| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02031488065007618, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002031488065007618, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002031488065007618, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1321, | |
| "eval_samples_per_second": 50.337, | |
| "eval_steps_per_second": 25.169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004062976130015236, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006094464195022855, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006094464195022855, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7438, | |
| "eval_samples_per_second": 55.558, | |
| "eval_steps_per_second": 27.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008125952260030472, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01015744032503809, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01218892839004571, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01218892839004571, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.6895, | |
| "eval_samples_per_second": 56.376, | |
| "eval_steps_per_second": 28.188, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014220416455053326, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016251904520060943, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018283392585068562, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018283392585068562, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7039, | |
| "eval_samples_per_second": 56.157, | |
| "eval_steps_per_second": 28.079, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02031488065007618, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 255791978250240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |