| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05739292632183084, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002295717052873233, | |
| "grad_norm": 0.012660520151257515, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002295717052873233, | |
| "eval_loss": 11.929409980773926, | |
| "eval_runtime": 0.1854, | |
| "eval_samples_per_second": 269.624, | |
| "eval_steps_per_second": 70.102, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004591434105746466, | |
| "grad_norm": 0.010631855577230453, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9317, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0068871511586197, | |
| "grad_norm": 0.012013992294669151, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009182868211492933, | |
| "grad_norm": 0.011967318132519722, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011478585264366167, | |
| "grad_norm": 0.011771964840590954, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0137743023172394, | |
| "grad_norm": 0.011810662224888802, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9318, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016070019370112633, | |
| "grad_norm": 0.012616390362381935, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018365736422985866, | |
| "grad_norm": 0.013262227177619934, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9311, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020661453475859102, | |
| "grad_norm": 0.013076732866466045, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022957170528732335, | |
| "grad_norm": 0.013569272123277187, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025252887581605567, | |
| "grad_norm": 0.013419965282082558, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9313, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0275486046344788, | |
| "grad_norm": 0.01281964872032404, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.932, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029844321687352033, | |
| "grad_norm": 0.016497211530804634, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9315, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032140038740225266, | |
| "grad_norm": 0.02070445939898491, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9319, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0344357557930985, | |
| "grad_norm": 0.021560179069638252, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03673147284597173, | |
| "grad_norm": 0.022953500971198082, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9309, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03902718989884497, | |
| "grad_norm": 0.02006385661661625, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9313, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.041322906951718204, | |
| "grad_norm": 0.022738860920071602, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9308, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04361862400459143, | |
| "grad_norm": 0.02438095398247242, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04591434105746467, | |
| "grad_norm": 0.01977449096739292, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0482100581103379, | |
| "grad_norm": 0.022069524973630905, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9311, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.050505775163211135, | |
| "grad_norm": 0.016071053221821785, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9316, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.052801492216084364, | |
| "grad_norm": 0.01722380891442299, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0550972092689576, | |
| "grad_norm": 0.01678800769150257, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9308, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05739292632183084, | |
| "grad_norm": 0.014287649653851986, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05739292632183084, | |
| "eval_loss": 11.928374290466309, | |
| "eval_runtime": 0.177, | |
| "eval_samples_per_second": 282.412, | |
| "eval_steps_per_second": 73.427, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 522224467968.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |