Training in progress, epoch 0
Browse files- all_results.json +7 -0
- model.safetensors +1 -1
- train_results.json +7 -0
- trainer_state.json +732 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.69,
|
| 3 |
+
"train_loss": 1.3989773021803962,
|
| 4 |
+
"train_runtime": 2686.7823,
|
| 5 |
+
"train_samples_per_second": 215.019,
|
| 6 |
+
"train_steps_per_second": 0.268
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 241501816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb537367d710dc552253241b93ccdfd63866346a17353f9e474d22fb8771a021
|
| 3 |
size 241501816
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.69,
|
| 3 |
+
"train_loss": 1.3989773021803962,
|
| 4 |
+
"train_runtime": 2686.7823,
|
| 5 |
+
"train_samples_per_second": 215.019,
|
| 6 |
+
"train_steps_per_second": 0.268
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,732 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8032710280373832,
|
| 3 |
+
"best_model_checkpoint": "resnet-152-finetuned-cassava-leaf-disease/checkpoint-703",
|
| 4 |
+
"epoch": 29.690721649484537,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 720,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.41,
|
| 13 |
+
"learning_rate": 6.944444444444445e-06,
|
| 14 |
+
"loss": 7.3336,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.82,
|
| 19 |
+
"learning_rate": 1.388888888888889e-05,
|
| 20 |
+
"loss": 7.2158,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.99,
|
| 25 |
+
"eval_accuracy": 0.0014018691588785046,
|
| 26 |
+
"eval_loss": 6.815145015716553,
|
| 27 |
+
"eval_runtime": 8.158,
|
| 28 |
+
"eval_samples_per_second": 262.318,
|
| 29 |
+
"eval_steps_per_second": 1.348,
|
| 30 |
+
"step": 24
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.24,
|
| 34 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 35 |
+
"loss": 6.9635,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.65,
|
| 40 |
+
"learning_rate": 2.777777777777778e-05,
|
| 41 |
+
"loss": 6.6136,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.98,
|
| 46 |
+
"eval_accuracy": 0.046261682242990654,
|
| 47 |
+
"eval_loss": 5.699448108673096,
|
| 48 |
+
"eval_runtime": 8.3972,
|
| 49 |
+
"eval_samples_per_second": 254.846,
|
| 50 |
+
"eval_steps_per_second": 1.31,
|
| 51 |
+
"step": 48
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.06,
|
| 55 |
+
"learning_rate": 3.472222222222222e-05,
|
| 56 |
+
"loss": 6.1712,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.47,
|
| 61 |
+
"learning_rate": 4.166666666666667e-05,
|
| 62 |
+
"loss": 5.5789,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.89,
|
| 67 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 68 |
+
"loss": 4.7064,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.97,
|
| 73 |
+
"eval_accuracy": 0.45560747663551404,
|
| 74 |
+
"eval_loss": 3.352895975112915,
|
| 75 |
+
"eval_runtime": 7.9592,
|
| 76 |
+
"eval_samples_per_second": 268.872,
|
| 77 |
+
"eval_steps_per_second": 1.382,
|
| 78 |
+
"step": 72
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.3,
|
| 82 |
+
"learning_rate": 4.938271604938271e-05,
|
| 83 |
+
"loss": 3.8038,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.71,
|
| 88 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 89 |
+
"loss": 3.0888,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.0,
|
| 94 |
+
"eval_accuracy": 0.5920560747663551,
|
| 95 |
+
"eval_loss": 2.1475517749786377,
|
| 96 |
+
"eval_runtime": 8.0136,
|
| 97 |
+
"eval_samples_per_second": 267.048,
|
| 98 |
+
"eval_steps_per_second": 1.373,
|
| 99 |
+
"step": 97
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.12,
|
| 103 |
+
"learning_rate": 4.783950617283951e-05,
|
| 104 |
+
"loss": 2.5659,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.54,
|
| 109 |
+
"learning_rate": 4.70679012345679e-05,
|
| 110 |
+
"loss": 2.1887,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.95,
|
| 115 |
+
"learning_rate": 4.62962962962963e-05,
|
| 116 |
+
"loss": 1.8458,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.99,
|
| 121 |
+
"eval_accuracy": 0.6285046728971962,
|
| 122 |
+
"eval_loss": 1.588365077972412,
|
| 123 |
+
"eval_runtime": 8.4217,
|
| 124 |
+
"eval_samples_per_second": 254.105,
|
| 125 |
+
"eval_steps_per_second": 1.306,
|
| 126 |
+
"step": 121
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.36,
|
| 130 |
+
"learning_rate": 4.5524691358024696e-05,
|
| 131 |
+
"loss": 1.6147,
|
| 132 |
+
"step": 130
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 5.77,
|
| 136 |
+
"learning_rate": 4.4753086419753084e-05,
|
| 137 |
+
"loss": 1.4168,
|
| 138 |
+
"step": 140
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.98,
|
| 142 |
+
"eval_accuracy": 0.6588785046728972,
|
| 143 |
+
"eval_loss": 1.2460048198699951,
|
| 144 |
+
"eval_runtime": 7.9049,
|
| 145 |
+
"eval_samples_per_second": 270.718,
|
| 146 |
+
"eval_steps_per_second": 1.392,
|
| 147 |
+
"step": 145
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.19,
|
| 151 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 152 |
+
"loss": 1.271,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 6.6,
|
| 157 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 158 |
+
"loss": 1.1951,
|
| 159 |
+
"step": 160
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.97,
|
| 163 |
+
"eval_accuracy": 0.6869158878504673,
|
| 164 |
+
"eval_loss": 1.0658469200134277,
|
| 165 |
+
"eval_runtime": 7.9886,
|
| 166 |
+
"eval_samples_per_second": 267.881,
|
| 167 |
+
"eval_steps_per_second": 1.377,
|
| 168 |
+
"step": 169
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.01,
|
| 172 |
+
"learning_rate": 4.243827160493827e-05,
|
| 173 |
+
"loss": 1.1222,
|
| 174 |
+
"step": 170
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 7.42,
|
| 178 |
+
"learning_rate": 4.166666666666667e-05,
|
| 179 |
+
"loss": 1.0719,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 7.84,
|
| 184 |
+
"learning_rate": 4.089506172839506e-05,
|
| 185 |
+
"loss": 0.9871,
|
| 186 |
+
"step": 190
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 8.0,
|
| 190 |
+
"eval_accuracy": 0.7037383177570093,
|
| 191 |
+
"eval_loss": 0.9436482191085815,
|
| 192 |
+
"eval_runtime": 8.7539,
|
| 193 |
+
"eval_samples_per_second": 244.461,
|
| 194 |
+
"eval_steps_per_second": 1.257,
|
| 195 |
+
"step": 194
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.25,
|
| 199 |
+
"learning_rate": 4.012345679012346e-05,
|
| 200 |
+
"loss": 0.9461,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 8.66,
|
| 205 |
+
"learning_rate": 3.935185185185186e-05,
|
| 206 |
+
"loss": 0.9247,
|
| 207 |
+
"step": 210
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 8.99,
|
| 211 |
+
"eval_accuracy": 0.7238317757009346,
|
| 212 |
+
"eval_loss": 0.8639922738075256,
|
| 213 |
+
"eval_runtime": 8.532,
|
| 214 |
+
"eval_samples_per_second": 250.821,
|
| 215 |
+
"eval_steps_per_second": 1.289,
|
| 216 |
+
"step": 218
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.07,
|
| 220 |
+
"learning_rate": 3.8580246913580246e-05,
|
| 221 |
+
"loss": 0.8806,
|
| 222 |
+
"step": 220
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 9.48,
|
| 226 |
+
"learning_rate": 3.780864197530865e-05,
|
| 227 |
+
"loss": 0.8467,
|
| 228 |
+
"step": 230
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 9.9,
|
| 232 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 233 |
+
"loss": 0.826,
|
| 234 |
+
"step": 240
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 9.98,
|
| 238 |
+
"eval_accuracy": 0.7317757009345794,
|
| 239 |
+
"eval_loss": 0.7976669073104858,
|
| 240 |
+
"eval_runtime": 7.7765,
|
| 241 |
+
"eval_samples_per_second": 275.189,
|
| 242 |
+
"eval_steps_per_second": 1.415,
|
| 243 |
+
"step": 242
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 10.31,
|
| 247 |
+
"learning_rate": 3.626543209876543e-05,
|
| 248 |
+
"loss": 0.79,
|
| 249 |
+
"step": 250
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 10.72,
|
| 253 |
+
"learning_rate": 3.5493827160493834e-05,
|
| 254 |
+
"loss": 0.7964,
|
| 255 |
+
"step": 260
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 10.97,
|
| 259 |
+
"eval_accuracy": 0.7509345794392523,
|
| 260 |
+
"eval_loss": 0.7539175152778625,
|
| 261 |
+
"eval_runtime": 7.6095,
|
| 262 |
+
"eval_samples_per_second": 281.226,
|
| 263 |
+
"eval_steps_per_second": 1.446,
|
| 264 |
+
"step": 266
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 11.13,
|
| 268 |
+
"learning_rate": 3.472222222222222e-05,
|
| 269 |
+
"loss": 0.7405,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 11.55,
|
| 274 |
+
"learning_rate": 3.395061728395062e-05,
|
| 275 |
+
"loss": 0.7471,
|
| 276 |
+
"step": 280
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 11.96,
|
| 280 |
+
"learning_rate": 3.317901234567901e-05,
|
| 281 |
+
"loss": 0.7168,
|
| 282 |
+
"step": 290
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 12.0,
|
| 286 |
+
"eval_accuracy": 0.7514018691588785,
|
| 287 |
+
"eval_loss": 0.7179247140884399,
|
| 288 |
+
"eval_runtime": 8.7034,
|
| 289 |
+
"eval_samples_per_second": 245.882,
|
| 290 |
+
"eval_steps_per_second": 1.264,
|
| 291 |
+
"step": 291
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 12.37,
|
| 295 |
+
"learning_rate": 3.240740740740741e-05,
|
| 296 |
+
"loss": 0.7166,
|
| 297 |
+
"step": 300
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 12.78,
|
| 301 |
+
"learning_rate": 3.16358024691358e-05,
|
| 302 |
+
"loss": 0.6893,
|
| 303 |
+
"step": 310
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 12.99,
|
| 307 |
+
"eval_accuracy": 0.7630841121495328,
|
| 308 |
+
"eval_loss": 0.6952459812164307,
|
| 309 |
+
"eval_runtime": 8.8433,
|
| 310 |
+
"eval_samples_per_second": 241.991,
|
| 311 |
+
"eval_steps_per_second": 1.244,
|
| 312 |
+
"step": 315
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 13.2,
|
| 316 |
+
"learning_rate": 3.08641975308642e-05,
|
| 317 |
+
"loss": 0.6942,
|
| 318 |
+
"step": 320
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 13.61,
|
| 322 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 323 |
+
"loss": 0.687,
|
| 324 |
+
"step": 330
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 13.98,
|
| 328 |
+
"eval_accuracy": 0.764018691588785,
|
| 329 |
+
"eval_loss": 0.6812998652458191,
|
| 330 |
+
"eval_runtime": 8.1933,
|
| 331 |
+
"eval_samples_per_second": 261.19,
|
| 332 |
+
"eval_steps_per_second": 1.343,
|
| 333 |
+
"step": 339
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 14.02,
|
| 337 |
+
"learning_rate": 2.9320987654320992e-05,
|
| 338 |
+
"loss": 0.6621,
|
| 339 |
+
"step": 340
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 14.43,
|
| 343 |
+
"learning_rate": 2.8549382716049384e-05,
|
| 344 |
+
"loss": 0.6721,
|
| 345 |
+
"step": 350
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 14.85,
|
| 349 |
+
"learning_rate": 2.777777777777778e-05,
|
| 350 |
+
"loss": 0.6496,
|
| 351 |
+
"step": 360
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 14.97,
|
| 355 |
+
"eval_accuracy": 0.7691588785046729,
|
| 356 |
+
"eval_loss": 0.6577351689338684,
|
| 357 |
+
"eval_runtime": 7.8611,
|
| 358 |
+
"eval_samples_per_second": 272.227,
|
| 359 |
+
"eval_steps_per_second": 1.399,
|
| 360 |
+
"step": 363
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 15.26,
|
| 364 |
+
"learning_rate": 2.700617283950617e-05,
|
| 365 |
+
"loss": 0.6403,
|
| 366 |
+
"step": 370
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 15.67,
|
| 370 |
+
"learning_rate": 2.623456790123457e-05,
|
| 371 |
+
"loss": 0.6477,
|
| 372 |
+
"step": 380
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 16.0,
|
| 376 |
+
"eval_accuracy": 0.7813084112149533,
|
| 377 |
+
"eval_loss": 0.6433616280555725,
|
| 378 |
+
"eval_runtime": 7.6827,
|
| 379 |
+
"eval_samples_per_second": 278.548,
|
| 380 |
+
"eval_steps_per_second": 1.432,
|
| 381 |
+
"step": 388
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 16.08,
|
| 385 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 386 |
+
"loss": 0.6452,
|
| 387 |
+
"step": 390
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 16.49,
|
| 391 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 392 |
+
"loss": 0.6371,
|
| 393 |
+
"step": 400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 16.91,
|
| 397 |
+
"learning_rate": 2.3919753086419755e-05,
|
| 398 |
+
"loss": 0.5992,
|
| 399 |
+
"step": 410
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 16.99,
|
| 403 |
+
"eval_accuracy": 0.7771028037383177,
|
| 404 |
+
"eval_loss": 0.6388670802116394,
|
| 405 |
+
"eval_runtime": 8.24,
|
| 406 |
+
"eval_samples_per_second": 259.708,
|
| 407 |
+
"eval_steps_per_second": 1.335,
|
| 408 |
+
"step": 412
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 17.32,
|
| 412 |
+
"learning_rate": 2.314814814814815e-05,
|
| 413 |
+
"loss": 0.6016,
|
| 414 |
+
"step": 420
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 17.73,
|
| 418 |
+
"learning_rate": 2.2376543209876542e-05,
|
| 419 |
+
"loss": 0.6059,
|
| 420 |
+
"step": 430
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 17.98,
|
| 424 |
+
"eval_accuracy": 0.7906542056074767,
|
| 425 |
+
"eval_loss": 0.623566746711731,
|
| 426 |
+
"eval_runtime": 8.516,
|
| 427 |
+
"eval_samples_per_second": 251.293,
|
| 428 |
+
"eval_steps_per_second": 1.292,
|
| 429 |
+
"step": 436
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 18.14,
|
| 433 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 434 |
+
"loss": 0.6031,
|
| 435 |
+
"step": 440
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 18.56,
|
| 439 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 440 |
+
"loss": 0.6126,
|
| 441 |
+
"step": 450
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 18.97,
|
| 445 |
+
"learning_rate": 2.006172839506173e-05,
|
| 446 |
+
"loss": 0.5993,
|
| 447 |
+
"step": 460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 18.97,
|
| 451 |
+
"eval_accuracy": 0.7934579439252336,
|
| 452 |
+
"eval_loss": 0.6181445717811584,
|
| 453 |
+
"eval_runtime": 7.8023,
|
| 454 |
+
"eval_samples_per_second": 274.277,
|
| 455 |
+
"eval_steps_per_second": 1.41,
|
| 456 |
+
"step": 460
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 19.38,
|
| 460 |
+
"learning_rate": 1.9290123456790123e-05,
|
| 461 |
+
"loss": 0.5872,
|
| 462 |
+
"step": 470
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 19.79,
|
| 466 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 467 |
+
"loss": 0.5802,
|
| 468 |
+
"step": 480
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 20.0,
|
| 472 |
+
"eval_accuracy": 0.7911214953271029,
|
| 473 |
+
"eval_loss": 0.611458957195282,
|
| 474 |
+
"eval_runtime": 8.4234,
|
| 475 |
+
"eval_samples_per_second": 254.054,
|
| 476 |
+
"eval_steps_per_second": 1.306,
|
| 477 |
+
"step": 485
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 20.21,
|
| 481 |
+
"learning_rate": 1.7746913580246917e-05,
|
| 482 |
+
"loss": 0.6008,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 20.62,
|
| 487 |
+
"learning_rate": 1.697530864197531e-05,
|
| 488 |
+
"loss": 0.5905,
|
| 489 |
+
"step": 500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 20.99,
|
| 493 |
+
"eval_accuracy": 0.7929906542056074,
|
| 494 |
+
"eval_loss": 0.6005003452301025,
|
| 495 |
+
"eval_runtime": 7.7149,
|
| 496 |
+
"eval_samples_per_second": 277.386,
|
| 497 |
+
"eval_steps_per_second": 1.426,
|
| 498 |
+
"step": 509
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 21.03,
|
| 502 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 503 |
+
"loss": 0.5861,
|
| 504 |
+
"step": 510
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 21.44,
|
| 508 |
+
"learning_rate": 1.54320987654321e-05,
|
| 509 |
+
"loss": 0.5865,
|
| 510 |
+
"step": 520
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 21.86,
|
| 514 |
+
"learning_rate": 1.4660493827160496e-05,
|
| 515 |
+
"loss": 0.5825,
|
| 516 |
+
"step": 530
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 21.98,
|
| 520 |
+
"eval_accuracy": 0.7953271028037383,
|
| 521 |
+
"eval_loss": 0.5945016145706177,
|
| 522 |
+
"eval_runtime": 7.5452,
|
| 523 |
+
"eval_samples_per_second": 283.623,
|
| 524 |
+
"eval_steps_per_second": 1.458,
|
| 525 |
+
"step": 533
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 22.27,
|
| 529 |
+
"learning_rate": 1.388888888888889e-05,
|
| 530 |
+
"loss": 0.5732,
|
| 531 |
+
"step": 540
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 22.68,
|
| 535 |
+
"learning_rate": 1.3117283950617285e-05,
|
| 536 |
+
"loss": 0.5837,
|
| 537 |
+
"step": 550
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 22.97,
|
| 541 |
+
"eval_accuracy": 0.7981308411214953,
|
| 542 |
+
"eval_loss": 0.5882120132446289,
|
| 543 |
+
"eval_runtime": 8.1333,
|
| 544 |
+
"eval_samples_per_second": 263.116,
|
| 545 |
+
"eval_steps_per_second": 1.352,
|
| 546 |
+
"step": 557
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 23.09,
|
| 550 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 551 |
+
"loss": 0.5791,
|
| 552 |
+
"step": 560
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 23.51,
|
| 556 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 557 |
+
"loss": 0.5783,
|
| 558 |
+
"step": 570
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 23.92,
|
| 562 |
+
"learning_rate": 1.0802469135802469e-05,
|
| 563 |
+
"loss": 0.5501,
|
| 564 |
+
"step": 580
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 24.0,
|
| 568 |
+
"eval_accuracy": 0.8023364485981308,
|
| 569 |
+
"eval_loss": 0.5847517251968384,
|
| 570 |
+
"eval_runtime": 8.0927,
|
| 571 |
+
"eval_samples_per_second": 264.435,
|
| 572 |
+
"eval_steps_per_second": 1.359,
|
| 573 |
+
"step": 582
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 24.33,
|
| 577 |
+
"learning_rate": 1.0030864197530866e-05,
|
| 578 |
+
"loss": 0.5841,
|
| 579 |
+
"step": 590
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 24.74,
|
| 583 |
+
"learning_rate": 9.259259259259259e-06,
|
| 584 |
+
"loss": 0.5593,
|
| 585 |
+
"step": 600
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 24.99,
|
| 589 |
+
"eval_accuracy": 0.7962616822429907,
|
| 590 |
+
"eval_loss": 0.5861061811447144,
|
| 591 |
+
"eval_runtime": 7.5867,
|
| 592 |
+
"eval_samples_per_second": 282.074,
|
| 593 |
+
"eval_steps_per_second": 1.45,
|
| 594 |
+
"step": 606
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 25.15,
|
| 598 |
+
"learning_rate": 8.487654320987654e-06,
|
| 599 |
+
"loss": 0.5526,
|
| 600 |
+
"step": 610
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 25.57,
|
| 604 |
+
"learning_rate": 7.71604938271605e-06,
|
| 605 |
+
"loss": 0.5792,
|
| 606 |
+
"step": 620
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 25.98,
|
| 610 |
+
"learning_rate": 6.944444444444445e-06,
|
| 611 |
+
"loss": 0.5454,
|
| 612 |
+
"step": 630
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 25.98,
|
| 616 |
+
"eval_accuracy": 0.8014018691588785,
|
| 617 |
+
"eval_loss": 0.5776079893112183,
|
| 618 |
+
"eval_runtime": 7.665,
|
| 619 |
+
"eval_samples_per_second": 279.191,
|
| 620 |
+
"eval_steps_per_second": 1.435,
|
| 621 |
+
"step": 630
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 26.39,
|
| 625 |
+
"learning_rate": 6.172839506172839e-06,
|
| 626 |
+
"loss": 0.5477,
|
| 627 |
+
"step": 640
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 26.8,
|
| 631 |
+
"learning_rate": 5.401234567901234e-06,
|
| 632 |
+
"loss": 0.5656,
|
| 633 |
+
"step": 650
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 26.97,
|
| 637 |
+
"eval_accuracy": 0.7976635514018692,
|
| 638 |
+
"eval_loss": 0.579258143901825,
|
| 639 |
+
"eval_runtime": 7.9989,
|
| 640 |
+
"eval_samples_per_second": 267.536,
|
| 641 |
+
"eval_steps_per_second": 1.375,
|
| 642 |
+
"step": 654
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 27.22,
|
| 646 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 647 |
+
"loss": 0.5546,
|
| 648 |
+
"step": 660
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 27.63,
|
| 652 |
+
"learning_rate": 3.858024691358025e-06,
|
| 653 |
+
"loss": 0.5708,
|
| 654 |
+
"step": 670
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 28.0,
|
| 658 |
+
"eval_accuracy": 0.8004672897196262,
|
| 659 |
+
"eval_loss": 0.5814595818519592,
|
| 660 |
+
"eval_runtime": 8.2466,
|
| 661 |
+
"eval_samples_per_second": 259.502,
|
| 662 |
+
"eval_steps_per_second": 1.334,
|
| 663 |
+
"step": 679
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 28.04,
|
| 667 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 668 |
+
"loss": 0.5505,
|
| 669 |
+
"step": 680
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 28.45,
|
| 673 |
+
"learning_rate": 2.3148148148148148e-06,
|
| 674 |
+
"loss": 0.5565,
|
| 675 |
+
"step": 690
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 28.87,
|
| 679 |
+
"learning_rate": 1.5432098765432098e-06,
|
| 680 |
+
"loss": 0.5541,
|
| 681 |
+
"step": 700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 28.99,
|
| 685 |
+
"eval_accuracy": 0.8032710280373832,
|
| 686 |
+
"eval_loss": 0.5749428868293762,
|
| 687 |
+
"eval_runtime": 8.685,
|
| 688 |
+
"eval_samples_per_second": 246.402,
|
| 689 |
+
"eval_steps_per_second": 1.267,
|
| 690 |
+
"step": 703
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 29.28,
|
| 694 |
+
"learning_rate": 7.716049382716049e-07,
|
| 695 |
+
"loss": 0.5511,
|
| 696 |
+
"step": 710
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 29.69,
|
| 700 |
+
"learning_rate": 0.0,
|
| 701 |
+
"loss": 0.5439,
|
| 702 |
+
"step": 720
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 29.69,
|
| 706 |
+
"eval_accuracy": 0.7995327102803739,
|
| 707 |
+
"eval_loss": 0.5757396221160889,
|
| 708 |
+
"eval_runtime": 7.6093,
|
| 709 |
+
"eval_samples_per_second": 281.236,
|
| 710 |
+
"eval_steps_per_second": 1.446,
|
| 711 |
+
"step": 720
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 29.69,
|
| 715 |
+
"step": 720,
|
| 716 |
+
"total_flos": 3.1088341164957254e+19,
|
| 717 |
+
"train_loss": 1.3989773021803962,
|
| 718 |
+
"train_runtime": 2686.7823,
|
| 719 |
+
"train_samples_per_second": 215.019,
|
| 720 |
+
"train_steps_per_second": 0.268
|
| 721 |
+
}
|
| 722 |
+
],
|
| 723 |
+
"logging_steps": 10,
|
| 724 |
+
"max_steps": 720,
|
| 725 |
+
"num_input_tokens_seen": 0,
|
| 726 |
+
"num_train_epochs": 30,
|
| 727 |
+
"save_steps": 500,
|
| 728 |
+
"total_flos": 3.1088341164957254e+19,
|
| 729 |
+
"train_batch_size": 200,
|
| 730 |
+
"trial_name": null,
|
| 731 |
+
"trial_params": null
|
| 732 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfddf1013031b1a74db418158b66097226c7d8c2e9ed6d9fa0551310fe72edac
|
| 3 |
size 4728
|