End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +804 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.09,
|
| 3 |
+
"eval_accuracy": 0.6296296296296297,
|
| 4 |
+
"eval_loss": 0.9675703644752502,
|
| 5 |
+
"eval_runtime": 245.8322,
|
| 6 |
+
"eval_samples_per_second": 0.879,
|
| 7 |
+
"eval_steps_per_second": 0.22
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.09,
|
| 3 |
+
"eval_accuracy": 0.6296296296296297,
|
| 4 |
+
"eval_loss": 0.9675703644752502,
|
| 5 |
+
"eval_runtime": 245.8322,
|
| 6 |
+
"eval_samples_per_second": 0.879,
|
| 7 |
+
"eval_steps_per_second": 0.22
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,804 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.695852534562212,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-subset-check10\\checkpoint-672",
|
| 4 |
+
"epoch": 9.091891891891892,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1110,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.00900900900901e-07,
|
| 14 |
+
"loss": 1.5887,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1.801801801801802e-06,
|
| 20 |
+
"loss": 1.5353,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 2.702702702702703e-06,
|
| 26 |
+
"loss": 1.7015,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 3.603603603603604e-06,
|
| 32 |
+
"loss": 1.7182,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 4.504504504504505e-06,
|
| 38 |
+
"loss": 1.6539,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 5.405405405405406e-06,
|
| 44 |
+
"loss": 1.6226,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 6.3063063063063065e-06,
|
| 50 |
+
"loss": 1.6224,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 7.207207207207208e-06,
|
| 56 |
+
"loss": 1.6235,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08,
|
| 61 |
+
"learning_rate": 8.108108108108109e-06,
|
| 62 |
+
"loss": 1.5938,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.09,
|
| 67 |
+
"learning_rate": 9.00900900900901e-06,
|
| 68 |
+
"loss": 1.6337,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1,
|
| 73 |
+
"learning_rate": 9.90990990990991e-06,
|
| 74 |
+
"loss": 1.6046,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.1,
|
| 79 |
+
"eval_accuracy": 0.25806451612903225,
|
| 80 |
+
"eval_loss": 1.5695339441299438,
|
| 81 |
+
"eval_runtime": 249.7787,
|
| 82 |
+
"eval_samples_per_second": 0.869,
|
| 83 |
+
"eval_steps_per_second": 0.22,
|
| 84 |
+
"step": 112
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.01,
|
| 88 |
+
"learning_rate": 9.90990990990991e-06,
|
| 89 |
+
"loss": 1.647,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.02,
|
| 94 |
+
"learning_rate": 9.80980980980981e-06,
|
| 95 |
+
"loss": 1.6145,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.03,
|
| 100 |
+
"learning_rate": 9.70970970970971e-06,
|
| 101 |
+
"loss": 1.6142,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.03,
|
| 106 |
+
"learning_rate": 9.60960960960961e-06,
|
| 107 |
+
"loss": 1.5794,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.04,
|
| 112 |
+
"learning_rate": 9.50950950950951e-06,
|
| 113 |
+
"loss": 1.6285,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.05,
|
| 118 |
+
"learning_rate": 9.40940940940941e-06,
|
| 119 |
+
"loss": 1.6502,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.06,
|
| 124 |
+
"learning_rate": 9.30930930930931e-06,
|
| 125 |
+
"loss": 1.592,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.07,
|
| 130 |
+
"learning_rate": 9.20920920920921e-06,
|
| 131 |
+
"loss": 1.5668,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.08,
|
| 136 |
+
"learning_rate": 9.10910910910911e-06,
|
| 137 |
+
"loss": 1.5899,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.09,
|
| 142 |
+
"learning_rate": 9.00900900900901e-06,
|
| 143 |
+
"loss": 1.5833,
|
| 144 |
+
"step": 210
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1,
|
| 148 |
+
"learning_rate": 8.90890890890891e-06,
|
| 149 |
+
"loss": 1.5968,
|
| 150 |
+
"step": 220
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.1,
|
| 154 |
+
"eval_accuracy": 0.35023041474654376,
|
| 155 |
+
"eval_loss": 1.5343234539031982,
|
| 156 |
+
"eval_runtime": 242.9337,
|
| 157 |
+
"eval_samples_per_second": 0.893,
|
| 158 |
+
"eval_steps_per_second": 0.226,
|
| 159 |
+
"step": 224
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.01,
|
| 163 |
+
"learning_rate": 8.80880880880881e-06,
|
| 164 |
+
"loss": 1.5773,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.01,
|
| 169 |
+
"learning_rate": 8.70870870870871e-06,
|
| 170 |
+
"loss": 1.5444,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.02,
|
| 175 |
+
"learning_rate": 8.60860860860861e-06,
|
| 176 |
+
"loss": 1.5415,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.03,
|
| 181 |
+
"learning_rate": 8.50850850850851e-06,
|
| 182 |
+
"loss": 1.6062,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.04,
|
| 187 |
+
"learning_rate": 8.408408408408409e-06,
|
| 188 |
+
"loss": 1.5822,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.05,
|
| 193 |
+
"learning_rate": 8.308308308308309e-06,
|
| 194 |
+
"loss": 1.5927,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.06,
|
| 199 |
+
"learning_rate": 8.208208208208209e-06,
|
| 200 |
+
"loss": 1.5522,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.07,
|
| 205 |
+
"learning_rate": 8.108108108108109e-06,
|
| 206 |
+
"loss": 1.5235,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.08,
|
| 211 |
+
"learning_rate": 8.00800800800801e-06,
|
| 212 |
+
"loss": 1.4114,
|
| 213 |
+
"step": 310
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.09,
|
| 217 |
+
"learning_rate": 7.90790790790791e-06,
|
| 218 |
+
"loss": 1.4298,
|
| 219 |
+
"step": 320
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.1,
|
| 223 |
+
"learning_rate": 7.807807807807808e-06,
|
| 224 |
+
"loss": 1.4175,
|
| 225 |
+
"step": 330
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.1,
|
| 229 |
+
"eval_accuracy": 0.3087557603686636,
|
| 230 |
+
"eval_loss": 1.4348102807998657,
|
| 231 |
+
"eval_runtime": 240.8731,
|
| 232 |
+
"eval_samples_per_second": 0.901,
|
| 233 |
+
"eval_steps_per_second": 0.228,
|
| 234 |
+
"step": 336
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.0,
|
| 238 |
+
"learning_rate": 7.707707707707708e-06,
|
| 239 |
+
"loss": 1.4797,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.01,
|
| 244 |
+
"learning_rate": 7.607607607607608e-06,
|
| 245 |
+
"loss": 1.3278,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.02,
|
| 250 |
+
"learning_rate": 7.507507507507507e-06,
|
| 251 |
+
"loss": 1.3857,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.03,
|
| 256 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 257 |
+
"loss": 1.3716,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.04,
|
| 262 |
+
"learning_rate": 7.307307307307308e-06,
|
| 263 |
+
"loss": 1.2211,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.05,
|
| 268 |
+
"learning_rate": 7.207207207207208e-06,
|
| 269 |
+
"loss": 1.1444,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.06,
|
| 274 |
+
"learning_rate": 7.107107107107107e-06,
|
| 275 |
+
"loss": 1.3465,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.07,
|
| 280 |
+
"learning_rate": 7.007007007007007e-06,
|
| 281 |
+
"loss": 1.1234,
|
| 282 |
+
"step": 410
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.08,
|
| 286 |
+
"learning_rate": 6.906906906906907e-06,
|
| 287 |
+
"loss": 1.2907,
|
| 288 |
+
"step": 420
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.08,
|
| 292 |
+
"learning_rate": 6.8068068068068075e-06,
|
| 293 |
+
"loss": 1.425,
|
| 294 |
+
"step": 430
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.09,
|
| 298 |
+
"learning_rate": 6.706706706706707e-06,
|
| 299 |
+
"loss": 1.2801,
|
| 300 |
+
"step": 440
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.1,
|
| 304 |
+
"eval_accuracy": 0.6774193548387096,
|
| 305 |
+
"eval_loss": 0.9526783227920532,
|
| 306 |
+
"eval_runtime": 245.305,
|
| 307 |
+
"eval_samples_per_second": 0.885,
|
| 308 |
+
"eval_steps_per_second": 0.224,
|
| 309 |
+
"step": 448
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 4.0,
|
| 313 |
+
"learning_rate": 6.606606606606607e-06,
|
| 314 |
+
"loss": 1.2925,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.01,
|
| 319 |
+
"learning_rate": 6.506506506506507e-06,
|
| 320 |
+
"loss": 1.3201,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.02,
|
| 325 |
+
"learning_rate": 6.406406406406407e-06,
|
| 326 |
+
"loss": 1.1051,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.03,
|
| 331 |
+
"learning_rate": 6.3063063063063065e-06,
|
| 332 |
+
"loss": 1.2123,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.04,
|
| 337 |
+
"learning_rate": 6.206206206206207e-06,
|
| 338 |
+
"loss": 1.2441,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.05,
|
| 343 |
+
"learning_rate": 6.106106106106107e-06,
|
| 344 |
+
"loss": 1.1385,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.06,
|
| 349 |
+
"learning_rate": 6.006006006006007e-06,
|
| 350 |
+
"loss": 1.3137,
|
| 351 |
+
"step": 510
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.06,
|
| 355 |
+
"learning_rate": 5.905905905905906e-06,
|
| 356 |
+
"loss": 0.9632,
|
| 357 |
+
"step": 520
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.07,
|
| 361 |
+
"learning_rate": 5.805805805805806e-06,
|
| 362 |
+
"loss": 1.0695,
|
| 363 |
+
"step": 530
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.08,
|
| 367 |
+
"learning_rate": 5.7057057057057065e-06,
|
| 368 |
+
"loss": 1.1174,
|
| 369 |
+
"step": 540
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.09,
|
| 373 |
+
"learning_rate": 5.605605605605607e-06,
|
| 374 |
+
"loss": 1.0316,
|
| 375 |
+
"step": 550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.1,
|
| 379 |
+
"learning_rate": 5.505505505505506e-06,
|
| 380 |
+
"loss": 1.1862,
|
| 381 |
+
"step": 560
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.1,
|
| 385 |
+
"eval_accuracy": 0.5253456221198156,
|
| 386 |
+
"eval_loss": 1.1451939344406128,
|
| 387 |
+
"eval_runtime": 246.4332,
|
| 388 |
+
"eval_samples_per_second": 0.881,
|
| 389 |
+
"eval_steps_per_second": 0.223,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.01,
|
| 394 |
+
"learning_rate": 5.405405405405406e-06,
|
| 395 |
+
"loss": 1.3134,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.02,
|
| 400 |
+
"learning_rate": 5.305305305305306e-06,
|
| 401 |
+
"loss": 1.0395,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.03,
|
| 406 |
+
"learning_rate": 5.205205205205206e-06,
|
| 407 |
+
"loss": 1.2184,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.04,
|
| 412 |
+
"learning_rate": 5.105105105105106e-06,
|
| 413 |
+
"loss": 1.1067,
|
| 414 |
+
"step": 600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.05,
|
| 418 |
+
"learning_rate": 5.005005005005006e-06,
|
| 419 |
+
"loss": 1.0606,
|
| 420 |
+
"step": 610
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.05,
|
| 424 |
+
"learning_rate": 4.904904904904905e-06,
|
| 425 |
+
"loss": 1.1704,
|
| 426 |
+
"step": 620
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.06,
|
| 430 |
+
"learning_rate": 4.804804804804805e-06,
|
| 431 |
+
"loss": 1.0887,
|
| 432 |
+
"step": 630
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.07,
|
| 436 |
+
"learning_rate": 4.704704704704705e-06,
|
| 437 |
+
"loss": 1.0193,
|
| 438 |
+
"step": 640
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 5.08,
|
| 442 |
+
"learning_rate": 4.604604604604605e-06,
|
| 443 |
+
"loss": 1.278,
|
| 444 |
+
"step": 650
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.09,
|
| 448 |
+
"learning_rate": 4.504504504504505e-06,
|
| 449 |
+
"loss": 1.0477,
|
| 450 |
+
"step": 660
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.1,
|
| 454 |
+
"learning_rate": 4.404404404404405e-06,
|
| 455 |
+
"loss": 1.1711,
|
| 456 |
+
"step": 670
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 5.1,
|
| 460 |
+
"eval_accuracy": 0.695852534562212,
|
| 461 |
+
"eval_loss": 0.9195253849029541,
|
| 462 |
+
"eval_runtime": 261.4129,
|
| 463 |
+
"eval_samples_per_second": 0.83,
|
| 464 |
+
"eval_steps_per_second": 0.21,
|
| 465 |
+
"step": 672
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.01,
|
| 469 |
+
"learning_rate": 4.304304304304305e-06,
|
| 470 |
+
"loss": 1.239,
|
| 471 |
+
"step": 680
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.02,
|
| 475 |
+
"learning_rate": 4.204204204204204e-06,
|
| 476 |
+
"loss": 1.073,
|
| 477 |
+
"step": 690
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.03,
|
| 481 |
+
"learning_rate": 4.1041041041041045e-06,
|
| 482 |
+
"loss": 1.2066,
|
| 483 |
+
"step": 700
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.03,
|
| 487 |
+
"learning_rate": 4.004004004004005e-06,
|
| 488 |
+
"loss": 1.0543,
|
| 489 |
+
"step": 710
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 6.04,
|
| 493 |
+
"learning_rate": 3.903903903903904e-06,
|
| 494 |
+
"loss": 1.1592,
|
| 495 |
+
"step": 720
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 6.05,
|
| 499 |
+
"learning_rate": 3.803803803803804e-06,
|
| 500 |
+
"loss": 0.8946,
|
| 501 |
+
"step": 730
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 6.06,
|
| 505 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 506 |
+
"loss": 1.1558,
|
| 507 |
+
"step": 740
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 6.07,
|
| 511 |
+
"learning_rate": 3.603603603603604e-06,
|
| 512 |
+
"loss": 1.1437,
|
| 513 |
+
"step": 750
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 6.08,
|
| 517 |
+
"learning_rate": 3.5035035035035036e-06,
|
| 518 |
+
"loss": 0.9612,
|
| 519 |
+
"step": 760
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 6.09,
|
| 523 |
+
"learning_rate": 3.4034034034034037e-06,
|
| 524 |
+
"loss": 1.0189,
|
| 525 |
+
"step": 770
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.1,
|
| 529 |
+
"learning_rate": 3.3033033033033035e-06,
|
| 530 |
+
"loss": 1.0642,
|
| 531 |
+
"step": 780
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 6.1,
|
| 535 |
+
"eval_accuracy": 0.663594470046083,
|
| 536 |
+
"eval_loss": 0.930267333984375,
|
| 537 |
+
"eval_runtime": 258.3915,
|
| 538 |
+
"eval_samples_per_second": 0.84,
|
| 539 |
+
"eval_steps_per_second": 0.213,
|
| 540 |
+
"step": 784
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 7.01,
|
| 544 |
+
"learning_rate": 3.2032032032032036e-06,
|
| 545 |
+
"loss": 1.1002,
|
| 546 |
+
"step": 790
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 7.01,
|
| 550 |
+
"learning_rate": 3.1031031031031033e-06,
|
| 551 |
+
"loss": 1.0455,
|
| 552 |
+
"step": 800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 7.02,
|
| 556 |
+
"learning_rate": 3.0030030030030034e-06,
|
| 557 |
+
"loss": 0.8475,
|
| 558 |
+
"step": 810
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 7.03,
|
| 562 |
+
"learning_rate": 2.902902902902903e-06,
|
| 563 |
+
"loss": 1.0692,
|
| 564 |
+
"step": 820
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 7.04,
|
| 568 |
+
"learning_rate": 2.8028028028028033e-06,
|
| 569 |
+
"loss": 1.0054,
|
| 570 |
+
"step": 830
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 7.05,
|
| 574 |
+
"learning_rate": 2.702702702702703e-06,
|
| 575 |
+
"loss": 0.9281,
|
| 576 |
+
"step": 840
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.06,
|
| 580 |
+
"learning_rate": 2.602602602602603e-06,
|
| 581 |
+
"loss": 1.1439,
|
| 582 |
+
"step": 850
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 7.07,
|
| 586 |
+
"learning_rate": 2.502502502502503e-06,
|
| 587 |
+
"loss": 1.16,
|
| 588 |
+
"step": 860
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 7.08,
|
| 592 |
+
"learning_rate": 2.4024024024024026e-06,
|
| 593 |
+
"loss": 1.0354,
|
| 594 |
+
"step": 870
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 7.09,
|
| 598 |
+
"learning_rate": 2.3023023023023023e-06,
|
| 599 |
+
"loss": 1.0337,
|
| 600 |
+
"step": 880
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 7.1,
|
| 604 |
+
"learning_rate": 2.2022022022022024e-06,
|
| 605 |
+
"loss": 1.2081,
|
| 606 |
+
"step": 890
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 7.1,
|
| 610 |
+
"eval_accuracy": 0.5714285714285714,
|
| 611 |
+
"eval_loss": 1.0957374572753906,
|
| 612 |
+
"eval_runtime": 262.8467,
|
| 613 |
+
"eval_samples_per_second": 0.826,
|
| 614 |
+
"eval_steps_per_second": 0.209,
|
| 615 |
+
"step": 896
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 8.0,
|
| 619 |
+
"learning_rate": 2.102102102102102e-06,
|
| 620 |
+
"loss": 0.9907,
|
| 621 |
+
"step": 900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 8.01,
|
| 625 |
+
"learning_rate": 2.0020020020020023e-06,
|
| 626 |
+
"loss": 0.8092,
|
| 627 |
+
"step": 910
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 8.02,
|
| 631 |
+
"learning_rate": 1.901901901901902e-06,
|
| 632 |
+
"loss": 1.0036,
|
| 633 |
+
"step": 920
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 8.03,
|
| 637 |
+
"learning_rate": 1.801801801801802e-06,
|
| 638 |
+
"loss": 1.1223,
|
| 639 |
+
"step": 930
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 8.04,
|
| 643 |
+
"learning_rate": 1.7017017017017019e-06,
|
| 644 |
+
"loss": 0.9677,
|
| 645 |
+
"step": 940
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 8.05,
|
| 649 |
+
"learning_rate": 1.6016016016016018e-06,
|
| 650 |
+
"loss": 1.2335,
|
| 651 |
+
"step": 950
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 8.06,
|
| 655 |
+
"learning_rate": 1.5015015015015017e-06,
|
| 656 |
+
"loss": 0.955,
|
| 657 |
+
"step": 960
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 8.07,
|
| 661 |
+
"learning_rate": 1.4014014014014016e-06,
|
| 662 |
+
"loss": 0.9118,
|
| 663 |
+
"step": 970
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 8.08,
|
| 667 |
+
"learning_rate": 1.3013013013013016e-06,
|
| 668 |
+
"loss": 0.8291,
|
| 669 |
+
"step": 980
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 8.08,
|
| 673 |
+
"learning_rate": 1.2012012012012013e-06,
|
| 674 |
+
"loss": 0.9022,
|
| 675 |
+
"step": 990
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 8.09,
|
| 679 |
+
"learning_rate": 1.1011011011011012e-06,
|
| 680 |
+
"loss": 0.9326,
|
| 681 |
+
"step": 1000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.1,
|
| 685 |
+
"eval_accuracy": 0.6774193548387096,
|
| 686 |
+
"eval_loss": 0.9903221130371094,
|
| 687 |
+
"eval_runtime": 269.2441,
|
| 688 |
+
"eval_samples_per_second": 0.806,
|
| 689 |
+
"eval_steps_per_second": 0.204,
|
| 690 |
+
"step": 1008
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 9.0,
|
| 694 |
+
"learning_rate": 1.0010010010010011e-06,
|
| 695 |
+
"loss": 0.9637,
|
| 696 |
+
"step": 1010
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 9.01,
|
| 700 |
+
"learning_rate": 9.00900900900901e-07,
|
| 701 |
+
"loss": 0.9025,
|
| 702 |
+
"step": 1020
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 9.02,
|
| 706 |
+
"learning_rate": 8.008008008008009e-07,
|
| 707 |
+
"loss": 1.1127,
|
| 708 |
+
"step": 1030
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 9.03,
|
| 712 |
+
"learning_rate": 7.007007007007008e-07,
|
| 713 |
+
"loss": 1.1973,
|
| 714 |
+
"step": 1040
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 9.04,
|
| 718 |
+
"learning_rate": 6.006006006006006e-07,
|
| 719 |
+
"loss": 1.0499,
|
| 720 |
+
"step": 1050
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 9.05,
|
| 724 |
+
"learning_rate": 5.005005005005006e-07,
|
| 725 |
+
"loss": 0.9258,
|
| 726 |
+
"step": 1060
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 9.06,
|
| 730 |
+
"learning_rate": 4.0040040040040045e-07,
|
| 731 |
+
"loss": 0.9574,
|
| 732 |
+
"step": 1070
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 9.06,
|
| 736 |
+
"learning_rate": 3.003003003003003e-07,
|
| 737 |
+
"loss": 0.9015,
|
| 738 |
+
"step": 1080
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 9.07,
|
| 742 |
+
"learning_rate": 2.0020020020020022e-07,
|
| 743 |
+
"loss": 0.8953,
|
| 744 |
+
"step": 1090
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 9.08,
|
| 748 |
+
"learning_rate": 1.0010010010010011e-07,
|
| 749 |
+
"loss": 0.9562,
|
| 750 |
+
"step": 1100
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 9.09,
|
| 754 |
+
"learning_rate": 0.0,
|
| 755 |
+
"loss": 0.9876,
|
| 756 |
+
"step": 1110
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 9.09,
|
| 760 |
+
"eval_accuracy": 0.6820276497695853,
|
| 761 |
+
"eval_loss": 0.9823296666145325,
|
| 762 |
+
"eval_runtime": 254.2301,
|
| 763 |
+
"eval_samples_per_second": 0.854,
|
| 764 |
+
"eval_steps_per_second": 0.216,
|
| 765 |
+
"step": 1110
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 9.09,
|
| 769 |
+
"step": 1110,
|
| 770 |
+
"total_flos": 5.521459915462902e+18,
|
| 771 |
+
"train_loss": 1.2459339373820537,
|
| 772 |
+
"train_runtime": 8821.2839,
|
| 773 |
+
"train_samples_per_second": 0.503,
|
| 774 |
+
"train_steps_per_second": 0.126
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 9.09,
|
| 778 |
+
"eval_accuracy": 0.6296296296296297,
|
| 779 |
+
"eval_loss": 0.9675703644752502,
|
| 780 |
+
"eval_runtime": 263.6821,
|
| 781 |
+
"eval_samples_per_second": 0.819,
|
| 782 |
+
"eval_steps_per_second": 0.205,
|
| 783 |
+
"step": 1110
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.09,
|
| 787 |
+
"eval_accuracy": 0.6296296296296297,
|
| 788 |
+
"eval_loss": 0.9675703644752502,
|
| 789 |
+
"eval_runtime": 245.8322,
|
| 790 |
+
"eval_samples_per_second": 0.879,
|
| 791 |
+
"eval_steps_per_second": 0.22,
|
| 792 |
+
"step": 1110
|
| 793 |
+
}
|
| 794 |
+
],
|
| 795 |
+
"logging_steps": 10,
|
| 796 |
+
"max_steps": 1110,
|
| 797 |
+
"num_input_tokens_seen": 0,
|
| 798 |
+
"num_train_epochs": 9223372036854775807,
|
| 799 |
+
"save_steps": 500,
|
| 800 |
+
"total_flos": 5.521459915462902e+18,
|
| 801 |
+
"train_batch_size": 4,
|
| 802 |
+
"trial_name": null,
|
| 803 |
+
"trial_params": null
|
| 804 |
+
}
|