| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027785495971103084, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001389274798555154, | |
| "eval_loss": 2.472825765609741, | |
| "eval_runtime": 288.4466, | |
| "eval_samples_per_second": 10.508, | |
| "eval_steps_per_second": 5.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006946373992775772, | |
| "grad_norm": 0.7895943522453308, | |
| "learning_rate": 5e-05, | |
| "loss": 6.3296, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013892747985551543, | |
| "grad_norm": 1.3175629377365112, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020839121978327314, | |
| "grad_norm": 1.6610268354415894, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 8.5633, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027785495971103086, | |
| "grad_norm": 1.8091799020767212, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 7.7043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034731869963878855, | |
| "grad_norm": 2.3642632961273193, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 7.5649, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004167824395665463, | |
| "grad_norm": 2.7922849655151367, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 6.599, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0048624617949430396, | |
| "grad_norm": 3.5944840908050537, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 7.3915, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005557099194220617, | |
| "grad_norm": 4.525637149810791, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 8.0343, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006251736593498194, | |
| "grad_norm": 6.427048683166504, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 8.2018, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006946373992775771, | |
| "grad_norm": 9.417752265930176, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 7.8271, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006946373992775771, | |
| "eval_loss": 1.688758373260498, | |
| "eval_runtime": 290.1662, | |
| "eval_samples_per_second": 10.446, | |
| "eval_steps_per_second": 5.225, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007641011392053348, | |
| "grad_norm": 2.2982845306396484, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 4.8406, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.008335648791330925, | |
| "grad_norm": 1.8996556997299194, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 5.3847, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009030286190608503, | |
| "grad_norm": 1.6495345830917358, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 5.992, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.009724923589886079, | |
| "grad_norm": 2.2762582302093506, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 6.4391, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010419560989163657, | |
| "grad_norm": 1.997231364250183, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 6.304, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011114198388441235, | |
| "grad_norm": 2.5489630699157715, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 6.3471, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01180883578771881, | |
| "grad_norm": 4.514221668243408, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 6.3654, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.012503473186996388, | |
| "grad_norm": 6.375067234039307, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 6.3578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.013198110586273964, | |
| "grad_norm": 10.424362182617188, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 6.8525, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.013892747985551542, | |
| "grad_norm": 8.787095069885254, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 6.9822, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013892747985551542, | |
| "eval_loss": 1.5637677907943726, | |
| "eval_runtime": 290.3574, | |
| "eval_samples_per_second": 10.439, | |
| "eval_steps_per_second": 5.221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01458738538482912, | |
| "grad_norm": 1.920885443687439, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4138, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.015282022784106696, | |
| "grad_norm": 1.7754857540130615, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 4.7733, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.015976660183384273, | |
| "grad_norm": 2.1266419887542725, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 5.9913, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.01667129758266185, | |
| "grad_norm": 2.144942045211792, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 6.1769, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01736593498193943, | |
| "grad_norm": 2.360759973526001, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 6.0735, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.018060572381217006, | |
| "grad_norm": 2.8511805534362793, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 6.0674, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01875520978049458, | |
| "grad_norm": 3.699951410293579, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 7.084, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.019449847179772158, | |
| "grad_norm": 6.2040557861328125, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 6.0296, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.020144484579049736, | |
| "grad_norm": 6.199789047241211, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 6.3335, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.020839121978327314, | |
| "grad_norm": 12.588438034057617, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 6.7239, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.020839121978327314, | |
| "eval_loss": 1.5134177207946777, | |
| "eval_runtime": 290.0025, | |
| "eval_samples_per_second": 10.452, | |
| "eval_steps_per_second": 5.228, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02153375937760489, | |
| "grad_norm": 1.827096939086914, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 4.103, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.02222839677688247, | |
| "grad_norm": 1.7426300048828125, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 4.4376, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.022923034176160043, | |
| "grad_norm": 1.9147125482559204, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 5.1879, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.02361767157543762, | |
| "grad_norm": 2.1786575317382812, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 6.0528, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0243123089747152, | |
| "grad_norm": 3.0548410415649414, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 5.7481, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.025006946373992776, | |
| "grad_norm": 2.6999576091766357, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 6.2866, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.025701583773270354, | |
| "grad_norm": 4.492112636566162, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 5.8095, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.02639622117254793, | |
| "grad_norm": 4.557647228240967, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 6.2617, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.027090858571825506, | |
| "grad_norm": 7.8843584060668945, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 6.8044, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.027785495971103084, | |
| "grad_norm": 8.694259643554688, | |
| "learning_rate": 0.0, | |
| "loss": 7.3994, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.027785495971103084, | |
| "eval_loss": 1.5116981267929077, | |
| "eval_runtime": 290.4363, | |
| "eval_samples_per_second": 10.436, | |
| "eval_steps_per_second": 5.22, | |
| "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": 6.719421228993331e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |