File size: 2,027 Bytes
276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb 5aa3053 276b3eb |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.851063829787234,
"eval_steps": 500,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1702127659574468,
"grad_norm": 1.0480449041222901,
"learning_rate": 4.980286753286196e-06,
"loss": 1.1367,
"step": 1
},
{
"epoch": 0.851063829787234,
"grad_norm": 0.7218518716452021,
"learning_rate": 4.522542485937369e-06,
"loss": 0.7212,
"step": 5
},
{
"epoch": 1.851063829787234,
"grad_norm": 0.48974754683120497,
"learning_rate": 3.272542485937369e-06,
"loss": 0.5486,
"step": 10
},
{
"epoch": 2.851063829787234,
"grad_norm": 0.05989476827451271,
"learning_rate": 1.7274575140626318e-06,
"loss": 0.4988,
"step": 15
},
{
"epoch": 3.851063829787234,
"grad_norm": 0.04162142765751137,
"learning_rate": 4.774575140626317e-07,
"loss": 0.4812,
"step": 20
},
{
"epoch": 4.851063829787234,
"grad_norm": 0.03625801845951793,
"learning_rate": 0.0,
"loss": 0.4803,
"step": 25
},
{
"epoch": 4.851063829787234,
"step": 25,
"total_flos": 1.70668694534357e+17,
"train_loss": 0.5626590156555176,
"train_runtime": 583.7651,
"train_samples_per_second": 6.407,
"train_steps_per_second": 0.043
}
],
"logging_steps": 5,
"max_steps": 25,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.70668694534357e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|