| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01238390092879257, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001238390092879257, | |
| "grad_norm": 0.046144999563694, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001238390092879257, | |
| "eval_loss": 11.929296493530273, | |
| "eval_runtime": 1.8247, | |
| "eval_samples_per_second": 186.331, | |
| "eval_steps_per_second": 93.166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002476780185758514, | |
| "grad_norm": 0.015044029802083969, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037151702786377707, | |
| "grad_norm": 0.03627518191933632, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9321, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037151702786377707, | |
| "eval_loss": 11.929285049438477, | |
| "eval_runtime": 1.8543, | |
| "eval_samples_per_second": 183.357, | |
| "eval_steps_per_second": 91.679, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004953560371517028, | |
| "grad_norm": 0.028869060799479485, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9283, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006191950464396285, | |
| "grad_norm": 0.036302898079156876, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007430340557275541, | |
| "grad_norm": 0.03408890962600708, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9371, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007430340557275541, | |
| "eval_loss": 11.929229736328125, | |
| "eval_runtime": 1.9773, | |
| "eval_samples_per_second": 171.947, | |
| "eval_steps_per_second": 85.974, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0086687306501548, | |
| "grad_norm": 0.03345184028148651, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9317, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009907120743034056, | |
| "grad_norm": 0.023903626948595047, | |
| "learning_rate": 0.00016, | |
| "loss": 11.935, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011145510835913313, | |
| "grad_norm": 0.01851605996489525, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9277, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011145510835913313, | |
| "eval_loss": 11.929133415222168, | |
| "eval_runtime": 1.8641, | |
| "eval_samples_per_second": 182.393, | |
| "eval_steps_per_second": 91.196, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 0.023385345935821533, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9291, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2304147456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |