File size: 1,517 Bytes
180390d 57e34a0 180390d 57e34a0 180390d 57e34a0 180390d 57e34a0 180390d 57e34a0 180390d |
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": 3.0,
"eval_steps": 500,
"global_step": 1626,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.922509225092251,
"grad_norm": 0.6193047165870667,
"learning_rate": 3.4624846248462485e-05,
"loss": 0.5669,
"step": 500
},
{
"epoch": 1.8450184501845017,
"grad_norm": 0.5879950523376465,
"learning_rate": 1.924969249692497e-05,
"loss": 0.4066,
"step": 1000
},
{
"epoch": 2.767527675276753,
"grad_norm": 0.9034110307693481,
"learning_rate": 3.874538745387454e-06,
"loss": 0.3173,
"step": 1500
},
{
"epoch": 3.0,
"step": 1626,
"total_flos": 2.068561910815949e+16,
"train_loss": 0.41841167248189814,
"train_runtime": 3228.8428,
"train_samples_per_second": 0.504,
"train_steps_per_second": 0.504
}
],
"logging_steps": 500,
"max_steps": 1626,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2.068561910815949e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|