| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003987322359676924, | |
| "eval_steps": 5, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010223903486351089, | |
| "eval_loss": NaN, | |
| "eval_runtime": 507.1973, | |
| "eval_samples_per_second": 8.121, | |
| "eval_steps_per_second": 4.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030671710459053266, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005111951743175544, | |
| "eval_loss": NaN, | |
| "eval_runtime": 508.2702, | |
| "eval_samples_per_second": 8.104, | |
| "eval_steps_per_second": 4.053, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006134342091810653, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000920151313771598, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010223903486351088, | |
| "eval_loss": NaN, | |
| "eval_runtime": 508.3721, | |
| "eval_samples_per_second": 8.102, | |
| "eval_steps_per_second": 4.052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012268684183621306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015335855229526632, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015335855229526632, | |
| "eval_loss": NaN, | |
| "eval_runtime": 508.283, | |
| "eval_samples_per_second": 8.104, | |
| "eval_steps_per_second": 4.053, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001840302627543196, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0020447806972702176, | |
| "eval_loss": NaN, | |
| "eval_runtime": 507.9795, | |
| "eval_samples_per_second": 8.109, | |
| "eval_steps_per_second": 4.055, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0021470197321337287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0024537368367242613, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0025559758715877723, | |
| "eval_loss": NaN, | |
| "eval_runtime": 507.9292, | |
| "eval_samples_per_second": 8.109, | |
| "eval_steps_per_second": 4.056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002760453941314794, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0030671710459053265, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0030671710459053265, | |
| "eval_loss": NaN, | |
| "eval_runtime": 507.8584, | |
| "eval_samples_per_second": 8.111, | |
| "eval_steps_per_second": 4.056, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0033738881504958595, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003578366220222881, | |
| "eval_loss": NaN, | |
| "eval_runtime": 507.9758, | |
| "eval_samples_per_second": 8.109, | |
| "eval_steps_per_second": 4.055, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003680605255086392, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003987322359676924, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 21, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.481165604749312e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |