| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017030335284725917, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004257583821181479, | |
| "grad_norm": 0.7288269400596619, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004257583821181479, | |
| "eval_loss": 0.2810235023498535, | |
| "eval_runtime": 65.8894, | |
| "eval_samples_per_second": 6.01, | |
| "eval_steps_per_second": 3.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008515167642362959, | |
| "grad_norm": 0.7341122031211853, | |
| "learning_rate": 2e-05, | |
| "loss": 4.2695, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008515167642362959, | |
| "eval_loss": 0.2778320908546448, | |
| "eval_runtime": 16.6233, | |
| "eval_samples_per_second": 23.822, | |
| "eval_steps_per_second": 11.911, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012772751463544438, | |
| "grad_norm": 0.7728283405303955, | |
| "learning_rate": 3e-05, | |
| "loss": 3.6937, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017030335284725917, | |
| "grad_norm": 0.7061855792999268, | |
| "learning_rate": 4e-05, | |
| "loss": 4.877, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017030335284725917, | |
| "eval_loss": 0.2760697901248932, | |
| "eval_runtime": 16.5179, | |
| "eval_samples_per_second": 23.974, | |
| "eval_steps_per_second": 11.987, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5211997574529024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |