| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2079002079002079, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002079002079002079, | |
| "eval_loss": 1.589306116104126, | |
| "eval_runtime": 17.2284, | |
| "eval_samples_per_second": 47.073, | |
| "eval_steps_per_second": 5.92, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006237006237006237, | |
| "grad_norm": 14.470773696899414, | |
| "learning_rate": 1.5e-05, | |
| "loss": 6.2348, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012474012474012475, | |
| "grad_norm": 16.791234970092773, | |
| "learning_rate": 3e-05, | |
| "loss": 6.425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018711018711018712, | |
| "grad_norm": 15.026961326599121, | |
| "learning_rate": 4.5e-05, | |
| "loss": 6.2303, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018711018711018712, | |
| "eval_loss": 1.5716018676757812, | |
| "eval_runtime": 16.8699, | |
| "eval_samples_per_second": 48.074, | |
| "eval_steps_per_second": 6.046, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02494802494802495, | |
| "grad_norm": 16.293886184692383, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 6.2293, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031185031185031187, | |
| "grad_norm": 15.004469871520996, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 6.2384, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037422037422037424, | |
| "grad_norm": 15.824647903442383, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 6.295, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.037422037422037424, | |
| "eval_loss": 1.5255180597305298, | |
| "eval_runtime": 16.9119, | |
| "eval_samples_per_second": 47.955, | |
| "eval_steps_per_second": 6.031, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04365904365904366, | |
| "grad_norm": 14.596535682678223, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 6.0402, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0498960498960499, | |
| "grad_norm": 14.863687515258789, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 6.0821, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.056133056133056136, | |
| "grad_norm": 16.809812545776367, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 5.6924, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.056133056133056136, | |
| "eval_loss": 1.5095850229263306, | |
| "eval_runtime": 16.948, | |
| "eval_samples_per_second": 47.852, | |
| "eval_steps_per_second": 6.018, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.062370062370062374, | |
| "grad_norm": 16.096187591552734, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 5.9183, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06860706860706861, | |
| "grad_norm": 20.93190574645996, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 5.9423, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07484407484407485, | |
| "grad_norm": 13.659626960754395, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 5.8591, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07484407484407485, | |
| "eval_loss": 1.4858307838439941, | |
| "eval_runtime": 16.9606, | |
| "eval_samples_per_second": 47.817, | |
| "eval_steps_per_second": 6.014, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08108108108108109, | |
| "grad_norm": 17.836809158325195, | |
| "learning_rate": 3.824798160583012e-05, | |
| "loss": 5.9271, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08731808731808732, | |
| "grad_norm": 18.114580154418945, | |
| "learning_rate": 3.5959278669726935e-05, | |
| "loss": 5.98, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09355509355509356, | |
| "grad_norm": 14.93269157409668, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 5.7138, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09355509355509356, | |
| "eval_loss": 1.4723652601242065, | |
| "eval_runtime": 17.0031, | |
| "eval_samples_per_second": 47.697, | |
| "eval_steps_per_second": 5.999, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0997920997920998, | |
| "grad_norm": 17.410306930541992, | |
| "learning_rate": 3.104804738999169e-05, | |
| "loss": 5.7513, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10602910602910603, | |
| "grad_norm": 14.01071548461914, | |
| "learning_rate": 2.8479327524001636e-05, | |
| "loss": 5.7436, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.11226611226611227, | |
| "grad_norm": 18.12236976623535, | |
| "learning_rate": 2.587248741756253e-05, | |
| "loss": 5.7549, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11226611226611227, | |
| "eval_loss": 1.4610991477966309, | |
| "eval_runtime": 17.0078, | |
| "eval_samples_per_second": 47.684, | |
| "eval_steps_per_second": 5.997, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11850311850311851, | |
| "grad_norm": 14.946257591247559, | |
| "learning_rate": 2.3256088156396868e-05, | |
| "loss": 5.6165, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.12474012474012475, | |
| "grad_norm": 13.974392890930176, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 5.7818, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13097713097713098, | |
| "grad_norm": 12.578408241271973, | |
| "learning_rate": 1.8109066104575023e-05, | |
| "loss": 5.7894, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.13097713097713098, | |
| "eval_loss": 1.4533125162124634, | |
| "eval_runtime": 16.9995, | |
| "eval_samples_per_second": 47.707, | |
| "eval_steps_per_second": 6.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.13721413721413722, | |
| "grad_norm": 15.311647415161133, | |
| "learning_rate": 1.56348351646022e-05, | |
| "loss": 5.6134, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.14345114345114346, | |
| "grad_norm": 16.411733627319336, | |
| "learning_rate": 1.3263210930352737e-05, | |
| "loss": 5.6947, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1496881496881497, | |
| "grad_norm": 16.464454650878906, | |
| "learning_rate": 1.1020177413231334e-05, | |
| "loss": 5.7208, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1496881496881497, | |
| "eval_loss": 1.4471385478973389, | |
| "eval_runtime": 17.0027, | |
| "eval_samples_per_second": 47.698, | |
| "eval_steps_per_second": 5.999, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.15592515592515593, | |
| "grad_norm": 14.08195972442627, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 5.7267, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 13.681715965270996, | |
| "learning_rate": 7.016504991533726e-06, | |
| "loss": 5.7964, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1683991683991684, | |
| "grad_norm": 14.724468231201172, | |
| "learning_rate": 5.299731159831953e-06, | |
| "loss": 5.689, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.1683991683991684, | |
| "eval_loss": 1.4433274269104004, | |
| "eval_runtime": 17.0342, | |
| "eval_samples_per_second": 47.61, | |
| "eval_steps_per_second": 5.988, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.17463617463617465, | |
| "grad_norm": 18.234542846679688, | |
| "learning_rate": 3.798797596089351e-06, | |
| "loss": 5.7375, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.18087318087318088, | |
| "grad_norm": 15.848942756652832, | |
| "learning_rate": 2.5301488425208296e-06, | |
| "loss": 5.7259, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.18711018711018712, | |
| "grad_norm": 13.509082794189453, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 5.8097, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18711018711018712, | |
| "eval_loss": 1.4427199363708496, | |
| "eval_runtime": 17.0241, | |
| "eval_samples_per_second": 47.638, | |
| "eval_steps_per_second": 5.991, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19334719334719336, | |
| "grad_norm": 15.008647918701172, | |
| "learning_rate": 7.426068431000882e-07, | |
| "loss": 5.7227, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1995841995841996, | |
| "grad_norm": 14.886467933654785, | |
| "learning_rate": 2.4329828146074095e-07, | |
| "loss": 5.7242, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.20582120582120583, | |
| "grad_norm": 12.942763328552246, | |
| "learning_rate": 1.522932452260595e-08, | |
| "loss": 5.7465, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.20582120582120583, | |
| "eval_loss": 1.4416875839233398, | |
| "eval_runtime": 17.0119, | |
| "eval_samples_per_second": 47.672, | |
| "eval_steps_per_second": 5.996, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.41602655830016e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |