|
{ |
|
"best_metric": 2.4560940265655518, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.005063803929511849, |
|
"eval_steps": 50, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00010127607859023699, |
|
"grad_norm": 31.39533233642578, |
|
"learning_rate": 1e-05, |
|
"loss": 5.6035, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00010127607859023699, |
|
"eval_loss": 6.345576286315918, |
|
"eval_runtime": 1568.5781, |
|
"eval_samples_per_second": 10.602, |
|
"eval_steps_per_second": 2.651, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00020255215718047398, |
|
"grad_norm": 23.184526443481445, |
|
"learning_rate": 2e-05, |
|
"loss": 5.6016, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00030382823577071097, |
|
"grad_norm": 30.848772048950195, |
|
"learning_rate": 3e-05, |
|
"loss": 5.0115, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00040510431436094796, |
|
"grad_norm": 20.879568099975586, |
|
"learning_rate": 4e-05, |
|
"loss": 4.0997, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0005063803929511849, |
|
"grad_norm": 56.598411560058594, |
|
"learning_rate": 5e-05, |
|
"loss": 3.3008, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0006076564715414219, |
|
"grad_norm": 29.526737213134766, |
|
"learning_rate": 6e-05, |
|
"loss": 2.5314, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0007089325501316589, |
|
"grad_norm": 12.449617385864258, |
|
"learning_rate": 7e-05, |
|
"loss": 1.7549, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0008102086287218959, |
|
"grad_norm": 16.119483947753906, |
|
"learning_rate": 8e-05, |
|
"loss": 1.6059, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0009114847073121329, |
|
"grad_norm": 9.31202220916748, |
|
"learning_rate": 9e-05, |
|
"loss": 1.5359, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0010127607859023698, |
|
"grad_norm": 19.932828903198242, |
|
"learning_rate": 0.0001, |
|
"loss": 1.7887, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.001114036864492607, |
|
"grad_norm": 6.6560163497924805, |
|
"learning_rate": 9.999316524962345e-05, |
|
"loss": 1.1223, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0012153129430828439, |
|
"grad_norm": 7.101311206817627, |
|
"learning_rate": 9.997266286704631e-05, |
|
"loss": 1.3276, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0013165890216730808, |
|
"grad_norm": 5.894531726837158, |
|
"learning_rate": 9.993849845741524e-05, |
|
"loss": 1.4501, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.0014178651002633178, |
|
"grad_norm": 6.54768180847168, |
|
"learning_rate": 9.989068136093873e-05, |
|
"loss": 1.4689, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.0015191411788535547, |
|
"grad_norm": 6.256585597991943, |
|
"learning_rate": 9.98292246503335e-05, |
|
"loss": 1.5853, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0016204172574437918, |
|
"grad_norm": 8.225622177124023, |
|
"learning_rate": 9.975414512725057e-05, |
|
"loss": 1.6304, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.0017216933360340288, |
|
"grad_norm": 5.209911346435547, |
|
"learning_rate": 9.966546331768191e-05, |
|
"loss": 1.3861, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.0018229694146242657, |
|
"grad_norm": 7.358743667602539, |
|
"learning_rate": 9.956320346634876e-05, |
|
"loss": 1.4267, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0019242454932145027, |
|
"grad_norm": 5.794778823852539, |
|
"learning_rate": 9.944739353007344e-05, |
|
"loss": 1.4137, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.0020255215718047396, |
|
"grad_norm": 5.440245151519775, |
|
"learning_rate": 9.931806517013612e-05, |
|
"loss": 1.7719, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0021267976503949767, |
|
"grad_norm": 9.398520469665527, |
|
"learning_rate": 9.917525374361912e-05, |
|
"loss": 1.8461, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.002228073728985214, |
|
"grad_norm": 7.62516975402832, |
|
"learning_rate": 9.901899829374047e-05, |
|
"loss": 1.8011, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.0023293498075754506, |
|
"grad_norm": 4.325904369354248, |
|
"learning_rate": 9.884934153917997e-05, |
|
"loss": 1.4682, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.0024306258861656878, |
|
"grad_norm": 6.48047399520874, |
|
"learning_rate": 9.86663298624003e-05, |
|
"loss": 1.8256, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0025319019647559245, |
|
"grad_norm": 6.384871482849121, |
|
"learning_rate": 9.847001329696653e-05, |
|
"loss": 1.6956, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0026331780433461616, |
|
"grad_norm": 4.6459126472473145, |
|
