| { | |
| "best_metric": 0.6586966514587402, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.9501187648456056, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03800475059382423, | |
| "grad_norm": 0.28412196040153503, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03800475059382423, | |
| "eval_loss": 1.0110955238342285, | |
| "eval_runtime": 2.4806, | |
| "eval_samples_per_second": 20.156, | |
| "eval_steps_per_second": 5.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07600950118764846, | |
| "grad_norm": 0.4208658039569855, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11401425178147269, | |
| "grad_norm": 0.5144053101539612, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.7878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15201900237529692, | |
| "grad_norm": 0.4457476735115051, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6879, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19002375296912113, | |
| "grad_norm": 0.5541384816169739, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.8254, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22802850356294538, | |
| "grad_norm": 0.6464670896530151, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8822, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2660332541567696, | |
| "grad_norm": 0.21147261559963226, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6924, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30403800475059384, | |
| "grad_norm": 0.2564125061035156, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4347, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.342042755344418, | |
| "grad_norm": 0.3210887908935547, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4277, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38004750593824227, | |
| "grad_norm": 0.34536251425743103, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4985, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4180522565320665, | |
| "grad_norm": 0.2939271032810211, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5087, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45605700712589076, | |
| "grad_norm": 0.31520816683769226, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5726, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.49406175771971494, | |
| "grad_norm": 0.47069475054740906, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7795, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5320665083135392, | |
| "grad_norm": 0.20200864970684052, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5919, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5700712589073634, | |
| "grad_norm": 0.19906656444072723, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5505, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6080760095011877, | |
| "grad_norm": 0.19475938379764557, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6460807600950119, | |
| "grad_norm": 0.19246743619441986, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.474, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.684085510688836, | |
| "grad_norm": 0.228928342461586, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5931, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7220902612826603, | |
| "grad_norm": 0.2785808742046356, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.587, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7600950118764845, | |
| "grad_norm": 0.19578416645526886, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7980997624703088, | |
| "grad_norm": 0.14827033877372742, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4847, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.836104513064133, | |
| "grad_norm": 0.2006971836090088, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6011, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8741092636579573, | |
| "grad_norm": 0.20054136216640472, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.478, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9121140142517815, | |
| "grad_norm": 0.18890415132045746, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4875, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "grad_norm": 0.23377546668052673, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6926, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "eval_loss": 0.6586966514587402, | |
| "eval_runtime": 1.8453, | |
| "eval_samples_per_second": 27.095, | |
| "eval_steps_per_second": 7.045, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.812028905324544e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |