| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.99302649930265, |
| "eval_steps": 23, |
| "global_step": 89, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 1.9032, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01, |
| "eval_loss": 1.8872443437576294, |
| "eval_runtime": 104.0076, |
| "eval_samples_per_second": 2.356, |
| "eval_steps_per_second": 1.183, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 1.9503, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 3e-06, |
| "loss": 1.8157, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.8814, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 5e-06, |
| "loss": 1.911, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 6e-06, |
| "loss": 1.8465, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 7e-06, |
| "loss": 1.937, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.9307, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 9e-06, |
| "loss": 1.8564, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 1e-05, |
| "loss": 1.904, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 9.999125804563732e-06, |
| "loss": 1.8991, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 9.996503523941994e-06, |
| "loss": 1.8563, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 9.992134075089085e-06, |
| "loss": 1.8044, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 9.986018985905901e-06, |
| "loss": 1.9173, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 9.978160394705669e-06, |
| "loss": 1.8906, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 9.968561049466214e-06, |
| "loss": 1.7627, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 9.957224306869053e-06, |
| "loss": 1.7209, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 1.8672, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 9.92935509259118e-06, |
| "loss": 1.8284, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 9.912832366166443e-06, |
| "loss": 1.8192, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 9.894591729488243e-06, |
| "loss": 1.7384, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 9.874639560909118e-06, |
| "loss": 1.8564, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 9.852982837266955e-06, |
| "loss": 1.8967, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.26, |
| "eval_loss": 1.8201656341552734, |
| "eval_runtime": 103.8038, |
| "eval_samples_per_second": 2.36, |
| "eval_steps_per_second": 1.185, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 9.829629131445342e-06, |
| "loss": 1.7113, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 9.804586609725499e-06, |
| "loss": 1.8199, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 9.777864028930705e-06, |
| "loss": 1.807, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 9.749470733364231e-06, |
| "loss": 1.7798, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 9.719416651541839e-06, |
| "loss": 1.7689, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 9.687712292719997e-06, |
| "loss": 1.7591, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 9.654368743221022e-06, |
| "loss": 1.7925, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 9.619397662556434e-06, |
| "loss": 1.753, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 9.582811279349881e-06, |
| "loss": 1.7839, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 9.544622387061055e-06, |
| "loss": 1.8029, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 9.504844339512096e-06, |
| "loss": 1.7641, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 9.463491046218058e-06, |
| "loss": 1.8029, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 9.420576967523049e-06, |
| "loss": 1.939, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 9.376117109543769e-06, |
| "loss": 2.0005, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 1.7393, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 9.282622777389258e-06, |
| "loss": 1.7763, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 9.233620996141421e-06, |
| "loss": 1.7835, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 9.1831388100321e-06, |
| "loss": 1.7128, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 9.131193871579975e-06, |
| "loss": 1.7393, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 9.077804344796302e-06, |
| "loss": 1.8303, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 9.022988898833342e-06, |
| "loss": 1.7212, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 8.966766701456177e-06, |
| "loss": 1.798, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 8.90915741234015e-06, |
| "loss": 1.7046, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.51, |
| "eval_loss": 1.7941572666168213, |
| "eval_runtime": 103.6987, |
| "eval_samples_per_second": 2.363, |
| "eval_steps_per_second": 1.186, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 8.850181176196316e-06, |
| "loss": 1.8044, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 8.789858615727266e-06, |
| "loss": 1.8393, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 8.728210824415829e-06, |
| "loss": 1.8268, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 8.665259359149132e-06, |
| "loss": 1.7932, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 8.601026232680634e-06, |
| "loss": 1.8526, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 8.535533905932739e-06, |
| "loss": 1.7844, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 8.46880528014271e-06, |
| "loss": 1.7712, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 8.400863688854598e-06, |
| "loss": 1.8715, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 8.331732889760021e-06, |
| "loss": 1.6952, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 8.261437056390607e-06, |
| "loss": 1.802, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 8.190000769665044e-06, |
| "loss": 1.7953, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 1.6147, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 8.043807145043604e-06, |
| "loss": 1.6873, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 7.969100927867508e-06, |
| "loss": 1.7806, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 7.89335648089903e-06, |
| "loss": 1.7586, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 7.81660029031811e-06, |
| "loss": 1.6867, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 7.738859196089358e-06, |
| "loss": 1.6218, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 7.660160382576683e-06, |
| "loss": 1.8595, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 7.580531369037534e-06, |
| "loss": 1.7955, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 1.7399, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 7.4185944355261996e-06, |
| "loss": 1.793, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 7.336343141365311e-06, |
| "loss": 1.6875, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 7.253274878999728e-06, |
| "loss": 1.7318, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.77, |
| "eval_loss": 1.784773349761963, |
| "eval_runtime": 103.7559, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 1.185, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 7.169418695587791e-06, |
| "loss": 1.543, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 7.084803913806642e-06, |
| "loss": 1.7971, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 6.999460121598704e-06, |
| "loss": 1.7076, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 6.913417161825449e-06, |
| "loss": 1.6304, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 6.8267051218319766e-06, |
| "loss": 1.6569, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 6.739354322926136e-06, |
| "loss": 1.6308, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 6.651395309775837e-06, |
| "loss": 1.6361, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 6.562858839728224e-06, |
| "loss": 1.8096, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 6.473775872054522e-06, |
| "loss": 1.7652, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 6.384177557124247e-06, |
| "loss": 1.971, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 6.294095225512604e-06, |
| "loss": 1.9038, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 6.2035603770448664e-06, |
| "loss": 1.5964, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 6.112604669781572e-06, |
| "loss": 1.7846, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 6.0212599089484026e-06, |
| "loss": 1.7502, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 5.929558035814574e-06, |
| "loss": 1.7273, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 5.837531116523683e-06, |
| "loss": 1.8532, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 5.745211330880872e-06, |
| "loss": 1.518, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 5.65263096110026e-06, |
| "loss": 1.6235, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 5.559822380516539e-06, |
| "loss": 1.9637, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 5.466818042264754e-06, |
| "loss": 1.9624, |
| "step": 89 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 178, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 89, |
| "total_flos": 7.632140301049528e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
