File size: 1,511 Bytes
9d660e6 8d1974f 9d660e6 8d1974f 9d660e6 8d1974f 9d660e6 8d1974f 9d660e6 8d1974f 9d660e6 8d1974f 9d660e6 8d1974f 9d660e6 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.00020051130382475312,
"eval_steps": 10,
"global_step": 13,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.542394644805793e-05,
"eval_loss": 2.7992300987243652,
"eval_runtime": 2235.1802,
"eval_samples_per_second": 12.213,
"eval_steps_per_second": 6.107,
"step": 1
},
{
"epoch": 7.711973224028966e-05,
"grad_norm": 2.202889919281006,
"learning_rate": 5e-05,
"loss": 2.6748,
"step": 5
},
{
"epoch": 0.00015423946448057932,
"grad_norm": 2.989361524581909,
"learning_rate": 0.0001,
"loss": 2.7346,
"step": 10
},
{
"epoch": 0.00015423946448057932,
"eval_loss": 2.4348955154418945,
"eval_runtime": 2264.5204,
"eval_samples_per_second": 12.055,
"eval_steps_per_second": 6.028,
"step": 10
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2404433522589696.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|