File size: 2,596 Bytes
ce30918 0e2e36c ce30918 0e2e36c ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 ce30918 0e2e36c 927a8c7 0e2e36c 927a8c7 0e2e36c 927a8c7 0e2e36c 927a8c7 0e2e36c 927a8c7 0e2e36c 927a8c7 0e2e36c ce30918 0e2e36c ce30918 0e2e36c ce30918 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9905660377358491,
"eval_steps": 10,
"global_step": 42,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.9930094929529506e-05,
"loss": 1.1016,
"step": 1
},
{
"epoch": 0.12,
"learning_rate": 4.827184371610511e-05,
"loss": 1.0942,
"step": 5
},
{
"epoch": 0.24,
"learning_rate": 4.332629679574566e-05,
"loss": 1.1071,
"step": 10
},
{
"epoch": 0.24,
"eval_loss": 1.0860216617584229,
"eval_runtime": 24.5643,
"eval_samples_per_second": 5.252,
"eval_steps_per_second": 1.751,
"step": 10
},
{
"epoch": 0.35,
"learning_rate": 3.5847093477938956e-05,
"loss": 1.0982,
"step": 15
},
{
"epoch": 0.47,
"learning_rate": 2.686825233966061e-05,
"loss": 1.0907,
"step": 20
},
{
"epoch": 0.47,
"eval_loss": 1.0737882852554321,
"eval_runtime": 24.5637,
"eval_samples_per_second": 5.252,
"eval_steps_per_second": 1.751,
"step": 20
},
{
"epoch": 0.59,
"learning_rate": 1.7631120639727393e-05,
"loss": 1.0756,
"step": 25
},
{
"epoch": 0.71,
"learning_rate": 9.412754953531663e-06,
"loss": 1.0866,
"step": 30
},
{
"epoch": 0.71,
"eval_loss": 1.0668362379074097,
"eval_runtime": 24.554,
"eval_samples_per_second": 5.254,
"eval_steps_per_second": 1.751,
"step": 30
},
{
"epoch": 0.83,
"learning_rate": 3.3493649053890326e-06,
"loss": 1.0749,
"step": 35
},
{
"epoch": 0.94,
"learning_rate": 2.7922934437178695e-07,
"loss": 1.0689,
"step": 40
},
{
"epoch": 0.94,
"eval_loss": 1.0651096105575562,
"eval_runtime": 24.5601,
"eval_samples_per_second": 5.252,
"eval_steps_per_second": 1.751,
"step": 40
},
{
"epoch": 0.99,
"step": 42,
"total_flos": 6.447644673468006e+16,
"train_loss": 1.086761324178605,
"train_runtime": 3234.0471,
"train_samples_per_second": 1.572,
"train_steps_per_second": 0.013
}
],
"logging_steps": 5,
"max_steps": 42,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 20,
"total_flos": 6.447644673468006e+16,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}
|