| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00024782379728013383, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.478237972801338e-05, | |
| "grad_norm": 0.6054084300994873, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.478237972801338e-05, | |
| "eval_loss": 0.9835758209228516, | |
| "eval_runtime": 629.7981, | |
| "eval_samples_per_second": 26.977, | |
| "eval_steps_per_second": 13.488, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.956475945602676e-05, | |
| "grad_norm": 1.0214717388153076, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.434713918404015e-05, | |
| "grad_norm": 1.0177044868469238, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9346, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.434713918404015e-05, | |
| "eval_loss": 0.9747242331504822, | |
| "eval_runtime": 626.0009, | |
| "eval_samples_per_second": 27.141, | |
| "eval_steps_per_second": 13.57, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.912951891205352e-05, | |
| "grad_norm": 0.9408998489379883, | |
| "learning_rate": 8e-05, | |
| "loss": 1.065, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00012391189864006691, | |
| "grad_norm": 0.7956117987632751, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8118, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001486942783680803, | |
| "grad_norm": 1.0171177387237549, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001486942783680803, | |
| "eval_loss": 0.8637855052947998, | |
| "eval_runtime": 625.9504, | |
| "eval_samples_per_second": 27.143, | |
| "eval_steps_per_second": 13.571, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017347665809609367, | |
| "grad_norm": 0.6194573044776917, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0728, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00019825903782410705, | |
| "grad_norm": 0.6491646766662598, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9076, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00022304141755212045, | |
| "grad_norm": 0.6161671876907349, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7104, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022304141755212045, | |
| "eval_loss": 0.7862219214439392, | |
| "eval_runtime": 625.4316, | |
| "eval_samples_per_second": 27.165, | |
| "eval_steps_per_second": 13.583, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00024782379728013383, | |
| "grad_norm": 0.5031097531318665, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6461, | |
| "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": 2265716203978752.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |