| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01469341621927098, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011302627860977678, | |
| "eval_loss": 0.7253943681716919, | |
| "eval_runtime": 222.5674, | |
| "eval_samples_per_second": 6.695, | |
| "eval_steps_per_second": 0.84, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003390788358293303, | |
| "grad_norm": 6.4600725173950195, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.9057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006781576716586606, | |
| "grad_norm": 4.287564277648926, | |
| "learning_rate": 3e-05, | |
| "loss": 2.7228, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010172365074879909, | |
| "grad_norm": 4.434852600097656, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.2412, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013563153433173212, | |
| "grad_norm": 4.096804618835449, | |
| "learning_rate": 4.997482666353287e-05, | |
| "loss": 1.6976, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01469341621927098, | |
| "eval_loss": 0.281572163105011, | |
| "eval_runtime": 224.6256, | |
| "eval_samples_per_second": 6.633, | |
| "eval_steps_per_second": 0.832, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.656277580736102e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |