| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015217391304347827, | |
| "eval_steps": 1, | |
| "global_step": 7, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002173913043478261, | |
| "grad_norm": 3.4586541652679443, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 3.1186, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002173913043478261, | |
| "eval_loss": 2.910125255584717, | |
| "eval_runtime": 9.3365, | |
| "eval_samples_per_second": 51.411, | |
| "eval_steps_per_second": 1.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004347826086956522, | |
| "grad_norm": 3.0273189544677734, | |
| "learning_rate": 4.9e-05, | |
| "loss": 2.9823, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004347826086956522, | |
| "eval_loss": 2.720604658126831, | |
| "eval_runtime": 9.3759, | |
| "eval_samples_per_second": 51.195, | |
| "eval_steps_per_second": 1.6, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006521739130434782, | |
| "grad_norm": 2.8461098670959473, | |
| "learning_rate": 4.85e-05, | |
| "loss": 2.743, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006521739130434782, | |
| "eval_loss": 2.527026414871216, | |
| "eval_runtime": 9.4179, | |
| "eval_samples_per_second": 50.967, | |
| "eval_steps_per_second": 1.593, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008695652173913044, | |
| "grad_norm": 2.745748281478882, | |
| "learning_rate": 4.8e-05, | |
| "loss": 2.6276, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008695652173913044, | |
| "eval_loss": 2.3465826511383057, | |
| "eval_runtime": 9.4584, | |
| "eval_samples_per_second": 50.749, | |
| "eval_steps_per_second": 1.586, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010869565217391304, | |
| "grad_norm": 2.7337284088134766, | |
| "learning_rate": 4.75e-05, | |
| "loss": 2.4355, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010869565217391304, | |
| "eval_loss": 2.1909377574920654, | |
| "eval_runtime": 9.4662, | |
| "eval_samples_per_second": 50.707, | |
| "eval_steps_per_second": 1.585, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013043478260869565, | |
| "grad_norm": 2.2131495475769043, | |
| "learning_rate": 4.7e-05, | |
| "loss": 2.2119, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013043478260869565, | |
| "eval_loss": 2.05778169631958, | |
| "eval_runtime": 9.4891, | |
| "eval_samples_per_second": 50.584, | |
| "eval_steps_per_second": 1.581, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015217391304347827, | |
| "grad_norm": 2.225778341293335, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 2.0567, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015217391304347827, | |
| "eval_loss": 1.9339481592178345, | |
| "eval_runtime": 9.4903, | |
| "eval_samples_per_second": 50.578, | |
| "eval_steps_per_second": 1.581, | |
| "step": 7 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1260402868224000.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |