| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007362414872078042, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007362414872078042, | |
| "grad_norm": 0.011801125481724739, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007362414872078042, | |
| "eval_loss": 11.930981636047363, | |
| "eval_runtime": 5.1896, | |
| "eval_samples_per_second": 55.11, | |
| "eval_steps_per_second": 55.11, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014724829744156083, | |
| "grad_norm": 0.019920406863093376, | |
| "learning_rate": 4e-05, | |
| "loss": 11.929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022087244616234127, | |
| "grad_norm": 0.027734071016311646, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9268, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022087244616234127, | |
| "eval_loss": 11.9309720993042, | |
| "eval_runtime": 5.1801, | |
| "eval_samples_per_second": 55.211, | |
| "eval_steps_per_second": 55.211, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029449659488312166, | |
| "grad_norm": 0.028326112776994705, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9315, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003681207436039021, | |
| "grad_norm": 0.02255975268781185, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9335, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004417448923246825, | |
| "grad_norm": 0.023017868399620056, | |
| "learning_rate": 0.00012, | |
| "loss": 11.936, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004417448923246825, | |
| "eval_loss": 11.930936813354492, | |
| "eval_runtime": 5.2221, | |
| "eval_samples_per_second": 54.767, | |
| "eval_steps_per_second": 54.767, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005153690410454629, | |
| "grad_norm": 0.03027837909758091, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9297, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005889931897662433, | |
| "grad_norm": 0.022188223898410797, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9334, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006626173384870237, | |
| "grad_norm": 0.01987503655254841, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9283, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006626173384870237, | |
| "eval_loss": 11.930867195129395, | |
| "eval_runtime": 5.2215, | |
| "eval_samples_per_second": 54.774, | |
| "eval_steps_per_second": 54.774, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007362414872078042, | |
| "grad_norm": 0.014438302256166935, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9368, | |
| "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": 7494696960.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |