File size: 1,629 Bytes
b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 53aa0f9 b2cda63 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.02141648641123937,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005354121602809843,
"grad_norm": NaN,
"learning_rate": 2.5e-06,
"loss": 11.8252,
"step": 500
},
{
"epoch": 0.010708243205619685,
"grad_norm": NaN,
"learning_rate": 1.6666666666666669e-06,
"loss": 0.0,
"step": 1000
},
{
"epoch": 0.01606236480842953,
"grad_norm": NaN,
"learning_rate": 8.333333333333334e-07,
"loss": 0.0,
"step": 1500
},
{
"epoch": 0.02141648641123937,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 0.0,
"step": 2000
},
{
"epoch": 0.02141648641123937,
"step": 2000,
"total_flos": 8.380982415051637e+18,
"train_loss": 2.956299072265625,
"train_runtime": 3006.0711,
"train_samples_per_second": 2.661,
"train_steps_per_second": 0.665
}
],
"logging_steps": 500,
"max_steps": 2000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.380982415051637e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|