| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 50, | |
| "global_step": 219, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 0.17780767381191254, | |
| "learning_rate": 9.79562374273544e-05, | |
| "loss": 0.3412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 0.06632925570011139, | |
| "learning_rate": 9.19920283275515e-05, | |
| "loss": 0.0075, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "eval_loss": 0.005886094179004431, | |
| "eval_runtime": 62.5805, | |
| "eval_samples_per_second": 7.782, | |
| "eval_steps_per_second": 0.399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.0776129812002182, | |
| "learning_rate": 8.259494979393563e-05, | |
| "loss": 0.0059, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 0.025069398805499077, | |
| "learning_rate": 7.053321772247545e-05, | |
| "loss": 0.0054, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 0.06095319241285324, | |
| "learning_rate": 5.679288477592815e-05, | |
| "loss": 0.0057, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "eval_loss": 0.00544710224494338, | |
| "eval_runtime": 62.5695, | |
| "eval_samples_per_second": 7.783, | |
| "eval_steps_per_second": 0.4, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.034162312746047974, | |
| "learning_rate": 4.249723008276737e-05, | |
| "loss": 0.0053, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 0.030082939192652702, | |
| "learning_rate": 2.8814930603527068e-05, | |
| "loss": 0.0051, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "eval_loss": 0.0049239168874919415, | |
| "eval_runtime": 62.5741, | |
| "eval_samples_per_second": 7.783, | |
| "eval_steps_per_second": 0.4, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.026808856055140495, | |
| "learning_rate": 1.6864521201543197e-05, | |
| "loss": 0.005, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.0478011779487133, | |
| "learning_rate": 7.6229538553584556e-06, | |
| "loss": 0.0045, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 0.05524557828903198, | |
| "learning_rate": 1.8457313431614498e-06, | |
| "loss": 0.0043, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "eval_loss": 0.00419235322624445, | |
| "eval_runtime": 62.5256, | |
| "eval_samples_per_second": 7.789, | |
| "eval_steps_per_second": 0.4, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 219, | |
| "total_flos": 4.685177916793815e+17, | |
| "train_loss": 0.03597381513684852, | |
| "train_runtime": 2055.0645, | |
| "train_samples_per_second": 2.13, | |
| "train_steps_per_second": 0.107 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 219, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.685177916793815e+17, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |