| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4, |
| "eval_steps": 100, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 6.820826530456543, |
| "learning_rate": 3.266666666666667e-05, |
| "loss": 39.8282, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 2.321176290512085, |
| "learning_rate": 6.6e-05, |
| "loss": 32.0977, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_accuracy": 0.11411070917707537, |
| "eval_loss": 7.302488327026367, |
| "eval_runtime": 12.8861, |
| "eval_samples_per_second": 75.275, |
| "eval_steps_per_second": 4.734, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 2.403538465499878, |
| "learning_rate": 9.933333333333334e-05, |
| "loss": 27.9639, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 2.440488338470459, |
| "learning_rate": 9.91822760447871e-05, |
| "loss": 26.0238, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_accuracy": 0.16184917453329808, |
| "eval_loss": 6.333618640899658, |
| "eval_runtime": 13.3491, |
| "eval_samples_per_second": 72.664, |
| "eval_steps_per_second": 4.57, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 1.5482277870178223, |
| "learning_rate": 9.669005017492143e-05, |
| "loss": 25.0247, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 3.2663464546203613, |
| "learning_rate": 9.26078506448917e-05, |
| "loss": 24.2338, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_accuracy": 0.1829634890115987, |
| "eval_loss": 5.955964088439941, |
| "eval_runtime": 12.3645, |
| "eval_samples_per_second": 78.45, |
| "eval_steps_per_second": 4.933, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 2.2301456928253174, |
| "learning_rate": 8.707469186363446e-05, |
| "loss": 23.716, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 2.1302545070648193, |
| "learning_rate": 8.027899891715287e-05, |
| "loss": 23.2729, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_accuracy": 0.1966725107382293, |
| "eval_loss": 5.7180047035217285, |
| "eval_runtime": 13.1479, |
| "eval_samples_per_second": 73.776, |
| "eval_steps_per_second": 4.64, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.69006654603264e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
