| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14378145219266714, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002875629043853343, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3955, | |
| "eval_samples_per_second": 9.548, | |
| "eval_steps_per_second": 4.807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014378145219266714, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3273, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02875629043853343, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2254, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02875629043853343, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.8199, | |
| "eval_samples_per_second": 10.637, | |
| "eval_steps_per_second": 5.355, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043134435657800146, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.393, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05751258087706686, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05751258087706686, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.8031, | |
| "eval_samples_per_second": 10.65, | |
| "eval_steps_per_second": 5.361, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07189072609633357, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1538, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08626887131560029, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08626887131560029, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.8087, | |
| "eval_samples_per_second": 10.645, | |
| "eval_steps_per_second": 5.359, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.100647016534867, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9161, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11502516175413371, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11502516175413371, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.8751, | |
| "eval_samples_per_second": 10.595, | |
| "eval_steps_per_second": 5.333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12940330697340044, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6246, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14378145219266714, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14378145219266714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.8369, | |
| "eval_samples_per_second": 10.624, | |
| "eval_steps_per_second": 5.348, | |
| "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": 1.437674738024448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |