File size: 3,083 Bytes
7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc 4609af2 7a880dc |
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 |
{
"best_metric": 0.6374139189720154,
"best_model_checkpoint": "./llama3/28-08-24-Weni-Pipeline_test_Experiment with SFT and Llama3 70b-2_max_steps-1362_batch_16_2024-08-28/checkpoint-100",
"epoch": 0.2202036884117809,
"eval_steps": 100,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02202036884117809,
"grad_norm": 0.6965782642364502,
"learning_rate": 7.5e-05,
"loss": 2.1201,
"step": 10
},
{
"epoch": 0.04404073768235618,
"grad_norm": 0.7504029870033264,
"learning_rate": 0.00015,
"loss": 0.9392,
"step": 20
},
{
"epoch": 0.06606110652353427,
"grad_norm": 0.7269854545593262,
"learning_rate": 0.000225,
"loss": 0.7958,
"step": 30
},
{
"epoch": 0.08808147536471236,
"grad_norm": 0.15891791880130768,
"learning_rate": 0.0003,
"loss": 0.7251,
"step": 40
},
{
"epoch": 0.11010184420589045,
"grad_norm": 0.14764881134033203,
"learning_rate": 0.00029995764763563235,
"loss": 0.6941,
"step": 50
},
{
"epoch": 0.13212221304706853,
"grad_norm": 0.11882930248975754,
"learning_rate": 0.00029983061445883305,
"loss": 0.673,
"step": 60
},
{
"epoch": 0.15414258188824662,
"grad_norm": 0.15152081847190857,
"learning_rate": 0.0002996189722050073,
"loss": 0.6428,
"step": 70
},
{
"epoch": 0.17616295072942473,
"grad_norm": 0.1619480848312378,
"learning_rate": 0.0002993228403881531,
"loss": 0.6465,
"step": 80
},
{
"epoch": 0.1981833195706028,
"grad_norm": 0.15019242465496063,
"learning_rate": 0.00029894238623337174,
"loss": 0.6308,
"step": 90
},
{
"epoch": 0.2202036884117809,
"grad_norm": 0.14553773403167725,
"learning_rate": 0.00029847782458243663,
"loss": 0.6314,
"step": 100
},
{
"epoch": 0.2202036884117809,
"eval_accuracy": 1.0,
"eval_f1": 1.0,
"eval_f1_macro": 1.0,
"eval_f1_micro": 1.0,
"eval_loss": 0.6374139189720154,
"eval_precision": 1.0,
"eval_precision_macro": 1.0,
"eval_precision_micro": 1.0,
"eval_recall": 1.0,
"eval_recall_macro": 1.0,
"eval_recall_micro": 1.0,
"eval_runtime": 1957.1676,
"eval_samples_per_second": 0.413,
"eval_steps_per_second": 0.206,
"step": 100
}
],
"logging_steps": 10,
"max_steps": 1362,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4711855325184.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|