|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.5095541401273885, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01019108280254777, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01019108280254777, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.6759, |
|
"eval_samples_per_second": 179.821, |
|
"eval_steps_per_second": 22.58, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02038216560509554, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.030573248407643312, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.04076433121019108, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.050955414012738856, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.061146496815286625, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.07133757961783439, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.08152866242038216, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.09171974522292993, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.10191082802547771, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.11210191082802548, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.12229299363057325, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.13248407643312102, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.14267515923566879, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.15286624203821655, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.16305732484076432, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.1732484076433121, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.18343949044585986, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.19363057324840766, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.20382165605095542, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2140127388535032, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.22420382165605096, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.23439490445859873, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.2445859872611465, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.25477707006369427, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.25477707006369427, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.6614, |
|
"eval_samples_per_second": 180.53, |
|
"eval_steps_per_second": 22.669, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.26496815286624203, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.2751592356687898, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6729843538492847e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.28535031847133757, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.29554140127388534, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.3057324840764331, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.3159235668789809, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.392802673484193e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.32611464968152865, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.3363057324840764, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7885565489049946e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.3464968152866242, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.35668789808917195, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.3668789808917197, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.37707006369426754, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.703270924499656e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.3872611464968153, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.3974522292993631, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2408009626051137e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.40764331210191085, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4178343949044586, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.4280254777070064, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.43821656050955415, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.156362923365588e-06, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.4484076433121019, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.4585987261146497, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.653493525244721e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.46878980891719746, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.4789808917197452, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.489171974522293, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.277569313094809e-07, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.49936305732484076, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0705383806982606e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.5095541401273885, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5095541401273885, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.6606, |
|
"eval_samples_per_second": 180.574, |
|
"eval_steps_per_second": 22.674, |
|
"step": 50 |
|
} |
|
], |
|
"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": 1 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 843055104000.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|