File size: 1,802 Bytes
0886a6b |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.11707317073170732,
"eval_steps": 500,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01951219512195122,
"grad_norm": 0.14488260447978973,
"learning_rate": 0.00019934683213585893,
"loss": 0.6356,
"step": 10
},
{
"epoch": 0.03902439024390244,
"grad_norm": 0.1634250283241272,
"learning_rate": 0.00019804049640757677,
"loss": 0.4368,
"step": 20
},
{
"epoch": 0.05853658536585366,
"grad_norm": 0.1504327356815338,
"learning_rate": 0.0001967341606792946,
"loss": 0.407,
"step": 30
},
{
"epoch": 0.07804878048780488,
"grad_norm": 0.16282524168491364,
"learning_rate": 0.00019542782495101242,
"loss": 0.3788,
"step": 40
},
{
"epoch": 0.0975609756097561,
"grad_norm": 0.17505913972854614,
"learning_rate": 0.00019412148922273026,
"loss": 0.3705,
"step": 50
},
{
"epoch": 0.11707317073170732,
"grad_norm": 0.18271876871585846,
"learning_rate": 0.00019281515349444807,
"loss": 0.3654,
"step": 60
}
],
"logging_steps": 10,
"max_steps": 1536,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 4022303701475328.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|