| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "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 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 2.3908166885375977, |
| "learning_rate": 7.24521909782041e-05, |
| "loss": 22.8638, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 2.105929136276245, |
| "learning_rate": 6.386080060392754e-05, |
| "loss": 22.5651, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 0.20586229645784704, |
| "eval_loss": 5.55440616607666, |
| "eval_runtime": 13.4924, |
| "eval_samples_per_second": 71.892, |
| "eval_steps_per_second": 4.521, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 2.184967041015625, |
| "learning_rate": 5.479739728928219e-05, |
| "loss": 22.2741, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 2.2348268032073975, |
| "learning_rate": 4.5570624363794226e-05, |
| "loss": 22.0473, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_accuracy": 0.21187852939218293, |
| "eval_loss": 5.435864448547363, |
| "eval_runtime": 12.3748, |
| "eval_samples_per_second": 78.385, |
| "eval_steps_per_second": 4.929, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 2.2103075981140137, |
| "learning_rate": 3.649468851314669e-05, |
| "loss": 21.8233, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 1.6479830741882324, |
| "learning_rate": 2.7878659847348175e-05, |
| "loss": 21.7227, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_accuracy": 0.21617785614706886, |
| "eval_loss": 5.362000942230225, |
| "eval_runtime": 12.8392, |
| "eval_samples_per_second": 75.55, |
| "eval_steps_per_second": 4.751, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 1.3954864740371704, |
| "learning_rate": 2.0015946888825077e-05, |
| "loss": 21.6333, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.4790278673171997, |
| "learning_rate": 1.3174304897095113e-05, |
| "loss": 21.4768, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_accuracy": 0.21887124010660555, |
| "eval_loss": 5.3149943351745605, |
| "eval_runtime": 12.5786, |
| "eval_samples_per_second": 77.115, |
| "eval_steps_per_second": 4.85, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 1.464524507522583, |
| "learning_rate": 7.586717784541531e-06, |
| "loss": 21.3955, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 1.6547788381576538, |
| "learning_rate": 3.443464128710239e-06, |
| "loss": 21.3548, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.9, |
| "eval_accuracy": 0.2200151717208807, |
| "eval_loss": 5.29579496383667, |
| "eval_runtime": 12.9348, |
| "eval_samples_per_second": 74.992, |
| "eval_steps_per_second": 4.716, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 1.0555720329284668, |
| "learning_rate": 8.856374635655695e-07, |
| "loss": 21.3268, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.3585398197174072, |
| "learning_rate": 3.4150841404789745e-10, |
| "loss": 21.3675, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.22028451011683436, |
| "eval_loss": 5.292044639587402, |
| "eval_runtime": 13.1086, |
| "eval_samples_per_second": 73.997, |
| "eval_steps_per_second": 4.653, |
| "step": 1000 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.67251663650816e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
