| { |
| "best_metric": 1.0340933799743652, |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", |
| "epoch": 0.004733307694583321, |
| "eval_steps": 25, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00018933230778333285, |
| "grad_norm": 26.538738250732422, |
| "learning_rate": 5e-05, |
| "loss": 32.5509, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00018933230778333285, |
| "eval_loss": 1.500787615776062, |
| "eval_runtime": 13.2544, |
| "eval_samples_per_second": 3.772, |
| "eval_steps_per_second": 3.772, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0003786646155666657, |
| "grad_norm": 29.488525390625, |
| "learning_rate": 0.0001, |
| "loss": 36.5778, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0005679969233499985, |
| "grad_norm": 36.321956634521484, |
| "learning_rate": 9.958086757163489e-05, |
| "loss": 41.7217, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0007573292311333314, |
| "grad_norm": 34.57386016845703, |
| "learning_rate": 9.833127793065098e-05, |
| "loss": 40.5149, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0009466615389166642, |
| "grad_norm": 25.122905731201172, |
| "learning_rate": 9.627450856774539e-05, |
| "loss": 34.4766, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.001135993846699997, |
| "grad_norm": 26.807296752929688, |
| "learning_rate": 9.3448873204592e-05, |
| "loss": 36.1043, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.00132532615448333, |
| "grad_norm": 23.09415626525879, |
| "learning_rate": 8.990700808169889e-05, |
| "loss": 34.7522, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0015146584622666628, |
| "grad_norm": 22.82590103149414, |
| "learning_rate": 8.571489144483944e-05, |
| "loss": 35.5535, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0017039907700499956, |
| "grad_norm": 23.842958450317383, |
| "learning_rate": 8.095061449516903e-05, |
| "loss": 34.4606, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0018933230778333285, |
| "grad_norm": 25.988386154174805, |
| "learning_rate": 7.570292669790186e-05, |
| "loss": 33.901, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002082655385616661, |
| "grad_norm": 20.00263786315918, |
| "learning_rate": 7.006958254769438e-05, |
| "loss": 30.6267, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.002271987693399994, |
| "grad_norm": 22.96904754638672, |
| "learning_rate": 6.415552058736854e-05, |
| "loss": 30.5838, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.002461320001183327, |
| "grad_norm": 19.958139419555664, |
| "learning_rate": 5.80709086014102e-05, |
| "loss": 37.5163, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.00265065230896666, |
| "grad_norm": 20.89811134338379, |
| "learning_rate": 5.192909139858981e-05, |
| "loss": 35.0669, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0028399846167499925, |
| "grad_norm": 18.02518081665039, |
| "learning_rate": 4.584447941263149e-05, |
| "loss": 31.9782, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0030293169245333255, |
| "grad_norm": 18.874174118041992, |
| "learning_rate": 3.9930417452305626e-05, |
| "loss": 33.0318, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.003218649232316658, |
| "grad_norm": 17.94559097290039, |
| "learning_rate": 3.4297073302098156e-05, |
| "loss": 31.2892, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.0034079815400999912, |
| "grad_norm": 21.376195907592773, |
| "learning_rate": 2.9049385504830985e-05, |
| "loss": 34.6142, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.003597313847883324, |
| "grad_norm": 20.425045013427734, |
| "learning_rate": 2.4285108555160577e-05, |
| "loss": 36.647, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.003786646155666657, |
| "grad_norm": 22.36380958557129, |
| "learning_rate": 2.0092991918301108e-05, |
| "loss": 32.5341, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00397597846344999, |
| "grad_norm": 19.978683471679688, |
| "learning_rate": 1.6551126795408016e-05, |
| "loss": 35.2849, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.004165310771233322, |
| "grad_norm": 18.254627227783203, |
| "learning_rate": 1.3725491432254624e-05, |
| "loss": 31.8784, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.004354643079016655, |
| "grad_norm": 23.935752868652344, |
| "learning_rate": 1.1668722069349041e-05, |
| "loss": 34.3253, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.004543975386799988, |
| "grad_norm": 20.54456329345703, |
| "learning_rate": 1.0419132428365116e-05, |
| "loss": 31.752, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.004733307694583321, |
| "grad_norm": 20.954647064208984, |
| "learning_rate": 1e-05, |
| "loss": 34.6768, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.004733307694583321, |
| "eval_loss": 1.0340933799743652, |
| "eval_runtime": 13.3951, |
| "eval_samples_per_second": 3.733, |
| "eval_steps_per_second": 3.733, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.71355818089513e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
