| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.350109409190372, |
| "eval_steps": 50, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00175054704595186, |
| "eval_loss": 3.942631959915161, |
| "eval_runtime": 6.5116, |
| "eval_samples_per_second": 37.011, |
| "eval_steps_per_second": 18.582, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0175054704595186, |
| "grad_norm": 4.979578971862793, |
| "learning_rate": 0.00019967573081342103, |
| "loss": 2.0182, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0350109409190372, |
| "grad_norm": 1.4861304759979248, |
| "learning_rate": 0.0001970941817426052, |
| "loss": 0.3124, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0525164113785558, |
| "grad_norm": 3.228330612182617, |
| "learning_rate": 0.00019199794436588243, |
| "loss": 0.2282, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0700218818380744, |
| "grad_norm": 1.115767478942871, |
| "learning_rate": 0.0001845190085543795, |
| "loss": 0.1118, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.087527352297593, |
| "grad_norm": 2.745464563369751, |
| "learning_rate": 0.00017485107481711012, |
| "loss": 0.1915, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.087527352297593, |
| "eval_loss": 0.15154829621315002, |
| "eval_runtime": 6.5631, |
| "eval_samples_per_second": 36.721, |
| "eval_steps_per_second": 18.437, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1050328227571116, |
| "grad_norm": 1.6342604160308838, |
| "learning_rate": 0.00016324453755953773, |
| "loss": 0.0955, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.12253829321663019, |
| "grad_norm": 1.03786039352417, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 0.1122, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.1400437636761488, |
| "grad_norm": 0.6428198218345642, |
| "learning_rate": 0.00013546048870425356, |
| "loss": 0.0688, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.1575492341356674, |
| "grad_norm": 0.3404603898525238, |
| "learning_rate": 0.00012000256937760445, |
| "loss": 0.1697, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.175054704595186, |
| "grad_norm": 1.3271960020065308, |
| "learning_rate": 0.00010402659401094152, |
| "loss": 0.1069, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.175054704595186, |
| "eval_loss": 0.1051642894744873, |
| "eval_runtime": 6.6187, |
| "eval_samples_per_second": 36.412, |
| "eval_steps_per_second": 18.282, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1925601750547046, |
| "grad_norm": 0.5494540929794312, |
| "learning_rate": 8.79463319744677e-05, |
| "loss": 0.139, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2100656455142232, |
| "grad_norm": 1.3071264028549194, |
| "learning_rate": 7.217825360835473e-05, |
| "loss": 0.1121, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2275711159737418, |
| "grad_norm": 0.791406512260437, |
| "learning_rate": 5.713074385969457e-05, |
| "loss": 0.0977, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.24507658643326038, |
| "grad_norm": 0.7328794002532959, |
| "learning_rate": 4.3193525326884435e-05, |
| "loss": 0.0691, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.26258205689277897, |
| "grad_norm": 2.1033480167388916, |
| "learning_rate": 3.072756464904006e-05, |
| "loss": 0.0896, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.26258205689277897, |
| "eval_loss": 0.08178930729627609, |
| "eval_runtime": 6.5966, |
| "eval_samples_per_second": 36.534, |
| "eval_steps_per_second": 18.343, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2800875273522976, |
| "grad_norm": 0.6359676122665405, |
| "learning_rate": 2.0055723659649904e-05, |
| "loss": 0.0679, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.2975929978118162, |
| "grad_norm": 1.084639072418213, |
| "learning_rate": 1.1454397434679021e-05, |
| "loss": 0.0587, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.3150984682713348, |
| "grad_norm": 0.6518976092338562, |
| "learning_rate": 5.146355805285452e-06, |
| "loss": 0.0666, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.33260393873085337, |
| "grad_norm": 2.068160057067871, |
| "learning_rate": 1.2949737362087156e-06, |
| "loss": 0.075, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.350109409190372, |
| "grad_norm": 1.11619234085083, |
| "learning_rate": 0.0, |
| "loss": 0.102, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.350109409190372, |
| "eval_loss": 0.07777100801467896, |
| "eval_runtime": 6.6104, |
| "eval_samples_per_second": 36.458, |
| "eval_steps_per_second": 18.304, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.00019466141696e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
