| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005608524957936063, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005608524957936063, | |
| "grad_norm": 0.012027375400066376, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9315, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005608524957936063, | |
| "eval_loss": 11.931306838989258, | |
| "eval_runtime": 2.6701, | |
| "eval_samples_per_second": 281.261, | |
| "eval_steps_per_second": 140.818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011217049915872126, | |
| "grad_norm": 0.008168625645339489, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016825574873808188, | |
| "grad_norm": 0.014232893474400043, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016825574873808188, | |
| "eval_loss": 11.931304931640625, | |
| "eval_runtime": 2.7097, | |
| "eval_samples_per_second": 277.154, | |
| "eval_steps_per_second": 138.761, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002243409983174425, | |
| "grad_norm": 0.016437681391835213, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9328, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028042624789680315, | |
| "grad_norm": 0.01582423411309719, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9248, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033651149747616375, | |
| "grad_norm": 0.00874681118875742, | |
| "learning_rate": 0.00012, | |
| "loss": 11.926, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033651149747616375, | |
| "eval_loss": 11.931292533874512, | |
| "eval_runtime": 2.7957, | |
| "eval_samples_per_second": 268.623, | |
| "eval_steps_per_second": 134.491, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003925967470555244, | |
| "grad_norm": 0.010923205874860287, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00448681996634885, | |
| "grad_norm": 0.006914525292813778, | |
| "learning_rate": 0.00016, | |
| "loss": 11.935, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005047672462142457, | |
| "grad_norm": 0.012705798260867596, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005047672462142457, | |
| "eval_loss": 11.931265830993652, | |
| "eval_runtime": 2.7101, | |
| "eval_samples_per_second": 277.111, | |
| "eval_steps_per_second": 138.74, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005608524957936063, | |
| "grad_norm": 0.008798080496490002, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9334, | |
| "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": 1211154432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |