| { | |
| "best_metric": 0.7650073170661926, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1069767441860465, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 26.82486915588379, | |
| "learning_rate": 5e-05, | |
| "loss": 15.5404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "eval_loss": 1.1030958890914917, | |
| "eval_runtime": 4.0595, | |
| "eval_samples_per_second": 12.317, | |
| "eval_steps_per_second": 3.202, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 32.55805969238281, | |
| "learning_rate": 0.0001, | |
| "loss": 17.9188, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": 23.376680374145508, | |
| "learning_rate": 9.985407886603945e-05, | |
| "loss": 17.5531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29767441860465116, | |
| "grad_norm": 15.263604164123535, | |
| "learning_rate": 9.941726181870608e-05, | |
| "loss": 14.8715, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 13.026528358459473, | |
| "learning_rate": 9.869238178417235e-05, | |
| "loss": 14.1927, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.44651162790697674, | |
| "grad_norm": 11.496667861938477, | |
| "learning_rate": 9.768413988762156e-05, | |
| "loss": 14.7444, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5209302325581395, | |
| "grad_norm": 8.687058448791504, | |
| "learning_rate": 9.639907496464709e-05, | |
| "loss": 13.8784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5953488372093023, | |
| "grad_norm": 7.8401970863342285, | |
| "learning_rate": 9.484552115439445e-05, | |
| "loss": 13.6697, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6697674418604651, | |
| "grad_norm": 7.2838263511657715, | |
| "learning_rate": 9.303355384947076e-05, | |
| "loss": 13.5577, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 7.735969066619873, | |
| "learning_rate": 9.097492435315756e-05, | |
| "loss": 12.9802, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8186046511627907, | |
| "grad_norm": 6.482202053070068, | |
| "learning_rate": 8.868298366769954e-05, | |
| "loss": 13.1186, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8930232558139535, | |
| "grad_norm": 6.737044811248779, | |
| "learning_rate": 8.617259590793198e-05, | |
| "loss": 13.2019, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9674418604651163, | |
| "grad_norm": 8.719466209411621, | |
| "learning_rate": 8.346004190179198e-05, | |
| "loss": 13.6937, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0604651162790697, | |
| "grad_norm": 5.885293483734131, | |
| "learning_rate": 8.056291360290201e-05, | |
| "loss": 11.8573, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1348837209302325, | |
| "grad_norm": 7.148478031158447, | |
| "learning_rate": 7.75e-05, | |
| "loss": 12.4117, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2093023255813953, | |
| "grad_norm": 7.730895519256592, | |
| "learning_rate": 7.429116526313744e-05, | |
| "loss": 12.0587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.283720930232558, | |
| "grad_norm": 7.085984230041504, | |
| "learning_rate": 7.095721991691411e-05, | |
| "loss": 11.7461, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3581395348837209, | |
| "grad_norm": 6.469642639160156, | |
| "learning_rate": 6.751978587624037e-05, | |
| "loss": 11.8886, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4325581395348836, | |
| "grad_norm": 6.971822738647461, | |
| "learning_rate": 6.400115621992201e-05, | |
| "loss": 11.9513, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5069767441860464, | |
| "grad_norm": 6.892801284790039, | |
| "learning_rate": 6.042415061148954e-05, | |
| "loss": 11.5344, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5813953488372094, | |
| "grad_norm": 5.958037853240967, | |
| "learning_rate": 5.681196730492368e-05, | |
| "loss": 11.6245, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.655813953488372, | |
| "grad_norm": 6.668700218200684, | |
| "learning_rate": 5.318803269507634e-05, | |
| "loss": 11.5543, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.730232558139535, | |
| "grad_norm": 7.723108291625977, | |
| "learning_rate": 4.9575849388510473e-05, | |
| "loss": 11.489, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.8046511627906976, | |
| "grad_norm": 5.082211494445801, | |
| "learning_rate": 4.599884378007802e-05, | |
| "loss": 11.2579, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8790697674418606, | |
| "grad_norm": 6.550709247589111, | |
| "learning_rate": 4.248021412375963e-05, | |
| "loss": 11.8115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8790697674418606, | |
| "eval_loss": 0.7650073170661926, | |
| "eval_runtime": 3.3463, | |
| "eval_samples_per_second": 14.942, | |
| "eval_steps_per_second": 3.885, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9534883720930232, | |
| "grad_norm": 7.476520538330078, | |
| "learning_rate": 3.904278008308589e-05, | |
| "loss": 11.5912, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.046511627906977, | |
| "grad_norm": 5.527069091796875, | |
| "learning_rate": 3.570883473686256e-05, | |
| "loss": 11.2094, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.1209302325581394, | |
| "grad_norm": 5.50228214263916, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.0862, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1953488372093024, | |
| "grad_norm": 6.5125651359558105, | |
| "learning_rate": 2.9437086397097995e-05, | |
| "loss": 10.4032, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.269767441860465, | |
| "grad_norm": 6.218883514404297, | |
| "learning_rate": 2.6539958098208027e-05, | |
| "loss": 10.4676, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.344186046511628, | |
| "grad_norm": 5.223501205444336, | |
| "learning_rate": 2.3827404092068032e-05, | |
| "loss": 10.3137, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.4186046511627906, | |
| "grad_norm": 6.159942150115967, | |
| "learning_rate": 2.1317016332300447e-05, | |
| "loss": 10.5853, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.4930232558139536, | |
| "grad_norm": 6.657078266143799, | |
| "learning_rate": 1.902507564684246e-05, | |
| "loss": 10.3025, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.567441860465116, | |
| "grad_norm": 5.459758758544922, | |
| "learning_rate": 1.6966446150529244e-05, | |
| "loss": 10.4436, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.641860465116279, | |
| "grad_norm": 6.186044692993164, | |
| "learning_rate": 1.515447884560556e-05, | |
| "loss": 10.5271, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.7162790697674417, | |
| "grad_norm": 7.22088098526001, | |
| "learning_rate": 1.3600925035352913e-05, | |
| "loss": 10.1892, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7906976744186047, | |
| "grad_norm": 5.603003025054932, | |
| "learning_rate": 1.2315860112378455e-05, | |
| "loss": 10.7062, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8651162790697673, | |
| "grad_norm": 5.911949157714844, | |
| "learning_rate": 1.130761821582766e-05, | |
| "loss": 10.5918, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.9395348837209303, | |
| "grad_norm": 6.643774032592773, | |
| "learning_rate": 1.0582738181293923e-05, | |
| "loss": 10.518, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.0325581395348835, | |
| "grad_norm": 5.792553424835205, | |
| "learning_rate": 1.0145921133960554e-05, | |
| "loss": 10.4178, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.1069767441860465, | |
| "grad_norm": 5.410275936126709, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3721, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "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": 4.63958278020268e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |