File size: 1,745 Bytes
df7b3ef | 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": 1.0,
"eval_steps": 500,
"global_step": 313,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1597444089456869,
"grad_norm": 3.102206230163574,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.8333,
"step": 50
},
{
"epoch": 0.3194888178913738,
"grad_norm": 2.281259298324585,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.5443,
"step": 100
},
{
"epoch": 0.4792332268370607,
"grad_norm": 3.091155767440796,
"learning_rate": 7.4e-06,
"loss": 0.3887,
"step": 150
},
{
"epoch": 0.6389776357827476,
"grad_norm": 2.561985969543457,
"learning_rate": 9.9e-06,
"loss": 0.292,
"step": 200
},
{
"epoch": 0.7987220447284346,
"grad_norm": 3.2992053031921387,
"learning_rate": 8.87323943661972e-06,
"loss": 0.228,
"step": 250
},
{
"epoch": 0.9584664536741214,
"grad_norm": 5.076635837554932,
"learning_rate": 7.699530516431926e-06,
"loss": 0.2053,
"step": 300
}
],
"logging_steps": 50,
"max_steps": 626,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 653253688320000.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|