| { | |
| "best_metric": 0.4461486041545868, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1388888888888889, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005555555555555556, | |
| "grad_norm": 0.5632655024528503, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005555555555555556, | |
| "eval_loss": 1.9876978397369385, | |
| "eval_runtime": 16.5805, | |
| "eval_samples_per_second": 18.275, | |
| "eval_steps_per_second": 2.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011111111111111112, | |
| "grad_norm": 0.7303450107574463, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4406, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016666666666666666, | |
| "grad_norm": 0.7765696048736572, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.4979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022222222222222223, | |
| "grad_norm": 0.990936279296875, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.2878, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 1.1548110246658325, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.1542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03333333333333333, | |
| "grad_norm": 1.173454999923706, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.876, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03888888888888889, | |
| "grad_norm": 1.0297809839248657, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.7575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 1.0571157932281494, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6936, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.0746943950653076, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.6233, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 1.202501654624939, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06111111111111111, | |
| "grad_norm": 1.1679050922393799, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.6314, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 0.9829458594322205, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.4984, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07222222222222222, | |
| "grad_norm": 2.6869962215423584, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.6553, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07777777777777778, | |
| "grad_norm": 1.1565390825271606, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.4891, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.731761634349823, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.4605, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 1.2121446132659912, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.4157, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09444444444444444, | |
| "grad_norm": 0.971774697303772, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.4223, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.7811177968978882, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.4969, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10555555555555556, | |
| "grad_norm": 0.6840196251869202, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.4396, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.6061505079269409, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.4485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11666666666666667, | |
| "grad_norm": 0.6416930556297302, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.4732, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12222222222222222, | |
| "grad_norm": 0.6488082408905029, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12777777777777777, | |
| "grad_norm": 0.6531954407691956, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.4577, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 0.719580352306366, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.4735, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 0.9697103500366211, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.5967, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "eval_loss": 0.4461486041545868, | |
| "eval_runtime": 16.6413, | |
| "eval_samples_per_second": 18.208, | |
| "eval_steps_per_second": 2.283, | |
| "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": 1.398077353099264e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |