| { | |
| "best_metric": 2.7029125690460205, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.024390243902439, | |
| "eval_steps": 25, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 7.10798978805542, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2901, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "eval_loss": 6.794641494750977, | |
| "eval_runtime": 0.6416, | |
| "eval_samples_per_second": 77.936, | |
| "eval_steps_per_second": 20.263, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 13.896225929260254, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7989, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 6.749074459075928, | |
| "learning_rate": 9.97362080719462e-05, | |
| "loss": 5.3098, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 11.291173934936523, | |
| "learning_rate": 9.89479250069539e-05, | |
| "loss": 4.9457, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 51.770416259765625, | |
| "learning_rate": 9.764439270322611e-05, | |
| "loss": 6.001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 7.940297603607178, | |
| "learning_rate": 9.584089388519307e-05, | |
| "loss": 3.9051, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 23.023454666137695, | |
| "learning_rate": 9.355857292754152e-05, | |
| "loss": 3.9001, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 5.207144737243652, | |
| "learning_rate": 9.082418795675397e-05, | |
| "loss": 3.8266, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 8.671276092529297, | |
| "learning_rate": 8.766979713654089e-05, | |
| "loss": 3.5264, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 17.078868865966797, | |
| "learning_rate": 8.413238281518225e-05, | |
| "loss": 3.9503, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 6.692962646484375, | |
| "learning_rate": 8.025341794130722e-05, | |
| "loss": 5.3809, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 5.900484085083008, | |
| "learning_rate": 7.607837983149056e-05, | |
| "loss": 3.0676, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 3.715177297592163, | |
| "learning_rate": 7.165621699029615e-05, | |
| "loss": 2.3503, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 8.826342582702637, | |
| "learning_rate": 6.703877523381496e-05, | |
| "loss": 3.4234, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 7.122591972351074, | |
| "learning_rate": 6.228018984487442e-05, | |
| "loss": 2.9165, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 4.160889148712158, | |
| "learning_rate": 5.74362508863438e-05, | |
| "loss": 2.9145, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 5.585999011993408, | |
| "learning_rate": 5.2563749113656216e-05, | |
| "loss": 2.6976, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 2.9115383625030518, | |
| "learning_rate": 4.771981015512559e-05, | |
| "loss": 2.1684, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 5.3558268547058105, | |
| "learning_rate": 4.296122476618507e-05, | |
| "loss": 2.8113, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 11.97620964050293, | |
| "learning_rate": 3.834378300970385e-05, | |
| "loss": 2.7463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "grad_norm": 6.126107692718506, | |
| "learning_rate": 3.392162016850945e-05, | |
| "loss": 4.1316, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.1463414634146343, | |
| "grad_norm": 3.347085475921631, | |
| "learning_rate": 2.97465820586928e-05, | |
| "loss": 2.2521, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.2439024390243905, | |
| "grad_norm": 3.246694326400757, | |
| "learning_rate": 2.586761718481776e-05, | |
| "loss": 1.2408, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 6.535632133483887, | |
| "learning_rate": 2.2330202863459122e-05, | |
| "loss": 3.2995, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 3.856961250305176, | |
| "learning_rate": 1.9175812043246033e-05, | |
| "loss": 2.2837, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "eval_loss": 2.7029125690460205, | |
| "eval_runtime": 0.6175, | |
| "eval_samples_per_second": 80.966, | |
| "eval_steps_per_second": 21.051, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5365853658536586, | |
| "grad_norm": 4.493419170379639, | |
| "learning_rate": 1.6441427072458494e-05, | |
| "loss": 2.7897, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.6341463414634148, | |
| "grad_norm": 3.798736810684204, | |
| "learning_rate": 1.4159106114806942e-05, | |
| "loss": 2.2273, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 3.0154953002929688, | |
| "learning_rate": 1.2355607296773895e-05, | |
| "loss": 1.2718, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.8292682926829267, | |
| "grad_norm": 6.761699199676514, | |
| "learning_rate": 1.1052074993046102e-05, | |
| "loss": 3.4291, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 3.54974365234375, | |
| "learning_rate": 1.0263791928053819e-05, | |
| "loss": 2.36, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.024390243902439, | |
| "grad_norm": 5.698737144470215, | |
| "learning_rate": 1e-05, | |
| "loss": 4.0453, | |
| "step": 31 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 31, | |
| "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": 1.830865658393395e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |