End of training
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- tokenizer.json +0 -0
- train_results.json +5 -5
- trainer_state.json +370 -88
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples":
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7424,
|
| 4 |
+
"eval_loss": 0.44141659140586853,
|
| 5 |
+
"eval_runtime": 57.1961,
|
| 6 |
+
"eval_samples": 4887,
|
| 7 |
+
"eval_samples_per_second": 85.443,
|
| 8 |
+
"eval_steps_per_second": 5.35,
|
| 9 |
+
"train_loss": 0.35377963603946533,
|
| 10 |
+
"train_runtime": 9210.1652,
|
| 11 |
+
"train_samples": 87866,
|
| 12 |
+
"train_samples_per_second": 28.62,
|
| 13 |
+
"train_steps_per_second": 3.578
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7424,
|
| 4 |
+
"eval_loss": 0.44141659140586853,
|
| 5 |
+
"eval_runtime": 57.1961,
|
| 6 |
+
"eval_samples": 4887,
|
| 7 |
+
"eval_samples_per_second": 85.443,
|
| 8 |
+
"eval_steps_per_second": 5.35
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891644863
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8970dbc9879cd941712bd5cfba5104dbb7f5422e9c3fb19139e0a949bed7305
|
| 3 |
size 891644863
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.35377963603946533,
|
| 4 |
+
"train_runtime": 9210.1652,
|
| 5 |
+
"train_samples": 87866,
|
| 6 |
+
"train_samples_per_second": 28.62,
|
| 7 |
+
"train_steps_per_second": 3.578
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,160 +1,442 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate": 9.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 9.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"eval_runtime": 410.0505,
|
| 51 |
-
"eval_samples_per_second": 7.28,
|
| 52 |
-
"eval_steps_per_second": 0.456,
|
| 53 |
-
"step": 3157
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"epoch": 1.11,
|
| 57 |
-
"learning_rate": 6.371785295059226e-05,
|
| 58 |
-
"loss": 0.3701,
|
| 59 |
"step": 3500
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 4000
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss": 0.
|
| 71 |
"step": 4500
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch":
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss": 0.
|
| 77 |
"step": 5000
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch":
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
"step": 5500
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 6000
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch":
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"eval_runtime": 410.3466,
|
| 96 |
-
"eval_samples_per_second": 7.274,
|
| 97 |
-
"eval_steps_per_second": 0.456,
|
| 98 |
-
"step": 6314
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 2.06,
|
| 102 |
-
"learning_rate": 3.170419378935012e-05,
|
| 103 |
-
"loss": 0.2607,
|
| 104 |
"step": 6500
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 7000
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 7500
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 8000
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 8500
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 9000
|
| 135 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
{
|
| 137 |
"epoch": 3.0,
|
| 138 |
-
"eval_accuracy": 0.
|
| 139 |
-
"eval_loss": 0.
|
| 140 |
-
"eval_runtime":
|
| 141 |
-
"eval_samples_per_second":
|
| 142 |
-
"eval_steps_per_second":
|
| 143 |
-
"step":
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 3.0,
|
| 147 |
-
"step":
|
| 148 |
-
"total_flos":
|
| 149 |
-
"train_loss": 0.
|
| 150 |
-
"train_runtime":
|
| 151 |
-
"train_samples_per_second":
|
| 152 |
-
"train_steps_per_second":
|
| 153 |
}
|
| 154 |
],
|
| 155 |
-
"max_steps":
|
| 156 |
"num_train_epochs": 3,
|
| 157 |
-
"total_flos":
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|
| 160 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 32952,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 9.878241811761841e-05,
|
| 13 |
+
"loss": 0.8515,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 9.726044076464142e-05,
|
| 19 |
+
"loss": 0.6069,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.14,
|
| 24 |
+
"learning_rate": 9.573846341166444e-05,
|
| 25 |
+
"loss": 0.5641,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 9.421648605868745e-05,
|
| 31 |
+
"loss": 0.5586,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.23,
|
| 36 |
+
"learning_rate": 9.269450870571045e-05,
|
| 37 |
+
"loss": 0.5239,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"learning_rate": 9.117253135273349e-05,
|
| 43 |
+
"loss": 0.508,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.32,
|
| 48 |
+
"learning_rate": 8.96505539997565e-05,
|
| 49 |
+
"loss": 0.5077,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"learning_rate": 8.81285766467795e-05,
|
| 55 |
+
"loss": 0.5063,
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.41,
|
| 60 |
+
"learning_rate": 8.660659929380252e-05,
|
| 61 |
+
"loss": 0.4774,
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.46,
|
| 66 |
+
"learning_rate": 8.508462194082553e-05,
|
| 67 |
+
"loss": 0.4782,
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.5,
|
| 72 |
+
"learning_rate": 8.356264458784853e-05,
|
| 73 |
+
"loss": 0.4743,
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.55,
|
| 78 |
+
"learning_rate": 8.204066723487156e-05,
|
| 79 |
+
"loss": 0.4735,
|
| 80 |
"step": 6000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.59,
|
| 84 |
+
"learning_rate": 8.051868988189456e-05,
|
| 85 |
+
"loss": 0.4609,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"step": 6500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.64,
|
| 90 |
+
"learning_rate": 7.899671252891757e-05,
|
| 91 |
+
"loss": 0.448,
|
| 92 |
"step": 7000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.68,
|
| 96 |
+
"learning_rate": 7.747473517594059e-05,
|
| 97 |
+
"loss": 0.4652,
|
| 98 |
"step": 7500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.73,
|
| 102 |
+
"learning_rate": 7.59527578229636e-05,
|
| 103 |
+
"loss": 0.4387,
|
| 104 |
"step": 8000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.77,
|
| 108 |
+
"learning_rate": 7.44307804699866e-05,
|
| 109 |
+
"loss": 0.4547,
|
| 110 |
"step": 8500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.82,
|
| 114 |
+
"learning_rate": 7.290880311700962e-05,
|
| 115 |
+
"loss": 0.4391,
|
| 116 |
"step": 9000
|
| 117 |
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.86,
|
| 120 |
+
"learning_rate": 7.138682576403264e-05,
|
| 121 |
+
"loss": 0.4377,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.91,
|
| 126 |
+
"learning_rate": 6.986484841105565e-05,
|
| 127 |
+
"loss": 0.4415,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.96,
|
| 132 |
+
"learning_rate": 6.834287105807866e-05,
|
| 133 |
+
"loss": 0.4355,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.0,
|
| 138 |
+
"eval_accuracy": 0.7072,
|
| 139 |
+
"eval_loss": 0.3910021185874939,
|
| 140 |
+
"eval_runtime": 57.1361,
|
| 141 |
+
"eval_samples_per_second": 85.533,
|
| 142 |
+
"eval_steps_per_second": 5.356,
|
| 143 |
+
"step": 10984
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.0,
|
| 147 |
+
"learning_rate": 6.682089370510168e-05,
|
| 148 |
+
"loss": 0.4319,
|
| 149 |
+
"step": 11000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.05,
|
| 153 |
+
"learning_rate": 6.529891635212468e-05,
|
| 154 |
+
"loss": 0.3413,
|
| 155 |
+
"step": 11500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.09,
|
| 159 |
+
"learning_rate": 6.377693899914769e-05,
|
| 160 |
+
"loss": 0.3365,
|
| 161 |
+
"step": 12000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.14,
|
| 165 |
+
"learning_rate": 6.225496164617071e-05,
|
| 166 |
+
"loss": 0.3261,
|
| 167 |
+
"step": 12500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.18,
|
| 171 |
+
"learning_rate": 6.073298429319372e-05,
|
| 172 |
+
"loss": 0.3228,
|
| 173 |
+
"step": 13000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.23,
|
| 177 |
+
"learning_rate": 5.921100694021673e-05,
|
| 178 |
+
"loss": 0.3396,
|
| 179 |
+
"step": 13500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.27,
|
| 183 |
+
"learning_rate": 5.768902958723974e-05,
|
| 184 |
+
"loss": 0.3431,
|
| 185 |
+
"step": 14000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.32,
|
| 189 |
+
"learning_rate": 5.616705223426275e-05,
|
| 190 |
+
"loss": 0.3318,
|
| 191 |
+
"step": 14500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.37,
|
| 195 |
+
"learning_rate": 5.464507488128577e-05,
|
| 196 |
+
"loss": 0.3363,
|
| 197 |
+
"step": 15000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.41,
|
| 201 |
+
"learning_rate": 5.3123097528308786e-05,
|
| 202 |
+
"loss": 0.3303,
|
| 203 |
+
"step": 15500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.46,
|
| 207 |
+
"learning_rate": 5.16011201753318e-05,
|
| 208 |
+
"loss": 0.3295,
|
| 209 |
+
"step": 16000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.5,
|
| 213 |
+
"learning_rate": 5.0079142822354806e-05,
|
| 214 |
+
"loss": 0.3304,
|
| 215 |
+
"step": 16500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.55,
|
| 219 |
+
"learning_rate": 4.855716546937782e-05,
|
| 220 |
+
"loss": 0.342,
|
| 221 |
+
"step": 17000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.59,
|
| 225 |
+
"learning_rate": 4.703518811640083e-05,
|
| 226 |
+
"loss": 0.3274,
|
| 227 |
+
"step": 17500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.64,
|
| 231 |
+
"learning_rate": 4.551321076342384e-05,
|
| 232 |
+
"loss": 0.3242,
|
| 233 |
+
"step": 18000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.68,
|
| 237 |
+
"learning_rate": 4.3991233410446854e-05,
|
| 238 |
+
"loss": 0.3311,
|
| 239 |
+
"step": 18500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.73,
|
| 243 |
+
"learning_rate": 4.246925605746987e-05,
|
| 244 |
+
"loss": 0.3424,
|
| 245 |
+
"step": 19000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.78,
|
| 249 |
+
"learning_rate": 4.094727870449288e-05,
|
| 250 |
+
"loss": 0.3192,
|
| 251 |
+
"step": 19500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.82,
|
| 255 |
+
"learning_rate": 3.9425301351515894e-05,
|
| 256 |
+
"loss": 0.3151,
|
| 257 |
+
"step": 20000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.87,
|
| 261 |
+
"learning_rate": 3.79033239985389e-05,
|
| 262 |
+
"loss": 0.323,
|
| 263 |
+
"step": 20500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.91,
|
| 267 |
+
"learning_rate": 3.6381346645561915e-05,
|
| 268 |
+
"loss": 0.334,
|
| 269 |
+
"step": 21000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.96,
|
| 273 |
+
"learning_rate": 3.485936929258493e-05,
|
| 274 |
+
"loss": 0.3233,
|
| 275 |
+
"step": 21500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.0,
|
| 279 |
+
"eval_accuracy": 0.7321,
|
| 280 |
+
"eval_loss": 0.38333889842033386,
|
| 281 |
+
"eval_runtime": 57.0615,
|
| 282 |
+
"eval_samples_per_second": 85.644,
|
| 283 |
+
"eval_steps_per_second": 5.363,
|
| 284 |
+
"step": 21968
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.0,
|
| 288 |
+
"learning_rate": 3.333739193960794e-05,
|
| 289 |
+
"loss": 0.3239,
|
| 290 |
+
"step": 22000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.05,
|
| 294 |
+
"learning_rate": 3.1815414586630955e-05,
|
| 295 |
+
"loss": 0.2248,
|
| 296 |
+
"step": 22500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.09,
|
| 300 |
+
"learning_rate": 3.0293437233653966e-05,
|
| 301 |
+
"loss": 0.2207,
|
| 302 |
+
"step": 23000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.14,
|
| 306 |
+
"learning_rate": 2.8771459880676976e-05,
|
| 307 |
+
"loss": 0.2394,
|
| 308 |
+
"step": 23500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.18,
|
| 312 |
+
"learning_rate": 2.724948252769999e-05,
|
| 313 |
+
"loss": 0.2378,
|
| 314 |
+
"step": 24000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.23,
|
| 318 |
+
"learning_rate": 2.5727505174723e-05,
|
| 319 |
+
"loss": 0.2318,
|
| 320 |
+
"step": 24500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.28,
|
| 324 |
+
"learning_rate": 2.4205527821746013e-05,
|
| 325 |
+
"loss": 0.2357,
|
| 326 |
+
"step": 25000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.32,
|
| 330 |
+
"learning_rate": 2.2683550468769027e-05,
|
| 331 |
+
"loss": 0.2325,
|
| 332 |
+
"step": 25500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.37,
|
| 336 |
+
"learning_rate": 2.1161573115792037e-05,
|
| 337 |
+
"loss": 0.2309,
|
| 338 |
+
"step": 26000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.41,
|
| 342 |
+
"learning_rate": 1.963959576281505e-05,
|
| 343 |
+
"loss": 0.2416,
|
| 344 |
+
"step": 26500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.46,
|
| 348 |
+
"learning_rate": 1.8117618409838064e-05,
|
| 349 |
+
"loss": 0.2287,
|
| 350 |
+
"step": 27000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.5,
|
| 354 |
+
"learning_rate": 1.6595641056861074e-05,
|
| 355 |
+
"loss": 0.2385,
|
| 356 |
+
"step": 27500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.55,
|
| 360 |
+
"learning_rate": 1.5073663703884086e-05,
|
| 361 |
+
"loss": 0.2336,
|
| 362 |
+
"step": 28000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.59,
|
| 366 |
+
"learning_rate": 1.35516863509071e-05,
|
| 367 |
+
"loss": 0.2252,
|
| 368 |
+
"step": 28500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.64,
|
| 372 |
+
"learning_rate": 1.2029708997930111e-05,
|
| 373 |
+
"loss": 0.2329,
|
| 374 |
+
"step": 29000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.69,
|
| 378 |
+
"learning_rate": 1.0507731644953125e-05,
|
| 379 |
+
"loss": 0.2214,
|
| 380 |
+
"step": 29500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.73,
|
| 384 |
+
"learning_rate": 8.985754291976135e-06,
|
| 385 |
+
"loss": 0.2335,
|
| 386 |
+
"step": 30000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.78,
|
| 390 |
+
"learning_rate": 7.463776938999148e-06,
|
| 391 |
+
"loss": 0.219,
|
| 392 |
+
"step": 30500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.82,
|
| 396 |
+
"learning_rate": 5.94179958602216e-06,
|
| 397 |
+
"loss": 0.2252,
|
| 398 |
+
"step": 31000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.87,
|
| 402 |
+
"learning_rate": 4.419822233045172e-06,
|
| 403 |
+
"loss": 0.2381,
|
| 404 |
+
"step": 31500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.91,
|
| 408 |
+
"learning_rate": 2.8978448800681847e-06,
|
| 409 |
+
"loss": 0.2359,
|
| 410 |
+
"step": 32000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.96,
|
| 414 |
+
"learning_rate": 1.375867527091197e-06,
|
| 415 |
+
"loss": 0.229,
|
| 416 |
+
"step": 32500
|
| 417 |
+
},
|
| 418 |
{
|
| 419 |
"epoch": 3.0,
|
| 420 |
+
"eval_accuracy": 0.7424,
|
| 421 |
+
"eval_loss": 0.44141659140586853,
|
| 422 |
+
"eval_runtime": 57.0579,
|
| 423 |
+
"eval_samples_per_second": 85.65,
|
| 424 |
+
"eval_steps_per_second": 5.363,
|
| 425 |
+
"step": 32952
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 3.0,
|
| 429 |
+
"step": 32952,
|
| 430 |
+
"total_flos": 1.6052008203583488e+17,
|
| 431 |
+
"train_loss": 0.35377963603946533,
|
| 432 |
+
"train_runtime": 9210.1652,
|
| 433 |
+
"train_samples_per_second": 28.62,
|
| 434 |
+
"train_steps_per_second": 3.578
|
| 435 |
}
|
| 436 |
],
|
| 437 |
+
"max_steps": 32952,
|
| 438 |
"num_train_epochs": 3,
|
| 439 |
+
"total_flos": 1.6052008203583488e+17,
|
| 440 |
"trial_name": null,
|
| 441 |
"trial_params": null
|
| 442 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2927
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6d16380302cbd0224b44f153c64112de5d9a742244076fbb99e683fd78d985d
|
| 3 |
size 2927
|