File size: 3,010 Bytes
1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 1ed8096 1166828 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0032512395350727465,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003251239535072746,
"grad_norm": 0.021640103310346603,
"learning_rate": 1e-05,
"loss": 11.7645,
"step": 1
},
{
"epoch": 0.0003251239535072746,
"eval_loss": 11.76447582244873,
"eval_runtime": 249.3031,
"eval_samples_per_second": 41.56,
"eval_steps_per_second": 20.782,
"step": 1
},
{
"epoch": 0.0006502479070145493,
"grad_norm": 0.024706723168492317,
"learning_rate": 2e-05,
"loss": 11.7658,
"step": 2
},
{
"epoch": 0.000975371860521824,
"grad_norm": 0.022929754108190536,
"learning_rate": 3e-05,
"loss": 11.7649,
"step": 3
},
{
"epoch": 0.0013004958140290985,
"grad_norm": 0.022171195596456528,
"learning_rate": 4e-05,
"loss": 11.7648,
"step": 4
},
{
"epoch": 0.0016256197675363732,
"grad_norm": 0.02208411693572998,
"learning_rate": 5e-05,
"loss": 11.7649,
"step": 5
},
{
"epoch": 0.0016256197675363732,
"eval_loss": 11.764402389526367,
"eval_runtime": 249.1579,
"eval_samples_per_second": 41.584,
"eval_steps_per_second": 20.794,
"step": 5
},
{
"epoch": 0.001950743721043648,
"grad_norm": 0.02443164400756359,
"learning_rate": 6e-05,
"loss": 11.7634,
"step": 6
},
{
"epoch": 0.0022758676745509225,
"grad_norm": 0.023470092564821243,
"learning_rate": 7e-05,
"loss": 11.7654,
"step": 7
},
{
"epoch": 0.002600991628058197,
"grad_norm": 0.023716744035482407,
"learning_rate": 8e-05,
"loss": 11.7644,
"step": 8
},
{
"epoch": 0.002926115581565472,
"grad_norm": 0.022970277816057205,
"learning_rate": 9e-05,
"loss": 11.7658,
"step": 9
},
{
"epoch": 0.0032512395350727465,
"grad_norm": 0.022244542837142944,
"learning_rate": 0.0001,
"loss": 11.7641,
"step": 10
},
{
"epoch": 0.0032512395350727465,
"eval_loss": 11.764139175415039,
"eval_runtime": 248.9949,
"eval_samples_per_second": 41.611,
"eval_steps_per_second": 20.808,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 20,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 32592007004160.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|