Commit
•
75658bb
1
Parent(s):
daf6642
Upload trainer_state.json
Browse files- trainer_state.json +130 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 9820,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 4.9693251533742335e-05,
|
| 13 |
+
"loss": 20966.374,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 4.918200408997955e-05,
|
| 19 |
+
"loss": 2277.2115,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.31,
|
| 24 |
+
"learning_rate": 4.867075664621677e-05,
|
| 25 |
+
"loss": 549.5879,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.41,
|
| 30 |
+
"learning_rate": 4.815950920245399e-05,
|
| 31 |
+
"loss": 283.1544,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.51,
|
| 36 |
+
"learning_rate": 4.764826175869121e-05,
|
| 37 |
+
"loss": 184.1967,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.61,
|
| 42 |
+
"learning_rate": 4.7137014314928426e-05,
|
| 43 |
+
"loss": 137.0529,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.71,
|
| 48 |
+
"learning_rate": 4.6625766871165645e-05,
|
| 49 |
+
"loss": 114.6247,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.81,
|
| 54 |
+
"learning_rate": 4.611451942740286e-05,
|
| 55 |
+
"loss": 102.8662,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.92,
|
| 60 |
+
"learning_rate": 4.560327198364008e-05,
|
| 61 |
+
"loss": 97.2861,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.02,
|
| 66 |
+
"learning_rate": 4.5092024539877307e-05,
|
| 67 |
+
"loss": 87.1393,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.12,
|
| 72 |
+
"learning_rate": 4.4580777096114525e-05,
|
| 73 |
+
"loss": 73.0929,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.22,
|
| 78 |
+
"learning_rate": 4.4069529652351736e-05,
|
| 79 |
+
"loss": 70.3143,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.32,
|
| 84 |
+
"learning_rate": 4.3558282208588955e-05,
|
| 85 |
+
"loss": 67.2985,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.43,
|
| 90 |
+
"learning_rate": 4.304703476482618e-05,
|
| 91 |
+
"loss": 69.378,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.53,
|
| 96 |
+
"learning_rate": 4.25357873210634e-05,
|
| 97 |
+
"loss": 64.2011,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.63,
|
| 102 |
+
"learning_rate": 4.2024539877300617e-05,
|
| 103 |
+
"loss": 63.1896,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.73,
|
| 108 |
+
"learning_rate": 4.1513292433537835e-05,
|
| 109 |
+
"loss": 63.1367,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.83,
|
| 114 |
+
"learning_rate": 4.100204498977505e-05,
|
| 115 |
+
"loss": 60.7672,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.93,
|
| 120 |
+
"learning_rate": 4.049079754601227e-05,
|
| 121 |
+
"loss": 61.0841,
|
| 122 |
+
"step": 9500
|
| 123 |
+
}
|
| 124 |
+
],
|
| 125 |
+
"max_steps": 49100,
|
| 126 |
+
"num_train_epochs": 10,
|
| 127 |
+
"total_flos": 9.13949176598519e+16,
|
| 128 |
+
"trial_name": null,
|
| 129 |
+
"trial_params": null
|
| 130 |
+
}
|