File size: 2,690 Bytes
ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae a78bcb6 ea661ae | 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 | {
"best_global_step": 80,
"best_metric": 0.6859903381642513,
"best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-80",
"epoch": 1.5686274509803921,
"eval_steps": 20,
"global_step": 80,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.39215686274509803,
"grad_norm": 24.230987548828125,
"learning_rate": 8.137254901960784e-06,
"loss": 1.1665,
"step": 20
},
{
"epoch": 0.39215686274509803,
"eval_accuracy": 0.6206896551724138,
"eval_f1": 0.631578947368421,
"eval_loss": 1.0547616481781006,
"eval_runtime": 34.5129,
"eval_samples_per_second": 5.882,
"eval_steps_per_second": 0.203,
"step": 20
},
{
"epoch": 0.7843137254901961,
"grad_norm": 26.34092140197754,
"learning_rate": 6.176470588235295e-06,
"loss": 0.8846,
"step": 40
},
{
"epoch": 0.7843137254901961,
"eval_accuracy": 0.6551724137931034,
"eval_f1": 0.6634615384615384,
"eval_loss": 0.8848929405212402,
"eval_runtime": 34.4309,
"eval_samples_per_second": 5.896,
"eval_steps_per_second": 0.203,
"step": 40
},
{
"epoch": 1.1764705882352942,
"grad_norm": 28.944477081298828,
"learning_rate": 4.215686274509805e-06,
"loss": 0.5412,
"step": 60
},
{
"epoch": 1.1764705882352942,
"eval_accuracy": 0.6699507389162561,
"eval_f1": 0.6824644549763034,
"eval_loss": 0.8630681037902832,
"eval_runtime": 34.3671,
"eval_samples_per_second": 5.907,
"eval_steps_per_second": 0.204,
"step": 60
},
{
"epoch": 1.5686274509803921,
"grad_norm": 14.226760864257812,
"learning_rate": 2.254901960784314e-06,
"loss": 0.3088,
"step": 80
},
{
"epoch": 1.5686274509803921,
"eval_accuracy": 0.6798029556650246,
"eval_f1": 0.6859903381642513,
"eval_loss": 0.8230202794075012,
"eval_runtime": 34.5725,
"eval_samples_per_second": 5.872,
"eval_steps_per_second": 0.202,
"step": 80
}
],
"logging_steps": 20,
"max_steps": 102,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 20,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4553569010414592.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|