| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00421896424427803, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 226.531, | |
| "eval_samples_per_second": 22.028, | |
| "eval_steps_per_second": 11.014, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "eval_loss": NaN, | |
| "eval_runtime": 225.781, | |
| "eval_samples_per_second": 22.101, | |
| "eval_steps_per_second": 11.051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012656892732834089, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "eval_loss": NaN, | |
| "eval_runtime": 225.7426, | |
| "eval_samples_per_second": 22.105, | |
| "eval_steps_per_second": 11.052, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002109482122139015, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "eval_loss": NaN, | |
| "eval_runtime": 225.6608, | |
| "eval_samples_per_second": 22.113, | |
| "eval_steps_per_second": 11.056, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029532749709946207, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "eval_loss": NaN, | |
| "eval_runtime": 225.9549, | |
| "eval_samples_per_second": 22.084, | |
| "eval_steps_per_second": 11.042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037970678198502267, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "eval_loss": NaN, | |
| "eval_runtime": 225.8319, | |
| "eval_samples_per_second": 22.096, | |
| "eval_steps_per_second": 11.048, | |
| "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": 3097048368807936.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |