File size: 2,784 Bytes
a3e4d25 e5c4fcc ad09a8d e5c4fcc a3e4d25 ad09a8d a3e4d25 ad09a8d 7a53762 e5c4fcc a3e4d25 ad09a8d a3e4d25 ad09a8d a3e4d25 ad09a8d a3e4d25 e5c4fcc a3e4d25 |
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 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.009175930827598376,
"eval_steps": 10,
"global_step": 39,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002352802776307276,
"eval_loss": 3.421792507171631,
"eval_runtime": 125.7544,
"eval_samples_per_second": 14.234,
"eval_steps_per_second": 7.117,
"step": 1
},
{
"epoch": 0.001176401388153638,
"grad_norm": 1.2427492141723633,
"learning_rate": 5e-05,
"loss": 3.4053,
"step": 5
},
{
"epoch": 0.002352802776307276,
"grad_norm": 2.223381280899048,
"learning_rate": 0.0001,
"loss": 3.4449,
"step": 10
},
{
"epoch": 0.002352802776307276,
"eval_loss": 3.1467432975769043,
"eval_runtime": 131.4609,
"eval_samples_per_second": 13.616,
"eval_steps_per_second": 6.808,
"step": 10
},
{
"epoch": 0.0035292041644609143,
"grad_norm": 2.0198276042938232,
"learning_rate": 9.619397662556435e-05,
"loss": 2.8499,
"step": 15
},
{
"epoch": 0.004705605552614552,
"grad_norm": 3.1428215503692627,
"learning_rate": 8.535533905932738e-05,
"loss": 2.0307,
"step": 20
},
{
"epoch": 0.004705605552614552,
"eval_loss": 1.6161822080612183,
"eval_runtime": 131.4252,
"eval_samples_per_second": 13.62,
"eval_steps_per_second": 6.81,
"step": 20
},
{
"epoch": 0.00588200694076819,
"grad_norm": 1.708250641822815,
"learning_rate": 6.91341716182545e-05,
"loss": 1.2073,
"step": 25
},
{
"epoch": 0.0070584083289218285,
"grad_norm": 4.847468376159668,
"learning_rate": 5e-05,
"loss": 0.9374,
"step": 30
},
{
"epoch": 0.0070584083289218285,
"eval_loss": 1.0444806814193726,
"eval_runtime": 131.4278,
"eval_samples_per_second": 13.62,
"eval_steps_per_second": 6.81,
"step": 30
},
{
"epoch": 0.008234809717075466,
"grad_norm": 2.204052209854126,
"learning_rate": 3.086582838174551e-05,
"loss": 1.0669,
"step": 35
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6408340481507328.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|