_per_second": 5.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012205355099549928, | |
| "grad_norm": 2.4883432388305664, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1519, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012205355099549928, | |
| "eval_loss": 3.636899948120117, | |
| "eval_runtime": 128.4391, | |
| "eval_samples_per_second": 5.372, | |
| "eval_steps_per_second": 5.372, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018308032649324891, | |
| "grad_norm": 2.6212241649627686, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024410710199099855, | |
| "grad_norm": 2.9304161071777344, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8665, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024410710199099855, | |
| "eval_loss": 3.6247403621673584, | |
| "eval_runtime": 128.9195, | |
| "eval_samples_per_second": 5.352, | |
| "eval_steps_per_second": 5.352, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 7, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 565649715757056.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |