|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.2723658051689861, |
|
"eval_steps": 500, |
|
"global_step": 100, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0198, |
|
"loss": 0.8181, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0196, |
|
"loss": 0.787, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0194, |
|
"loss": 1.0047, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0192, |
|
"loss": 0.8688, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.019, |
|
"loss": 0.7173, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0188, |
|
"loss": 0.5175, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.018600000000000002, |
|
"loss": 0.7559, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0184, |
|
"loss": 0.9278, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0182, |
|
"loss": 0.6011, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.018000000000000002, |
|
"loss": 0.8014, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0178, |
|
"loss": 1.2581, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0176, |
|
"loss": 0.9886, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0174, |
|
"loss": 0.7866, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0172, |
|
"loss": 0.936, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.017, |
|
"loss": 1.0503, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0168, |
|
"loss": 0.5689, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0166, |
|
"loss": 0.8576, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.016399999999999998, |
|
"loss": 1.0946, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.016200000000000003, |
|
"loss": 0.9075, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.016, |
|
"loss": 1.1441, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0158, |
|
"loss": 0.7794, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.015600000000000001, |
|
"loss": 0.9574, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0154, |
|
"loss": 0.8937, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0152, |
|
"loss": 0.709, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.015, |
|
"loss": 0.8731, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0148, |
|
"loss": 0.719, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0146, |
|
"loss": 0.7419, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0144, |
|
"loss": 0.9224, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.014199999999999999, |
|
"loss": 1.0802, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.013999999999999999, |
|
"loss": 0.8187, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0138, |
|
"loss": 0.615, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.013600000000000001, |
|
"loss": 0.5214, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0134, |
|
"loss": 0.649, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.013200000000000002, |
|
"loss": 0.6523, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.013000000000000001, |
|
"loss": 0.7002, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0128, |
|
"loss": 0.6161, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0126, |
|
"loss": 1.0374, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0124, |
|
"loss": 1.0328, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.0122, |
|
"loss": 0.7637, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.012, |
|
"loss": 0.6332, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.0118, |
|
"loss": 0.74, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0116, |
|
"loss": 0.7284, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.011399999999999999, |
|
"loss": 0.9198, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.011200000000000002, |
|
"loss": 0.626, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.011000000000000001, |
|
"loss": 0.628, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0108, |
|
"loss": 0.5322, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.0106, |
|
"loss": 0.7844, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.010400000000000001, |
|
"loss": 0.5957, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.0102, |
|
"loss": 0.6681, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.01, |
|
"loss": 0.8281, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0098, |
|
"loss": 0.5284, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0096, |
|
"loss": 0.8251, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0094, |
|
"loss": 0.9845, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.0092, |
|
"loss": 0.9525, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.009000000000000001, |
|
"loss": 0.9454, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0088, |
|
"loss": 0.4058, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.0086, |
|
"loss": 0.5435, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.0084, |
|
"loss": 0.6892, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.008199999999999999, |
|
"loss": 0.6426, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.008, |
|
"loss": 0.9414, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.0078000000000000005, |
|
"loss": 0.7945, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0076, |
|
"loss": 0.6295, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0074, |
|
"loss": 0.7888, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0072, |
|
"loss": 0.5454, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.006999999999999999, |
|
"loss": 0.711, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0068000000000000005, |
|
"loss": 0.713, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.006600000000000001, |
|
"loss": 0.6058, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0064, |
|
"loss": 0.8203, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0062, |
|
"loss": 0.8275, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.006, |
|
"loss": 0.4923, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0058, |
|
"loss": 0.5219, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.005600000000000001, |
|
"loss": 0.9954, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0054, |
|
"loss": 0.6206, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.005200000000000001, |
|
"loss": 0.6064, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.005, |
|
"loss": 0.6584, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.0048, |
|
"loss": 0.8461, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0046, |
|
"loss": 0.9615, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0044, |
|
"loss": 0.6508, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0042, |
|
"loss": 1.0089, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.004, |
|
"loss": 0.7515, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0038, |
|
"loss": 0.4172, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0036, |
|
"loss": 0.7634, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0034000000000000002, |
|
"loss": 0.585, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0032, |
|
"loss": 0.7668, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.003, |
|
"loss": 0.5403, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0028000000000000004, |
|
"loss": 0.5995, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0026000000000000003, |
|
"loss": 0.4515, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0024, |
|
"loss": 0.6288, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.0022, |
|
"loss": 0.7387, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.002, |
|
"loss": 0.6517, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0018, |
|
"loss": 0.5389, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0016, |
|
"loss": 0.4433, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0014000000000000002, |
|
"loss": 0.6643, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0012, |
|
"loss": 0.5825, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.001, |
|
"loss": 0.7709, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.0008, |
|
"loss": 0.562, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0006, |
|
"loss": 0.5581, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0004, |
|
"loss": 0.4679, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5063, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.0, |
|
"loss": 0.5527, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"step": 100, |
|
"total_flos": 1.323218757484544e+17, |
|
"train_loss": 0.7395605874061585, |
|
"train_runtime": 1218.4689, |
|
"train_samples_per_second": 2.626, |
|
"train_steps_per_second": 0.082 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 1.323218757484544e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|