|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.023798545313917688, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0004759709062783537, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0004759709062783537, |
|
"eval_loss": NaN, |
|
"eval_runtime": 4.3411, |
|
"eval_samples_per_second": 11.518, |
|
"eval_steps_per_second": 2.995, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0009519418125567075, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.666666666666667e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0014279127188350613, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.001903883625113415, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.99571699711836e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0023798545313917685, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.982876141412856e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0028558254376701226, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.003331796343948476, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.931634888554937e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.00380776725022683, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.893332032039701e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.004283738156505183, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.004759709062783537, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.791726278367022e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0052356799690618915, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.728616793536588e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.005711650875340245, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.006187621781618599, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.578385041664925e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.006663592687896952, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.491548749301997e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.007139563594175306, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.00761553450045366, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.295261506157986e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.008091505406732013, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.186184199300464e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.008567476313010367, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.00904344721928872, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.947199994035401e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.009519418125567074, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.817748015645558e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.009995389031845428, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.010471359938123783, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.540155934270471e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.010947330844402137, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.392544243589427e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.01142330175068049, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.011899272656958844, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.081093963579707e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.011899272656958844, |
|
"eval_loss": NaN, |
|
"eval_runtime": 4.2294, |
|
"eval_samples_per_second": 11.822, |
|
"eval_steps_per_second": 3.074, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.012375243563237198, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.917848237560709e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.012851214469515551, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.013327185375793905, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.577868759557654e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.013803156282072258, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.401782177833148e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.014279127188350612, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.014755098094628966, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.03909064496551e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.01523106900090732, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.853176097769229e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.015707039907185673, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.016183010813464026, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.473978262721463e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.01665898171974238, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.281416799501188e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.017134952626020734, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.017610923532299087, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.8922008423644624e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.01808689443857744, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.696287243144013e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.018562865344855795, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.019038836251134148, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.303712756855988e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.019514807157412502, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.107799157635538e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.019990778063690855, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.02046674896996921, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.718583200498814e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.020942719876247566, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.526021737278538e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.02141869078252592, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.021894661688804273, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.146823902230772e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.022370632595082627, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.960909355034491e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.02284660350136098, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.023322574407639334, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.598217822166854e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.023798545313917688, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.422131240442349e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.023798545313917688, |
|
"eval_loss": NaN, |
|
"eval_runtime": 4.2537, |
|
"eval_samples_per_second": 11.754, |
|
"eval_steps_per_second": 3.056, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 75, |
|
"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": 5.658021338284032e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|