| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12463000467362517, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "grad_norm": 0.17523826658725739, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9821, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 1.2142947912216187, | |
| "eval_runtime": 1.471, | |
| "eval_samples_per_second": 33.991, | |
| "eval_steps_per_second": 8.838, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 0.16094042360782623, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9898, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 0.15218870341777802, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.0625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 0.14270199835300446, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.1132, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 0.12215384840965271, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.0641, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 0.12544846534729004, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0655, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 0.12683986127376556, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.0796, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 0.1615746170282364, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0755, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 0.2131444662809372, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1313, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 0.26765531301498413, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1033, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 0.3512992858886719, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.1407, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 0.47519487142562866, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.2682, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 0.21195052564144135, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9317, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 0.2161616086959839, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9664, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 0.1996673345565796, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.9741, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 0.17872454226016998, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.9974, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 0.1452234983444214, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9676, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 0.13248209655284882, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.0346, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 0.1325431913137436, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.0321, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 0.13787950575351715, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0155, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 0.16382256150245667, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.0721, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 0.20875383913516998, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.0523, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 0.28410249948501587, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.0444, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 0.3669584393501282, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1593, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 0.5296462774276733, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.2156, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 1.0974667072296143, | |
| "eval_runtime": 1.3184, | |
| "eval_samples_per_second": 37.924, | |
| "eval_steps_per_second": 9.86, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06480760243028509, | |
| "grad_norm": 0.09114177525043488, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.886, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0673002025237576, | |
| "grad_norm": 0.09418703615665436, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.9273, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0697928026172301, | |
| "grad_norm": 0.09414679557085037, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.9459, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0722854027107026, | |
| "grad_norm": 0.10642877221107483, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.9734, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07477800280417511, | |
| "grad_norm": 0.1117902398109436, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.0237, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0772706028976476, | |
| "grad_norm": 0.12783116102218628, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.0062, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07976320299112011, | |
| "grad_norm": 0.13062702119350433, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0148, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08225580308459261, | |
| "grad_norm": 0.14114302396774292, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0211, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08474840317806512, | |
| "grad_norm": 0.15735821425914764, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0175, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08724100327153762, | |
| "grad_norm": 0.19599683582782745, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0264, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08973360336501013, | |
| "grad_norm": 0.2594337463378906, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0313, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09222620345848263, | |
| "grad_norm": 0.35799410939216614, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1004, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09471880355195514, | |
| "grad_norm": 0.09532549232244492, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.8871, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09721140364542763, | |
| "grad_norm": 0.088306725025177, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9009, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09970400373890013, | |
| "grad_norm": 0.08932317048311234, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.9248, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10219660383237264, | |
| "grad_norm": 0.08780187368392944, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.9517, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10468920392584515, | |
| "grad_norm": 0.09193553030490875, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.9641, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10718180401931765, | |
| "grad_norm": 0.10254494100809097, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.9808, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10967440411279016, | |
| "grad_norm": 0.11288368701934814, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.9895, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11216700420626266, | |
| "grad_norm": 0.12878137826919556, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.0026, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11465960429973517, | |
| "grad_norm": 0.15530207753181458, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0257, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11715220439320767, | |
| "grad_norm": 0.17546328902244568, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0257, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11964480448668016, | |
| "grad_norm": 0.22210463881492615, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0215, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 0.2874910533428192, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "grad_norm": 0.4640187621116638, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "eval_loss": 1.064849615097046, | |
| "eval_runtime": 1.4728, | |
| "eval_samples_per_second": 33.95, | |
| "eval_steps_per_second": 8.827, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.0399634261803e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |