| { | |
| "best_metric": 0.36255866289138794, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.073446327683616, | |
| "eval_steps": 25, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 40.97779083251953, | |
| "learning_rate": 5e-05, | |
| "loss": 8.227, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "eval_loss": 8.391592025756836, | |
| "eval_runtime": 1.4447, | |
| "eval_samples_per_second": 34.61, | |
| "eval_steps_per_second": 8.999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 40.57859802246094, | |
| "learning_rate": 0.0001, | |
| "loss": 8.3493, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 37.76644515991211, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 6.2252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 27.821704864501953, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 23.382740020751953, | |
| "learning_rate": 9.80623151079494e-05, | |
| "loss": 1.332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 6.967331409454346, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6393, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 5.6305365562438965, | |
| "learning_rate": 9.468645689567598e-05, | |
| "loss": 0.4871, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 5.748826503753662, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4325, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 1.4002121686935425, | |
| "learning_rate": 8.978547040132317e-05, | |
| "loss": 0.3653, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 1.6485339403152466, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9943502824858758, | |
| "grad_norm": 4.030787467956543, | |
| "learning_rate": 8.354769778736406e-05, | |
| "loss": 0.3826, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 4.237292766571045, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.694, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1751412429378532, | |
| "grad_norm": 2.3578829765319824, | |
| "learning_rate": 7.62128531571699e-05, | |
| "loss": 0.3633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2655367231638417, | |
| "grad_norm": 1.2775280475616455, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3493, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 5.237298011779785, | |
| "learning_rate": 6.80628104764508e-05, | |
| "loss": 0.3867, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4463276836158192, | |
| "grad_norm": 1.780826210975647, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3456, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.536723163841808, | |
| "grad_norm": 0.4675554633140564, | |
| "learning_rate": 5.941077131483025e-05, | |
| "loss": 0.3453, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 1.3954887390136719, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3559, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7175141242937855, | |
| "grad_norm": 0.9117836952209473, | |
| "learning_rate": 5.058922868516978e-05, | |
| "loss": 0.3576, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.807909604519774, | |
| "grad_norm": 1.012261986732483, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.3659, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 2.663132429122925, | |
| "learning_rate": 4.19371895235492e-05, | |
| "loss": 0.358, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9887005649717513, | |
| "grad_norm": 1.1675078868865967, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.3509, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.07909604519774, | |
| "grad_norm": 3.068908214569092, | |
| "learning_rate": 3.378714684283011e-05, | |
| "loss": 0.672, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 0.39603307843208313, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3361, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "grad_norm": 0.6155238151550293, | |
| "learning_rate": 2.645230221263596e-05, | |
| "loss": 0.3329, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "eval_loss": 0.36255866289138794, | |
| "eval_runtime": 1.4631, | |
| "eval_samples_per_second": 34.174, | |
| "eval_steps_per_second": 8.885, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3502824858757063, | |
| "grad_norm": 1.7378867864608765, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3541, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 1.1388368606567383, | |
| "learning_rate": 2.0214529598676836e-05, | |
| "loss": 0.3549, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.5310734463276834, | |
| "grad_norm": 2.1477389335632324, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3571, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.621468926553672, | |
| "grad_norm": 0.21045787632465363, | |
| "learning_rate": 1.531354310432403e-05, | |
| "loss": 0.3426, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 0.26963287591934204, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3498, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.8022598870056497, | |
| "grad_norm": 0.897307813167572, | |
| "learning_rate": 1.1937684892050604e-05, | |
| "loss": 0.3472, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.8926553672316384, | |
| "grad_norm": 0.2607298791408539, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3494, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": 0.660701334476471, | |
| "learning_rate": 1.0216687299751144e-05, | |
| "loss": 0.3465, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.073446327683616, | |
| "grad_norm": 1.1560474634170532, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6403, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1.0808353705112371e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |