| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028170005986126274, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005634001197225254, | |
| "grad_norm": 2.126387596130371, | |
| "learning_rate": 1e-05, | |
| "loss": 14.343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005634001197225254, | |
| "eval_loss": 0.8838437795639038, | |
| "eval_runtime": 520.5619, | |
| "eval_samples_per_second": 5.744, | |
| "eval_steps_per_second": 2.872, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011268002394450509, | |
| "grad_norm": 2.3964614868164062, | |
| "learning_rate": 2e-05, | |
| "loss": 15.4059, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011268002394450509, | |
| "eval_loss": 0.8824300169944763, | |
| "eval_runtime": 233.5333, | |
| "eval_samples_per_second": 12.803, | |
| "eval_steps_per_second": 6.402, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016902003591675763, | |
| "grad_norm": 3.199329137802124, | |
| "learning_rate": 3e-05, | |
| "loss": 14.5531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022536004788901018, | |
| "grad_norm": 2.3833396434783936, | |
| "learning_rate": 4e-05, | |
| "loss": 13.065, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022536004788901018, | |
| "eval_loss": 0.8808584809303284, | |
| "eval_runtime": 370.8435, | |
| "eval_samples_per_second": 8.063, | |
| "eval_steps_per_second": 4.031, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028170005986126274, | |
| "grad_norm": 2.100451946258545, | |
| "learning_rate": 5e-05, | |
| "loss": 13.6954, | |
| "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": 1.139833502171136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |