File size: 3,726 Bytes
46e7657 3f14c7e 440f5c8 3f14c7e 46e7657 440f5c8 46e7657 440f5c8 8dd66db 282189e 3f14c7e 46e7657 440f5c8 46e7657 440f5c8 46e7657 3f14c7e 46e7657 3f14c7e 46e7657 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.022753128555176336,
"eval_steps": 10,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004550625711035267,
"eval_loss": 8.276806831359863,
"eval_runtime": 191.4525,
"eval_samples_per_second": 4.837,
"eval_steps_per_second": 2.418,
"step": 1
},
{
"epoch": 0.0022753128555176336,
"grad_norm": 18.482772827148438,
"learning_rate": 5e-05,
"loss": 7.6,
"step": 5
},
{
"epoch": 0.004550625711035267,
"grad_norm": 16.873130798339844,
"learning_rate": 0.0001,
"loss": 4.5357,
"step": 10
},
{
"epoch": 0.004550625711035267,
"eval_loss": 1.0215221643447876,
"eval_runtime": 193.2723,
"eval_samples_per_second": 4.791,
"eval_steps_per_second": 2.396,
"step": 10
},
{
"epoch": 0.006825938566552901,
"grad_norm": 9.969215393066406,
"learning_rate": 9.619397662556435e-05,
"loss": 0.3175,
"step": 15
},
{
"epoch": 0.009101251422070534,
"grad_norm": 0.0247463658452034,
"learning_rate": 8.535533905932738e-05,
"loss": 0.4614,
"step": 20
},
{
"epoch": 0.009101251422070534,
"eval_loss": 0.2140456885099411,
"eval_runtime": 193.1936,
"eval_samples_per_second": 4.793,
"eval_steps_per_second": 2.397,
"step": 20
},
{
"epoch": 0.011376564277588168,
"grad_norm": 0.7247423529624939,
"learning_rate": 6.91341716182545e-05,
"loss": 0.1652,
"step": 25
},
{
"epoch": 0.013651877133105802,
"grad_norm": 0.0034711698535829782,
"learning_rate": 5e-05,
"loss": 0.1079,
"step": 30
},
{
"epoch": 0.013651877133105802,
"eval_loss": 0.16020071506500244,
"eval_runtime": 193.3016,
"eval_samples_per_second": 4.79,
"eval_steps_per_second": 2.395,
"step": 30
},
{
"epoch": 0.015927189988623434,
"grad_norm": 20.983272552490234,
"learning_rate": 3.086582838174551e-05,
"loss": 0.1722,
"step": 35
},
{
"epoch": 0.01820250284414107,
"grad_norm": 0.6138023138046265,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.1248,
"step": 40
},
{
"epoch": 0.01820250284414107,
"eval_loss": 0.14828301966190338,
"eval_runtime": 193.2763,
"eval_samples_per_second": 4.791,
"eval_steps_per_second": 2.396,
"step": 40
},
{
"epoch": 0.020477815699658702,
"grad_norm": 12.502432823181152,
"learning_rate": 3.8060233744356633e-06,
"loss": 0.4113,
"step": 45
},
{
"epoch": 0.022753128555176336,
"grad_norm": 0.00241334387101233,
"learning_rate": 0.0,
"loss": 0.2781,
"step": 50
},
{
"epoch": 0.022753128555176336,
"eval_loss": 0.13595092296600342,
"eval_runtime": 193.1785,
"eval_samples_per_second": 4.793,
"eval_steps_per_second": 2.397,
"step": 50
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.61937503551488e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|