File size: 4,538 Bytes
8bdfbfb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
{
"best_metric": 0.4493897557258606,
"best_model_checkpoint": "mikhail-panzo/fil_b32_le5_s8000/checkpoint-1000",
"epoch": 22.22222222222222,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.1111111111111112,
"grad_norm": 3.579704523086548,
"learning_rate": 2.4500000000000004e-07,
"loss": 0.8282,
"step": 50
},
{
"epoch": 2.2222222222222223,
"grad_norm": 2.0918073654174805,
"learning_rate": 4.95e-07,
"loss": 0.7857,
"step": 100
},
{
"epoch": 3.3333333333333335,
"grad_norm": 1.283610224723816,
"learning_rate": 7.450000000000001e-07,
"loss": 0.7356,
"step": 150
},
{
"epoch": 4.444444444444445,
"grad_norm": 1.5381903648376465,
"learning_rate": 9.950000000000002e-07,
"loss": 0.7606,
"step": 200
},
{
"epoch": 5.555555555555555,
"grad_norm": 1.613647222518921,
"learning_rate": 1.2450000000000002e-06,
"loss": 0.7314,
"step": 250
},
{
"epoch": 6.666666666666667,
"grad_norm": 2.6762027740478516,
"learning_rate": 1.495e-06,
"loss": 0.6933,
"step": 300
},
{
"epoch": 7.777777777777778,
"grad_norm": 2.667527675628662,
"learning_rate": 1.745e-06,
"loss": 0.6863,
"step": 350
},
{
"epoch": 8.88888888888889,
"grad_norm": 1.9682470560073853,
"learning_rate": 1.9950000000000004e-06,
"loss": 0.6649,
"step": 400
},
{
"epoch": 10.0,
"grad_norm": 2.0042927265167236,
"learning_rate": 2.245e-06,
"loss": 0.6507,
"step": 450
},
{
"epoch": 11.11111111111111,
"grad_norm": 2.6399147510528564,
"learning_rate": 2.4950000000000003e-06,
"loss": 0.632,
"step": 500
},
{
"epoch": 11.11111111111111,
"eval_loss": 0.5323343276977539,
"eval_runtime": 7.6175,
"eval_samples_per_second": 20.873,
"eval_steps_per_second": 2.626,
"step": 500
},
{
"epoch": 12.222222222222221,
"grad_norm": 2.593517780303955,
"learning_rate": 2.7450000000000004e-06,
"loss": 0.5956,
"step": 550
},
{
"epoch": 13.333333333333334,
"grad_norm": 5.524081707000732,
"learning_rate": 2.99e-06,
"loss": 0.577,
"step": 600
},
{
"epoch": 14.444444444444445,
"grad_norm": 2.2165024280548096,
"learning_rate": 3.2400000000000003e-06,
"loss": 0.5614,
"step": 650
},
{
"epoch": 15.555555555555555,
"grad_norm": 2.4440901279449463,
"learning_rate": 3.49e-06,
"loss": 0.5654,
"step": 700
},
{
"epoch": 16.666666666666668,
"grad_norm": 1.8401445150375366,
"learning_rate": 3.74e-06,
"loss": 0.5329,
"step": 750
},
{
"epoch": 17.77777777777778,
"grad_norm": 2.101787567138672,
"learning_rate": 3.990000000000001e-06,
"loss": 0.5293,
"step": 800
},
{
"epoch": 18.88888888888889,
"grad_norm": 2.1338887214660645,
"learning_rate": 4.24e-06,
"loss": 0.5345,
"step": 850
},
{
"epoch": 20.0,
"grad_norm": 1.8499983549118042,
"learning_rate": 4.49e-06,
"loss": 0.5148,
"step": 900
},
{
"epoch": 21.11111111111111,
"grad_norm": 1.3982588052749634,
"learning_rate": 4.74e-06,
"loss": 0.5085,
"step": 950
},
{
"epoch": 22.22222222222222,
"grad_norm": 1.7611488103866577,
"learning_rate": 4.9900000000000005e-06,
"loss": 0.519,
"step": 1000
},
{
"epoch": 22.22222222222222,
"eval_loss": 0.4493897557258606,
"eval_runtime": 7.4167,
"eval_samples_per_second": 21.438,
"eval_steps_per_second": 2.697,
"step": 1000
}
],
"logging_steps": 50,
"max_steps": 8000,
"num_input_tokens_seen": 0,
"num_train_epochs": 178,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7298262141920640.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|