| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04996252810392206, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009992505620784412, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.9419, | |
| "eval_samples_per_second": 32.607, | |
| "eval_steps_per_second": 16.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004996252810392206, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009992505620784412, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009992505620784412, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.4155, | |
| "eval_samples_per_second": 33.99, | |
| "eval_steps_per_second": 16.995, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014988758431176618, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019985011241568824, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019985011241568824, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.4785, | |
| "eval_samples_per_second": 33.818, | |
| "eval_steps_per_second": 16.909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02498126405196103, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029977516862353237, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.029977516862353237, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.346, | |
| "eval_samples_per_second": 34.181, | |
| "eval_steps_per_second": 17.091, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03497376967274544, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03997002248313765, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03997002248313765, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.4461, | |
| "eval_samples_per_second": 33.906, | |
| "eval_steps_per_second": 16.953, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04496627529352985, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04996252810392206, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04996252810392206, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.3635, | |
| "eval_samples_per_second": 34.133, | |
| "eval_steps_per_second": 17.066, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 445190819020800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |