File size: 2,021 Bytes
f1e2c14 c232821 f1e2c14 c232821 f1e2c14 c232821 f1e2c14 c232821 f1e2c14 |
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 77 78 79 80 81 82 83 84 85 86 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.023686158401184307,
"eval_steps": 2,
"global_step": 4,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005921539600296077,
"grad_norm": 0.7750168442726135,
"learning_rate": 1e-05,
"loss": 0.6543,
"step": 1
},
{
"epoch": 0.005921539600296077,
"eval_loss": 0.6377593874931335,
"eval_runtime": 73.9398,
"eval_samples_per_second": 3.854,
"eval_steps_per_second": 1.934,
"step": 1
},
{
"epoch": 0.011843079200592153,
"grad_norm": 0.7847601175308228,
"learning_rate": 2e-05,
"loss": 0.7245,
"step": 2
},
{
"epoch": 0.011843079200592153,
"eval_loss": 0.6308547258377075,
"eval_runtime": 10.3795,
"eval_samples_per_second": 27.458,
"eval_steps_per_second": 13.777,
"step": 2
},
{
"epoch": 0.01776461880088823,
"grad_norm": 0.8490102887153625,
"learning_rate": 3e-05,
"loss": 0.7567,
"step": 3
},
{
"epoch": 0.023686158401184307,
"grad_norm": 0.7016004920005798,
"learning_rate": 4e-05,
"loss": 0.5979,
"step": 4
},
{
"epoch": 0.023686158401184307,
"eval_loss": 0.614459753036499,
"eval_runtime": 10.408,
"eval_samples_per_second": 27.383,
"eval_steps_per_second": 13.739,
"step": 4
}
],
"logging_steps": 1,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1566328938823680.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|