File size: 4,196 Bytes
ea92de7 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1587,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1890359168241966,
"grad_norm": 0.5558584332466125,
"learning_rate": 3e-05,
"loss": 2.1103,
"step": 100
},
{
"epoch": 0.3780718336483932,
"grad_norm": 0.4733140468597412,
"learning_rate": 3e-05,
"loss": 1.931,
"step": 200
},
{
"epoch": 0.5671077504725898,
"grad_norm": 0.48580050468444824,
"learning_rate": 3e-05,
"loss": 1.8948,
"step": 300
},
{
"epoch": 0.7561436672967864,
"grad_norm": 0.40655234456062317,
"learning_rate": 3e-05,
"loss": 1.8988,
"step": 400
},
{
"epoch": 0.945179584120983,
"grad_norm": 0.6303955316543579,
"learning_rate": 3e-05,
"loss": 1.8745,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.5701538461538461,
"eval_loss": 1.6455246210098267,
"eval_runtime": 5.0805,
"eval_samples_per_second": 98.415,
"eval_steps_per_second": 12.4,
"step": 529
},
{
"epoch": 1.0,
"eval_exact_match": 15.0,
"eval_f1": 23.927619047619068,
"step": 529
},
{
"epoch": 1.1342155009451795,
"grad_norm": 0.4278818666934967,
"learning_rate": 3e-05,
"loss": 1.8798,
"step": 600
},
{
"epoch": 1.3232514177693762,
"grad_norm": 0.449830025434494,
"learning_rate": 3e-05,
"loss": 1.8613,
"step": 700
},
{
"epoch": 1.5122873345935728,
"grad_norm": 0.5130725502967834,
"learning_rate": 3e-05,
"loss": 1.8709,
"step": 800
},
{
"epoch": 1.7013232514177694,
"grad_norm": 0.4889715611934662,
"learning_rate": 3e-05,
"loss": 1.8448,
"step": 900
},
{
"epoch": 1.8903591682419658,
"grad_norm": 11.186380386352539,
"learning_rate": 3e-05,
"loss": 1.8764,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.5723589743589743,
"eval_loss": 1.6143561601638794,
"eval_runtime": 5.0466,
"eval_samples_per_second": 99.077,
"eval_steps_per_second": 12.484,
"step": 1058
},
{
"epoch": 2.0,
"eval_exact_match": 15.6,
"eval_f1": 25.825238095238113,
"step": 1058
},
{
"epoch": 2.0793950850661624,
"grad_norm": 0.5414931774139404,
"learning_rate": 3e-05,
"loss": 1.8398,
"step": 1100
},
{
"epoch": 2.268431001890359,
"grad_norm": 7.441005706787109,
"learning_rate": 3e-05,
"loss": 1.8348,
"step": 1200
},
{
"epoch": 2.4574669187145557,
"grad_norm": 24.312145233154297,
"learning_rate": 3e-05,
"loss": 1.8421,
"step": 1300
},
{
"epoch": 2.6465028355387523,
"grad_norm": 0.7407662868499756,
"learning_rate": 3e-05,
"loss": 1.8292,
"step": 1400
},
{
"epoch": 2.835538752362949,
"grad_norm": 0.9653642177581787,
"learning_rate": 3e-05,
"loss": 1.828,
"step": 1500
},
{
"epoch": 3.0,
"eval_accuracy": 0.5734358974358974,
"eval_loss": 1.617864727973938,
"eval_runtime": 5.2153,
"eval_samples_per_second": 95.872,
"eval_steps_per_second": 12.08,
"step": 1587
},
{
"epoch": 3.0,
"eval_exact_match": 16.2,
"eval_f1": 25.811428571428586,
"step": 1587
}
],
"logging_steps": 100,
"max_steps": 26450,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"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": 1.2930665086661427e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|