| { | |
| "best_metric": 3.628095865249634, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.003885003885003885, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "grad_norm": 2.517857313156128, | |
| "learning_rate": 2e-05, | |
| "loss": 5.5472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "eval_loss": 5.986268520355225, | |
| "eval_runtime": 480.177, | |
| "eval_samples_per_second": 5.644, | |
| "eval_steps_per_second": 2.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003108003108003108, | |
| "grad_norm": 1.6737048625946045, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2218, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004662004662004662, | |
| "grad_norm": 2.7980663776397705, | |
| "learning_rate": 6e-05, | |
| "loss": 5.9418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006216006216006216, | |
| "grad_norm": 2.564962387084961, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3491, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000777000777000777, | |
| "grad_norm": 1.8410054445266724, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000777000777000777, | |
| "eval_loss": 5.913425922393799, | |
| "eval_runtime": 484.5813, | |
| "eval_samples_per_second": 5.592, | |
| "eval_steps_per_second": 2.796, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009324009324009324, | |
| "grad_norm": 3.5232038497924805, | |
| "learning_rate": 0.00012, | |
| "loss": 5.8329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010878010878010878, | |
| "grad_norm": 3.0337979793548584, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012432012432012432, | |
| "grad_norm": 3.325150966644287, | |
| "learning_rate": 0.00016, | |
| "loss": 5.6252, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "grad_norm": 3.465092658996582, | |
| "learning_rate": 0.00018, | |
| "loss": 4.7447, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001554001554001554, | |
| "grad_norm": 3.6227757930755615, | |
| "learning_rate": 0.0002, | |
| "loss": 4.7645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001554001554001554, | |
| "eval_loss": 4.757584571838379, | |
| "eval_runtime": 476.3877, | |
| "eval_samples_per_second": 5.689, | |
| "eval_steps_per_second": 2.844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017094017094017094, | |
| "grad_norm": 4.928085803985596, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.2605, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0018648018648018648, | |
| "grad_norm": 3.8864288330078125, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.1881, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00202020202020202, | |
| "grad_norm": 5.182751655578613, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.6251, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0021756021756021756, | |
| "grad_norm": 6.373917102813721, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.051, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002331002331002331, | |
| "grad_norm": 7.264593124389648, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.6214, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002331002331002331, | |
| "eval_loss": 3.908417224884033, | |
| "eval_runtime": 476.9646, | |
| "eval_samples_per_second": 5.682, | |
| "eval_steps_per_second": 2.841, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0024864024864024864, | |
| "grad_norm": 7.405270099639893, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.8455, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002641802641802642, | |
| "grad_norm": 5.975386142730713, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.7157, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002797202797202797, | |
| "grad_norm": 6.4273881912231445, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.7263, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0029526029526029526, | |
| "grad_norm": 5.193171501159668, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.7786, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003108003108003108, | |
| "grad_norm": 6.251737594604492, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.4756, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003108003108003108, | |
| "eval_loss": 3.67405366897583, | |
| "eval_runtime": 472.2966, | |
| "eval_samples_per_second": 5.738, | |
| "eval_steps_per_second": 2.869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032634032634032634, | |
| "grad_norm": 5.634303092956543, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.7469, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003418803418803419, | |
| "grad_norm": 5.808221817016602, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.8198, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003574203574203574, | |
| "grad_norm": 5.099615097045898, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.4756, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0037296037296037296, | |
| "grad_norm": 4.355826377868652, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.568, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003885003885003885, | |
| "grad_norm": 4.638548851013184, | |
| "learning_rate": 0.0, | |
| "loss": 3.7543, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003885003885003885, | |
| "eval_loss": 3.628095865249634, | |
| "eval_runtime": 480.1391, | |
| "eval_samples_per_second": 5.644, | |
| "eval_steps_per_second": 2.822, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 6889626824343552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |