Training in progress, epoch 1
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- pytorch_model.bin +1 -1
- train_results.json +7 -0
- trainer_state.json +628 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9269269269269269,
|
| 4 |
+
"eval_f1": 0.92613906123654,
|
| 5 |
+
"eval_loss": 0.2517949640750885,
|
| 6 |
+
"eval_precision": 0.9269688236583458,
|
| 7 |
+
"eval_recall": 0.9262789837431067,
|
| 8 |
+
"eval_runtime": 10.8606,
|
| 9 |
+
"eval_samples_per_second": 91.984,
|
| 10 |
+
"eval_steps_per_second": 3.683,
|
| 11 |
+
"train_loss": 0.6694481897354126,
|
| 12 |
+
"train_runtime": 1321.2072,
|
| 13 |
+
"train_samples_per_second": 60.483,
|
| 14 |
+
"train_steps_per_second": 0.606
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.9269269269269269,
|
| 3 |
+
"eval_f1": 0.92613906123654,
|
| 4 |
+
"eval_loss": 0.2517949640750885,
|
| 5 |
+
"eval_precision": 0.9269688236583458,
|
| 6 |
+
"eval_recall": 0.9262789837431067,
|
| 7 |
+
"eval_runtime": 10.8606,
|
| 8 |
+
"eval_samples_per_second": 91.984,
|
| 9 |
+
"eval_steps_per_second": 3.683
|
| 10 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 60037773
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5faedece9d78b426356035ff5eca506cfc686ce4a1548529848b5f557904060a
|
| 3 |
size 60037773
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.6694481897354126,
|
| 4 |
+
"train_runtime": 1321.2072,
|
| 5 |
+
"train_samples_per_second": 60.483,
|
| 6 |
+
"train_steps_per_second": 0.606
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,628 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9099099099099099,
|
| 3 |
+
"best_model_checkpoint": "10-convnextv2-nano-22k-384-finetuned-spiderTraining20-500/checkpoint-800",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 6.25e-06,
|
| 14 |
+
"loss": 3.1451,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.25,
|
| 19 |
+
"learning_rate": 1.25e-05,
|
| 20 |
+
"loss": 3.1259,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.38,
|
| 25 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 26 |
+
"loss": 2.9715,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.5,
|
| 31 |
+
"learning_rate": 2.5e-05,
|
| 32 |
+
"loss": 2.7642,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.62,
|
| 37 |
+
"learning_rate": 3.125e-05,
|
| 38 |
+
"loss": 2.5662,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.75,
|
| 43 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 44 |
+
"loss": 2.2829,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.88,
|
| 49 |
+
"learning_rate": 4.375e-05,
|
| 50 |
+
"loss": 2.0106,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"learning_rate": 5e-05,
|
| 56 |
+
"loss": 1.7156,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.0,
|
| 61 |
+
"eval_accuracy": 0.6316316316316316,
|
| 62 |
+
"eval_f1": 0.6154711933932746,
|
| 63 |
+
"eval_loss": 1.4313874244689941,
|
| 64 |
+
"eval_precision": 0.6182233977895779,
|
| 65 |
+
"eval_recall": 0.6246499047821599,
|
| 66 |
+
"eval_runtime": 10.8324,
|
| 67 |
+
"eval_samples_per_second": 92.223,
|
| 68 |
+
"eval_steps_per_second": 3.693,
|
| 69 |
+
"step": 80
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.12,
|
| 73 |
+
"learning_rate": 4.930555555555556e-05,
|
| 74 |
+
"loss": 1.4422,
|
| 75 |
+
"step": 90
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.25,
|
| 79 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 80 |
+
"loss": 1.2846,
|
| 81 |
+
"step": 100
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.38,
|
| 85 |
+
"learning_rate": 4.791666666666667e-05,
|
| 86 |
+
"loss": 1.0943,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.5,
|
| 91 |
+
"learning_rate": 4.722222222222222e-05,
|
| 92 |
+
"loss": 1.024,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.62,
|
| 97 |
+
"learning_rate": 4.652777777777778e-05,
|
| 98 |
+
"loss": 0.8952,
|
| 99 |
+
"step": 130
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.75,
|
| 103 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 104 |
+
"loss": 0.8542,
|
| 105 |
+
"step": 140
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.88,
|
| 109 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 110 |
+
"loss": 0.8182,
|
| 111 |
+
"step": 150
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.0,
|
| 115 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 116 |
+
"loss": 0.7565,
|
| 117 |
+
"step": 160
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.0,
|
| 121 |
+
"eval_accuracy": 0.8168168168168168,
|
| 122 |
+
"eval_f1": 0.8095428833652196,
|
| 123 |
+
"eval_loss": 0.634009063243866,
|
| 124 |
+
"eval_precision": 0.8213363501056982,
|
| 125 |
+
"eval_recall": 0.8074183342516351,
|
| 126 |
+
"eval_runtime": 11.5227,
|
| 127 |
+
"eval_samples_per_second": 86.698,
|
| 128 |
+
"eval_steps_per_second": 3.471,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.12,
|
| 133 |
+
"learning_rate": 4.375e-05,
|
| 134 |
+
"loss": 0.7224,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.25,
|
| 139 |
+
"learning_rate": 4.305555555555556e-05,
|
| 140 |
+
"loss": 0.6599,
|
| 141 |
+
"step": 180
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.38,
|
| 145 |
+
"learning_rate": 4.236111111111111e-05,
|
| 146 |
+
"loss": 0.617,
|
| 147 |
+
"step": 190
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.5,
|
| 151 |
+
"learning_rate": 4.166666666666667e-05,
|
| 152 |
+
"loss": 0.6116,
|
| 153 |
+
"step": 200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.62,
|
| 157 |
+
"learning_rate": 4.0972222222222225e-05,
|
| 158 |
+
"loss": 0.5726,
|
| 159 |
+
"step": 210
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.75,
|
| 163 |
+
"learning_rate": 4.027777777777778e-05,
|
| 164 |
+
"loss": 0.6103,
|
| 165 |
+
"step": 220
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.88,
|
| 169 |
+
"learning_rate": 3.958333333333333e-05,
|
| 170 |
+
"loss": 0.5996,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.0,
|
| 175 |
+
"learning_rate": 3.888888888888889e-05,
|
| 176 |
+
"loss": 0.5802,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.0,
|
| 181 |
+
"eval_accuracy": 0.8588588588588588,
|
| 182 |
+
"eval_f1": 0.8539214264372446,
|
| 183 |
+
"eval_loss": 0.4632730782032013,
|
| 184 |
+
"eval_precision": 0.8566478880124299,
|
| 185 |
+
"eval_recall": 0.8544949553061285,
|
| 186 |
+
"eval_runtime": 10.9172,
|
| 187 |
+
"eval_samples_per_second": 91.507,
|
| 188 |
+
"eval_steps_per_second": 3.664,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.12,
|
| 193 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 194 |
+
"loss": 0.528,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.25,
|
| 199 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 200 |
+
"loss": 0.481,
|
| 201 |
+
"step": 260
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.38,
|
| 205 |
+
"learning_rate": 3.6805555555555556e-05,
|
| 206 |
+
"loss": 0.4882,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.5,
|
| 211 |
+
"learning_rate": 3.611111111111111e-05,
|
| 212 |
+
"loss": 0.5335,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 3.62,
|
| 217 |
+
"learning_rate": 3.541666666666667e-05,
|
| 218 |
+
"loss": 0.5088,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.75,
|
| 223 |
+
"learning_rate": 3.472222222222222e-05,
|
| 224 |
+
"loss": 0.4647,
|
| 225 |
+
"step": 300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.88,
|
| 229 |
+
"learning_rate": 3.402777777777778e-05,
|
| 230 |
+
"loss": 0.4677,
|
| 231 |
+
"step": 310
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.0,
|
| 235 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 236 |
+
"loss": 0.4765,
|
| 237 |
+
"step": 320
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.0,
|
| 241 |
+
"eval_accuracy": 0.8758758758758759,
|
| 242 |
+
"eval_f1": 0.8708195092986228,
|
| 243 |
+
"eval_loss": 0.4005794823169708,
|
| 244 |
+
"eval_precision": 0.8745697101491127,
|
| 245 |
+
"eval_recall": 0.8709417256085896,
|
| 246 |
+
"eval_runtime": 10.712,
|
| 247 |
+
"eval_samples_per_second": 93.26,
|
| 248 |
+
"eval_steps_per_second": 3.734,
|
| 249 |
+
"step": 320
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.12,
|
| 253 |
+
"learning_rate": 3.263888888888889e-05,
|
| 254 |
+
"loss": 0.4197,
|
| 255 |
+
"step": 330
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.25,
|
| 259 |
+
"learning_rate": 3.194444444444444e-05,
|
| 260 |
+
"loss": 0.3985,
|
| 261 |
+
"step": 340
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.38,
|
| 265 |
+
"learning_rate": 3.125e-05,
|
| 266 |
+
"loss": 0.4315,
|
| 267 |
+
"step": 350
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.5,
|
| 271 |
+
"learning_rate": 3.055555555555556e-05,
|
| 272 |
+
"loss": 0.4256,
|
| 273 |
+
"step": 360
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 4.62,
|
| 277 |
+
"learning_rate": 2.9861111111111113e-05,
|
| 278 |
+
"loss": 0.4086,
|
| 279 |
+
"step": 370
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.75,
|
| 283 |
+
"learning_rate": 2.916666666666667e-05,
|
| 284 |
+
"loss": 0.3753,
|
| 285 |
+
"step": 380
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.88,
|
| 289 |
+
"learning_rate": 2.8472222222222223e-05,
|
| 290 |
+
"loss": 0.4019,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 5.0,
|
| 295 |
+
"learning_rate": 2.777777777777778e-05,
|
| 296 |
+
"loss": 0.3644,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 5.0,
|
| 301 |
+
"eval_accuracy": 0.9019019019019019,
|
| 302 |
+
"eval_f1": 0.8979132685961181,
|
| 303 |
+
"eval_loss": 0.35299161076545715,
|
| 304 |
+
"eval_precision": 0.8994843529874992,
|
| 305 |
+
"eval_recall": 0.8984207235280925,
|
| 306 |
+
"eval_runtime": 11.3754,
|
| 307 |
+
"eval_samples_per_second": 87.821,
|
| 308 |
+
"eval_steps_per_second": 3.516,
|
| 309 |
+
"step": 400
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 5.12,
|
| 313 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 314 |
+
"loss": 0.4145,
|
| 315 |
+
"step": 410
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 5.25,
|
| 319 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 320 |
+
"loss": 0.3786,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.38,
|
| 325 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 326 |
+
"loss": 0.3845,
|
| 327 |
+
"step": 430
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 5.5,
|
| 331 |
+
"learning_rate": 2.5e-05,
|
| 332 |
+
"loss": 0.3951,
|
| 333 |
+
"step": 440
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 5.62,
|
| 337 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 338 |
+
"loss": 0.361,
|
| 339 |
+
"step": 450
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.75,
|
| 343 |
+
"learning_rate": 2.361111111111111e-05,
|
| 344 |
+
"loss": 0.3661,
|
| 345 |
+
"step": 460
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.88,
|
| 349 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 350 |
+
"loss": 0.3278,
|
| 351 |
+
"step": 470
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.0,
|
| 355 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 356 |
+
"loss": 0.3622,
|
| 357 |
+
"step": 480
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 6.0,
|
| 361 |
+
"eval_accuracy": 0.9049049049049049,
|
| 362 |
+
"eval_f1": 0.9013077009350899,
|
| 363 |
+
"eval_loss": 0.33261367678642273,
|
| 364 |
+
"eval_precision": 0.9019378592590697,
|
| 365 |
+
"eval_recall": 0.9019909969066763,
|
| 366 |
+
"eval_runtime": 10.7748,
|
| 367 |
+
"eval_samples_per_second": 92.716,
|
| 368 |
+
"eval_steps_per_second": 3.712,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 6.12,
|
| 373 |
+
"learning_rate": 2.152777777777778e-05,
|
| 374 |
+
"loss": 0.3612,
|
| 375 |
+
"step": 490
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.25,
|
| 379 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 380 |
+
"loss": 0.3223,
|
| 381 |
+
"step": 500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 6.38,
|
| 385 |
+
"learning_rate": 2.013888888888889e-05,
|
| 386 |
+
"loss": 0.3559,
|
| 387 |
+
"step": 510
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 6.5,
|
| 391 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 392 |
+
"loss": 0.3575,
|
| 393 |
+
"step": 520
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 6.62,
|
| 397 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 398 |
+
"loss": 0.3275,
|
| 399 |
+
"step": 530
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 6.75,
|
| 403 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 404 |
+
"loss": 0.3051,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 6.88,
|
| 409 |
+
"learning_rate": 1.736111111111111e-05,
|
| 410 |
+
"loss": 0.3303,
|
| 411 |
+
"step": 550
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 7.0,
|
| 415 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 416 |
+
"loss": 0.3232,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 7.0,
|
| 421 |
+
"eval_accuracy": 0.8938938938938938,
|
| 422 |
+
"eval_f1": 0.8892011579580226,
|
| 423 |
+
"eval_loss": 0.3179842531681061,
|
| 424 |
+
"eval_precision": 0.8909630589714048,
|
| 425 |
+
"eval_recall": 0.8889252861904225,
|
| 426 |
+
"eval_runtime": 10.838,
|
| 427 |
+
"eval_samples_per_second": 92.176,
|
| 428 |
+
"eval_steps_per_second": 3.691,
|
| 429 |
+
"step": 560
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 7.12,
|
| 433 |
+
"learning_rate": 1.597222222222222e-05,
|
| 434 |
+
"loss": 0.3028,
|
| 435 |
+
"step": 570
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 7.25,
|
| 439 |
+
"learning_rate": 1.527777777777778e-05,
|
| 440 |
+
"loss": 0.3362,
|
| 441 |
+
"step": 580
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 7.38,
|
| 445 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 446 |
+
"loss": 0.2878,
|
| 447 |
+
"step": 590
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 7.5,
|
| 451 |
+
"learning_rate": 1.388888888888889e-05,
|
| 452 |
+
"loss": 0.3264,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 7.62,
|
| 457 |
+
"learning_rate": 1.3194444444444446e-05,
|
| 458 |
+
"loss": 0.2952,
|
| 459 |
+
"step": 610
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 7.75,
|
| 463 |
+
"learning_rate": 1.25e-05,
|
| 464 |
+
"loss": 0.3197,
|
| 465 |
+
"step": 620
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.88,
|
| 469 |
+
"learning_rate": 1.1805555555555555e-05,
|
| 470 |
+
"loss": 0.3291,
|
| 471 |
+
"step": 630
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 8.0,
|
| 475 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 476 |
+
"loss": 0.2968,
|
| 477 |
+
"step": 640
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 8.0,
|
| 481 |
+
"eval_accuracy": 0.908908908908909,
|
| 482 |
+
"eval_f1": 0.9038850741319278,
|
| 483 |
+
"eval_loss": 0.3018168807029724,
|
| 484 |
+
"eval_precision": 0.9049510380750571,
|
| 485 |
+
"eval_recall": 0.903886107847755,
|
| 486 |
+
"eval_runtime": 11.3593,
|
| 487 |
+
"eval_samples_per_second": 87.946,
|
| 488 |
+
"eval_steps_per_second": 3.521,
|
| 489 |
+
"step": 640
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 8.12,
|
| 493 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 494 |
+
"loss": 0.2701,
|
| 495 |
+
"step": 650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.25,
|
| 499 |
+
"learning_rate": 9.722222222222223e-06,
|
| 500 |
+
"loss": 0.3409,
|
| 501 |
+
"step": 660
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 8.38,
|
| 505 |
+
"learning_rate": 9.027777777777777e-06,
|
| 506 |
+
"loss": 0.2587,
|
| 507 |
+
"step": 670
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 8.5,
|
| 511 |
+
"learning_rate": 8.333333333333334e-06,
|
| 512 |
+
"loss": 0.3128,
|
| 513 |
+
"step": 680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 8.62,
|
| 517 |
+
"learning_rate": 7.63888888888889e-06,
|
| 518 |
+
"loss": 0.2789,
|
| 519 |
+
"step": 690
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 8.75,
|
| 523 |
+
"learning_rate": 6.944444444444445e-06,
|
| 524 |
+
"loss": 0.3111,
|
| 525 |
+
"step": 700
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 8.88,
|
| 529 |
+
"learning_rate": 6.25e-06,
|
| 530 |
+
"loss": 0.2833,
|
| 531 |
+
"step": 710
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 9.0,
|
| 535 |
+
"learning_rate": 5.555555555555556e-06,
|
| 536 |
+
"loss": 0.285,
|
| 537 |
+
"step": 720
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 9.0,
|
| 541 |
+
"eval_accuracy": 0.9029029029029029,
|
| 542 |
+
"eval_f1": 0.8974149218187346,
|
| 543 |
+
"eval_loss": 0.30974340438842773,
|
| 544 |
+
"eval_precision": 0.897913672792708,
|
| 545 |
+
"eval_recall": 0.8990571292245519,
|
| 546 |
+
"eval_runtime": 10.8119,
|
| 547 |
+
"eval_samples_per_second": 92.398,
|
| 548 |
+
"eval_steps_per_second": 3.7,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 9.12,
|
| 553 |
+
"learning_rate": 4.861111111111111e-06,
|
| 554 |
+
"loss": 0.293,
|
| 555 |
+
"step": 730
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 9.25,
|
| 559 |
+
"learning_rate": 4.166666666666667e-06,
|
| 560 |
+
"loss": 0.2697,
|
| 561 |
+
"step": 740
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 9.38,
|
| 565 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 566 |
+
"loss": 0.254,
|
| 567 |
+
"step": 750
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 9.5,
|
| 571 |
+
"learning_rate": 2.777777777777778e-06,
|
| 572 |
+
"loss": 0.2803,
|
| 573 |
+
"step": 760
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 9.62,
|
| 577 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 578 |
+
"loss": 0.2539,
|
| 579 |
+
"step": 770
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.75,
|
| 583 |
+
"learning_rate": 1.388888888888889e-06,
|
| 584 |
+
"loss": 0.2605,
|
| 585 |
+
"step": 780
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 9.88,
|
| 589 |
+
"learning_rate": 6.944444444444445e-07,
|
| 590 |
+
"loss": 0.249,
|
| 591 |
+
"step": 790
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 10.0,
|
| 595 |
+
"learning_rate": 0.0,
|
| 596 |
+
"loss": 0.2889,
|
| 597 |
+
"step": 800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 10.0,
|
| 601 |
+
"eval_accuracy": 0.9099099099099099,
|
| 602 |
+
"eval_f1": 0.9048297543768958,
|
| 603 |
+
"eval_loss": 0.2969054877758026,
|
| 604 |
+
"eval_precision": 0.9049316662055762,
|
| 605 |
+
"eval_recall": 0.9057042739377195,
|
| 606 |
+
"eval_runtime": 10.8178,
|
| 607 |
+
"eval_samples_per_second": 92.347,
|
| 608 |
+
"eval_steps_per_second": 3.698,
|
| 609 |
+
"step": 800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.0,
|
| 613 |
+
"step": 800,
|
| 614 |
+
"total_flos": 3.1805375717677466e+18,
|
| 615 |
+
"train_loss": 0.6694481897354126,
|
| 616 |
+
"train_runtime": 1321.2072,
|
| 617 |
+
"train_samples_per_second": 60.483,
|
| 618 |
+
"train_steps_per_second": 0.606
|
| 619 |
+
}
|
| 620 |
+
],
|
| 621 |
+
"logging_steps": 10,
|
| 622 |
+
"max_steps": 800,
|
| 623 |
+
"num_train_epochs": 10,
|
| 624 |
+
"save_steps": 500,
|
| 625 |
+
"total_flos": 3.1805375717677466e+18,
|
| 626 |
+
"trial_name": null,
|
| 627 |
+
"trial_params": null
|
| 628 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4155
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ddf8ee65ad2eda6b82df5713faf8f837b59cf1d97122b832196fdb36b3385ff
|
| 3 |
size 4155
|