| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004253056884635832, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "grad_norm": 2.6827280521392822, | |
| "learning_rate": 2e-05, | |
| "loss": 8.9009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 8.532660484313965, | |
| "eval_runtime": 27.5485, | |
| "eval_samples_per_second": 35.937, | |
| "eval_steps_per_second": 17.968, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": 2.467726707458496, | |
| "learning_rate": 4e-05, | |
| "loss": 8.2356, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 2.839933156967163, | |
| "learning_rate": 6e-05, | |
| "loss": 8.982, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "eval_loss": 8.52444839477539, | |
| "eval_runtime": 27.5088, | |
| "eval_samples_per_second": 35.988, | |
| "eval_steps_per_second": 17.994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": 2.6999123096466064, | |
| "learning_rate": 8e-05, | |
| "loss": 8.5405, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 2.2829253673553467, | |
| "learning_rate": 0.0001, | |
| "loss": 8.1173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 2.351006507873535, | |
| "learning_rate": 0.00012, | |
| "loss": 8.7051, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "eval_loss": 8.4379301071167, | |
| "eval_runtime": 27.4565, | |
| "eval_samples_per_second": 36.057, | |
| "eval_steps_per_second": 18.029, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029771398192450825, | |
| "grad_norm": 2.6640219688415527, | |
| "learning_rate": 0.00014, | |
| "loss": 8.891, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": 2.275404453277588, | |
| "learning_rate": 0.00016, | |
| "loss": 8.5015, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 1.836250901222229, | |
| "learning_rate": 0.00018, | |
| "loss": 8.0423, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "eval_loss": 8.309639930725098, | |
| "eval_runtime": 27.2243, | |
| "eval_samples_per_second": 36.365, | |
| "eval_steps_per_second": 18.182, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 1.9176832437515259, | |
| "learning_rate": 0.0002, | |
| "loss": 8.4335, | |
| "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": 5429904015360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |