veryverypro
commited on
Commit
•
682891b
1
Parent(s):
a04dcc3
fine tuning ViT for CiFAR10 dataset
Browse files- config.json +48 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +619 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "airplane",
|
| 13 |
+
"1": "automobile",
|
| 14 |
+
"2": "bird",
|
| 15 |
+
"3": "cat",
|
| 16 |
+
"4": "deer",
|
| 17 |
+
"5": "dog",
|
| 18 |
+
"6": "frog",
|
| 19 |
+
"7": "horse",
|
| 20 |
+
"8": "ship",
|
| 21 |
+
"9": "truck"
|
| 22 |
+
},
|
| 23 |
+
"image_size": 224,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 3072,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"airplane": 0,
|
| 28 |
+
"automobile": 1,
|
| 29 |
+
"bird": 2,
|
| 30 |
+
"cat": 3,
|
| 31 |
+
"deer": 4,
|
| 32 |
+
"dog": 5,
|
| 33 |
+
"frog": 6,
|
| 34 |
+
"horse": 7,
|
| 35 |
+
"ship": 8,
|
| 36 |
+
"truck": 9
|
| 37 |
+
},
|
| 38 |
+
"layer_norm_eps": 1e-12,
|
| 39 |
+
"model_type": "vit",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_channels": 3,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"problem_type": "single_label_classification",
|
| 45 |
+
"qkv_bias": true,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.33.0"
|
| 48 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:433c0eba27f5c1897025268cc0700fe9914efe3ee9d71d928af791d3bd44c3b6
|
| 3 |
+
size 686617605
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17f929e2202237c2bab9c881bbe31009fbdff49f2f799adc6f3efd578b46a303
|
| 3 |
+
size 343293293
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7155940833476e49976920d68eb308ee5fe989c7fb13559027facfff2b3927f4
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.557544757033248,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 14 |
+
"loss": 2.4523,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 20 |
+
"loss": 2.4396,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 3e-06,
|
| 26 |
+
"loss": 2.3918,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 4.000000000000001e-06,
|
| 32 |
+
"loss": 2.2748,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.13,
|
| 37 |
+
"learning_rate": 5e-06,
|
| 38 |
+
"loss": 2.166,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.15,
|
| 43 |
+
"learning_rate": 6e-06,
|
| 44 |
+
"loss": 1.9984,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.18,
|
| 49 |
+
"learning_rate": 7.000000000000001e-06,
|
| 50 |
+
"loss": 1.8286,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2,
|
| 55 |
+
"learning_rate": 8.000000000000001e-06,
|
| 56 |
+
"loss": 1.6089,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.23,
|
| 61 |
+
"learning_rate": 9e-06,
|
| 62 |
+
"loss": 1.387,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.26,
|
| 67 |
+
"learning_rate": 1e-05,
|
| 68 |
+
"loss": 1.1289,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.28,
|
| 73 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 74 |
+
"loss": 0.8848,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.31,
|
| 79 |
+
"learning_rate": 1.2e-05,
|
| 80 |
+
"loss": 0.6848,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.33,
|
| 85 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 86 |
+
"loss": 0.4791,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.36,
|
| 91 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 92 |
+
"loss": 0.3629,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.38,
|
| 97 |
+
"learning_rate": 1.5e-05,
|
| 98 |
+
"loss": 0.2723,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.41,
|
| 103 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 104 |
+
"loss": 0.2076,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.43,
|
| 109 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 110 |
+
"loss": 0.1543,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.46,
|
| 115 |
+
"learning_rate": 1.8e-05,
|
| 116 |
+
"loss": 0.1494,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.49,
|
| 121 |
+
"learning_rate": 1.9e-05,
|
| 122 |
+
"loss": 0.1076,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.51,
|
| 127 |
+
"learning_rate": 2e-05,
|
| 128 |
+
"loss": 0.1173,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.54,
|
| 133 |
+
"learning_rate": 2.1e-05,
|
| 134 |
+
"loss": 0.1025,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.56,
|
| 139 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 140 |
+
"loss": 0.1056,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.59,
|
| 145 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 146 |
+
"loss": 0.0841,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.61,
|
| 151 |
+
"learning_rate": 2.4e-05,
|
| 152 |
+
"loss": 0.079,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.64,
|
| 157 |
+
"learning_rate": 2.5e-05,
|
| 158 |
+
"loss": 0.0764,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.66,
|
| 163 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 164 |
+
"loss": 0.0659,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.69,
|
| 169 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 170 |
+
"loss": 0.0766,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.72,
|
| 175 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 176 |
+
"loss": 0.0729,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.74,
|
| 181 |
+
"learning_rate": 2.9e-05,
|
| 182 |
+
"loss": 0.0862,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.77,
|
| 187 |
+
"learning_rate": 3e-05,
|
| 188 |
+
"loss": 0.0565,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.79,
|
| 193 |
+
"learning_rate": 3.1e-05,
|
| 194 |
+
"loss": 0.0725,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.82,
|
| 199 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 200 |
+
"loss": 0.0757,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.84,
|
| 205 |
+
"learning_rate": 3.3e-05,
|
| 206 |
+
"loss": 0.0872,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.87,
|
| 211 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 212 |
+
"loss": 0.0692,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.9,
|
| 217 |
+
"learning_rate": 3.5e-05,
|
| 218 |
+
"loss": 0.0646,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.92,
|
| 223 |
+
"learning_rate": 3.6e-05,
|
| 224 |
+
"loss": 0.0517,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.95,
|
| 229 |
+
"learning_rate": 3.7e-05,
|
| 230 |
+
"loss": 0.0708,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.97,
|
| 235 |
+
"learning_rate": 3.8e-05,
|
| 236 |
+
"loss": 0.0744,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.0,
|
| 241 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 242 |
+
"loss": 0.0745,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.02,
|
| 247 |
+
"learning_rate": 4e-05,
|
| 248 |
+
"loss": 0.0433,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.05,
|
| 253 |
+
"learning_rate": 4.1e-05,
|
| 254 |
+
"loss": 0.0369,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.07,
|
| 259 |
+
"learning_rate": 4.2e-05,
|
| 260 |
+
"loss": 0.0347,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.1,
|
| 265 |
+
"learning_rate": 4.3e-05,
|
| 266 |
+
"loss": 0.0426,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.13,
|
| 271 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 272 |
+
"loss": 0.0254,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.15,
|
| 277 |
+
"learning_rate": 4.5e-05,
|
| 278 |
+
"loss": 0.0296,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.18,
|
| 283 |
+
"learning_rate": 4.600000000000001e-05,
|
| 284 |
+
"loss": 0.0329,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.2,
|
| 289 |
+
"learning_rate": 4.7e-05,
|
| 290 |
+
"loss": 0.0373,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.23,
|
| 295 |
+
"learning_rate": 4.8e-05,
|
| 296 |
+
"loss": 0.0185,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.25,
|
| 301 |
+
"learning_rate": 4.9e-05,
|
| 302 |
+
"loss": 0.0346,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.28,
|
| 307 |
+
"learning_rate": 5e-05,
|
| 308 |
+
"loss": 0.0343,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3,
|
| 313 |
+
"learning_rate": 4.9257057949479945e-05,
|
| 314 |
+
"loss": 0.0398,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.33,
|
| 319 |
+
"learning_rate": 4.851411589895988e-05,
|
| 320 |
+
"loss": 0.0266,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.36,
|
| 325 |
+
"learning_rate": 4.777117384843983e-05,
|
| 326 |
+
"loss": 0.0394,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.38,
|
| 331 |
+
"learning_rate": 4.7028231797919764e-05,
|
| 332 |
+
"loss": 0.0385,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.41,
|
| 337 |
+
"learning_rate": 4.6285289747399706e-05,
|
| 338 |
+
"loss": 0.0467,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.43,
|
| 343 |
+
"learning_rate": 4.554234769687964e-05,
|
| 344 |
+
"loss": 0.0561,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.46,
|
| 349 |
+
"learning_rate": 4.479940564635959e-05,
|
| 350 |
+
"loss": 0.0224,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.48,
|
| 355 |
+
"learning_rate": 4.4056463595839526e-05,
|
| 356 |
+
"loss": 0.0279,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.51,
|
| 361 |
+
"learning_rate": 4.331352154531947e-05,
|
| 362 |
+
"loss": 0.0336,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.53,
|
| 367 |
+
"learning_rate": 4.25705794947994e-05,
|
| 368 |
+
"loss": 0.0327,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.56,
|
| 373 |
+
"learning_rate": 4.182763744427935e-05,
|
| 374 |
+
"loss": 0.0284,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.59,
|
| 379 |
+
"learning_rate": 4.108469539375929e-05,
|
| 380 |
+
"loss": 0.0317,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.61,
|
| 385 |
+
"learning_rate": 4.034175334323923e-05,
|
| 386 |
+
"loss": 0.0429,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.64,
|
| 391 |
+
"learning_rate": 3.9598811292719165e-05,
|
| 392 |
+
"loss": 0.0342,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.66,
|
| 397 |
+
"learning_rate": 3.8855869242199114e-05,
|
| 398 |
+
"loss": 0.0429,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.69,
|
| 403 |
+
"learning_rate": 3.811292719167905e-05,
|
| 404 |
+
"loss": 0.055,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.71,
|
| 409 |
+
"learning_rate": 3.736998514115899e-05,
|
| 410 |
+
"loss": 0.039,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.74,
|
| 415 |
+
"learning_rate": 3.662704309063893e-05,
|
| 416 |
+
"loss": 0.0303,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.76,
|
| 421 |
+
"learning_rate": 3.5884101040118876e-05,
|
| 422 |
+
"loss": 0.0299,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.79,
|
| 427 |
+
"learning_rate": 3.514115898959881e-05,
|
| 428 |
+
"loss": 0.0331,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.82,
|
| 433 |
+
"learning_rate": 3.439821693907875e-05,
|
| 434 |
+
"loss": 0.0287,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.84,
|
| 439 |
+
"learning_rate": 3.3655274888558695e-05,
|
| 440 |
+
"loss": 0.0298,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.87,
|
| 445 |
+
"learning_rate": 3.291233283803864e-05,
|
| 446 |
+
"loss": 0.0206,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.89,
|
| 451 |
+
"learning_rate": 3.216939078751858e-05,
|
| 452 |
+
"loss": 0.0283,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.92,
|
| 457 |
+
"learning_rate": 3.1426448736998515e-05,
|
| 458 |
+
"loss": 0.0359,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.94,
|
| 463 |
+
"learning_rate": 3.068350668647846e-05,
|
| 464 |
+
"loss": 0.0199,
|
| 465 |
+
"step": 760
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.97,
|
| 469 |
+
"learning_rate": 2.9940564635958396e-05,
|
| 470 |
+
"loss": 0.0325,
|
| 471 |
+
"step": 770
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.99,
|
