| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.011470520761642579, |
| "eval_steps": 5, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0011470520761642578, |
| "eval_loss": 2.755366325378418, |
| "eval_runtime": 14.0088, |
| "eval_samples_per_second": 469.989, |
| "eval_steps_per_second": 3.712, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0022941041523285156, |
| "eval_loss": 2.750617027282715, |
| "eval_runtime": 14.0654, |
| "eval_samples_per_second": 468.099, |
| "eval_steps_per_second": 3.697, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0034411562284927736, |
| "eval_loss": 2.7424304485321045, |
| "eval_runtime": 14.1186, |
| "eval_samples_per_second": 466.336, |
| "eval_steps_per_second": 3.683, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.004588208304657031, |
| "eval_loss": 2.730889081954956, |
| "eval_runtime": 14.2451, |
| "eval_samples_per_second": 462.193, |
| "eval_steps_per_second": 3.65, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.005735260380821289, |
| "eval_loss": 2.7159576416015625, |
| "eval_runtime": 14.245, |
| "eval_samples_per_second": 462.199, |
| "eval_steps_per_second": 3.65, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.006882312456985547, |
| "eval_loss": 2.6975343227386475, |
| "eval_runtime": 14.3448, |
| "eval_samples_per_second": 458.981, |
| "eval_steps_per_second": 3.625, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.008029364533149804, |
| "eval_loss": 2.675693988800049, |
| "eval_runtime": 16.965, |
| "eval_samples_per_second": 388.094, |
| "eval_steps_per_second": 3.065, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.009176416609314062, |
| "eval_loss": 2.650242328643799, |
| "eval_runtime": 14.2414, |
| "eval_samples_per_second": 462.315, |
| "eval_steps_per_second": 3.651, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.01032346868547832, |
| "eval_loss": 2.6213560104370117, |
| "eval_runtime": 14.4168, |
| "eval_samples_per_second": 456.689, |
| "eval_steps_per_second": 3.607, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.011470520761642579, |
| "eval_loss": 2.5892951488494873, |
| "eval_runtime": 14.3332, |
| "eval_samples_per_second": 459.353, |
| "eval_steps_per_second": 3.628, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 13077, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 5, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
