{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 4.878048780487805, | |
"eval_steps": 500, | |
"global_step": 100, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.05, | |
"learning_rate": 0.0, | |
"loss": 1.9127, | |
"step": 1 | |
}, | |
{ | |
"epoch": 0.1, | |
"learning_rate": 0.0003, | |
"loss": 1.6223, | |
"step": 2 | |
}, | |
{ | |
"epoch": 0.15, | |
"learning_rate": 0.0003, | |
"loss": 1.7017, | |
"step": 3 | |
}, | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.0003, | |
"loss": 1.5725, | |
"step": 4 | |
}, | |
{ | |
"epoch": 0.24, | |
"learning_rate": 0.0003, | |
"loss": 1.3237, | |
"step": 5 | |
}, | |
{ | |
"epoch": 0.29, | |
"learning_rate": 0.0003, | |
"loss": 1.6277, | |
"step": 6 | |
}, | |
{ | |
"epoch": 0.34, | |
"learning_rate": 0.0003, | |
"loss": 1.4285, | |
"step": 7 | |
}, | |
{ | |
"epoch": 0.39, | |
"learning_rate": 0.0003, | |
"loss": 1.6318, | |
"step": 8 | |
}, | |
{ | |
"epoch": 0.44, | |
"learning_rate": 0.0003, | |
"loss": 1.4886, | |
"step": 9 | |
}, | |
{ | |
"epoch": 0.49, | |
"learning_rate": 0.0003, | |
"loss": 1.6511, | |
"step": 10 | |
}, | |
{ | |
"epoch": 0.54, | |
"learning_rate": 0.0003, | |
"loss": 1.5332, | |
"step": 11 | |
}, | |
{ | |
"epoch": 0.59, | |
"learning_rate": 0.0003, | |
"loss": 0.9434, | |
"step": 12 | |
}, | |
{ | |
"epoch": 0.63, | |
"learning_rate": 0.0003, | |
"loss": 1.2452, | |
"step": 13 | |
}, | |
{ | |
"epoch": 0.68, | |
"learning_rate": 0.0003, | |
"loss": 1.1687, | |
"step": 14 | |
}, | |
{ | |
"epoch": 0.73, | |
"learning_rate": 0.0003, | |
"loss": 1.108, | |
"step": 15 | |
}, | |
{ | |
"epoch": 0.78, | |
"learning_rate": 0.0003, | |
"loss": 1.1153, | |
"step": 16 | |
}, | |
{ | |
"epoch": 0.83, | |
"learning_rate": 0.0003, | |
"loss": 1.1613, | |
"step": 17 | |
}, | |
{ | |
"epoch": 0.88, | |
"learning_rate": 0.0003, | |
"loss": 1.1092, | |
"step": 18 | |
}, | |
{ | |
"epoch": 0.93, | |
"learning_rate": 0.0003, | |
"loss": 1.1527, | |
"step": 19 | |
}, | |
{ | |
"epoch": 0.98, | |
"learning_rate": 0.0003, | |
"loss": 1.2231, | |
"step": 20 | |
}, | |
{ | |
"epoch": 1.02, | |
"learning_rate": 0.0003, | |
"loss": 0.9448, | |
"step": 21 | |
}, | |
{ | |
"epoch": 1.07, | |
"learning_rate": 0.0003, | |
"loss": 1.1813, | |
"step": 22 | |
}, | |
{ | |
"epoch": 1.12, | |
"learning_rate": 0.0003, | |
"loss": 1.187, | |
"step": 23 | |
}, | |
{ | |
"epoch": 1.17, | |
"learning_rate": 0.0003, | |
"loss": 0.8751, | |
"step": 24 | |
}, | |
{ | |
"epoch": 1.22, | |
"learning_rate": 0.0003, | |
"loss": 0.8133, | |
"step": 25 | |
}, | |
{ | |
"epoch": 1.27, | |
"learning_rate": 0.0003, | |
"loss": 0.736, | |
"step": 26 | |
}, | |
{ | |
"epoch": 1.32, | |
"learning_rate": 0.0003, | |
"loss": 0.9983, | |
"step": 27 | |
}, | |
{ | |
"epoch": 1.37, | |
"learning_rate": 0.0003, | |
"loss": 0.9744, | |
"step": 28 | |
}, | |
{ | |
"epoch": 1.41, | |
"learning_rate": 0.0003, | |
"loss": 0.828, | |
"step": 29 | |
}, | |
{ | |
"epoch": 1.46, | |
"learning_rate": 0.0003, | |
"loss": 0.9366, | |
"step": 30 | |
}, | |
{ | |
"epoch": 1.51, | |
"learning_rate": 0.0003, | |
"loss": 0.7095, | |
"step": 31 | |
}, | |
{ | |
"epoch": 1.56, | |
"learning_rate": 0.0003, | |
"loss": 0.6713, | |
"step": 32 | |
}, | |
{ | |
"epoch": 1.61, | |
"learning_rate": 0.0003, | |
"loss": 0.5446, | |
"step": 33 | |
}, | |
{ | |
"epoch": 1.66, | |
"learning_rate": 0.0003, | |
"loss": 0.679, | |
"step": 34 | |
}, | |
{ | |
"epoch": 1.71, | |
"learning_rate": 0.0003, | |
"loss": 0.9321, | |
"step": 35 | |
}, | |
{ | |
"epoch": 1.76, | |
"learning_rate": 0.0003, | |
"loss": 0.6742, | |
"step": 36 | |
}, | |
{ | |
"epoch": 1.8, | |
"learning_rate": 0.0003, | |
"loss": 0.6489, | |
"step": 37 | |
}, | |
{ | |
"epoch": 1.85, | |
"learning_rate": 0.0003, | |
"loss": 0.5977, | |
"step": 38 | |
}, | |
{ | |
"epoch": 1.9, | |
"learning_rate": 0.0003, | |
"loss": 0.5707, | |
"step": 39 | |
}, | |
{ | |
"epoch": 1.95, | |
"learning_rate": 0.0003, | |
"loss": 0.5331, | |
"step": 40 | |
}, | |
{ | |
"epoch": 2.0, | |
"learning_rate": 0.0003, | |
"loss": 0.8341, | |
"step": 41 | |
}, | |
{ | |
"epoch": 2.05, | |
"learning_rate": 0.0003, | |
"loss": 0.5085, | |
"step": 42 | |
}, | |
{ | |
"epoch": 2.1, | |
"learning_rate": 0.0003, | |
"loss": 0.4151, | |
"step": 43 | |
}, | |
{ | |
"epoch": 2.15, | |
"learning_rate": 0.0003, | |
"loss": 0.403, | |
"step": 44 | |
}, | |
{ | |
"epoch": 2.2, | |
"learning_rate": 0.0003, | |
"loss": 0.5118, | |
"step": 45 | |
}, | |
{ | |
"epoch": 2.24, | |
"learning_rate": 0.0003, | |
"loss": 0.6122, | |
"step": 46 | |
}, | |
{ | |
"epoch": 2.29, | |
"learning_rate": 0.0003, | |
"loss": 0.6884, | |
"step": 47 | |
}, | |
{ | |
"epoch": 2.34, | |
"learning_rate": 0.0003, | |
"loss": 0.3991, | |
"step": 48 | |
}, | |
{ | |
"epoch": 2.39, | |
"learning_rate": 0.0003, | |
"loss": 0.3691, | |
"step": 49 | |
}, | |
{ | |
"epoch": 2.44, | |
"learning_rate": 0.0003, | |
"loss": 0.3823, | |
"step": 50 | |
}, | |
{ | |
"epoch": 2.49, | |
"learning_rate": 0.0003, | |
"loss": 0.4922, | |
"step": 51 | |
}, | |
{ | |
"epoch": 2.54, | |
"learning_rate": 0.0003, | |
"loss": 0.3043, | |
"step": 52 | |
}, | |
{ | |
"epoch": 2.59, | |
"learning_rate": 0.0003, | |
"loss": 0.3247, | |
"step": 53 | |
}, | |
{ | |
"epoch": 2.63, | |
"learning_rate": 0.0003, | |
"loss": 0.3904, | |
"step": 54 | |
}, | |
{ | |
"epoch": 2.68, | |
"learning_rate": 0.0003, | |
"loss": 0.5179, | |
"step": 55 | |
}, | |
{ | |
"epoch": 2.73, | |
"learning_rate": 0.0003, | |
"loss": 0.395, | |
"step": 56 | |
}, | |
{ | |
"epoch": 2.78, | |
"learning_rate": 0.0003, | |
"loss": 0.5595, | |
"step": 57 | |
}, | |
{ | |
"epoch": 2.83, | |
"learning_rate": 0.0003, | |
"loss": 0.5284, | |
"step": 58 | |
}, | |
{ | |
"epoch": 2.88, | |
"learning_rate": 0.0003, | |
"loss": 0.4803, | |
"step": 59 | |
}, | |
{ | |
"epoch": 2.93, | |
"learning_rate": 0.0003, | |
"loss": 0.3198, | |
"step": 60 | |
}, | |
{ | |
"epoch": 2.98, | |
"learning_rate": 0.0003, | |
"loss": 0.2737, | |
"step": 61 | |
}, | |
{ | |
"epoch": 3.02, | |
"learning_rate": 0.0003, | |
"loss": 0.241, | |
"step": 62 | |
}, | |
{ | |
"epoch": 3.07, | |
"learning_rate": 0.0003, | |
"loss": 0.4295, | |
"step": 63 | |
}, | |
{ | |
"epoch": 3.12, | |
"learning_rate": 0.0003, | |
"loss": 0.1114, | |
"step": 64 | |
}, | |
{ | |
"epoch": 3.17, | |
"learning_rate": 0.0003, | |
"loss": 0.2759, | |
"step": 65 | |
}, | |
{ | |
"epoch": 3.22, | |
"learning_rate": 0.0003, | |
"loss": 0.2036, | |
"step": 66 | |
}, | |
{ | |
"epoch": 3.27, | |
"learning_rate": 0.0003, | |
"loss": 0.2958, | |
"step": 67 | |
}, | |
{ | |
"epoch": 3.32, | |
"learning_rate": 0.0003, | |
"loss": 0.207, | |
"step": 68 | |
}, | |
{ | |
"epoch": 3.37, | |
"learning_rate": 0.0003, | |
"loss": 0.3716, | |
"step": 69 | |
}, | |
{ | |
"epoch": 3.41, | |
"learning_rate": 0.0003, | |
"loss": 0.2515, | |
"step": 70 | |
}, | |
{ | |
"epoch": 3.46, | |
"learning_rate": 0.0003, | |
"loss": 0.1133, | |
"step": 71 | |
}, | |
{ | |
"epoch": 3.51, | |
"learning_rate": 0.0003, | |
"loss": 0.2211, | |
"step": 72 | |
}, | |
{ | |
"epoch": 3.56, | |
"learning_rate": 0.0003, | |
"loss": 0.2328, | |
"step": 73 | |
}, | |
{ | |
"epoch": 3.61, | |
"learning_rate": 0.0003, | |
"loss": 0.2376, | |
"step": 74 | |
}, | |
{ | |
"epoch": 3.66, | |
"learning_rate": 0.0003, | |
"loss": 0.1928, | |
"step": 75 | |
}, | |
{ | |
"epoch": 3.71, | |
"learning_rate": 0.0003, | |
"loss": 0.2285, | |
"step": 76 | |
}, | |
{ | |
"epoch": 3.76, | |
"learning_rate": 0.0003, | |
"loss": 0.2829, | |
"step": 77 | |
}, | |
{ | |
"epoch": 3.8, | |
"learning_rate": 0.0003, | |
"loss": 0.2565, | |
"step": 78 | |
}, | |
{ | |
"epoch": 3.85, | |
"learning_rate": 0.0003, | |
"loss": 0.3561, | |
"step": 79 | |
}, | |
{ | |
"epoch": 3.9, | |
"learning_rate": 0.0003, | |
"loss": 0.27, | |
"step": 80 | |
}, | |
{ | |
"epoch": 3.95, | |
"learning_rate": 0.0003, | |
"loss": 0.1845, | |
"step": 81 | |
}, | |
{ | |
"epoch": 4.0, | |
"learning_rate": 0.0003, | |
"loss": 0.1198, | |
"step": 82 | |
}, | |
{ | |
"epoch": 4.05, | |
"learning_rate": 0.0003, | |
"loss": 0.0894, | |
"step": 83 | |
}, | |
{ | |
"epoch": 4.1, | |
"learning_rate": 0.0003, | |
"loss": 0.2383, | |
"step": 84 | |
}, | |
{ | |
"epoch": 4.15, | |
"learning_rate": 0.0003, | |
"loss": 0.1564, | |
"step": 85 | |
}, | |
{ | |
"epoch": 4.2, | |
"learning_rate": 0.0003, | |
"loss": 0.1512, | |
"step": 86 | |
}, | |
{ | |
"epoch": 4.24, | |
"learning_rate": 0.0003, | |
"loss": 0.1242, | |
"step": 87 | |
}, | |
{ | |
"epoch": 4.29, | |
"learning_rate": 0.0003, | |
"loss": 0.1703, | |
"step": 88 | |
}, | |
{ | |
"epoch": 4.34, | |
"learning_rate": 0.0003, | |
"loss": 0.1446, | |
"step": 89 | |
}, | |
{ | |
"epoch": 4.39, | |
"learning_rate": 0.0003, | |
"loss": 0.1159, | |
"step": 90 | |
}, | |
{ | |
"epoch": 4.44, | |
"learning_rate": 0.0003, | |
"loss": 0.1161, | |
"step": 91 | |
}, | |
{ | |
"epoch": 4.49, | |
"learning_rate": 0.0003, | |
"loss": 0.2265, | |
"step": 92 | |
}, | |
{ | |
"epoch": 4.54, | |
"learning_rate": 0.0003, | |
"loss": 0.2019, | |
"step": 93 | |
}, | |
{ | |
"epoch": 4.59, | |
"learning_rate": 0.0003, | |
"loss": 0.1319, | |
"step": 94 | |
}, | |
{ | |
"epoch": 4.63, | |
"learning_rate": 0.0003, | |
"loss": 0.105, | |
"step": 95 | |
}, | |
{ | |
"epoch": 4.68, | |
"learning_rate": 0.0003, | |
"loss": 0.0819, | |
"step": 96 | |
}, | |
{ | |
"epoch": 4.73, | |
"learning_rate": 0.0003, | |
"loss": 0.1048, | |
"step": 97 | |
}, | |
{ | |
"epoch": 4.78, | |
"learning_rate": 0.0003, | |
"loss": 0.1657, | |
"step": 98 | |
}, | |
{ | |
"epoch": 4.83, | |
"learning_rate": 0.0003, | |
"loss": 0.0757, | |
"step": 99 | |
}, | |
{ | |
"epoch": 4.88, | |
"learning_rate": 0.0003, | |
"loss": 0.1793, | |
"step": 100 | |
}, | |
{ | |
"epoch": 4.88, | |
"step": 100, | |
"total_flos": 1.5054799896576e+16, | |
"train_loss": 0.6112891125679016, | |
"train_runtime": 11476.1728, | |
"train_samples_per_second": 0.143, | |
"train_steps_per_second": 0.009 | |
} | |
], | |
"logging_steps": 1.0, | |
"max_steps": 100, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 5, | |
"save_steps": 1000, | |
"total_flos": 1.5054799896576e+16, | |
"train_batch_size": 2, | |
"trial_name": null, | |
"trial_params": null | |
} | |