| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029271862422246614, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029271862422246617, | |
| "grad_norm": 3.7403578758239746, | |
| "learning_rate": 2e-05, | |
| "loss": 8.7807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029271862422246617, | |
| "eval_loss": 9.16074275970459, | |
| "eval_runtime": 72.5817, | |
| "eval_samples_per_second": 79.276, | |
| "eval_steps_per_second": 9.92, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005854372484449323, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 9.4806, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008781558726673985, | |
| "grad_norm": 4.048379898071289, | |
| "learning_rate": 4e-05, | |
| "loss": 9.4762, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008781558726673985, | |
| "eval_loss": 9.127564430236816, | |
| "eval_runtime": 71.9136, | |
| "eval_samples_per_second": 80.013, | |
| "eval_steps_per_second": 10.012, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011708744968898647, | |
| "grad_norm": 3.715500593185425, | |
| "learning_rate": 6e-05, | |
| "loss": 9.3834, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014635931211123307, | |
| "grad_norm": 4.088770866394043, | |
| "learning_rate": 8e-05, | |
| "loss": 9.2807, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001756311745334797, | |
| "grad_norm": 3.8607888221740723, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6573, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001756311745334797, | |
| "eval_loss": 8.29586124420166, | |
| "eval_runtime": 71.9482, | |
| "eval_samples_per_second": 79.974, | |
| "eval_steps_per_second": 10.007, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002049030369557263, | |
| "grad_norm": 3.9022231101989746, | |
| "learning_rate": 0.00012, | |
| "loss": 8.7262, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023417489937797293, | |
| "grad_norm": 3.7130041122436523, | |
| "learning_rate": 0.00014, | |
| "loss": 7.817, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026344676180021956, | |
| "grad_norm": 3.589695930480957, | |
| "learning_rate": 0.00016, | |
| "loss": 7.2472, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026344676180021956, | |
| "eval_loss": 6.745285987854004, | |
| "eval_runtime": 71.9266, | |
| "eval_samples_per_second": 79.998, | |
| "eval_steps_per_second": 10.01, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029271862422246614, | |
| "grad_norm": 3.3299129009246826, | |
| "learning_rate": 0.00018, | |
| "loss": 6.7157, | |
| "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": 1.045015069458432e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |