| { |
| "best_metric": 1.0403923988342285, |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", |
| "epoch": 0.847457627118644, |
| "eval_steps": 50, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01694915254237288, |
| "grad_norm": 0.9787123203277588, |
| "learning_rate": 1e-05, |
| "loss": 3.0209, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01694915254237288, |
| "eval_loss": 4.1999897956848145, |
| "eval_runtime": 1.4503, |
| "eval_samples_per_second": 68.951, |
| "eval_steps_per_second": 17.238, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03389830508474576, |
| "grad_norm": 2.4502038955688477, |
| "learning_rate": 2e-05, |
| "loss": 4.4497, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05084745762711865, |
| "grad_norm": 2.665430784225464, |
| "learning_rate": 3e-05, |
| "loss": 4.639, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06779661016949153, |
| "grad_norm": 2.4935710430145264, |
| "learning_rate": 4e-05, |
| "loss": 4.4997, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0847457627118644, |
| "grad_norm": 2.3885178565979004, |
| "learning_rate": 5e-05, |
| "loss": 4.3788, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1016949152542373, |
| "grad_norm": 2.521230459213257, |
| "learning_rate": 6e-05, |
| "loss": 4.4601, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.11864406779661017, |
| "grad_norm": 2.408069133758545, |
| "learning_rate": 7e-05, |
| "loss": 4.3255, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.13559322033898305, |
| "grad_norm": 1.1387848854064941, |
| "learning_rate": 8e-05, |
| "loss": 3.355, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.15254237288135594, |
| "grad_norm": 1.0923254489898682, |
| "learning_rate": 9e-05, |
| "loss": 3.0777, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.1694915254237288, |
| "grad_norm": 1.489324688911438, |
| "learning_rate": 0.0001, |
| "loss": 3.4978, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1864406779661017, |
| "grad_norm": 1.415766716003418, |
| "learning_rate": 9.999115304121457e-05, |
| "loss": 3.4619, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.2033898305084746, |
| "grad_norm": 1.4508241415023804, |
| "learning_rate": 9.996461529560553e-05, |
| "loss": 3.2672, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.22033898305084745, |
| "grad_norm": 1.6372668743133545, |
| "learning_rate": 9.992039615430648e-05, |
| "loss": 3.3624, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.23728813559322035, |
| "grad_norm": 2.086595296859741, |
| "learning_rate": 9.985851126551428e-05, |
| "loss": 3.8379, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.2542372881355932, |
| "grad_norm": 1.075448751449585, |
| "learning_rate": 9.977898252895134e-05, |
| "loss": 2.6479, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2711864406779661, |
| "grad_norm": 2.2425975799560547, |
| "learning_rate": 9.968183808811586e-05, |
| "loss": 2.9848, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.288135593220339, |
| "grad_norm": 2.2366819381713867, |
| "learning_rate": 9.95671123203224e-05, |
| "loss": 2.818, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.3050847457627119, |
| "grad_norm": 2.1117076873779297, |
| "learning_rate": 9.943484582453653e-05, |
| "loss": 2.6075, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.3220338983050847, |
| "grad_norm": 2.0897672176361084, |
| "learning_rate": 9.928508540700774e-05, |
| "loss": 2.5123, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.3389830508474576, |
| "grad_norm": 1.8737945556640625, |
| "learning_rate": 9.911788406470569e-05, |
| "loss": 2.3475, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3559322033898305, |
| "grad_norm": 1.7135223150253296, |
| "learning_rate": 9.893330096656574e-05, |
| "loss": 2.2067, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.3728813559322034, |
| "grad_norm": 0.705153226852417, |
| "learning_rate": 9.873140143255036e-05, |
| "loss": 2.1873, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.3898305084745763, |
| "grad_norm": 0.7329670190811157, |
| "learning_rate": 9.85122569105338e-05, |
| "loss": 2.6215, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.4067796610169492, |
| "grad_norm": 1.136795163154602, |
| "learning_rate": 9.827594495101823e-05, |
| "loss": 2.8488, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.423728813559322, |
| "grad_norm": 1.0769141912460327, |
| "learning_rate": 9.802254917969032e-05, |
| "loss": 2.8395, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4406779661016949, |
| "grad_norm": 1.4403115510940552, |
| "learning_rate": 9.775215926782788e-05, |
| "loss": 2.6802, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.4576271186440678, |
| "grad_norm": 1.4279862642288208, |
| "learning_rate": 9.746487090056713e-05, |
| "loss": 2.7192, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.4745762711864407, |
| "grad_norm": 1.699432611465454, |
| "learning_rate": 9.716078574304189e-05, |
| "loss": 2.8853, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.4915254237288136, |
| "grad_norm": 1.4521034955978394, |
| "learning_rate": 9.684001140440639e-05, |
| "loss": 1.9164, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.5084745762711864, |
| "grad_norm": 2.434119939804077, |
| "learning_rate": 9.650266139975474e-05, |
| "loss": 1.3542, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5254237288135594, |
| "grad_norm": 1.6792948246002197, |
| "learning_rate": 9.614885510995047e-05, |
| "loss": 1.3436, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.5423728813559322, |
| "grad_norm": 1.6474392414093018, |
| "learning_rate": 9.577871773938011e-05, |
| "loss": 1.1094, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.559322033898305, |
| "grad_norm": 1.6065335273742676, |
| "learning_rate": 9.539238027164619e-05, |
| "loss": 0.9116, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.576271186440678, |
| "grad_norm": 1.514753818511963, |
| "learning_rate": 9.498997942321483e-05, |
| "loss": 0.8389, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.5932203389830508, |
| "grad_norm": 1.2533358335494995, |
| "learning_rate": 9.457165759503493e-05, |
| "loss": 0.9727, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.6101694915254238, |
| "grad_norm": 0.8802417516708374, |
| "learning_rate": 9.413756282214537e-05, |
| "loss": 1.7009, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6271186440677966, |
| "grad_norm": 1.1750346422195435, |
| "learning_rate": 9.368784872128878e-05, |
| "loss": 2.5651, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.6440677966101694, |
| "grad_norm": 1.331346035003662, |
| "learning_rate": 9.322267443654972e-05, |
| "loss": 2.5368, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.6610169491525424, |
| "grad_norm": 1.1209417581558228, |
| "learning_rate": 9.274220458303727e-05, |
| "loss": 2.8612, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.6779661016949152, |
| "grad_norm": 1.2335385084152222, |
| "learning_rate": 9.224660918863104e-05, |
| "loss": 2.6824, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6949152542372882, |
| "grad_norm": 1.1797600984573364, |
| "learning_rate": 9.173606363381219e-05, |
| "loss": 2.4775, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.711864406779661, |
| "grad_norm": 1.6770628690719604, |
| "learning_rate": 9.121074858959997e-05, |
| "loss": 2.7293, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.7288135593220338, |
| "grad_norm": 1.0169050693511963, |
| "learning_rate": 9.067084995361623e-05, |
| "loss": 1.3915, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.7457627118644068, |
| "grad_norm": 1.1066895723342896, |
| "learning_rate": 9.011655878430019e-05, |
| "loss": 0.5636, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.7627118644067796, |
| "grad_norm": 0.9063847661018372, |
| "learning_rate": 8.954807123329704e-05, |
| "loss": 0.1767, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.7796610169491526, |
| "grad_norm": 0.5006846189498901, |
| "learning_rate": 8.896558847604414e-05, |
| "loss": 0.3629, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.7966101694915254, |
| "grad_norm": 0.42200618982315063, |
| "learning_rate": 8.836931664057935e-05, |
| "loss": 0.2745, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.8135593220338984, |
| "grad_norm": 0.3802186846733093, |
| "learning_rate": 8.775946673459681e-05, |
| "loss": 0.1882, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.8305084745762712, |
| "grad_norm": 0.3861039876937866, |
| "learning_rate": 8.713625457077585e-05, |
| "loss": 0.4487, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.847457627118644, |
| "grad_norm": 0.9502959847450256, |
| "learning_rate": 8.649990069040961e-05, |
| "loss": 2.1698, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.847457627118644, |
| "eval_loss": 1.0403923988342285, |
| "eval_runtime": 1.442, |
| "eval_samples_per_second": 69.349, |
| "eval_steps_per_second": 17.337, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 177, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1236088022630400.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
