| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017191361340926185, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003438272268185237, | |
| "grad_norm": 7.615189552307129, | |
| "learning_rate": 1e-05, | |
| "loss": 59.4782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003438272268185237, | |
| "eval_loss": 3.719777822494507, | |
| "eval_runtime": 797.3252, | |
| "eval_samples_per_second": 6.144, | |
| "eval_steps_per_second": 3.073, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006876544536370474, | |
| "grad_norm": 7.117115020751953, | |
| "learning_rate": 2e-05, | |
| "loss": 59.4513, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006876544536370474, | |
| "eval_loss": 3.6812143325805664, | |
| "eval_runtime": 784.2806, | |
| "eval_samples_per_second": 6.246, | |
| "eval_steps_per_second": 3.124, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010314816804555711, | |
| "grad_norm": 7.610560417175293, | |
| "learning_rate": 3e-05, | |
| "loss": 60.8528, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013753089072740948, | |
| "grad_norm": 7.584437847137451, | |
| "learning_rate": 4e-05, | |
| "loss": 59.9693, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013753089072740948, | |
| "eval_loss": 3.6589016914367676, | |
| "eval_runtime": 899.3134, | |
| "eval_samples_per_second": 5.447, | |
| "eval_steps_per_second": 2.724, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017191361340926185, | |
| "grad_norm": 8.735809326171875, | |
| "learning_rate": 5e-05, | |
| "loss": 58.6865, | |
| "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": 6807382256517120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |