File size: 2,377 Bytes
d66a283 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2,
"eval_steps": 25,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 2.3797595190380762e-05,
"loss": 3.5104,
"step": 25
},
{
"epoch": 0.03,
"eval_loss": 2.643505334854126,
"eval_runtime": 13.8992,
"eval_samples_per_second": 17.987,
"eval_steps_per_second": 2.302,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 2.2545090180360722e-05,
"loss": 2.2052,
"step": 50
},
{
"epoch": 0.07,
"eval_loss": 1.966366171836853,
"eval_runtime": 13.6092,
"eval_samples_per_second": 18.37,
"eval_steps_per_second": 2.351,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 2.1292585170340683e-05,
"loss": 1.81,
"step": 75
},
{
"epoch": 0.1,
"eval_loss": 1.8134992122650146,
"eval_runtime": 13.5125,
"eval_samples_per_second": 18.501,
"eval_steps_per_second": 2.368,
"step": 75
},
{
"epoch": 0.13,
"learning_rate": 2.0040080160320643e-05,
"loss": 1.705,
"step": 100
},
{
"epoch": 0.13,
"eval_loss": 1.7801309823989868,
"eval_runtime": 13.4868,
"eval_samples_per_second": 18.537,
"eval_steps_per_second": 2.373,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 1.87875751503006e-05,
"loss": 1.6288,
"step": 125
},
{
"epoch": 0.17,
"eval_loss": 1.7698311805725098,
"eval_runtime": 13.6256,
"eval_samples_per_second": 18.348,
"eval_steps_per_second": 2.349,
"step": 125
},
{
"epoch": 0.2,
"learning_rate": 1.7535070140280564e-05,
"loss": 1.7262,
"step": 150
},
{
"epoch": 0.2,
"eval_loss": 1.7579054832458496,
"eval_runtime": 13.6761,
"eval_samples_per_second": 18.28,
"eval_steps_per_second": 2.34,
"step": 150
}
],
"logging_steps": 25,
"max_steps": 500,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 2465119862784000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|