| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.15854141894569956, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007927070947284979, | |
| "eval_loss": 3.7623255252838135, | |
| "eval_runtime": 41.5223, | |
| "eval_samples_per_second": 12.812, | |
| "eval_steps_per_second": 6.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003963535473642489, | |
| "grad_norm": 39.19902038574219, | |
| "learning_rate": 5e-05, | |
| "loss": 14.2935, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007927070947284977, | |
| "grad_norm": 27.3358211517334, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8879, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011890606420927468, | |
| "grad_norm": 23.061885833740234, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 8.0259, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015854141894569955, | |
| "grad_norm": 31.14210319519043, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 6.9435, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019817677368212445, | |
| "grad_norm": 20.775039672851562, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 5.8112, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023781212841854936, | |
| "grad_norm": 17.643301010131836, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 5.784, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027744748315497423, | |
| "grad_norm": 22.302579879760742, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 5.4925, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03170828378913991, | |
| "grad_norm": 25.157142639160156, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 5.9852, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0356718192627824, | |
| "grad_norm": 17.76531219482422, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 5.5636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03963535473642489, | |
| "grad_norm": 28.448684692382812, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 5.6841, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03963535473642489, | |
| "eval_loss": 1.5165091753005981, | |
| "eval_runtime": 42.3073, | |
| "eval_samples_per_second": 12.575, | |
| "eval_steps_per_second": 6.287, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04359889021006738, | |
| "grad_norm": 15.901643753051758, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 6.0645, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04756242568370987, | |
| "grad_norm": 20.770709991455078, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 6.8659, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.051525961157352355, | |
| "grad_norm": 18.326112747192383, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 6.2574, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.055489496630994846, | |
| "grad_norm": 17.24193572998047, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 6.4748, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.059453032104637336, | |
| "grad_norm": 16.379873275756836, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 5.573, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06341656757827982, | |
| "grad_norm": 18.181900024414062, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 5.2359, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06738010305192231, | |
| "grad_norm": 16.709672927856445, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 5.7389, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0713436385255648, | |
| "grad_norm": 28.632057189941406, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 5.71, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07530717399920729, | |
| "grad_norm": 15.14612865447998, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 6.2396, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.07927070947284978, | |
| "grad_norm": 29.513324737548828, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 5.8555, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07927070947284978, | |
| "eval_loss": 1.454555630683899, | |
| "eval_runtime": 42.3314, | |
| "eval_samples_per_second": 12.568, | |
| "eval_steps_per_second": 6.284, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08323424494649227, | |
| "grad_norm": 19.355466842651367, | |
| "learning_rate": 5e-05, | |
| "loss": 5.965, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.08719778042013476, | |
| "grad_norm": 14.849666595458984, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 5.7417, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09116131589377725, | |
| "grad_norm": 18.657487869262695, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 5.9853, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.09512485136741974, | |
| "grad_norm": 19.843090057373047, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 5.9984, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09908838684106223, | |
| "grad_norm": 15.069567680358887, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 5.627, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.10305192231470471, | |
| "grad_norm": 13.904682159423828, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 5.1518, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1070154577883472, | |
| "grad_norm": 22.92823028564453, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 5.2211, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.11097899326198969, | |
| "grad_norm": 13.987442970275879, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 5.6965, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11494252873563218, | |
| "grad_norm": 15.198968887329102, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 5.6406, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.11890606420927467, | |
| "grad_norm": 19.313316345214844, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 5.307, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11890606420927467, | |
| "eval_loss": 1.4315520524978638, | |
| "eval_runtime": 42.3414, | |
| "eval_samples_per_second": 12.565, | |
| "eval_steps_per_second": 6.282, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12286959968291716, | |
| "grad_norm": 20.973207473754883, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 6.839, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.12683313515655964, | |
| "grad_norm": 21.357858657836914, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 6.7168, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13079667063020214, | |
| "grad_norm": 19.783832550048828, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 5.2595, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.13476020610384462, | |
| "grad_norm": 15.336380958557129, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 5.8644, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.13872374157748713, | |
| "grad_norm": 17.998332977294922, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 5.7488, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1426872770511296, | |
| "grad_norm": 15.746088027954102, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 5.5037, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1466508125247721, | |
| "grad_norm": 15.05075454711914, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 4.6136, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.15061434799841458, | |
| "grad_norm": 13.235702514648438, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 4.7946, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1545778834720571, | |
| "grad_norm": 17.659814834594727, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 6.2826, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.15854141894569956, | |
| "grad_norm": 15.750090599060059, | |
| "learning_rate": 0.0, | |
| "loss": 5.5645, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15854141894569956, | |
| "eval_loss": 1.4222187995910645, | |
| "eval_runtime": 42.3561, | |
| "eval_samples_per_second": 12.56, | |
| "eval_steps_per_second": 6.28, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.045732539511603e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |