Uploaded Model
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jun29_11-56-38_c47e2c16ad8c/events.out.tfevents.1688040680.c47e2c16ad8c.2021.5 +3 -0
- train_results.json +8 -0
- trainer_state.json +589 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9708904109589042,
|
| 4 |
+
"eval_f1": 0.9708904109589042,
|
| 5 |
+
"eval_loss": 0.0827358290553093,
|
| 6 |
+
"eval_precision": 0.9708904109589042,
|
| 7 |
+
"eval_recall": 0.9708904109589042,
|
| 8 |
+
"eval_runtime": 11.7112,
|
| 9 |
+
"eval_samples_per_second": 49.867,
|
| 10 |
+
"eval_steps_per_second": 6.233,
|
| 11 |
+
"total_flos": 2.973829456609837e+18,
|
| 12 |
+
"train_loss": 0.16232660566182697,
|
| 13 |
+
"train_runtime": 690.9367,
|
| 14 |
+
"train_samples_per_second": 15.712,
|
| 15 |
+
"train_steps_per_second": 0.984
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9708904109589042,
|
| 4 |
+
"eval_f1": 0.9708904109589042,
|
| 5 |
+
"eval_loss": 0.0827358290553093,
|
| 6 |
+
"eval_precision": 0.9708904109589042,
|
| 7 |
+
"eval_recall": 0.9708904109589042,
|
| 8 |
+
"eval_runtime": 11.7112,
|
| 9 |
+
"eval_samples_per_second": 49.867,
|
| 10 |
+
"eval_steps_per_second": 6.233
|
| 11 |
+
}
|
runs/Jun29_11-56-38_c47e2c16ad8c/events.out.tfevents.1688040680.c47e2c16ad8c.2021.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff0cd9ca6bc68fdaff5f220cd8910de6b72242052b7b61d49684b8f3bd8fe50
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 2.973829456609837e+18,
|
| 4 |
+
"train_loss": 0.16232660566182697,
|
| 5 |
+
"train_runtime": 690.9367,
|
| 6 |
+
"train_samples_per_second": 15.712,
|
| 7 |
+
"train_steps_per_second": 0.984
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0827358290553093,
|
| 3 |
+
"best_model_checkpoint": "./vit-large-modified-augmented-ph2-patch-16/checkpoint-650",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 680,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 0.00019705882352941177,
|
| 13 |
+
"loss": 0.6824,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 0.00019441176470588235,
|
| 19 |
+
"loss": 0.4985,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 0.00019147058823529414,
|
| 25 |
+
"loss": 0.4406,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 0.00018852941176470588,
|
| 31 |
+
"loss": 0.4613,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.29,
|
| 36 |
+
"learning_rate": 0.00018558823529411767,
|
| 37 |
+
"loss": 0.3402,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.29,
|
| 42 |
+
"eval_accuracy": 0.7945205479452054,
|
| 43 |
+
"eval_f1": 0.7945205479452053,
|
| 44 |
+
"eval_loss": 0.6269038915634155,
|
| 45 |
+
"eval_precision": 0.7945205479452054,
|
| 46 |
+
"eval_recall": 0.7945205479452054,
|
| 47 |
+
"eval_runtime": 11.3009,
|
| 48 |
+
"eval_samples_per_second": 51.677,
|
| 49 |
+
"eval_steps_per_second": 6.46,
|
| 50 |
+
"step": 50
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.35,
|
| 54 |
+
"learning_rate": 0.0001826470588235294,
|
| 55 |
+
"loss": 0.4146,
|
| 56 |
+
"step": 60
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.41,
|
| 60 |
+
"learning_rate": 0.0001797058823529412,
|
| 61 |
+
"loss": 0.3038,
|
| 62 |
+
"step": 70
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.47,
|
| 66 |
+
"learning_rate": 0.00017676470588235294,
|
| 67 |
+
"loss": 0.2719,
|
| 68 |
+
"step": 80
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.53,
|
| 72 |
+
"learning_rate": 0.00017382352941176473,
|
| 73 |
+
"loss": 0.3276,
|
| 74 |
+
"step": 90
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.59,
|
| 78 |
+
"learning_rate": 0.00017088235294117647,
|
| 79 |
+
"loss": 0.1387,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.59,
|
| 84 |
+
"eval_accuracy": 0.8921232876712328,
|
| 85 |
+
"eval_f1": 0.8921232876712328,
|
| 86 |
+
"eval_loss": 0.2956628203392029,
|
| 87 |
+
"eval_precision": 0.8921232876712328,
|
| 88 |
+
"eval_recall": 0.8921232876712328,
|
| 89 |
+
"eval_runtime": 11.8234,
|
| 90 |
+
"eval_samples_per_second": 49.393,
|
| 91 |
+
"eval_steps_per_second": 6.174,
|
| 92 |
+
"step": 100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.65,
|
| 96 |
+
"learning_rate": 0.00016794117647058823,
|
| 97 |
+
"loss": 0.2664,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.71,
|
| 102 |
+
"learning_rate": 0.000165,
|
| 103 |
+
"loss": 0.2601,
|
| 104 |
+
"step": 120
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.76,
|
| 108 |
+
"learning_rate": 0.00016205882352941176,
|
| 109 |
+
"loss": 0.2548,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.82,
|
| 114 |
+
"learning_rate": 0.00015911764705882353,
|
| 115 |
+
"loss": 0.3336,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.88,
|
| 120 |
+
"learning_rate": 0.0001561764705882353,
|
| 121 |
+
"loss": 0.2921,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.88,
|
| 126 |
+
"eval_accuracy": 0.8835616438356164,
|
| 127 |
+
"eval_f1": 0.8835616438356163,
|
| 128 |
+
"eval_loss": 0.31567689776420593,
|
| 129 |
+
"eval_precision": 0.8835616438356164,
|
| 130 |
+
"eval_recall": 0.8835616438356164,
|
| 131 |
+
"eval_runtime": 11.8613,
|
| 132 |
+
"eval_samples_per_second": 49.236,
|
| 133 |
+
"eval_steps_per_second": 6.154,
|
| 134 |
+
"step": 150
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.94,
|
| 138 |
+
"learning_rate": 0.00015323529411764709,
|
| 139 |
+
"loss": 0.2107,
|
| 140 |
+
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0,
|
| 144 |
+
"learning_rate": 0.00015029411764705882,
|
| 145 |
+
"loss": 0.1724,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.06,
|
| 150 |
+
"learning_rate": 0.00014735294117647062,
|
| 151 |
+
"loss": 0.1688,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.12,
|
| 156 |
+
"learning_rate": 0.00014441176470588235,
|
| 157 |
+
"loss": 0.2278,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.18,
|
| 162 |
+
"learning_rate": 0.00014147058823529415,
|
| 163 |
+
"loss": 0.1268,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.18,
|
| 168 |
+
"eval_accuracy": 0.8527397260273972,
|
| 169 |
+
"eval_f1": 0.8527397260273972,
|
| 170 |
+
"eval_loss": 0.455745130777359,
|
| 171 |
+
"eval_precision": 0.8527397260273972,
|
| 172 |
+
"eval_recall": 0.8527397260273972,
|
| 173 |
+
"eval_runtime": 11.8688,
|
| 174 |
+
"eval_samples_per_second": 49.205,
|
| 175 |
+
"eval_steps_per_second": 6.151,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.24,
|
| 180 |
+
"learning_rate": 0.00013852941176470588,
|
| 181 |
+
"loss": 0.2317,
|
| 182 |
+
"step": 210
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.29,
|
| 186 |
+
"learning_rate": 0.00013558823529411765,
|
| 187 |
+
"loss": 0.1221,
|
| 188 |
+
"step": 220
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.35,
|
| 192 |
+
"learning_rate": 0.00013264705882352941,
|
| 193 |
+
"loss": 0.1903,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.41,
|
| 198 |
+
"learning_rate": 0.00012970588235294118,
|
| 199 |
+
"loss": 0.1622,
|
| 200 |
+
"step": 240
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.47,
|
| 204 |
+
"learning_rate": 0.00012676470588235294,
|
| 205 |
+
"loss": 0.2071,
|
| 206 |
+
"step": 250
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.47,
|
| 210 |
+
"eval_accuracy": 0.8818493150684932,
|
| 211 |
+
"eval_f1": 0.8818493150684932,
|
| 212 |
+
"eval_loss": 0.26901647448539734,
|
| 213 |
+
"eval_precision": 0.8818493150684932,
|
| 214 |
+
"eval_recall": 0.8818493150684932,
|
| 215 |
+
"eval_runtime": 12.0775,
|
| 216 |
+
"eval_samples_per_second": 48.354,
|
| 217 |
+
"eval_steps_per_second": 6.044,
|
| 218 |
+
"step": 250
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.53,
|
| 222 |
+
"learning_rate": 0.0001238235294117647,
|
| 223 |
+
"loss": 0.265,
|
| 224 |
+
"step": 260
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.59,
|
| 228 |
+
"learning_rate": 0.00012088235294117647,
|
| 229 |
+
"loss": 0.215,
|
| 230 |
+
"step": 270
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.65,
|
| 234 |
+
"learning_rate": 0.00011794117647058824,
|
| 235 |
+
"loss": 0.1359,
|
| 236 |
+
"step": 280
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.71,
|
| 240 |
+
"learning_rate": 0.00011499999999999999,
|
| 241 |
+
"loss": 0.1603,
|
| 242 |
+
"step": 290
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.76,
|
| 246 |
+
"learning_rate": 0.00011205882352941177,
|
| 247 |
+
"loss": 0.1238,
|
| 248 |
+
"step": 300
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.76,
|
| 252 |
+
"eval_accuracy": 0.9178082191780822,
|
| 253 |
+
"eval_f1": 0.9178082191780822,
|
| 254 |
+
"eval_loss": 0.29986169934272766,
|
| 255 |
+
"eval_precision": 0.9178082191780822,
|
| 256 |
+
"eval_recall": 0.9178082191780822,
|
| 257 |
+
"eval_runtime": 12.0554,
|
| 258 |
+
"eval_samples_per_second": 48.443,
|
| 259 |
+
"eval_steps_per_second": 6.055,
|
| 260 |
+
"step": 300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.82,
|
| 264 |
+
"learning_rate": 0.00010911764705882352,
|
| 265 |
+
"loss": 0.097,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.88,
|
| 270 |
+
"learning_rate": 0.0001061764705882353,
|
| 271 |
+
"loss": 0.244,
|
| 272 |
+
"step": 320
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.94,
|
| 276 |
+
"learning_rate": 0.00010323529411764708,
|
| 277 |
+
"loss": 0.1553,
|
| 278 |
+
"step": 330
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.0,
|
| 282 |
+
"learning_rate": 0.00010029411764705883,
|
| 283 |
+
"loss": 0.0799,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.06,
|
| 288 |
+
"learning_rate": 9.73529411764706e-05,
|
| 289 |
+
"loss": 0.1327,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.06,
|
| 294 |
+
"eval_accuracy": 0.7876712328767124,
|
| 295 |
+
"eval_f1": 0.7876712328767124,
|
| 296 |
+
"eval_loss": 0.6025873422622681,
|
| 297 |
+
"eval_precision": 0.7876712328767124,
|
| 298 |
+
"eval_recall": 0.7876712328767124,
|
| 299 |
+
"eval_runtime": 12.0601,
|
| 300 |
+
"eval_samples_per_second": 48.424,
|
| 301 |
+
"eval_steps_per_second": 6.053,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.12,
|
| 306 |
+
"learning_rate": 9.441176470588236e-05,
|
| 307 |
+
"loss": 0.1859,
|
| 308 |
+
"step": 360
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.18,
|
| 312 |
+
"learning_rate": 9.147058823529412e-05,
|
| 313 |
+
"loss": 0.1577,
|
| 314 |
+
"step": 370
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.24,
|
| 318 |
+
"learning_rate": 8.852941176470589e-05,
|
| 319 |
+
"loss": 0.1616,
|
| 320 |
+
"step": 380
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.29,
|
| 324 |
+
"learning_rate": 8.558823529411765e-05,
|
| 325 |
+
"loss": 0.1998,
|
| 326 |
+
"step": 390
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.35,
|
| 330 |
+
"learning_rate": 8.26470588235294e-05,
|
| 331 |
+
"loss": 0.1453,
|
| 332 |
+
"step": 400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.35,
|
| 336 |
+
"eval_accuracy": 0.898972602739726,
|
| 337 |
+
"eval_f1": 0.8989726027397261,
|
| 338 |
+
"eval_loss": 0.2887475788593292,
|
| 339 |
+
"eval_precision": 0.898972602739726,
|
| 340 |
+
"eval_recall": 0.898972602739726,
|
| 341 |
+
"eval_runtime": 11.7988,
|
| 342 |
+
"eval_samples_per_second": 49.497,
|
| 343 |
+
"eval_steps_per_second": 6.187,
|
| 344 |
+
"step": 400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.41,
|
| 348 |
+
"learning_rate": 7.970588235294118e-05,
|
| 349 |
+
"loss": 0.1919,
|
| 350 |
+
"step": 410
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.47,
|
| 354 |
+
"learning_rate": 7.676470588235295e-05,
|
| 355 |
+
"loss": 0.0973,
|
| 356 |
+
"step": 420
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.53,
|
| 360 |
+
"learning_rate": 7.382352941176471e-05,
|
| 361 |
+
"loss": 0.0649,
|
| 362 |
+
"step": 430
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.59,
|
| 366 |
+
"learning_rate": 7.088235294117648e-05,
|
| 367 |
+
"loss": 0.1033,
|
| 368 |
+
"step": 440
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.65,
|
| 372 |
+
"learning_rate": 6.794117647058824e-05,
|
| 373 |
+
"loss": 0.0686,
|
| 374 |
+
"step": 450
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.65,
|
| 378 |
+
"eval_accuracy": 0.9503424657534246,
|
| 379 |
+
"eval_f1": 0.9503424657534246,
|
| 380 |
+
"eval_loss": 0.2048829048871994,
|
| 381 |
+
"eval_precision": 0.9503424657534246,
|
| 382 |
+
"eval_recall": 0.9503424657534246,
|
| 383 |
+
"eval_runtime": 11.8436,
|
| 384 |
+
"eval_samples_per_second": 49.309,
|
| 385 |
+
"eval_steps_per_second": 6.164,
|
| 386 |
+
"step": 450
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.71,
|
| 390 |
+
"learning_rate": 6.500000000000001e-05,
|
| 391 |
+
"loss": 0.0378,
|
| 392 |
+
"step": 460
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.76,
|
| 396 |
+
"learning_rate": 6.205882352941177e-05,
|
| 397 |
+
"loss": 0.095,
|
| 398 |
+
"step": 470
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.82,
|
| 402 |
+
"learning_rate": 5.911764705882353e-05,
|
| 403 |
+
"loss": 0.0501,
|
| 404 |
+
"step": 480
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.88,
|
| 408 |
+
"learning_rate": 5.6176470588235296e-05,
|
| 409 |
+
"loss": 0.0444,
|
| 410 |
+
"step": 490
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.94,
|
| 414 |
+
"learning_rate": 5.323529411764706e-05,
|
| 415 |
+
"loss": 0.0414,
|
| 416 |
+
"step": 500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.94,
|
| 420 |
+
"eval_accuracy": 0.9195205479452054,
|
| 421 |
+
"eval_f1": 0.9195205479452054,
|
| 422 |
+
"eval_loss": 0.30401644110679626,
|
| 423 |
+
"eval_precision": 0.9195205479452054,
|
| 424 |
+
"eval_recall": 0.9195205479452054,
|
| 425 |
+
"eval_runtime": 11.748,
|
| 426 |
+
"eval_samples_per_second": 49.711,
|
| 427 |
+
"eval_steps_per_second": 6.214,
|
| 428 |
+
"step": 500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.0,
|
| 432 |
+
"learning_rate": 5.0294117647058826e-05,
|
| 433 |
+
"loss": 0.0455,
|
| 434 |
+
"step": 510
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.06,
|
| 438 |
+
"learning_rate": 4.735294117647059e-05,
|
| 439 |
+
"loss": 0.0631,
|
| 440 |
+
"step": 520
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.12,
|
| 444 |
+
"learning_rate": 4.4411764705882356e-05,
|
| 445 |
+
"loss": 0.1279,
|
| 446 |
+
"step": 530
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.18,
|
| 450 |
+
"learning_rate": 4.147058823529412e-05,
|
| 451 |
+
"loss": 0.0111,
|
| 452 |
+
"step": 540
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.24,
|
| 456 |
+
"learning_rate": 3.8529411764705886e-05,
|
| 457 |
+
"loss": 0.0851,
|
| 458 |
+
"step": 550
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.24,
|
| 462 |
+
"eval_accuracy": 0.9297945205479452,
|
| 463 |
+
"eval_f1": 0.9297945205479452,
|
| 464 |
+
"eval_loss": 0.22443008422851562,
|
| 465 |
+
"eval_precision": 0.9297945205479452,
|
| 466 |
+
"eval_recall": 0.9297945205479452,
|
| 467 |
+
"eval_runtime": 11.6193,
|
| 468 |
+
"eval_samples_per_second": 50.261,
|
| 469 |
+
"eval_steps_per_second": 6.283,
|
| 470 |
+
"step": 550
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.29,
|
| 474 |
+
"learning_rate": 3.558823529411765e-05,
|
| 475 |
+
"loss": 0.0775,
|
| 476 |
+
"step": 560
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.35,
|
| 480 |
+
"learning_rate": 3.2647058823529416e-05,
|
| 481 |
+
"loss": 0.0075,
|
| 482 |
+
"step": 570
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.41,
|
| 486 |
+
"learning_rate": 2.9705882352941177e-05,
|
| 487 |
+
"loss": 0.0334,
|
| 488 |
+
"step": 580
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.47,
|
| 492 |
+
"learning_rate": 2.6764705882352942e-05,
|
| 493 |
+
"loss": 0.0253,
|
| 494 |
+
"step": 590
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.53,
|
| 498 |
+
"learning_rate": 2.3823529411764707e-05,
|
| 499 |
+
"loss": 0.0054,
|
| 500 |
+
"step": 600
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.53,
|
| 504 |
+
"eval_accuracy": 0.9554794520547946,
|
| 505 |
+
"eval_f1": 0.9554794520547946,
|
| 506 |
+
"eval_loss": 0.13558290898799896,
|
| 507 |
+
"eval_precision": 0.9554794520547946,
|
| 508 |
+
"eval_recall": 0.9554794520547946,
|
| 509 |
+
"eval_runtime": 11.7366,
|
| 510 |
+
"eval_samples_per_second": 49.759,
|
| 511 |
+
"eval_steps_per_second": 6.22,
|
| 512 |
+
"step": 600
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.59,
|
| 516 |
+
"learning_rate": 2.0882352941176472e-05,
|
| 517 |
+
"loss": 0.0032,
|
| 518 |
+
"step": 610
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.65,
|
| 522 |
+
"learning_rate": 1.7941176470588237e-05,
|
| 523 |
+
"loss": 0.0122,
|
| 524 |
+
"step": 620
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.71,
|
| 528 |
+
"learning_rate": 1.5e-05,
|
| 529 |
+
"loss": 0.0746,
|
| 530 |
+
"step": 630
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.76,
|
| 534 |
+
"learning_rate": 1.2058823529411765e-05,
|
| 535 |
+
"loss": 0.0416,
|
| 536 |
+
"step": 640
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.82,
|
| 540 |
+
"learning_rate": 9.117647058823529e-06,
|
| 541 |
+
"loss": 0.0029,
|
| 542 |
+
"step": 650
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.82,
|
| 546 |
+
"eval_accuracy": 0.9708904109589042,
|
| 547 |
+
"eval_f1": 0.9708904109589042,
|
| 548 |
+
"eval_loss": 0.0827358290553093,
|
| 549 |
+
"eval_precision": 0.9708904109589042,
|
| 550 |
+
"eval_recall": 0.9708904109589042,
|
| 551 |
+
"eval_runtime": 11.7473,
|
| 552 |
+
"eval_samples_per_second": 49.713,
|
| 553 |
+
"eval_steps_per_second": 6.214,
|
| 554 |
+
"step": 650
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.88,
|
| 558 |
+
"learning_rate": 6.1764705882352944e-06,
|
| 559 |
+
"loss": 0.012,
|
| 560 |
+
"step": 660
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.94,
|
| 564 |
+
"learning_rate": 3.2352941176470594e-06,
|
| 565 |
+
"loss": 0.0052,
|
| 566 |
+
"step": 670
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.0,
|
| 570 |
+
"learning_rate": 2.9411764705882356e-07,
|
| 571 |
+
"loss": 0.0441,
|
| 572 |
+
"step": 680
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.0,
|
| 576 |
+
"step": 680,
|
| 577 |
+
"total_flos": 2.973829456609837e+18,
|
| 578 |
+
"train_loss": 0.16232660566182697,
|
| 579 |
+
"train_runtime": 690.9367,
|
| 580 |
+
"train_samples_per_second": 15.712,
|
| 581 |
+
"train_steps_per_second": 0.984
|
| 582 |
+
}
|
| 583 |
+
],
|
| 584 |
+
"max_steps": 680,
|
| 585 |
+
"num_train_epochs": 4,
|
| 586 |
+
"total_flos": 2.973829456609837e+18,
|
| 587 |
+
"trial_name": null,
|
| 588 |
+
"trial_params": null
|
| 589 |
+
}
|