"learning_rate": 9.826044551386744e-05, |
|
"loss": 1.6426, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.002734454121936399, |
|
"grad_norm": 5.729737758636475, |
|
"learning_rate": 9.803768380684242e-05, |
|
"loss": 1.5419, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0028357302005266355, |
|
"grad_norm": 4.571890830993652, |
|
"learning_rate": 9.780178907671789e-05, |
|
"loss": 1.6178, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.0029370062791168727, |
|
"grad_norm": 4.613413333892822, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 1.6403, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.0030382823577071094, |
|
"grad_norm": 4.91149377822876, |
|
"learning_rate": 9.729086208503174e-05, |
|
"loss": 1.6804, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0031395584362973465, |
|
"grad_norm": 7.935057163238525, |
|
"learning_rate": 9.701596950580806e-05, |
|
"loss": 2.2117, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.0032408345148875837, |
|
"grad_norm": 5.093746185302734, |
|
"learning_rate": 9.672822322997305e-05, |
|
"loss": 2.1726, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.0033421105934778204, |
|
"grad_norm": 4.15211296081543, |
|
"learning_rate": 9.642770192448536e-05, |
|
"loss": 1.9019, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.0034433866720680576, |
|
"grad_norm": 3.5006465911865234, |
|
"learning_rate": 9.611448774886924e-05, |
|
"loss": 1.7625, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.0035446627506582947, |
|
"grad_norm": 3.709160089492798, |
|
"learning_rate": 9.578866633275288e-05, |
|
"loss": 1.7127, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.0036459388292485314, |
|
"grad_norm": 3.0920586585998535, |
|
"learning_rate": 9.545032675245813e-05, |
|
"loss": 1.5979, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.0037472149078387686, |
|
"grad_norm": 2.882312536239624, |
|
"learning_rate": 9.509956150664796e-05, |
|
"loss": 1.7251, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.0038484909864290053, |
|
"grad_norm": 5.489690780639648, |
|
"learning_rate": 9.473646649103818e-05, |
|
"loss": 2.3286, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.0039497670650192425, |
|
"grad_norm": 7.151604652404785, |
|
"learning_rate": 9.43611409721806e-05, |
|
"loss": 2.8412, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.004051043143609479, |
|
"grad_norm": 8.030261993408203, |
|
"learning_rate": 9.397368756032445e-05, |
|
"loss": 3.1621, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.004152319222199717, |
|
"grad_norm": 7.285529136657715, |
|
"learning_rate": 9.357421218136386e-05, |
|
"loss": 2.7091, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.0042535953007899535, |
|
"grad_norm": 5.098424911499023, |
|
"learning_rate": 9.316282404787871e-05, |
|
"loss": 2.3983, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.00435487137938019, |
|
"grad_norm": 5.375723838806152, |
|
"learning_rate": 9.273963562927695e-05, |
|
"loss": 2.3807, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.004456147457970428, |
|
"grad_norm": 4.936964988708496, |
|
"learning_rate": 9.230476262104677e-05, |
|
"loss": 2.3285, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.0045574235365606645, |
|
"grad_norm": 4.360125541687012, |
|
"learning_rate": 9.185832391312644e-05, |
|
"loss": 2.291, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.004658699615150901, |
|
"grad_norm": 7.072688102722168, |
|
"learning_rate": 9.140044155740101e-05, |
|
"loss": 2.8103, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.004759975693741138, |
|
"grad_norm": 6.983039379119873, |
|
"learning_rate": 9.093124073433463e-05, |
|
"loss": 2.6871, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.0048612517723313755, |
|
"grad_norm": 8.898165702819824, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 2.8689, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.004962527850921612, |
|
"grad_norm": 5.214823246002197, |
|
"learning_rate": 8.995939984474624e-05, |
|
"loss": 2.5026, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.005063803929511849, |
|
"grad_norm": 5.564656734466553, |
|
"learning_rate": 8.945702546981969e-05, |
|
"loss": 2.6417, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.005063803929511849, |
|
"eval_loss": 2.4560940265655518, |
|
"eval_runtime": 1574.7033, |
|
"eval_samples_per_second": 10.561, |
|
"eval_steps_per_second": 2.64, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 200, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"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": 8.63610951696384e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|