File size: 1,604 Bytes
aab2a07 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2114,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.23651844843897823,
"grad_norm": 1.046875,
"learning_rate": 1.881740775780511e-05,
"loss": 0.3019,
"mean_token_accuracy": 0.9215967762470245,
"step": 500
},
{
"epoch": 0.47303689687795647,
"grad_norm": 1.234375,
"learning_rate": 1.763481551561022e-05,
"loss": 0.246,
"mean_token_accuracy": 0.9323436969518661,
"step": 1000
},
{
"epoch": 0.7095553453169348,
"grad_norm": 1.890625,
"learning_rate": 1.6452223273415328e-05,
"loss": 0.2338,
"mean_token_accuracy": 0.9348658822774887,
"step": 1500
},
{
"epoch": 0.9460737937559129,
"grad_norm": 1.2109375,
"learning_rate": 1.5269631031220437e-05,
"loss": 0.2312,
"mean_token_accuracy": 0.9352898219823838,
"step": 2000
}
],
"logging_steps": 500,
"max_steps": 8456,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 1.4317446353092608e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|