| { | |
| "best_metric": 4.240368366241455, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03374957813027337, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "grad_norm": 151.8303985595703, | |
| "learning_rate": 5e-05, | |
| "loss": 55.2222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "eval_loss": 110.49451446533203, | |
| "eval_runtime": 367.2894, | |
| "eval_samples_per_second": 13.586, | |
| "eval_steps_per_second": 1.699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026999662504218697, | |
| "grad_norm": 194.731689453125, | |
| "learning_rate": 0.0001, | |
| "loss": 73.7774, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004049949375632805, | |
| "grad_norm": 177.084716796875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 72.807, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005399932500843739, | |
| "grad_norm": 225.96267700195312, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 65.2273, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006749915626054675, | |
| "grad_norm": 313.0947570800781, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 51.4295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00809989875126561, | |
| "grad_norm": 407.1618957519531, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 40.1723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009449881876476544, | |
| "grad_norm": 409.1275939941406, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 19.4778, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010799865001687479, | |
| "grad_norm": 57.939823150634766, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.0572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "grad_norm": 17.780284881591797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.6456, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01349983125210935, | |
| "grad_norm": 99.7518539428711, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.3322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014849814377320284, | |
| "grad_norm": 94.86551666259766, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.2899, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01619979750253122, | |
| "grad_norm": 22.37548065185547, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.2246, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017549780627742154, | |
| "grad_norm": 13.087552070617676, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.3783, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01889976375295309, | |
| "grad_norm": 14.338868141174316, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.2968, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020249746878164023, | |
| "grad_norm": 9.942703247070312, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.1482, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021599730003374958, | |
| "grad_norm": 7.916289806365967, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.1814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022949713128585892, | |
| "grad_norm": 10.01076889038086, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.447, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024299696253796826, | |
| "grad_norm": 11.480803489685059, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.6677, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02564967937900776, | |
| "grad_norm": 10.52211856842041, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.6511, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0269996625042187, | |
| "grad_norm": 9.410900115966797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.5054, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028349645629429633, | |
| "grad_norm": 41.73292922973633, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.9315, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029699628754640568, | |
| "grad_norm": 45.694610595703125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.6239, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031049611879851502, | |
| "grad_norm": 26.50372886657715, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.7849, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03239959500506244, | |
| "grad_norm": 9.058126449584961, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.9841, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "grad_norm": 11.410837173461914, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.813, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "eval_loss": 4.240368366241455, | |
| "eval_runtime": 367.5136, | |
| "eval_samples_per_second": 13.578, | |
| "eval_steps_per_second": 1.698, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.087239672233984e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |