| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04756242568370987, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009512485136741973, | |
| "grad_norm": 2.358306884765625, | |
| "learning_rate": 1e-05, | |
| "loss": 27.4781, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009512485136741973, | |
| "eval_loss": 1.6872767210006714, | |
| "eval_runtime": 68.9331, | |
| "eval_samples_per_second": 2.582, | |
| "eval_steps_per_second": 1.291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019024970273483946, | |
| "grad_norm": 2.2945337295532227, | |
| "learning_rate": 2e-05, | |
| "loss": 26.7268, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019024970273483946, | |
| "eval_loss": 1.6841931343078613, | |
| "eval_runtime": 25.2645, | |
| "eval_samples_per_second": 7.045, | |
| "eval_steps_per_second": 3.523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028537455410225922, | |
| "grad_norm": 2.3263285160064697, | |
| "learning_rate": 3e-05, | |
| "loss": 24.5399, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03804994054696789, | |
| "grad_norm": 3.3617522716522217, | |
| "learning_rate": 4e-05, | |
| "loss": 28.598, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03804994054696789, | |
| "eval_loss": 1.6818211078643799, | |
| "eval_runtime": 12.9828, | |
| "eval_samples_per_second": 13.71, | |
| "eval_steps_per_second": 6.855, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04756242568370987, | |
| "grad_norm": 2.8572473526000977, | |
| "learning_rate": 5e-05, | |
| "loss": 28.2054, | |
| "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": 1.060678397853696e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |