| { | |
| "best_metric": 0.5989376306533813, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0638297872340425, | |
| "eval_steps": 25, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 8.839696884155273, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6857, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "eval_loss": 3.0855712890625, | |
| "eval_runtime": 0.5388, | |
| "eval_samples_per_second": 146.629, | |
| "eval_steps_per_second": 18.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 10.66001033782959, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8787, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 7.742804527282715, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 2.4614, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 5.67116117477417, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 2.1595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 4.944119453430176, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 1.6716, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 4.608202934265137, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 1.3835, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 3.0601212978363037, | |
| "learning_rate": 9.475816456775313e-05, | |
| "loss": 1.0948, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 2.5471537113189697, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.8284, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 1.931269884109497, | |
| "learning_rate": 8.9900861364012e-05, | |
| "loss": 0.8407, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 2.042515516281128, | |
| "learning_rate": 8.695044586103296e-05, | |
| "loss": 0.9586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 2.114428758621216, | |
| "learning_rate": 8.368478218232787e-05, | |
| "loss": 0.6138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 2.6110360622406006, | |
| "learning_rate": 8.013173181896283e-05, | |
| "loss": 0.8813, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": 1.4234488010406494, | |
| "learning_rate": 7.63216081438678e-05, | |
| "loss": 0.7682, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1914893617021276, | |
| "grad_norm": 1.7401140928268433, | |
| "learning_rate": 7.228691778882693e-05, | |
| "loss": 0.6967, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 1.493860125541687, | |
| "learning_rate": 6.806208330935766e-05, | |
| "loss": 0.5233, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": 1.8245048522949219, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 0.7296, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4468085106382977, | |
| "grad_norm": 1.2929282188415527, | |
| "learning_rate": 5.918747589082853e-05, | |
| "loss": 0.5208, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5319148936170213, | |
| "grad_norm": 1.2650213241577148, | |
| "learning_rate": 5.4613417973165106e-05, | |
| "loss": 0.529, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6170212765957448, | |
| "grad_norm": 1.466747760772705, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5967, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 1.1956787109375, | |
| "learning_rate": 4.5386582026834906e-05, | |
| "loss": 0.4666, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "grad_norm": 1.869742751121521, | |
| "learning_rate": 4.0812524109171476e-05, | |
| "loss": 0.7583, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.872340425531915, | |
| "grad_norm": 1.5331084728240967, | |
| "learning_rate": 3.631685049639586e-05, | |
| "loss": 0.5254, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9574468085106385, | |
| "grad_norm": 2.150675058364868, | |
| "learning_rate": 3.1937916690642356e-05, | |
| "loss": 0.544, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": 1.9073337316513062, | |
| "learning_rate": 2.771308221117309e-05, | |
| "loss": 0.716, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 1.7541600465774536, | |
| "learning_rate": 2.3678391856132204e-05, | |
| "loss": 0.6128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "eval_loss": 0.5989376306533813, | |
| "eval_runtime": 0.536, | |
| "eval_samples_per_second": 147.401, | |
| "eval_steps_per_second": 18.658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2127659574468086, | |
| "grad_norm": 1.5322821140289307, | |
| "learning_rate": 1.9868268181037185e-05, | |
| "loss": 0.4246, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": 1.5346146821975708, | |
| "learning_rate": 1.631521781767214e-05, | |
| "loss": 0.526, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.382978723404255, | |
| "grad_norm": 1.4425619840621948, | |
| "learning_rate": 1.3049554138967051e-05, | |
| "loss": 0.4616, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.4680851063829787, | |
| "grad_norm": 1.0223990678787231, | |
| "learning_rate": 1.0099138635988026e-05, | |
| "loss": 0.4379, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 1.4977924823760986, | |
| "learning_rate": 7.489143213519301e-06, | |
| "loss": 0.5751, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6382978723404253, | |
| "grad_norm": 1.4635932445526123, | |
| "learning_rate": 5.241835432246889e-06, | |
| "loss": 0.5067, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.723404255319149, | |
| "grad_norm": 1.7609386444091797, | |
| "learning_rate": 3.376388529782215e-06, | |
| "loss": 0.4576, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.8085106382978724, | |
| "grad_norm": 1.5040547847747803, | |
| "learning_rate": 1.908717841359048e-06, | |
| "loss": 0.5874, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.8936170212765955, | |
| "grad_norm": 1.596747875213623, | |
| "learning_rate": 8.513450158049108e-07, | |
| "loss": 0.4815, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 2.097698450088501, | |
| "learning_rate": 2.1329118524827662e-07, | |
| "loss": 0.4825, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0638297872340425, | |
| "grad_norm": 2.1862497329711914, | |
| "learning_rate": 0.0, | |
| "loss": 0.6099, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 2.126166571037491e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |