File size: 1,913 Bytes
d3a2774 5d975fb d3a2774 5d975fb d3a2774 5d975fb d3a2774 5d975fb d3a2774 5d975fb d3a2774 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.014134275618374558,
"eval_steps": 5,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0028268551236749115,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 7.6743,
"step": 1
},
{
"epoch": 0.0028268551236749115,
"eval_loss": 7.129258632659912,
"eval_runtime": 20.9973,
"eval_samples_per_second": 28.385,
"eval_steps_per_second": 3.572,
"step": 1
},
{
"epoch": 0.005653710247349823,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 7.3349,
"step": 2
},
{
"epoch": 0.008480565371024734,
"grad_norm": 5.082520484924316,
"learning_rate": 2e-05,
"loss": 7.4669,
"step": 3
},
{
"epoch": 0.011307420494699646,
"grad_norm": 4.920047760009766,
"learning_rate": 4e-05,
"loss": 7.1521,
"step": 4
},
{
"epoch": 0.014134275618374558,
"grad_norm": NaN,
"learning_rate": 4e-05,
"loss": 7.7426,
"step": 5
},
{
"epoch": 0.014134275618374558,
"eval_loss": 7.097348213195801,
"eval_runtime": 20.8903,
"eval_samples_per_second": 28.53,
"eval_steps_per_second": 3.59,
"step": 5
}
],
"logging_steps": 1,
"max_steps": 20,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6719419828928512.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|