Commit
•
d2fd8a7
1
Parent(s):
bb88197
Training in progress, epoch 0
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Dec02_18-33-35_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542022.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.4449.0 +3 -0
- runs/Dec02_18-34-27_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542073.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.4449.1 +3 -0
- runs/Dec02_18-35-47_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542155.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.4449.2 +3 -0
- runs/Dec02_18-46-42_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542809.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.5191.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +529 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 1.5837129276562944e+19,
|
| 4 |
+
"train_loss": 1.3612600884640724,
|
| 5 |
+
"train_runtime": 3195.3608,
|
| 6 |
+
"train_samples_per_second": 64.007,
|
| 7 |
+
"train_steps_per_second": 0.25
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343528508
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3e969f4478aa8c3051806f73c6897f7d4fa18d7e4868b8babb431f9ceefe1c3
|
| 3 |
size 343528508
|
runs/Dec02_18-33-35_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542022.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.4449.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c53b71cb09ca97124a8a27295d5dd0f3a48c70c0c6b0275b5dc5e335da6c022
|
| 3 |
+
size 9009
|
runs/Dec02_18-34-27_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542073.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.4449.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bb446a72489363c49583a2d4cc790ffb42c88ac1608607486585e6ff73a163a
|
| 3 |
+
size 9009
|
runs/Dec02_18-35-47_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542155.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.4449.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e166e5af09c93322511a1b3debe6831dda585e2b7c632f3baa4c2fd2a108d283
|
| 3 |
+
size 9779
|
runs/Dec02_18-46-42_l-45850a67-7466-4f9c-9b08-8f8d14dc39f5/events.out.tfevents.1701542809.l-45850a67-7466-4f9c-9b08-8f8d14dc39f5.5191.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b36675ff674eadcb83f1b56b17b76c3d4b55a7a6539aec15bcaf154d08a361
|
| 3 |
+
size 13378
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 1.5837129276562944e+19,
|
| 4 |
+
"train_loss": 1.3612600884640724,
|
| 5 |
+
"train_runtime": 3195.3608,
|
| 6 |
+
"train_samples_per_second": 64.007,
|
| 7 |
+
"train_steps_per_second": 0.25
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.834983498349835,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-finetuned-eurosat/checkpoint-798",
|
| 4 |
+
"epoch": 2.9943714821763603,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 798,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 6.25e-06,
|
| 14 |
+
"loss": 4.7733,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 1.25e-05,
|
| 20 |
+
"loss": 4.7021,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 26 |
+
"loss": 4.6191,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 2.5e-05,
|
| 32 |
+
"loss": 4.487,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 3.125e-05,
|
| 38 |
+
"loss": 4.2957,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.23,
|
| 43 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 44 |
+
"loss": 4.0441,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"learning_rate": 4.375e-05,
|
| 50 |
+
"loss": 3.7251,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3,
|
| 55 |
+
"learning_rate": 5e-05,
|
| 56 |
+
"loss": 3.3993,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.34,
|
| 61 |
+
"learning_rate": 4.930362116991643e-05,
|
| 62 |
+
"loss": 3.0075,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.38,
|
| 67 |
+
"learning_rate": 4.860724233983287e-05,
|
| 68 |
+
"loss": 2.6314,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.41,
|
| 73 |
+
"learning_rate": 4.79108635097493e-05,
|
| 74 |
+
"loss": 2.4011,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.45,
|
| 79 |
+
"learning_rate": 4.721448467966574e-05,
|
| 80 |
+
"loss": 2.1461,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.49,
|
| 85 |
+
"learning_rate": 4.6518105849582176e-05,
|
| 86 |
+
"loss": 1.9426,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.53,
|
| 91 |
+
"learning_rate": 4.582172701949861e-05,
|
| 92 |
+
"loss": 1.8008,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.56,
|
| 97 |
+
"learning_rate": 4.5125348189415044e-05,
|
| 98 |
+
"loss": 1.6983,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.6,
|
| 103 |
+
"learning_rate": 4.442896935933148e-05,
|
| 104 |
+
"loss": 1.6476,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.64,
|
| 109 |
+
"learning_rate": 4.373259052924791e-05,
|
| 110 |
+
"loss": 1.4829,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.68,
|
| 115 |
+
"learning_rate": 4.303621169916435e-05,
|
| 116 |
+
"loss": 1.4473,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.71,
|
| 121 |
+
"learning_rate": 4.233983286908078e-05,
|
| 122 |
+
"loss": 1.3767,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.75,
|
| 127 |
+
"learning_rate": 4.164345403899722e-05,
|
| 128 |
+
"loss": 1.2828,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.79,
|
| 133 |
+
"learning_rate": 4.094707520891365e-05,
|
| 134 |
+
"loss": 1.3095,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.83,
|
| 139 |
+
"learning_rate": 4.0250696378830085e-05,
|
| 140 |
+
"loss": 1.2064,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.86,
|
| 145 |
+
"learning_rate": 3.955431754874652e-05,
|
| 146 |
+
"loss": 1.1614,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.9,
|
| 151 |
+
"learning_rate": 3.885793871866296e-05,
|
| 152 |
+
"loss": 1.2123,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.94,
|
| 157 |
+
"learning_rate": 3.816155988857939e-05,
|
| 158 |
+
"loss": 1.1367,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.98,
|
| 163 |
+
"learning_rate": 3.746518105849583e-05,
|
| 164 |
+
"loss": 1.0954,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"eval_accuracy": 0.7898349834983498,
|
| 170 |
+
"eval_loss": 0.9450869560241699,
|
| 171 |
+
"eval_runtime": 67.1006,
|
| 172 |
+
"eval_samples_per_second": 112.89,
|
| 173 |
+
"eval_steps_per_second": 1.773,
|
| 174 |
+
"step": 266
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.01,
|
| 178 |
+
"learning_rate": 3.676880222841226e-05,
|
| 179 |
+
"loss": 1.091,
|
| 180 |
+
"step": 270
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.05,
|
| 184 |
+
"learning_rate": 3.607242339832869e-05,
|
| 185 |
+
"loss": 1.0539,
|
| 186 |
+
"step": 280
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.09,
|
| 190 |
+
"learning_rate": 3.5376044568245126e-05,
|
| 191 |
+
"loss": 1.035,
|
| 192 |
+
"step": 290
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.13,
|
| 196 |
+
"learning_rate": 3.4679665738161556e-05,
|
| 197 |
+
"loss": 0.9419,
|
| 198 |
+
"step": 300
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.16,
|
| 202 |
+
"learning_rate": 3.3983286908077994e-05,
|
| 203 |
+
"loss": 1.0054,
|
| 204 |
+
"step": 310
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.2,
|
| 208 |
+
"learning_rate": 3.328690807799443e-05,
|
| 209 |
+
"loss": 1.0022,
|
| 210 |
+
"step": 320
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.24,
|
| 214 |
+
"learning_rate": 3.259052924791087e-05,
|
| 215 |
+
"loss": 0.9334,
|
| 216 |
+
"step": 330
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.28,
|
| 220 |
+
"learning_rate": 3.18941504178273e-05,
|
| 221 |
+
"loss": 0.9022,
|
| 222 |
+
"step": 340
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.31,
|
| 226 |
+
"learning_rate": 3.1197771587743737e-05,
|
| 227 |
+
"loss": 0.8882,
|
| 228 |
+
"step": 350
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.35,
|
| 232 |
+
"learning_rate": 3.050139275766017e-05,
|
| 233 |
+
"loss": 0.9736,
|
| 234 |
+
"step": 360
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.39,
|
| 238 |
+
"learning_rate": 2.98050139275766e-05,
|
| 239 |
+
"loss": 0.9085,
|
| 240 |
+
"step": 370
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.43,
