| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02345456411158509, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046909128223170175, | |
| "grad_norm": 0.021555056795477867, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00046909128223170175, | |
| "eval_loss": 10.375811576843262, | |
| "eval_runtime": 0.1016, | |
| "eval_samples_per_second": 491.894, | |
| "eval_steps_per_second": 127.893, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009381825644634035, | |
| "grad_norm": 0.021822381764650345, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3759, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014072738466951054, | |
| "grad_norm": 0.020989451557397842, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3756, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001876365128926807, | |
| "grad_norm": 0.018662070855498314, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3757, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002345456411158509, | |
| "grad_norm": 0.01889839768409729, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3743, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002814547693390211, | |
| "grad_norm": 0.017945516854524612, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3749, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032836389756219124, | |
| "grad_norm": 0.019389698281884193, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3745, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003752730257853614, | |
| "grad_norm": 0.018679462373256683, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3746, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004221821540085316, | |
| "grad_norm": 0.019041912630200386, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.374, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004690912822317018, | |
| "grad_norm": 0.01870439387857914, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00516000410454872, | |
| "grad_norm": 0.01823393441736698, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3735, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005629095386780422, | |
| "grad_norm": 0.02004813961684704, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3734, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006098186669012123, | |
| "grad_norm": 0.021872414276003838, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3738, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006567277951243825, | |
| "grad_norm": 0.020817754790186882, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3752, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007036369233475527, | |
| "grad_norm": 0.02583605982363224, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3738, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007505460515707228, | |
| "grad_norm": 0.02163218893110752, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3733, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00797455179793893, | |
| "grad_norm": 0.021959403529763222, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3759, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008443643080170631, | |
| "grad_norm": 0.020150721073150635, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3726, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008912734362402334, | |
| "grad_norm": 0.019531995058059692, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3739, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009381825644634035, | |
| "grad_norm": 0.022027425467967987, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3726, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009850916926865736, | |
| "grad_norm": 0.022007036954164505, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.373, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01032000820909744, | |
| "grad_norm": 0.021248240023851395, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3728, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01078909949132914, | |
| "grad_norm": 0.02485470473766327, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.372, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011258190773560843, | |
| "grad_norm": 0.026103204116225243, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3701, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011727282055792545, | |
| "grad_norm": 0.02261376939713955, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3694, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011727282055792545, | |
| "eval_loss": 10.373571395874023, | |
| "eval_runtime": 0.1011, | |
| "eval_samples_per_second": 494.484, | |
| "eval_steps_per_second": 128.566, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012196373338024246, | |
| "grad_norm": 0.02532474510371685, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3732, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012665464620255949, | |
| "grad_norm": 0.024724390357732773, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3739, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01313455590248765, | |
| "grad_norm": 0.02388211153447628, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3734, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013603647184719351, | |
| "grad_norm": 0.025568397715687752, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3717, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014072738466951054, | |
| "grad_norm": 0.024224581196904182, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3734, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014541829749182755, | |
| "grad_norm": 0.023164361715316772, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3719, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015010921031414456, | |
| "grad_norm": 0.0261879563331604, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3726, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.015480012313646159, | |
| "grad_norm": 0.024106085300445557, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3721, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01594910359587786, | |
| "grad_norm": 0.025720128789544106, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3738, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01641819487810956, | |
| "grad_norm": 0.02623668871819973, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3706, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016887286160341262, | |
| "grad_norm": 0.026861609891057014, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3714, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.017356377442572967, | |
| "grad_norm": 0.028205374255776405, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3704, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.017825468724804668, | |
| "grad_norm": 0.029525011777877808, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3726, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01829456000703637, | |
| "grad_norm": 0.028443878516554832, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3732, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01876365128926807, | |
| "grad_norm": 0.02772536873817444, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3729, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01923274257149977, | |
| "grad_norm": 0.03239374980330467, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019701833853731473, | |
| "grad_norm": 0.029728103429079056, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3728, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020170925135963177, | |
| "grad_norm": 0.0263677965849638, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3729, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02064001641819488, | |
| "grad_norm": 0.028645142912864685, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3708, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02110910770042658, | |
| "grad_norm": 0.03082318603992462, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3732, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02157819898265828, | |
| "grad_norm": 0.02954714372754097, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3724, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.022047290264889982, | |
| "grad_norm": 0.023500103503465652, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3709, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022516381547121687, | |
| "grad_norm": 0.031122390180826187, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.37, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022985472829353388, | |
| "grad_norm": 0.02998553402721882, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3728, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02345456411158509, | |
| "grad_norm": 0.02776142582297325, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02345456411158509, | |
| "eval_loss": 10.372435569763184, | |
| "eval_runtime": 0.112, | |
| "eval_samples_per_second": 446.254, | |
| "eval_steps_per_second": 116.026, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |