Upload checkpoint-1100/trainer_state.json with huggingface_hub
Browse files
checkpoint-1100/trainer_state.json
ADDED
|
@@ -0,0 +1,900 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.08991385996341705,
|
| 3 |
+
"best_model_checkpoint": "./fine_tuned_meta_encoder_20240823_155731/checkpoint-1100",
|
| 4 |
+
"epoch": 2.9042904290429044,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.026402640264026403,
|
| 13 |
+
"grad_norm": 1.2209537029266357,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 1.3132,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.052805280528052806,
|
| 20 |
+
"grad_norm": 0.8953336477279663,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 0.5263,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07920792079207921,
|
| 27 |
+
"grad_norm": 0.4192950427532196,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 0.2848,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10561056105610561,
|
| 34 |
+
"grad_norm": 0.27445298433303833,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.2399,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.132013201320132,
|
| 41 |
+
"grad_norm": 0.3270169794559479,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.2224,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15841584158415842,
|
| 48 |
+
"grad_norm": 0.27454960346221924,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.2188,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1848184818481848,
|
| 55 |
+
"grad_norm": 0.3361058235168457,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.1904,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.21122112211221122,
|
| 62 |
+
"grad_norm": 0.2786653935909271,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.1913,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2376237623762376,
|
| 69 |
+
"grad_norm": 0.2567278742790222,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.1818,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.264026402640264,
|
| 76 |
+
"grad_norm": 0.26846471428871155,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.1652,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.264026402640264,
|
| 83 |
+
"eval_loss": 0.17934565246105194,
|
| 84 |
+
"eval_runtime": 35.5662,
|
| 85 |
+
"eval_samples_per_second": 18.951,
|
| 86 |
+
"eval_steps_per_second": 4.752,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.29042904290429045,
|
| 91 |
+
"grad_norm": 0.3001416027545929,
|
| 92 |
+
"learning_rate": 0.0002,
|
| 93 |
+
"loss": 0.1711,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.31683168316831684,
|
| 98 |
+
"grad_norm": 0.27367591857910156,
|
| 99 |
+
"learning_rate": 0.0002,
|
| 100 |
+
"loss": 0.1649,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3432343234323432,
|
| 105 |
+
"grad_norm": 0.2346794754266739,
|
| 106 |
+
"learning_rate": 0.0002,
|
| 107 |
+
"loss": 0.1721,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3696369636963696,
|
| 112 |
+
"grad_norm": 0.2470114529132843,
|
| 113 |
+
"learning_rate": 0.0002,
|
| 114 |
+
"loss": 0.1599,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.39603960396039606,
|
| 119 |
+
"grad_norm": 0.2749585807323456,
|
| 120 |
+
"learning_rate": 0.0002,
|
| 121 |
+
"loss": 0.1648,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.42244224422442245,
|
| 126 |
+
"grad_norm": 0.23965956270694733,
|
| 127 |
+
"learning_rate": 0.0002,
|
| 128 |
+
"loss": 0.1584,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.44884488448844884,
|
| 133 |
+
"grad_norm": 0.2817020118236542,
|
| 134 |
+
"learning_rate": 0.0002,
|
| 135 |
+
"loss": 0.1567,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4752475247524752,
|
| 140 |
+
"grad_norm": 0.3235905170440674,
|
| 141 |
+
"learning_rate": 0.0002,
|
| 142 |
+
"loss": 0.1494,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5016501650165016,
|
| 147 |
+
"grad_norm": 0.2556610405445099,
|
| 148 |
+
"learning_rate": 0.0002,
|
| 149 |
+
"loss": 0.1494,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.528052805280528,
|
| 154 |
+
"grad_norm": 0.26074209809303284,
|
| 155 |
+
"learning_rate": 0.0002,
|
| 156 |
+
"loss": 0.1496,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.528052805280528,
|
| 161 |
+
"eval_loss": 0.15303318202495575,
|
| 162 |
+
"eval_runtime": 35.5044,
|
| 163 |
+
"eval_samples_per_second": 18.984,
|
| 164 |
+
"eval_steps_per_second": 4.76,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.5544554455445545,
|
| 169 |
+
"grad_norm": 0.24563810229301453,
|
| 170 |
+
"learning_rate": 0.0002,
|
| 171 |
+
"loss": 0.1523,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.5808580858085809,
|
| 176 |
+
"grad_norm": 0.2592566907405853,
|
| 177 |
+
"learning_rate": 0.0002,
|
| 178 |
+
"loss": 0.1453,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.6072607260726073,
|
| 183 |
+
"grad_norm": 0.3210408389568329,
|
| 184 |
+
"learning_rate": 0.0002,
|
| 185 |
+
"loss": 0.1414,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.6336633663366337,
|
| 190 |
+
"grad_norm": 0.2894737720489502,
|
| 191 |
+
"learning_rate": 0.0002,
|
| 192 |
+
"loss": 0.1479,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.6600660066006601,
|
| 197 |
+
"grad_norm": 0.307718425989151,
|
| 198 |
+
"learning_rate": 0.0002,
|
| 199 |
+
"loss": 0.143,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.6864686468646864,
|
| 204 |
+
"grad_norm": 0.2861904799938202,
|
| 205 |
+
"learning_rate": 0.0002,
|
| 206 |
+
"loss": 0.1422,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.7128712871287128,
|
| 211 |
+
"grad_norm": 0.2835065424442291,
|
| 212 |
+
"learning_rate": 0.0002,
|
| 213 |
+
"loss": 0.1381,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.7392739273927392,
|
| 218 |
+
"grad_norm": 0.36195576190948486,
|
| 219 |
+
"learning_rate": 0.0002,
|
| 220 |
+
"loss": 0.1364,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.7656765676567657,
|
| 225 |
+
"grad_norm": 0.36926591396331787,
|
| 226 |
+
"learning_rate": 0.0002,
|
| 227 |
+
"loss": 0.1364,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.7920792079207921,
|
| 232 |
+
"grad_norm": 0.2543686628341675,
|
| 233 |
+
"learning_rate": 0.0002,
|
| 234 |
+
"loss": 0.1295,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.7920792079207921,
|
| 239 |
+
"eval_loss": 0.13678725063800812,
|
| 240 |
+
"eval_runtime": 35.5612,
|
| 241 |
+
"eval_samples_per_second": 18.953,
|
| 242 |
+
"eval_steps_per_second": 4.752,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.8184818481848185,
|
| 247 |
+
"grad_norm": 0.2578878402709961,
|
| 248 |
+
"learning_rate": 0.0002,
|
| 249 |
+
"loss": 0.1373,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.8448844884488449,
|
| 254 |
+
"grad_norm": 0.2869018018245697,
|
| 255 |
+
"learning_rate": 0.0002,
|
| 256 |
+
"loss": 0.1365,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.8712871287128713,
|
| 261 |
+
"grad_norm": 0.2525601089000702,
|
| 262 |
+
"learning_rate": 0.0002,
|
| 263 |
+
"loss": 0.1263,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.8976897689768977,
|
| 268 |
+
"grad_norm": 0.33318400382995605,
|
| 269 |
+
"learning_rate": 0.0002,
|
| 270 |
+
"loss": 0.1342,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.9240924092409241,
|
| 275 |
+
"grad_norm": 0.26829567551612854,
|
| 276 |
+
"learning_rate": 0.0002,
|
| 277 |
+
"loss": 0.1217,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.9504950495049505,
|
| 282 |
+
"grad_norm": 0.29827719926834106,
|
| 283 |
+
"learning_rate": 0.0002,
|
| 284 |
+
"loss": 0.1251,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.976897689768977,
|
| 289 |
+
"grad_norm": 0.2644639313220978,
|
| 290 |
+
"learning_rate": 0.0002,
|
| 291 |
+
"loss": 0.1172,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.0033003300330032,
|
| 296 |
+
"grad_norm": 0.2535085082054138,
|
| 297 |
+
"learning_rate": 0.0002,
|
| 298 |
+
"loss": 0.1275,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0297029702970297,
|
| 303 |
+
"grad_norm": 0.2713930606842041,
|
| 304 |
+
"learning_rate": 0.0002,
|
| 305 |
+
"loss": 0.1162,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.056105610561056,
|
| 310 |
+
"grad_norm": 0.26092982292175293,
|
| 311 |
+
"learning_rate": 0.0002,
|
| 312 |
+
"loss": 0.1209,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.056105610561056,
|
| 317 |
+
"eval_loss": 0.12458474934101105,
|
| 318 |
+
"eval_runtime": 35.5248,
|
| 319 |
+
"eval_samples_per_second": 18.973,
|
| 320 |
+
"eval_steps_per_second": 4.757,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.0825082508250825,
|
| 325 |
+
"grad_norm": 0.3101023733615875,
|
| 326 |
+
"learning_rate": 0.0002,
|
| 327 |
+
"loss": 0.1206,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.108910891089109,
|
| 332 |
+
"grad_norm": 0.2629012167453766,
|
| 333 |
+
"learning_rate": 0.0002,
|
| 334 |
+
"loss": 0.1165,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.1353135313531353,
|
| 339 |
+
"grad_norm": 0.2954414188861847,
|
| 340 |
+
"learning_rate": 0.0002,
|
| 341 |
+
"loss": 0.121,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.1617161716171618,
|
| 346 |
+
"grad_norm": 0.3219696879386902,
|
| 347 |
+
"learning_rate": 0.0002,
|
| 348 |
+
"loss": 0.1155,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.188118811881188,
|
| 353 |
+
"grad_norm": 0.2916986346244812,
|
| 354 |
+
"learning_rate": 0.0002,
|
| 355 |
+
"loss": 0.1109,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.2145214521452146,
|
| 360 |
+
"grad_norm": 0.2607131600379944,
|
| 361 |
+
"learning_rate": 0.0002,
|
| 362 |
+
"loss": 0.1125,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.2409240924092408,
|
| 367 |
+
"grad_norm": 0.25215160846710205,
|
| 368 |
+
"learning_rate": 0.0002,
|
| 369 |
+
"loss": 0.1155,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.2673267326732673,
|
| 374 |
+
"grad_norm": 0.2367628961801529,
|
| 375 |
+
"learning_rate": 0.0002,
|
| 376 |
+
"loss": 0.1119,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.2937293729372938,
|
| 381 |
+
"grad_norm": 0.2621775269508362,
|
| 382 |
+
"learning_rate": 0.0002,
|
| 383 |
+
"loss": 0.106,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.3201320132013201,
|
| 388 |
+
"grad_norm": 0.27597054839134216,
|
| 389 |
+
"learning_rate": 0.0002,
|
| 390 |
+
"loss": 0.1071,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.3201320132013201,
|
| 395 |
+
"eval_loss": 0.11538028717041016,
|
| 396 |
+
"eval_runtime": 35.6246,
|
| 397 |
+
"eval_samples_per_second": 18.92,
|
| 398 |
+
"eval_steps_per_second": 4.744,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.3465346534653464,
|
| 403 |
+
"grad_norm": 0.3191552758216858,
|
| 404 |
+
"learning_rate": 0.0002,
|
| 405 |
+
"loss": 0.11,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.372937293729373,
|
| 410 |
+
"grad_norm": 0.32491299510002136,
|
| 411 |
+
"learning_rate": 0.0002,
|
| 412 |
+
"loss": 0.1072,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.3993399339933994,
|
| 417 |
+
"grad_norm": 0.3281764090061188,
|
| 418 |
+
"learning_rate": 0.0002,
|
| 419 |
+
"loss": 0.1141,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.4257425742574257,
|
| 424 |
+
"grad_norm": 0.24705563485622406,
|
| 425 |
+
"learning_rate": 0.0002,
|
| 426 |
+
"loss": 0.1026,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.4521452145214522,
|
| 431 |
+
"grad_norm": 0.24219994246959686,
|
| 432 |
+
"learning_rate": 0.0002,
|
| 433 |
+
"loss": 0.1058,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.4785478547854787,
|
| 438 |
+
"grad_norm": 0.2313147485256195,
|
| 439 |
+
"learning_rate": 0.0002,
|
| 440 |
+
"loss": 0.104,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.504950495049505,
|
| 445 |
+
"grad_norm": 0.34662193059921265,
|
| 446 |
+
"learning_rate": 0.0002,
|
| 447 |
+
"loss": 0.1007,
|
| 448 |
+
"step": 570
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.5313531353135312,
|
| 452 |
+
"grad_norm": 0.2655913829803467,
|
| 453 |
+
"learning_rate": 0.0002,
|
| 454 |
+
"loss": 0.102,
|
| 455 |
+
"step": 580
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.5577557755775577,
|
| 459 |
+
"grad_norm": 0.2477431297302246,
|
| 460 |
+
"learning_rate": 0.0002,
|
| 461 |
+
"loss": 0.1073,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.5841584158415842,
|
| 466 |
+
"grad_norm": 0.2847592532634735,
|
| 467 |
+
"learning_rate": 0.0002,
|
| 468 |
+
"loss": 0.1049,
|
| 469 |
+
"step": 600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.5841584158415842,
|
| 473 |
+
"eval_loss": 0.10829836875200272,
|
| 474 |
+
"eval_runtime": 35.5648,
|
| 475 |
+
"eval_samples_per_second": 18.951,
|
| 476 |
+
"eval_steps_per_second": 4.752,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.6105610561056105,
|
| 481 |
+
"grad_norm": 0.24044634401798248,
|
| 482 |
+
"learning_rate": 0.0002,
|
| 483 |
+
"loss": 0.1003,
|
| 484 |
+
"step": 610
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.636963696369637,
|
| 488 |
+
"grad_norm": 0.2383195161819458,
|
| 489 |
+
"learning_rate": 0.0002,
|
| 490 |
+
"loss": 0.1023,
|
| 491 |
+
"step": 620
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.6633663366336635,
|
| 495 |
+
"grad_norm": 0.2620280981063843,
|
| 496 |
+
"learning_rate": 0.0002,
|
| 497 |
+
"loss": 0.0978,
|
| 498 |
+
"step": 630
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.6897689768976898,
|
| 502 |
+
"grad_norm": 0.27225416898727417,
|
| 503 |
+
"learning_rate": 0.0002,
|
| 504 |
+
"loss": 0.1055,
|
| 505 |
+
"step": 640
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.716171617161716,
|
| 509 |
+
"grad_norm": 0.2959238588809967,
|
| 510 |
+
"learning_rate": 0.0002,
|
| 511 |
+
"loss": 0.1015,
|
| 512 |
+
"step": 650
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.7425742574257426,
|
| 516 |
+
"grad_norm": 0.2089966982603073,
|
| 517 |
+
"learning_rate": 0.0002,
|
| 518 |
+
"loss": 0.1024,
|
| 519 |
+
"step": 660
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.768976897689769,
|
| 523 |
+
"grad_norm": 0.23935158550739288,
|
| 524 |
+
"learning_rate": 0.0002,
|
| 525 |
+
"loss": 0.1002,
|
| 526 |
+
"step": 670
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.7953795379537953,
|
| 530 |
+
"grad_norm": 0.2478724718093872,
|
| 531 |
+
"learning_rate": 0.0002,
|
| 532 |
+
"loss": 0.1016,
|
| 533 |
+
"step": 680
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.8217821782178216,
|
| 537 |
+
"grad_norm": 0.25742414593696594,
|
| 538 |
+
"learning_rate": 0.0002,
|
| 539 |
+
"loss": 0.1016,
|
| 540 |
+
"step": 690
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.8481848184818483,
|
| 544 |
+
"grad_norm": 0.2547028064727783,
|
| 545 |
+
"learning_rate": 0.0002,
|
| 546 |
+
"loss": 0.0913,
|
| 547 |
+
"step": 700
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.8481848184818483,
|
| 551 |
+
"eval_loss": 0.10148681700229645,
|
| 552 |
+
"eval_runtime": 35.5107,
|
| 553 |
+
"eval_samples_per_second": 18.98,
|
| 554 |
+
"eval_steps_per_second": 4.759,
|
| 555 |
+
"step": 700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.8745874587458746,
|
| 559 |
+
"grad_norm": 0.2965940237045288,
|
| 560 |
+
"learning_rate": 0.0002,
|
| 561 |
+
"loss": 0.0989,
|
| 562 |
+
"step": 710
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.900990099009901,
|
| 566 |
+
"grad_norm": 0.22955147922039032,
|
| 567 |
+
"learning_rate": 0.0002,
|
| 568 |
+
"loss": 0.0936,
|
| 569 |
+
"step": 720
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.9273927392739274,
|
| 573 |
+
"grad_norm": 0.2257162481546402,
|
| 574 |
+
"learning_rate": 0.0002,
|
| 575 |
+
"loss": 0.0893,
|
| 576 |
+
"step": 730
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.953795379537954,
|
| 580 |
+
"grad_norm": 0.274249404668808,
|
| 581 |
+
"learning_rate": 0.0002,
|
| 582 |
+
"loss": 0.0983,
|
| 583 |
+
"step": 740
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.9801980198019802,
|
| 587 |
+
"grad_norm": 0.25331228971481323,
|
| 588 |
+
"learning_rate": 0.0002,
|
| 589 |
+
"loss": 0.0956,
|
| 590 |
+
"step": 750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.0066006600660065,
|
| 594 |
+
"grad_norm": 0.2801855802536011,
|
| 595 |
+
"learning_rate": 0.0002,
|
| 596 |
+
"loss": 0.0948,
|
| 597 |
+
"step": 760
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.033003300330033,
|
| 601 |
+
"grad_norm": 0.24239327013492584,
|
| 602 |
+
"learning_rate": 0.0002,
|
| 603 |
+
"loss": 0.0874,
|
| 604 |
+
"step": 770
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.0594059405940595,
|
| 608 |
+
"grad_norm": 0.292223185300827,
|
| 609 |
+
"learning_rate": 0.0002,
|
| 610 |
+
"loss": 0.0874,
|
| 611 |
+
"step": 780
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.0858085808580857,
|
| 615 |
+
"grad_norm": 0.2646115720272064,
|
| 616 |
+
"learning_rate": 0.0002,
|
| 617 |
+
"loss": 0.0857,
|
| 618 |
+
"step": 790
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.112211221122112,
|
| 622 |
+
"grad_norm": 0.22307829558849335,
|
| 623 |
+
"learning_rate": 0.0002,
|
| 624 |
+
"loss": 0.0867,
|
| 625 |
+
"step": 800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.112211221122112,
|
| 629 |
+
"eval_loss": 0.09895669668912888,
|
| 630 |
+
"eval_runtime": 35.4576,
|
| 631 |
+
"eval_samples_per_second": 19.009,
|
| 632 |
+
"eval_steps_per_second": 4.766,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.1386138613861387,
|
| 637 |
+
"grad_norm": 0.2283334881067276,
|
| 638 |
+
"learning_rate": 0.0002,
|
| 639 |
+
"loss": 0.0861,
|
| 640 |
+
"step": 810
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.165016501650165,
|
| 644 |
+
"grad_norm": 0.24495747685432434,
|
| 645 |
+
"learning_rate": 0.0002,
|
| 646 |
+
"loss": 0.0865,
|
| 647 |
+
"step": 820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.1914191419141913,
|
| 651 |
+
"grad_norm": 0.2823265790939331,
|
| 652 |
+
"learning_rate": 0.0002,
|
| 653 |
+
"loss": 0.0851,
|
| 654 |
+
"step": 830
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.217821782178218,
|
| 658 |
+
"grad_norm": 0.29882529377937317,
|
| 659 |
+
"learning_rate": 0.0002,
|
| 660 |
+
"loss": 0.0883,
|
| 661 |
+
"step": 840
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.2442244224422443,
|
| 665 |
+
"grad_norm": 0.2550313174724579,
|
| 666 |
+
"learning_rate": 0.0002,
|
| 667 |
+
"loss": 0.0872,
|
| 668 |
+
"step": 850
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.2706270627062706,
|
| 672 |
+
"grad_norm": 0.24576956033706665,
|
| 673 |
+
"learning_rate": 0.0002,
|
| 674 |
+
"loss": 0.0871,
|
| 675 |
+
"step": 860
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.297029702970297,
|
| 679 |
+
"grad_norm": 0.2293216437101364,
|
| 680 |
+
"learning_rate": 0.0002,
|
| 681 |
+
"loss": 0.0852,
|
| 682 |
+
"step": 870
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.3234323432343236,
|
| 686 |
+
"grad_norm": 0.2510163486003876,
|
| 687 |
+
"learning_rate": 0.0002,
|
| 688 |
+
"loss": 0.087,
|
| 689 |
+
"step": 880
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.34983498349835,
|
| 693 |
+
"grad_norm": 0.22960515320301056,
|
| 694 |
+
"learning_rate": 0.0002,
|
| 695 |
+
"loss": 0.0829,
|
| 696 |
+
"step": 890
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.376237623762376,
|
| 700 |
+
"grad_norm": 0.26182201504707336,
|
| 701 |
+
"learning_rate": 0.0002,
|
| 702 |
+
"loss": 0.0788,
|
| 703 |
+
"step": 900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.376237623762376,
|
| 707 |
+
"eval_loss": 0.09652868658304214,
|
| 708 |
+
"eval_runtime": 35.4522,
|
| 709 |
+
"eval_samples_per_second": 19.012,
|
| 710 |
+
"eval_steps_per_second": 4.767,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.4026402640264024,
|
| 715 |
+
"grad_norm": 0.22264224290847778,
|
| 716 |
+
"learning_rate": 0.0002,
|
| 717 |
+
"loss": 0.0867,
|
| 718 |
+
"step": 910
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.429042904290429,
|
| 722 |
+
"grad_norm": 0.24472057819366455,
|
| 723 |
+
"learning_rate": 0.0002,
|
| 724 |
+
"loss": 0.085,
|
| 725 |
+
"step": 920
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.4554455445544554,
|
| 729 |
+
"grad_norm": 0.21409814059734344,
|
| 730 |
+
"learning_rate": 0.0002,
|
| 731 |
+
"loss": 0.0902,
|
| 732 |
+
"step": 930
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.4818481848184817,
|
| 736 |
+
"grad_norm": 0.2275090515613556,
|
| 737 |
+
"learning_rate": 0.0002,
|
| 738 |
+
"loss": 0.0833,
|
| 739 |
+
"step": 940
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.5082508250825084,
|
| 743 |
+
"grad_norm": 0.24984212219715118,
|
| 744 |
+
"learning_rate": 0.0002,
|
| 745 |
+
"loss": 0.0875,
|
| 746 |
+
"step": 950
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.5346534653465347,
|
| 750 |
+
"grad_norm": 0.2913050949573517,
|
| 751 |
+
"learning_rate": 0.0002,
|
| 752 |
+
"loss": 0.0821,
|
| 753 |
+
"step": 960
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.561056105610561,
|
| 757 |
+
"grad_norm": 0.30677589774131775,
|
| 758 |
+
"learning_rate": 0.0002,
|
| 759 |
+
"loss": 0.0835,
|
| 760 |
+
"step": 970
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.5874587458745877,
|
| 764 |
+
"grad_norm": 0.2401341199874878,
|
| 765 |
+
"learning_rate": 0.0002,
|
| 766 |
+
"loss": 0.088,
|
| 767 |
+
"step": 980
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.613861386138614,
|
| 771 |
+
"grad_norm": 0.25704678893089294,
|
| 772 |
+
"learning_rate": 0.0002,
|
| 773 |
+
"loss": 0.0838,
|
| 774 |
+
"step": 990
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.6402640264026402,
|
| 778 |
+
"grad_norm": 0.20528723299503326,
|
| 779 |
+
"learning_rate": 0.0002,
|
| 780 |
+
"loss": 0.0839,
|
| 781 |
+
"step": 1000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.6402640264026402,
|
| 785 |
+
"eval_loss": 0.09263003617525101,
|
| 786 |
+
"eval_runtime": 35.5469,
|
| 787 |
+
"eval_samples_per_second": 18.961,
|
| 788 |
+
"eval_steps_per_second": 4.754,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.6666666666666665,
|
| 793 |
+
"grad_norm": 0.2680225968360901,
|
| 794 |
+
"learning_rate": 0.0002,
|
| 795 |
+
"loss": 0.0877,
|
| 796 |
+
"step": 1010
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.693069306930693,
|
| 800 |
+
"grad_norm": 0.24241389334201813,
|
| 801 |
+
"learning_rate": 0.0002,
|
| 802 |
+
"loss": 0.0793,
|
| 803 |
+
"step": 1020
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.7194719471947195,
|
| 807 |
+
"grad_norm": 0.2348719835281372,
|
| 808 |
+
"learning_rate": 0.0002,
|
| 809 |
+
"loss": 0.0857,
|
| 810 |
+
"step": 1030
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.745874587458746,
|
| 814 |
+
"grad_norm": 0.25451603531837463,
|
| 815 |
+
"learning_rate": 0.0002,
|
| 816 |
+
"loss": 0.0877,
|
| 817 |
+
"step": 1040
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.772277227722772,
|
| 821 |
+
"grad_norm": 0.28436726331710815,
|
| 822 |
+
"learning_rate": 0.0002,
|
| 823 |
+
"loss": 0.0829,
|
| 824 |
+
"step": 1050
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.798679867986799,
|
| 828 |
+
"grad_norm": 0.269794225692749,
|
| 829 |
+
"learning_rate": 0.0002,
|
| 830 |
+
"loss": 0.0826,
|
| 831 |
+
"step": 1060
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.825082508250825,
|
| 835 |
+
"grad_norm": 0.22040368616580963,
|
| 836 |
+
"learning_rate": 0.0002,
|
| 837 |
+
"loss": 0.0814,
|
| 838 |
+
"step": 1070
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.8514851485148514,
|
| 842 |
+
"grad_norm": 0.2117665708065033,
|
| 843 |
+
"learning_rate": 0.0002,
|
| 844 |
+
"loss": 0.084,
|
| 845 |
+
"step": 1080
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.877887788778878,
|
| 849 |
+
"grad_norm": 0.21133095026016235,
|
| 850 |
+
"learning_rate": 0.0002,
|
| 851 |
+
"loss": 0.0838,
|
| 852 |
+
"step": 1090
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.9042904290429044,
|
| 856 |
+
"grad_norm": 0.25484949350357056,
|
| 857 |
+
"learning_rate": 0.0002,
|
| 858 |
+
"loss": 0.082,
|
| 859 |
+
"step": 1100
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.9042904290429044,
|
| 863 |
+
"eval_loss": 0.08991385996341705,
|
| 864 |
+
"eval_runtime": 35.6202,
|
| 865 |
+
"eval_samples_per_second": 18.922,
|
| 866 |
+
"eval_steps_per_second": 4.744,
|
| 867 |
+
"step": 1100
|
| 868 |
+
}
|
| 869 |
+
],
|
| 870 |
+
"logging_steps": 10,
|
| 871 |
+
"max_steps": 1134,
|
| 872 |
+
"num_input_tokens_seen": 0,
|
| 873 |
+
"num_train_epochs": 3,
|
| 874 |
+
"save_steps": 100,
|
| 875 |
+
"stateful_callbacks": {
|
| 876 |
+
"EarlyStoppingCallback": {
|
| 877 |
+
"args": {
|
| 878 |
+
"early_stopping_patience": 3,
|
| 879 |
+
"early_stopping_threshold": 0.001
|
| 880 |
+
},
|
| 881 |
+
"attributes": {
|
| 882 |
+
"early_stopping_patience_counter": 0
|
| 883 |
+
}
|
| 884 |
+
},
|
| 885 |
+
"TrainerControl": {
|
| 886 |
+
"args": {
|
| 887 |
+
"should_epoch_stop": false,
|
| 888 |
+
"should_evaluate": false,
|
| 889 |
+
"should_log": false,
|
| 890 |
+
"should_save": true,
|
| 891 |
+
"should_training_stop": false
|
| 892 |
+
},
|
| 893 |
+
"attributes": {}
|
| 894 |
+
}
|
| 895 |
+
},
|
| 896 |
+
"total_flos": 4.017625090355036e+17,
|
| 897 |
+
"train_batch_size": 4,
|
| 898 |
+
"trial_name": null,
|
| 899 |
+
"trial_params": null
|
| 900 |
+
}
|