|
| 244 |
+
"learning_rate": 2.9108635097493035e-05,
|
| 245 |
+
"loss": 0.9588,
|
| 246 |
+
"step": 380
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.46,
|
| 250 |
+
"learning_rate": 2.841225626740947e-05,
|
| 251 |
+
"loss": 0.9093,
|
| 252 |
+
"step": 390
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.5,
|
| 256 |
+
"learning_rate": 2.7715877437325903e-05,
|
| 257 |
+
"loss": 0.8688,
|
| 258 |
+
"step": 400
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.54,
|
| 262 |
+
"learning_rate": 2.7019498607242337e-05,
|
| 263 |
+
"loss": 0.8283,
|
| 264 |
+
"step": 410
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.58,
|
| 268 |
+
"learning_rate": 2.6323119777158778e-05,
|
| 269 |
+
"loss": 0.886,
|
| 270 |
+
"step": 420
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.61,
|
| 274 |
+
"learning_rate": 2.562674094707521e-05,
|
| 275 |
+
"loss": 0.9259,
|
| 276 |
+
"step": 430
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.65,
|
| 280 |
+
"learning_rate": 2.4930362116991646e-05,
|
| 281 |
+
"loss": 0.8334,
|
| 282 |
+
"step": 440
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.69,
|
| 286 |
+
"learning_rate": 2.423398328690808e-05,
|
| 287 |
+
"loss": 0.8748,
|
| 288 |
+
"step": 450
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.73,
|
| 292 |
+
"learning_rate": 2.3537604456824514e-05,
|
| 293 |
+
"loss": 0.8367,
|
| 294 |
+
"step": 460
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.76,
|
| 298 |
+
"learning_rate": 2.2841225626740948e-05,
|
| 299 |
+
"loss": 0.8054,
|
| 300 |
+
"step": 470
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.8,
|
| 304 |
+
"learning_rate": 2.214484679665738e-05,
|
| 305 |
+
"loss": 0.85,
|
| 306 |
+
"step": 480
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.84,
|
| 310 |
+
"learning_rate": 2.144846796657382e-05,
|
| 311 |
+
"loss": 0.85,
|
| 312 |
+
"step": 490
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.88,
|
| 316 |
+
"learning_rate": 2.0752089136490253e-05,
|
| 317 |
+
"loss": 0.8617,
|
| 318 |
+
"step": 500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.91,
|
| 322 |
+
"learning_rate": 2.0055710306406687e-05,
|
| 323 |
+
"loss": 0.8337,
|
| 324 |
+
"step": 510
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.95,
|
| 328 |
+
"learning_rate": 1.935933147632312e-05,
|
| 329 |
+
"loss": 0.8182,
|
| 330 |
+
"step": 520
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.99,
|
| 334 |
+
"learning_rate": 1.8662952646239558e-05,
|
| 335 |
+
"loss": 0.8207,
|
| 336 |
+
"step": 530
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.0,
|
| 340 |
+
"eval_accuracy": 0.8281188118811881,
|
| 341 |
+
"eval_loss": 0.7111164331436157,
|
| 342 |
+
"eval_runtime": 66.016,
|
| 343 |
+
"eval_samples_per_second": 114.745,
|
| 344 |
+
"eval_steps_per_second": 1.803,
|
| 345 |
+
"step": 533
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.03,
|
| 349 |
+
"learning_rate": 1.7966573816155992e-05,
|
| 350 |
+
"loss": 0.7639,
|
| 351 |
+
"step": 540
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.06,
|
| 355 |
+
"learning_rate": 1.7270194986072426e-05,
|
| 356 |
+
"loss": 0.7439,
|
| 357 |
+
"step": 550
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.1,
|
| 361 |
+
"learning_rate": 1.6573816155988857e-05,
|
| 362 |
+
"loss": 0.7358,
|
| 363 |
+
"step": 560
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.14,
|
| 367 |
+
"learning_rate": 1.587743732590529e-05,
|
| 368 |
+
"loss": 0.7454,
|
| 369 |
+
"step": 570
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.18,
|
| 373 |
+
"learning_rate": 1.518105849582173e-05,
|
| 374 |
+
"loss": 0.7533,
|
| 375 |
+
"step": 580
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.21,
|
| 379 |
+
"learning_rate": 1.4484679665738164e-05,
|
| 380 |
+
"loss": 0.7898,
|
| 381 |
+
"step": 590
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.25,
|
| 385 |
+
"learning_rate": 1.3788300835654596e-05,
|
| 386 |
+
"loss": 0.734,
|
| 387 |
+
"step": 600
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.29,
|
| 391 |
+
"learning_rate": 1.309192200557103e-05,
|
| 392 |
+
"loss": 0.793,
|
| 393 |
+
"step": 610
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.33,
|
| 397 |
+
"learning_rate": 1.2395543175487466e-05,
|
| 398 |
+
"loss": 0.7409,
|
| 399 |
+
"step": 620
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.36,
|
| 403 |
+
"learning_rate": 1.16991643454039e-05,
|
| 404 |
+
"loss": 0.7768,
|
| 405 |
+
"step": 630
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.4,
|
| 409 |
+
"learning_rate": 1.1002785515320335e-05,
|
| 410 |
+
"loss": 0.7306,
|
| 411 |
+
"step": 640
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.44,
|
| 415 |
+
"learning_rate": 1.0306406685236769e-05,
|
| 416 |
+
"loss": 0.7125,
|
| 417 |
+
"step": 650
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.48,
|
| 421 |
+
"learning_rate": 9.610027855153205e-06,
|
| 422 |
+
"loss": 0.7176,
|
| 423 |
+
"step": 660
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.51,
|
| 427 |
+
"learning_rate": 8.913649025069639e-06,
|
| 428 |
+
"loss": 0.7669,
|
| 429 |
+
"step": 670
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.55,
|
| 433 |
+
"learning_rate": 8.217270194986073e-06,
|
| 434 |
+
"loss": 0.7372,
|
| 435 |
+
"step": 680
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.59,
|
| 439 |
+
"learning_rate": 7.5208913649025075e-06,
|
| 440 |
+
"loss": 0.7574,
|
| 441 |
+
"step": 690
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.63,
|
| 445 |
+
"learning_rate": 6.8245125348189415e-06,
|
| 446 |
+
"loss": 0.7493,
|
| 447 |
+
"step": 700
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.66,
|
| 451 |
+
"learning_rate": 6.128133704735376e-06,
|
| 452 |
+
"loss": 0.7554,
|
| 453 |
+
"step": 710
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.7,
|
| 457 |
+
"learning_rate": 5.43175487465181e-06,
|
| 458 |
+
"loss": 0.7465,
|
| 459 |
+
"step": 720
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.74,
|
| 463 |
+
"learning_rate": 4.735376044568245e-06,
|
| 464 |
+
"loss": 0.7608,
|
| 465 |
+
"step": 730
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.78,
|
| 469 |
+
"learning_rate": 4.03899721448468e-06,
|
| 470 |
+
"loss": 0.7534,
|
| 471 |
+
"step": 740
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.81,
|
| 475 |
+
"learning_rate": 3.3426183844011147e-06,
|
| 476 |
+
"loss": 0.7744,
|
| 477 |
+
"step": 750
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.85,
|
| 481 |
+
"learning_rate": 2.6462395543175487e-06,
|
| 482 |
+
"loss": 0.7158,
|
| 483 |
+
"step": 760
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.89,
|
| 487 |
+
"learning_rate": 1.9498607242339835e-06,
|
| 488 |
+
"loss": 0.7324,
|
| 489 |
+
"step": 770
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.93,
|
| 493 |
+
"learning_rate": 1.253481894150418e-06,
|
| 494 |
+
"loss": 0.749,
|
| 495 |
+
"step": 780
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.96,
|
| 499 |
+
"learning_rate": 5.571030640668524e-07,
|
| 500 |
+
"loss": 0.771,
|
| 501 |
+
"step": 790
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.99,
|
| 505 |
+
"eval_accuracy": 0.834983498349835,
|
| 506 |
+
"eval_loss": 0.6656444668769836,
|
| 507 |
+
"eval_runtime": 66.6691,
|
| 508 |
+
"eval_samples_per_second": 113.621,
|
| 509 |
+
"eval_steps_per_second": 1.785,
|
| 510 |
+
"step": 798
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.99,
|
| 514 |
+
"step": 798,
|
| 515 |
+
"total_flos": 1.5837129276562944e+19,
|
| 516 |
+
"train_loss": 1.3612600884640724,
|
| 517 |
+
"train_runtime": 3195.3608,
|
| 518 |
+
"train_samples_per_second": 64.007,
|
| 519 |
+
"train_steps_per_second": 0.25
|
| 520 |
+
}
|
| 521 |
+
],
|
| 522 |
+
"logging_steps": 10,
|
| 523 |
+
"max_steps": 798,
|
| 524 |
+
"num_train_epochs": 3,
|
| 525 |
+
"save_steps": 500,
|
| 526 |
+
"total_flos": 1.5837129276562944e+19,
|
| 527 |
+
"trial_name": null,
|
| 528 |
+
"trial_params": null
|
| 529 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4219
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b3c8be2aece4584dcae756d5668072069892f81dd337b0940badf2afc2a4164
|
| 3 |
size 4219
|