| 475 |
+
"learning_rate": 2.9197622585438338e-05,
|
| 476 |
+
"loss": 0.0319,
|
| 477 |
+
"step": 780
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.02,
|
| 481 |
+
"learning_rate": 2.8454680534918276e-05,
|
| 482 |
+
"loss": 0.0277,
|
| 483 |
+
"step": 790
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.05,
|
| 487 |
+
"learning_rate": 2.771173848439822e-05,
|
| 488 |
+
"loss": 0.0067,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.07,
|
| 493 |
+
"learning_rate": 2.6968796433878157e-05,
|
| 494 |
+
"loss": 0.0046,
|
| 495 |
+
"step": 810
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.1,
|
| 499 |
+
"learning_rate": 2.62258543833581e-05,
|
| 500 |
+
"loss": 0.0093,
|
| 501 |
+
"step": 820
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.12,
|
| 505 |
+
"learning_rate": 2.5482912332838038e-05,
|
| 506 |
+
"loss": 0.0104,
|
| 507 |
+
"step": 830
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.15,
|
| 511 |
+
"learning_rate": 2.473997028231798e-05,
|
| 512 |
+
"loss": 0.0046,
|
| 513 |
+
"step": 840
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.17,
|
| 517 |
+
"learning_rate": 2.3997028231797922e-05,
|
| 518 |
+
"loss": 0.0047,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.2,
|
| 523 |
+
"learning_rate": 2.325408618127786e-05,
|
| 524 |
+
"loss": 0.0048,
|
| 525 |
+
"step": 860
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.23,
|
| 529 |
+
"learning_rate": 2.2511144130757803e-05,
|
| 530 |
+
"loss": 0.004,
|
| 531 |
+
"step": 870
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.25,
|
| 535 |
+
"learning_rate": 2.1768202080237742e-05,
|
| 536 |
+
"loss": 0.011,
|
| 537 |
+
"step": 880
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.28,
|
| 541 |
+
"learning_rate": 2.1025260029717684e-05,
|
| 542 |
+
"loss": 0.0034,
|
| 543 |
+
"step": 890
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.3,
|
| 547 |
+
"learning_rate": 2.0282317979197623e-05,
|
| 548 |
+
"loss": 0.0068,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.33,
|
| 553 |
+
"learning_rate": 1.9539375928677565e-05,
|
| 554 |
+
"loss": 0.01,
|
| 555 |
+
"step": 910
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.35,
|
| 559 |
+
"learning_rate": 1.8796433878157504e-05,
|
| 560 |
+
"loss": 0.0069,
|
| 561 |
+
"step": 920
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.38,
|
| 565 |
+
"learning_rate": 1.8053491827637446e-05,
|
| 566 |
+
"loss": 0.0063,
|
| 567 |
+
"step": 930
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.4,
|
| 571 |
+
"learning_rate": 1.7310549777117385e-05,
|
| 572 |
+
"loss": 0.0058,
|
| 573 |
+
"step": 940
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.43,
|
| 577 |
+
"learning_rate": 1.6567607726597327e-05,
|
| 578 |
+
"loss": 0.0053,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.46,
|
| 583 |
+
"learning_rate": 1.5824665676077265e-05,
|
| 584 |
+
"loss": 0.0039,
|
| 585 |
+
"step": 960
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.48,
|
| 589 |
+
"learning_rate": 1.5081723625557206e-05,
|
| 590 |
+
"loss": 0.0033,
|
| 591 |
+
"step": 970
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.51,
|
| 595 |
+
"learning_rate": 1.4338781575037146e-05,
|
| 596 |
+
"loss": 0.0096,
|
| 597 |
+
"step": 980
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.53,
|
| 601 |
+
"learning_rate": 1.3595839524517087e-05,
|
| 602 |
+
"loss": 0.0132,
|
| 603 |
+
"step": 990
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.56,
|
| 607 |
+
"learning_rate": 1.2852897473997027e-05,
|
| 608 |
+
"loss": 0.003,
|
| 609 |
+
"step": 1000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 10,
|
| 613 |
+
"max_steps": 1173,
|
| 614 |
+
"num_train_epochs": 3,
|
| 615 |
+
"save_steps": 500,
|
| 616 |
+
"total_flos": 9.912246111321588e+18,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bea377ffc7f719cab94a18ba9afa3bb4914377af239dd8b7ddb9a8889c2fbbdc
|
| 3 |
+
size 3963
|