|
{ |
|
"best_metric": 0.6049863696098328, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.6914433880726015, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.013828867761452032, |
|
"grad_norm": 19.272890090942383, |
|
"learning_rate": 5e-05, |
|
"loss": 9.4334, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.013828867761452032, |
|
"eval_loss": 13.031184196472168, |
|
"eval_runtime": 2.0634, |
|
"eval_samples_per_second": 24.232, |
|
"eval_steps_per_second": 6.3, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.027657735522904063, |
|
"grad_norm": 25.992443084716797, |
|
"learning_rate": 0.0001, |
|
"loss": 11.5136, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04148660328435609, |
|
"grad_norm": 26.536561965942383, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 11.5422, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.055315471045808126, |
|
"grad_norm": 22.68117332458496, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 7.9708, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.06914433880726016, |
|
"grad_norm": 15.717791557312012, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 5.5858, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08297320656871218, |
|
"grad_norm": 9.368117332458496, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 3.687, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.09680207433016422, |
|
"grad_norm": 8.37127685546875, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 2.4233, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.11063094209161625, |
|
"grad_norm": 7.063530921936035, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 1.8125, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.12445980985306827, |
|
"grad_norm": 13.158529281616211, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 1.5912, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.13828867761452032, |
|
"grad_norm": 7.418514728546143, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 1.1176, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.15211754537597233, |
|
"grad_norm": 5.905298709869385, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.9247, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.16594641313742436, |
|
"grad_norm": 6.375161647796631, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.9905, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.1797752808988764, |
|
"grad_norm": 9.64967155456543, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 1.3429, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.19360414866032843, |
|
"grad_norm": 6.708484649658203, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.8378, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.20743301642178047, |
|
"grad_norm": 5.0837721824646, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.813, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.2212618841832325, |
|
"grad_norm": 3.983884572982788, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.7614, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.23509075194468454, |
|
"grad_norm": 3.8480591773986816, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.7761, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.24891961970613655, |
|
"grad_norm": 2.0242066383361816, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.5253, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.2627484874675886, |
|
"grad_norm": 3.126269817352295, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.6853, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.27657735522904064, |
|
"grad_norm": 2.6231629848480225, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.609, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2904062229904927, |
|
"grad_norm": 3.5714855194091797, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.7105, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.30423509075194466, |
|
"grad_norm": 3.146742105484009, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.6799, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.3180639585133967, |
|
"grad_norm": 4.249228477478027, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.651, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.33189282627484873, |
|
"grad_norm": 2.8550667762756348, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.5604, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.34572169403630076, |
|
"grad_norm": 3.0469322204589844, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.8102, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.34572169403630076, |
|
"eval_loss": 0.758933961391449, |
|
"eval_runtime": 2.0684, |
|
"eval_samples_per_second": 24.173, |
|
"eval_steps_per_second": 6.285, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.3595505617977528, |
|
"grad_norm": 3.900346040725708, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.6268, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.37337942955920483, |
|
"grad_norm": 1.8691695928573608, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.5065, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.38720829732065687, |
|
"grad_norm": 2.709653377532959, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.5134, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.4010371650821089, |
|
"grad_norm": 4.127618789672852, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.7177, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.41486603284356094, |
|
"grad_norm": 3.254377841949463, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.6108, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.428694900605013, |
|
"grad_norm": 2.024759292602539, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.4477, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.442523768366465, |
|
"grad_norm": 1.9464025497436523, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.5394, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.45635263612791704, |
|
"grad_norm": 1.8650126457214355, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.4821, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.4701815038893691, |
|
"grad_norm": 1.5287123918533325, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.4385, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.4840103716508211, |
|
"grad_norm": 1.276076078414917, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.4649, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.4978392394122731, |
|
"grad_norm": 1.4761910438537598, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.4801, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.5116681071737251, |
|
"grad_norm": 2.025033950805664, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.6552, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.5254969749351772, |
|
"grad_norm": 1.9071918725967407, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.5439, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.5393258426966292, |
|
"grad_norm": 3.013430118560791, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.4093, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.5531547104580813, |
|
"grad_norm": 2.1112544536590576, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.492, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.5669835782195333, |
|
"grad_norm": 1.9682427644729614, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.4969, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.5808124459809854, |
|
"grad_norm": 2.6426448822021484, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.4845, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.5946413137424373, |
|
"grad_norm": 2.1030192375183105, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.524, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.6084701815038893, |
|
"grad_norm": 1.8651204109191895, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.4401, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.6222990492653414, |
|
"grad_norm": 1.5484836101531982, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.4205, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.6361279170267934, |
|
"grad_norm": 1.8427436351776123, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.4307, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.6499567847882455, |
|
"grad_norm": 1.3399065732955933, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.3673, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.6637856525496975, |
|
"grad_norm": 2.0689697265625, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.5564, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.6776145203111495, |
|
"grad_norm": 1.9621024131774902, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.4653, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.6914433880726015, |
|
"grad_norm": 2.4232048988342285, |
|
"learning_rate": 1e-05, |
|
"loss": 0.7471, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.6914433880726015, |
|
"eval_loss": 0.6049863696098328, |
|
"eval_runtime": 2.0809, |
|
"eval_samples_per_second": 24.028, |
|
"eval_steps_per_second": 6.247, |
|
"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": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.62480894509056e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|