| { | |
| "best_metric": 11.924481391906738, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.022222222222222, | |
| "eval_steps": 25, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.02799796499311924, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "eval_loss": 11.927421569824219, | |
| "eval_runtime": 0.338, | |
| "eval_samples_per_second": 224.846, | |
| "eval_steps_per_second": 29.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.03451349958777428, | |
| "learning_rate": 0.0001, | |
| "loss": 11.923, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.03659261763095856, | |
| "learning_rate": 9.975923633360985e-05, | |
| "loss": 11.9211, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.029685290530323982, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9295, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.03657903894782066, | |
| "learning_rate": 9.784701678661045e-05, | |
| "loss": 11.9246, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.03866427019238472, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9239, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.040225185453891754, | |
| "learning_rate": 9.409606321741775e-05, | |
| "loss": 11.9262, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.048706311732530594, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9267, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.03764187544584274, | |
| "learning_rate": 8.865052266813685e-05, | |
| "loss": 11.9236, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.03297485411167145, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9277, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.059435416013002396, | |
| "learning_rate": 8.171966420818228e-05, | |
| "loss": 11.9257, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.05600995197892189, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 21.1529, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 0.03955496475100517, | |
| "learning_rate": 7.35698368412999e-05, | |
| "loss": 11.6465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 0.04789892956614494, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.0358, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.040386270731687546, | |
| "learning_rate": 6.451423386272312e-05, | |
| "loss": 13.133, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.051086291670799255, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.8129, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 0.0468028225004673, | |
| "learning_rate": 5.490085701647805e-05, | |
| "loss": 10.8342, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.04900282248854637, | |
| "learning_rate": 5e-05, | |
| "loss": 13.1318, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 0.05919504910707474, | |
| "learning_rate": 4.509914298352197e-05, | |
| "loss": 12.2616, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.05521504208445549, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.0512, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.04844598472118378, | |
| "learning_rate": 3.5485766137276894e-05, | |
| "loss": 12.0448, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.06266140937805176, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 12.5718, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 0.08195170760154724, | |
| "learning_rate": 2.6430163158700115e-05, | |
| "loss": 21.2846, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.05504274740815163, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.9366, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.06591450423002243, | |
| "learning_rate": 1.8280335791817733e-05, | |
| "loss": 11.4549, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "eval_loss": 11.924481391906738, | |
| "eval_runtime": 0.3244, | |
| "eval_samples_per_second": 234.279, | |
| "eval_steps_per_second": 30.826, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 0.04880596697330475, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 13.1801, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.060412779450416565, | |
| "learning_rate": 1.134947733186315e-05, | |
| "loss": 10.955, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.07174395024776459, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.4168, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 0.04970638453960419, | |
| "learning_rate": 5.903936782582253e-06, | |
| "loss": 14.1483, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.05909634754061699, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.6889, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 0.07133551687002182, | |
| "learning_rate": 2.152983213389559e-06, | |
| "loss": 11.3121, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.05919625237584114, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 12.2727, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 0.050839297473430634, | |
| "learning_rate": 2.407636663901591e-07, | |
| "loss": 12.6717, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.022222222222222, | |
| "grad_norm": 0.10524462908506393, | |
| "learning_rate": 0.0, | |
| "loss": 19.9286, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "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": 708896096256.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |