Training in progress, epoch 1
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +3 -0
- run-03pb2rjn/checkpoint-1232/model.safetensors +3 -0
- run-03pb2rjn/checkpoint-1232/optimizer.pt +3 -0
- run-03pb2rjn/checkpoint-1232/rng_state.pth +3 -0
- run-03pb2rjn/checkpoint-1232/scheduler.pt +3 -0
- run-03pb2rjn/checkpoint-1232/trainer_state.json +570 -0
- run-03pb2rjn/checkpoint-1232/training_args.bin +3 -0
- run-03pb2rjn/checkpoint-1260/model.safetensors +3 -0
- run-03pb2rjn/checkpoint-1260/optimizer.pt +3 -0
- run-03pb2rjn/checkpoint-1260/rng_state.pth +3 -0
- run-03pb2rjn/checkpoint-1260/scheduler.pt +3 -0
- run-03pb2rjn/checkpoint-1260/trainer_state.json +585 -0
- run-03pb2rjn/checkpoint-1260/training_args.bin +3 -0
- run-0t23cnxu/checkpoint-1232/model.safetensors +3 -0
- run-0t23cnxu/checkpoint-1232/optimizer.pt +3 -0
- run-0t23cnxu/checkpoint-1232/rng_state.pth +3 -0
- run-0t23cnxu/checkpoint-1232/scheduler.pt +3 -0
- run-0t23cnxu/checkpoint-1232/trainer_state.json +570 -0
- run-0t23cnxu/checkpoint-1232/training_args.bin +3 -0
- run-0t23cnxu/checkpoint-1260/model.safetensors +3 -0
- run-0t23cnxu/checkpoint-1260/optimizer.pt +3 -0
- run-0t23cnxu/checkpoint-1260/rng_state.pth +3 -0
- run-0t23cnxu/checkpoint-1260/scheduler.pt +3 -0
- run-0t23cnxu/checkpoint-1260/trainer_state.json +585 -0
- run-0t23cnxu/checkpoint-1260/training_args.bin +3 -0
- run-22pm9fz7/checkpoint-573/model.safetensors +3 -0
- run-22pm9fz7/checkpoint-573/optimizer.pt +3 -0
- run-22pm9fz7/checkpoint-573/rng_state.pth +3 -0
- run-22pm9fz7/checkpoint-573/scheduler.pt +3 -0
- run-22pm9fz7/checkpoint-573/trainer_state.json +616 -0
- run-22pm9fz7/checkpoint-573/training_args.bin +3 -0
- run-22pm9fz7/checkpoint-630/model.safetensors +3 -0
- run-22pm9fz7/checkpoint-630/optimizer.pt +3 -0
- run-22pm9fz7/checkpoint-630/rng_state.pth +3 -0
- run-22pm9fz7/checkpoint-630/scheduler.pt +3 -0
- run-22pm9fz7/checkpoint-630/trainer_state.json +676 -0
- run-22pm9fz7/checkpoint-630/training_args.bin +3 -0
- run-2787ye3h/checkpoint-1147/model.safetensors +3 -0
- run-2787ye3h/checkpoint-1147/optimizer.pt +3 -0
- run-2787ye3h/checkpoint-1147/rng_state.pth +3 -0
- run-2787ye3h/checkpoint-1147/scheduler.pt +3 -0
- run-2787ye3h/checkpoint-1147/trainer_state.json +534 -0
- run-2787ye3h/checkpoint-1147/training_args.bin +3 -0
- run-2787ye3h/checkpoint-1260/model.safetensors +3 -0
- run-2787ye3h/checkpoint-1260/optimizer.pt +3 -0
- run-2787ye3h/checkpoint-1260/rng_state.pth +3 -0
- run-2787ye3h/checkpoint-1260/scheduler.pt +3 -0
- run-2787ye3h/checkpoint-1260/trainer_state.json +585 -0
- run-2787ye3h/checkpoint-1260/training_args.bin +3 -0
- run-29h0ichm/checkpoint-1232/model.safetensors +3 -0
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d215462475f1d6bb29bf799908c221488163d6e780abe79a796b6fe2a71204c1
|
| 3 |
+
size 198025308
|
run-03pb2rjn/checkpoint-1232/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f88c4f450ef9f901b2ae4e10c2ebc62aaf0dbb6185e442cae281cead39dd1d
|
| 3 |
+
size 198025308
|
run-03pb2rjn/checkpoint-1232/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a2e770e79b07ea6a2763c0e1cc59c9cbd10a9ef34a9fda0e81b4710cc11e3a9
|
| 3 |
+
size 395900602
|
run-03pb2rjn/checkpoint-1232/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f20bd04985262159c8b072ab8016da869887f7af6ed0ffdedf1ca7c0cfc70216
|
| 3 |
+
size 14244
|
run-03pb2rjn/checkpoint-1232/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd700e1f1768b528d6a892cabb64f554f81bf377c5a1b46a76a44fcce36cbc1b
|
| 3 |
+
size 1064
|
run-03pb2rjn/checkpoint-1232/trainer_state.json
ADDED
|
@@ -0,0 +1,570 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.914079822616408,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-03pb2rjn/checkpoint-85",
|
| 4 |
+
"epoch": 28.988235294117647,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1232,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 5.406622924584476e-05,
|
| 14 |
+
"loss": 1.2456,
|
| 15 |
+
"step": 26
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8852549889135255,
|
| 20 |
+
"eval_loss": 0.908083438873291,
|
| 21 |
+
"eval_runtime": 7.1904,
|
| 22 |
+
"eval_samples_per_second": 501.78,
|
| 23 |
+
"eval_steps_per_second": 7.927,
|
| 24 |
+
"step": 42
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.22,
|
| 28 |
+
"learning_rate": 0.00010813245849168952,
|
| 29 |
+
"loss": 0.8815,
|
| 30 |
+
"step": 52
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.84,
|
| 34 |
+
"learning_rate": 0.00016219868773753427,
|
| 35 |
+
"loss": 0.8142,
|
| 36 |
+
"step": 78
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.914079822616408,
|
| 41 |
+
"eval_loss": 0.8091986775398254,
|
| 42 |
+
"eval_runtime": 6.629,
|
| 43 |
+
"eval_samples_per_second": 544.278,
|
| 44 |
+
"eval_steps_per_second": 8.599,
|
| 45 |
+
"step": 85
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.45,
|
| 49 |
+
"learning_rate": 0.00021626491698337904,
|
| 50 |
+
"loss": 0.8038,
|
| 51 |
+
"step": 104
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.99,
|
| 55 |
+
"eval_accuracy": 0.9079822616407982,
|
| 56 |
+
"eval_loss": 0.8263628482818604,
|
| 57 |
+
"eval_runtime": 7.0923,
|
| 58 |
+
"eval_samples_per_second": 508.721,
|
| 59 |
+
"eval_steps_per_second": 8.037,
|
| 60 |
+
"step": 127
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.06,
|
| 64 |
+
"learning_rate": 0.0002703311462292238,
|
| 65 |
+
"loss": 0.7993,
|
| 66 |
+
"step": 130
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.67,
|
| 70 |
+
"learning_rate": 0.00032439737547506855,
|
| 71 |
+
"loss": 0.7892,
|
| 72 |
+
"step": 156
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.7962860310421286,
|
| 77 |
+
"eval_loss": 1.0035172700881958,
|
| 78 |
+
"eval_runtime": 6.9076,
|
| 79 |
+
"eval_samples_per_second": 522.32,
|
| 80 |
+
"eval_steps_per_second": 8.252,
|
| 81 |
+
"step": 170
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.28,
|
| 85 |
+
"learning_rate": 0.0003784636047209133,
|
| 86 |
+
"loss": 0.7847,
|
| 87 |
+
"step": 182
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.89,
|
| 91 |
+
"learning_rate": 0.0004325298339667581,
|
| 92 |
+
"loss": 0.7907,
|
| 93 |
+
"step": 208
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.99,
|
| 97 |
+
"eval_accuracy": 0.9004988913525499,
|
| 98 |
+
"eval_loss": 0.8406698107719421,
|
| 99 |
+
"eval_runtime": 6.9242,
|
| 100 |
+
"eval_samples_per_second": 521.074,
|
| 101 |
+
"eval_steps_per_second": 8.232,
|
| 102 |
+
"step": 212
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.51,
|
| 106 |
+
"learning_rate": 0.00048659606321260285,
|
| 107 |
+
"loss": 0.788,
|
| 108 |
+
"step": 234
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.8902439024390244,
|
| 113 |
+
"eval_loss": 0.8500009179115295,
|
| 114 |
+
"eval_runtime": 6.5523,
|
| 115 |
+
"eval_samples_per_second": 550.643,
|
| 116 |
+
"eval_steps_per_second": 8.699,
|
| 117 |
+
"step": 255
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.12,
|
| 121 |
+
"learning_rate": 0.0005406622924584476,
|
| 122 |
+
"loss": 0.7905,
|
| 123 |
+
"step": 260
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.73,
|
| 127 |
+
"learning_rate": 0.0005947285217042924,
|
| 128 |
+
"loss": 0.7903,
|
| 129 |
+
"step": 286
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.99,
|
| 133 |
+
"eval_accuracy": 0.8722283813747228,
|
| 134 |
+
"eval_loss": 0.8836174607276917,
|
| 135 |
+
"eval_runtime": 6.8478,
|
| 136 |
+
"eval_samples_per_second": 526.885,
|
| 137 |
+
"eval_steps_per_second": 8.324,
|
| 138 |
+
"step": 297
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 7.34,
|
| 142 |
+
"learning_rate": 0.0006487947509501371,
|
| 143 |
+
"loss": 0.8044,
|
| 144 |
+
"step": 312
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.95,
|
| 148 |
+
"learning_rate": 0.0007028609801959819,
|
| 149 |
+
"loss": 0.8005,
|
| 150 |
+
"step": 338
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.8386917960088692,
|
| 155 |
+
"eval_loss": 0.9253634214401245,
|
| 156 |
+
"eval_runtime": 6.6711,
|
| 157 |
+
"eval_samples_per_second": 540.836,
|
| 158 |
+
"eval_steps_per_second": 8.544,
|
| 159 |
+
"step": 340
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.56,
|
| 163 |
+
"learning_rate": 0.0007569272094418266,
|
| 164 |
+
"loss": 0.8074,
|
| 165 |
+
"step": 364
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.99,
|
| 169 |
+
"eval_accuracy": 0.8539356984478935,
|
| 170 |
+
"eval_loss": 0.9217946529388428,
|
| 171 |
+
"eval_runtime": 6.8305,
|
| 172 |
+
"eval_samples_per_second": 528.221,
|
| 173 |
+
"eval_steps_per_second": 8.345,
|
| 174 |
+
"step": 382
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.18,
|
| 178 |
+
"learning_rate": 0.0008109934386876715,
|
| 179 |
+
"loss": 0.8214,
|
| 180 |
+
"step": 390
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.79,
|
| 184 |
+
"learning_rate": 0.0008650596679335162,
|
| 185 |
+
"loss": 0.8211,
|
| 186 |
+
"step": 416
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_accuracy": 0.8373059866962306,
|
| 191 |
+
"eval_loss": 1.0037873983383179,
|
| 192 |
+
"eval_runtime": 6.9272,
|
| 193 |
+
"eval_samples_per_second": 520.846,
|
| 194 |
+
"eval_steps_per_second": 8.228,
|
| 195 |
+
"step": 425
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.4,
|
| 199 |
+
"learning_rate": 0.000871900198866313,
|
| 200 |
+
"loss": 0.8096,
|
| 201 |
+
"step": 442
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.99,
|
| 205 |
+
"eval_accuracy": 0.873059866962306,
|
| 206 |
+
"eval_loss": 0.8749555945396423,
|
| 207 |
+
"eval_runtime": 6.9276,
|
| 208 |
+
"eval_samples_per_second": 520.816,
|
| 209 |
+
"eval_steps_per_second": 8.228,
|
| 210 |
+
"step": 467
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.01,
|
| 214 |
+
"learning_rate": 0.0008663597810925184,
|
| 215 |
+
"loss": 0.8142,
|
| 216 |
+
"step": 468
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.62,
|
| 220 |
+
"learning_rate": 0.0008567597779112751,
|
| 221 |
+
"loss": 0.8129,
|
| 222 |
+
"step": 494
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_accuracy": 0.8395232815964523,
|
| 227 |
+
"eval_loss": 0.9741567373275757,
|
| 228 |
+
"eval_runtime": 6.6401,
|
| 229 |
+
"eval_samples_per_second": 543.364,
|
| 230 |
+
"eval_steps_per_second": 8.584,
|
| 231 |
+
"step": 510
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.24,
|
| 235 |
+
"learning_rate": 0.0008431908913533095,
|
| 236 |
+
"loss": 0.8176,
|
| 237 |
+
"step": 520
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.85,
|
| 241 |
+
"learning_rate": 0.0008257813219558784,
|
| 242 |
+
"loss": 0.812,
|
| 243 |
+
"step": 546
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.99,
|
| 247 |
+
"eval_accuracy": 0.871119733924612,
|
| 248 |
+
"eval_loss": 0.8878970742225647,
|
| 249 |
+
"eval_runtime": 6.8805,
|
| 250 |
+
"eval_samples_per_second": 524.377,
|
| 251 |
+
"eval_steps_per_second": 8.284,
|
| 252 |
+
"step": 552
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.46,
|
| 256 |
+
"learning_rate": 0.0008046955575080593,
|
| 257 |
+
"loss": 0.7965,
|
| 258 |
+
"step": 572
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 14.0,
|
| 262 |
+
"eval_accuracy": 0.8503325942350333,
|
| 263 |
+
"eval_loss": 0.9190165400505066,
|
| 264 |
+
"eval_runtime": 7.1454,
|
| 265 |
+
"eval_samples_per_second": 504.939,
|
| 266 |
+
"eval_steps_per_second": 7.977,
|
| 267 |
+
"step": 595
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 14.07,
|
| 271 |
+
"learning_rate": 0.0007801328189495462,
|
| 272 |
+
"loss": 0.8128,
|
| 273 |
+
"step": 598
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 14.68,
|
| 277 |
+
"learning_rate": 0.0007523251781062956,
|
| 278 |
+
"loss": 0.7996,
|
| 279 |
+
"step": 624
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.99,
|
| 283 |
+
"eval_accuracy": 0.8924611973392461,
|
| 284 |
+
"eval_loss": 0.8424035906791687,
|
| 285 |
+
"eval_runtime": 6.9445,
|
| 286 |
+
"eval_samples_per_second": 519.551,
|
| 287 |
+
"eval_steps_per_second": 8.208,
|
| 288 |
+
"step": 637
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 15.29,
|
| 292 |
+
"learning_rate": 0.0007215353650468892,
|
| 293 |
+
"loss": 0.7975,
|
| 294 |
+
"step": 650
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.91,
|
| 298 |
+
"learning_rate": 0.0006880542857759862,
|
| 299 |
+
"loss": 0.7944,
|
| 300 |
+
"step": 676
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.0,
|
| 304 |
+
"eval_accuracy": 0.8744456762749445,
|
| 305 |
+
"eval_loss": 0.8793225288391113,
|
| 306 |
+
"eval_runtime": 6.6692,
|
| 307 |
+
"eval_samples_per_second": 540.99,
|
| 308 |
+
"eval_steps_per_second": 8.547,
|
| 309 |
+
"step": 680
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.52,
|
| 313 |
+
"learning_rate": 0.0006521982737180083,
|
| 314 |
+
"loss": 0.787,
|
| 315 |
+
"step": 702
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 16.99,
|
| 319 |
+
"eval_accuracy": 0.8824833702882483,
|
| 320 |
+
"eval_loss": 0.8486706614494324,
|
| 321 |
+
"eval_runtime": 6.908,
|
| 322 |
+
"eval_samples_per_second": 522.295,
|
| 323 |
+
"eval_steps_per_second": 8.251,
|
| 324 |
+
"step": 722
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.13,
|
| 328 |
+
"learning_rate": 0.0006143061009593818,
|
| 329 |
+
"loss": 0.7792,
|
| 330 |
+
"step": 728
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.74,
|
| 334 |
+
"learning_rate": 0.0005747357774874944,
|
| 335 |
+
"loss": 0.7753,
|
| 336 |
+
"step": 754
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 18.0,
|
| 340 |
+
"eval_accuracy": 0.8869179600886918,
|
| 341 |
+
"eval_loss": 0.8535000085830688,
|
| 342 |
+
"eval_runtime": 6.9297,
|
| 343 |
+
"eval_samples_per_second": 520.654,
|
| 344 |
+
"eval_steps_per_second": 8.225,
|
| 345 |
+
"step": 765
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 18.35,
|
| 349 |
+
"learning_rate": 0.0005338611686675588,
|
| 350 |
+
"loss": 0.7639,
|
| 351 |
+
"step": 780
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 18.96,
|
| 355 |
+
"learning_rate": 0.0004920684629158832,
|
| 356 |
+
"loss": 0.7647,
|
| 357 |
+
"step": 806
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.99,
|
| 361 |
+
"eval_accuracy": 0.9018847006651884,
|
| 362 |
+
"eval_loss": 0.8282992839813232,
|
| 363 |
+
"eval_runtime": 6.784,
|
| 364 |
+
"eval_samples_per_second": 531.841,
|
| 365 |
+
"eval_steps_per_second": 8.402,
|
| 366 |
+
"step": 807
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 19.58,
|
| 370 |
+
"learning_rate": 0.00044975252294341203,
|
| 371 |
+
"loss": 0.7658,
|
| 372 |
+
"step": 832
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.0,
|
| 376 |
+
"eval_accuracy": 0.8891352549889135,
|
| 377 |
+
"eval_loss": 0.8540334105491638,
|
| 378 |
+
"eval_runtime": 6.87,
|
| 379 |
+
"eval_samples_per_second": 525.183,
|
| 380 |
+
"eval_steps_per_second": 8.297,
|
| 381 |
+
"step": 850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 20.19,
|
| 385 |
+
"learning_rate": 0.00040731315504344935,
|
| 386 |
+
"loss": 0.7538,
|
| 387 |
+
"step": 858
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 20.8,
|
| 391 |
+
"learning_rate": 0.00036515133167179504,
|
| 392 |
+
"loss": 0.7442,
|
| 393 |
+
"step": 884
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.99,
|
| 397 |
+
"eval_accuracy": 0.8938470066518847,
|
| 398 |
+
"eval_loss": 0.8362773060798645,
|
| 399 |
+
"eval_runtime": 7.0082,
|
| 400 |
+
"eval_samples_per_second": 514.823,
|
| 401 |
+
"eval_steps_per_second": 8.133,
|
| 402 |
+
"step": 892
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 21.41,
|
| 406 |
+
"learning_rate": 0.000323665403008833,
|
| 407 |
+
"loss": 0.7353,
|
| 408 |
+
"step": 910
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 22.0,
|
| 412 |
+
"eval_accuracy": 0.9016075388026608,
|
| 413 |
+
"eval_loss": 0.8352402448654175,
|
| 414 |
+
"eval_runtime": 6.9197,
|
| 415 |
+
"eval_samples_per_second": 521.408,
|
| 416 |
+
"eval_steps_per_second": 8.237,
|
| 417 |
+
"step": 935
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 22.02,
|
| 421 |
+
"learning_rate": 0.0002832473332972056,
|
| 422 |
+
"loss": 0.7395,
|
| 423 |
+
"step": 936
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.64,
|
| 427 |
+
"learning_rate": 0.000244278997514626,
|
| 428 |
+
"loss": 0.7326,
|
| 429 |
+
"step": 962
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.99,
|
| 433 |
+
"eval_accuracy": 0.9057649667405765,
|
| 434 |
+
"eval_loss": 0.8239282965660095,
|
| 435 |
+
"eval_runtime": 6.561,
|
| 436 |
+
"eval_samples_per_second": 549.915,
|
| 437 |
+
"eval_steps_per_second": 8.688,
|
| 438 |
+
"step": 977
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 23.25,
|
| 442 |
+
"learning_rate": 0.0002071285733713279,
|
| 443 |
+
"loss": 0.7338,
|
| 444 |
+
"step": 988
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.86,
|
| 448 |
+
"learning_rate": 0.0001721470627210114,
|
| 449 |
+
"loss": 0.7224,
|
| 450 |
+
"step": 1014
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 24.0,
|
| 454 |
+
"eval_accuracy": 0.906319290465632,
|
| 455 |
+
"eval_loss": 0.8245892524719238,
|
| 456 |
+
"eval_runtime": 6.5794,
|
| 457 |
+
"eval_samples_per_second": 548.381,
|
| 458 |
+
"eval_steps_per_second": 8.663,
|
| 459 |
+
"step": 1020
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 24.47,
|
| 463 |
+
"learning_rate": 0.00013966497525142913,
|
| 464 |
+
"loss": 0.7165,
|
| 465 |
+
"step": 1040
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 24.99,
|
| 469 |
+
"eval_accuracy": 0.9121396895787139,
|
| 470 |
+
"eval_loss": 0.8174624443054199,
|
| 471 |
+
"eval_runtime": 6.9114,
|
| 472 |
+
"eval_samples_per_second": 522.036,
|
| 473 |
+
"eval_steps_per_second": 8.247,
|
| 474 |
+
"step": 1062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 25.08,
|
| 478 |
+
"learning_rate": 0.00010998920578752054,
|
| 479 |
+
"loss": 0.717,
|
| 480 |
+
"step": 1066
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 25.69,
|
| 484 |
+
"learning_rate": 8.340013471072141e-05,
|
| 485 |
+
"loss": 0.711,
|
| 486 |
+
"step": 1092
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 26.0,
|
| 490 |
+
"eval_accuracy": 0.9121396895787139,
|
| 491 |
+
"eval_loss": 0.8170289397239685,
|
| 492 |
+
"eval_runtime": 6.8654,
|
| 493 |
+
"eval_samples_per_second": 525.535,
|
| 494 |
+
"eval_steps_per_second": 8.303,
|
| 495 |
+
"step": 1105
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 26.31,
|
| 499 |
+
"learning_rate": 6.014897889005363e-05,
|
| 500 |
+
"loss": 0.7115,
|
| 501 |
+
"step": 1118
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.92,
|
| 505 |
+
"learning_rate": 4.0455418153727286e-05,
|
| 506 |
+
"loss": 0.7106,
|
| 507 |
+
"step": 1144
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 26.99,
|
| 511 |
+
"eval_accuracy": 0.914079822616408,
|
| 512 |
+
"eval_loss": 0.8164230585098267,
|
| 513 |
+
"eval_runtime": 6.9054,
|
| 514 |
+
"eval_samples_per_second": 522.493,
|
| 515 |
+
"eval_steps_per_second": 8.254,
|
| 516 |
+
"step": 1147
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 27.53,
|
| 520 |
+
"learning_rate": 2.450551972664773e-05,
|
| 521 |
+
"loss": 0.707,
|
| 522 |
+
"step": 1170
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 28.0,
|
| 526 |
+
"eval_accuracy": 0.9088137472283814,
|
| 527 |
+
"eval_loss": 0.8162174820899963,
|
| 528 |
+
"eval_runtime": 7.0016,
|
| 529 |
+
"eval_samples_per_second": 515.309,
|
| 530 |
+
"eval_steps_per_second": 8.141,
|
| 531 |
+
"step": 1190
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 28.14,
|
| 535 |
+
"learning_rate": 1.244998024400373e-05,
|
| 536 |
+
"loss": 0.7017,
|
| 537 |
+
"step": 1196
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 28.75,
|
| 541 |
+
"learning_rate": 4.402701950610671e-06,
|
| 542 |
+
"loss": 0.702,
|
| 543 |
+
"step": 1222
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 28.99,
|
| 547 |
+
"eval_accuracy": 0.9101995565410199,
|
| 548 |
+
"eval_loss": 0.8174305558204651,
|
| 549 |
+
"eval_runtime": 6.8715,
|
| 550 |
+
"eval_samples_per_second": 525.068,
|
| 551 |
+
"eval_steps_per_second": 8.295,
|
| 552 |
+
"step": 1232
|
| 553 |
+
}
|
| 554 |
+
],
|
| 555 |
+
"logging_steps": 26,
|
| 556 |
+
"max_steps": 1260,
|
| 557 |
+
"num_input_tokens_seen": 0,
|
| 558 |
+
"num_train_epochs": 30,
|
| 559 |
+
"save_steps": 500,
|
| 560 |
+
"total_flos": 0.0,
|
| 561 |
+
"train_batch_size": 64,
|
| 562 |
+
"trial_name": null,
|
| 563 |
+
"trial_params": {
|
| 564 |
+
"_wandb": {},
|
| 565 |
+
"assignments": {},
|
| 566 |
+
"learning_rate": 0.0008733775493559538,
|
| 567 |
+
"metric": "eval/loss",
|
| 568 |
+
"warmup_ratio": 0.3328703828976002
|
| 569 |
+
}
|
| 570 |
+
}
|
run-03pb2rjn/checkpoint-1232/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f790c3845918a315719ceecd0fdbf0a1a8fa12de0e64e0248d8e4265fdc5885b
|
| 3 |
+
size 4792
|
run-03pb2rjn/checkpoint-1260/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63841cb5aa23b01cf9dcd0d15d516e306e5f6febf74149cbf42f645b0c1cea2f
|
| 3 |
+
size 198025308
|
run-03pb2rjn/checkpoint-1260/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf803b29ab9913e181120e8ca5362cc4dbdd991984a7c240b70775709d6c3caf
|
| 3 |
+
size 395900602
|
run-03pb2rjn/checkpoint-1260/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deeb0d472f47497c93334cb3948d4032ad244442808af19b401a7a0fea1fe65c
|
| 3 |
+
size 14244
|
run-03pb2rjn/checkpoint-1260/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c257389676b3d8a7311d027a866546762fd2586818c6cf9d6c0acb1686182b64
|
| 3 |
+
size 1064
|
run-03pb2rjn/checkpoint-1260/trainer_state.json
ADDED
|
@@ -0,0 +1,585 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9154656319290465,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-03pb2rjn/checkpoint-1260",
|
| 4 |
+
"epoch": 29.647058823529413,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1260,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 5.406622924584476e-05,
|
| 14 |
+
"loss": 1.2456,
|
| 15 |
+
"step": 26
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8852549889135255,
|
| 20 |
+
"eval_loss": 0.908083438873291,
|
| 21 |
+
"eval_runtime": 7.1904,
|
| 22 |
+
"eval_samples_per_second": 501.78,
|
| 23 |
+
"eval_steps_per_second": 7.927,
|
| 24 |
+
"step": 42
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.22,
|
| 28 |
+
"learning_rate": 0.00010813245849168952,
|
| 29 |
+
"loss": 0.8815,
|
| 30 |
+
"step": 52
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.84,
|
| 34 |
+
"learning_rate": 0.00016219868773753427,
|
| 35 |
+
"loss": 0.8142,
|
| 36 |
+
"step": 78
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.914079822616408,
|
| 41 |
+
"eval_loss": 0.8091986775398254,
|
| 42 |
+
"eval_runtime": 6.629,
|
| 43 |
+
"eval_samples_per_second": 544.278,
|
| 44 |
+
"eval_steps_per_second": 8.599,
|
| 45 |
+
"step": 85
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.45,
|
| 49 |
+
"learning_rate": 0.00021626491698337904,
|
| 50 |
+
"loss": 0.8038,
|
| 51 |
+
"step": 104
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.99,
|
| 55 |
+
"eval_accuracy": 0.9079822616407982,
|
| 56 |
+
"eval_loss": 0.8263628482818604,
|
| 57 |
+
"eval_runtime": 7.0923,
|
| 58 |
+
"eval_samples_per_second": 508.721,
|
| 59 |
+
"eval_steps_per_second": 8.037,
|
| 60 |
+
"step": 127
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.06,
|
| 64 |
+
"learning_rate": 0.0002703311462292238,
|
| 65 |
+
"loss": 0.7993,
|
| 66 |
+
"step": 130
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.67,
|
| 70 |
+
"learning_rate": 0.00032439737547506855,
|
| 71 |
+
"loss": 0.7892,
|
| 72 |
+
"step": 156
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.7962860310421286,
|
| 77 |
+
"eval_loss": 1.0035172700881958,
|
| 78 |
+
"eval_runtime": 6.9076,
|
| 79 |
+
"eval_samples_per_second": 522.32,
|
| 80 |
+
"eval_steps_per_second": 8.252,
|
| 81 |
+
"step": 170
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.28,
|
| 85 |
+
"learning_rate": 0.0003784636047209133,
|
| 86 |
+
"loss": 0.7847,
|
| 87 |
+
"step": 182
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.89,
|
| 91 |
+
"learning_rate": 0.0004325298339667581,
|
| 92 |
+
"loss": 0.7907,
|
| 93 |
+
"step": 208
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.99,
|
| 97 |
+
"eval_accuracy": 0.9004988913525499,
|
| 98 |
+
"eval_loss": 0.8406698107719421,
|
| 99 |
+
"eval_runtime": 6.9242,
|
| 100 |
+
"eval_samples_per_second": 521.074,
|
| 101 |
+
"eval_steps_per_second": 8.232,
|
| 102 |
+
"step": 212
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.51,
|
| 106 |
+
"learning_rate": 0.00048659606321260285,
|
| 107 |
+
"loss": 0.788,
|
| 108 |
+
"step": 234
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.8902439024390244,
|
| 113 |
+
"eval_loss": 0.8500009179115295,
|
| 114 |
+
"eval_runtime": 6.5523,
|
| 115 |
+
"eval_samples_per_second": 550.643,
|
| 116 |
+
"eval_steps_per_second": 8.699,
|
| 117 |
+
"step": 255
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.12,
|
| 121 |
+
"learning_rate": 0.0005406622924584476,
|
| 122 |
+
"loss": 0.7905,
|
| 123 |
+
"step": 260
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.73,
|
| 127 |
+
"learning_rate": 0.0005947285217042924,
|
| 128 |
+
"loss": 0.7903,
|
| 129 |
+
"step": 286
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.99,
|
| 133 |
+
"eval_accuracy": 0.8722283813747228,
|
| 134 |
+
"eval_loss": 0.8836174607276917,
|
| 135 |
+
"eval_runtime": 6.8478,
|
| 136 |
+
"eval_samples_per_second": 526.885,
|
| 137 |
+
"eval_steps_per_second": 8.324,
|
| 138 |
+
"step": 297
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 7.34,
|
| 142 |
+
"learning_rate": 0.0006487947509501371,
|
| 143 |
+
"loss": 0.8044,
|
| 144 |
+
"step": 312
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.95,
|
| 148 |
+
"learning_rate": 0.0007028609801959819,
|
| 149 |
+
"loss": 0.8005,
|
| 150 |
+
"step": 338
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.8386917960088692,
|
| 155 |
+
"eval_loss": 0.9253634214401245,
|
| 156 |
+
"eval_runtime": 6.6711,
|
| 157 |
+
"eval_samples_per_second": 540.836,
|
| 158 |
+
"eval_steps_per_second": 8.544,
|
| 159 |
+
"step": 340
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.56,
|
| 163 |
+
"learning_rate": 0.0007569272094418266,
|
| 164 |
+
"loss": 0.8074,
|
| 165 |
+
"step": 364
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.99,
|
| 169 |
+
"eval_accuracy": 0.8539356984478935,
|
| 170 |
+
"eval_loss": 0.9217946529388428,
|
| 171 |
+
"eval_runtime": 6.8305,
|
| 172 |
+
"eval_samples_per_second": 528.221,
|
| 173 |
+
"eval_steps_per_second": 8.345,
|
| 174 |
+
"step": 382
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.18,
|
| 178 |
+
"learning_rate": 0.0008109934386876715,
|
| 179 |
+
"loss": 0.8214,
|
| 180 |
+
"step": 390
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.79,
|
| 184 |
+
"learning_rate": 0.0008650596679335162,
|
| 185 |
+
"loss": 0.8211,
|
| 186 |
+
"step": 416
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_accuracy": 0.8373059866962306,
|
| 191 |
+
"eval_loss": 1.0037873983383179,
|
| 192 |
+
"eval_runtime": 6.9272,
|
| 193 |
+
"eval_samples_per_second": 520.846,
|
| 194 |
+
"eval_steps_per_second": 8.228,
|
| 195 |
+
"step": 425
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.4,
|
| 199 |
+
"learning_rate": 0.000871900198866313,
|
| 200 |
+
"loss": 0.8096,
|
| 201 |
+
"step": 442
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.99,
|
| 205 |
+
"eval_accuracy": 0.873059866962306,
|
| 206 |
+
"eval_loss": 0.8749555945396423,
|
| 207 |
+
"eval_runtime": 6.9276,
|
| 208 |
+
"eval_samples_per_second": 520.816,
|
| 209 |
+
"eval_steps_per_second": 8.228,
|
| 210 |
+
"step": 467
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.01,
|
| 214 |
+
"learning_rate": 0.0008663597810925184,
|
| 215 |
+
"loss": 0.8142,
|
| 216 |
+
"step": 468
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.62,
|
| 220 |
+
"learning_rate": 0.0008567597779112751,
|
| 221 |
+
"loss": 0.8129,
|
| 222 |
+
"step": 494
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_accuracy": 0.8395232815964523,
|
| 227 |
+
"eval_loss": 0.9741567373275757,
|
| 228 |
+
"eval_runtime": 6.6401,
|
| 229 |
+
"eval_samples_per_second": 543.364,
|
| 230 |
+
"eval_steps_per_second": 8.584,
|
| 231 |
+
"step": 510
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.24,
|
| 235 |
+
"learning_rate": 0.0008431908913533095,
|
| 236 |
+
"loss": 0.8176,
|
| 237 |
+
"step": 520
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.85,
|
| 241 |
+
"learning_rate": 0.0008257813219558784,
|
| 242 |
+
"loss": 0.812,
|
| 243 |
+
"step": 546
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.99,
|
| 247 |
+
"eval_accuracy": 0.871119733924612,
|
| 248 |
+
"eval_loss": 0.8878970742225647,
|
| 249 |
+
"eval_runtime": 6.8805,
|
| 250 |
+
"eval_samples_per_second": 524.377,
|
| 251 |
+
"eval_steps_per_second": 8.284,
|
| 252 |
+
"step": 552
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.46,
|
| 256 |
+
"learning_rate": 0.0008046955575080593,
|
| 257 |
+
"loss": 0.7965,
|
| 258 |
+
"step": 572
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 14.0,
|
| 262 |
+
"eval_accuracy": 0.8503325942350333,
|
| 263 |
+
"eval_loss": 0.9190165400505066,
|
| 264 |
+
"eval_runtime": 7.1454,
|
| 265 |
+
"eval_samples_per_second": 504.939,
|
| 266 |
+
"eval_steps_per_second": 7.977,
|
| 267 |
+
"step": 595
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 14.07,
|
| 271 |
+
"learning_rate": 0.0007801328189495462,
|
| 272 |
+
"loss": 0.8128,
|
| 273 |
+
"step": 598
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 14.68,
|
| 277 |
+
"learning_rate": 0.0007523251781062956,
|
| 278 |
+
"loss": 0.7996,
|
| 279 |
+
"step": 624
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.99,
|
| 283 |
+
"eval_accuracy": 0.8924611973392461,
|
| 284 |
+
"eval_loss": 0.8424035906791687,
|
| 285 |
+
"eval_runtime": 6.9445,
|
| 286 |
+
"eval_samples_per_second": 519.551,
|
| 287 |
+
"eval_steps_per_second": 8.208,
|
| 288 |
+
"step": 637
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 15.29,
|
| 292 |
+
"learning_rate": 0.0007215353650468892,
|
| 293 |
+
"loss": 0.7975,
|
| 294 |
+
"step": 650
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.91,
|
| 298 |
+
"learning_rate": 0.0006880542857759862,
|
| 299 |
+
"loss": 0.7944,
|
| 300 |
+
"step": 676
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.0,
|
| 304 |
+
"eval_accuracy": 0.8744456762749445,
|
| 305 |
+
"eval_loss": 0.8793225288391113,
|
| 306 |
+
"eval_runtime": 6.6692,
|
| 307 |
+
"eval_samples_per_second": 540.99,
|
| 308 |
+
"eval_steps_per_second": 8.547,
|
| 309 |
+
"step": 680
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.52,
|
| 313 |
+
"learning_rate": 0.0006521982737180083,
|
| 314 |
+
"loss": 0.787,
|
| 315 |
+
"step": 702
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 16.99,
|
| 319 |
+
"eval_accuracy": 0.8824833702882483,
|
| 320 |
+
"eval_loss": 0.8486706614494324,
|
| 321 |
+
"eval_runtime": 6.908,
|
| 322 |
+
"eval_samples_per_second": 522.295,
|
| 323 |
+
"eval_steps_per_second": 8.251,
|
| 324 |
+
"step": 722
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.13,
|
| 328 |
+
"learning_rate": 0.0006143061009593818,
|
| 329 |
+
"loss": 0.7792,
|
| 330 |
+
"step": 728
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.74,
|
| 334 |
+
"learning_rate": 0.0005747357774874944,
|
| 335 |
+
"loss": 0.7753,
|
| 336 |
+
"step": 754
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 18.0,
|
| 340 |
+
"eval_accuracy": 0.8869179600886918,
|
| 341 |
+
"eval_loss": 0.8535000085830688,
|
| 342 |
+
"eval_runtime": 6.9297,
|
| 343 |
+
"eval_samples_per_second": 520.654,
|
| 344 |
+
"eval_steps_per_second": 8.225,
|
| 345 |
+
"step": 765
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 18.35,
|
| 349 |
+
"learning_rate": 0.0005338611686675588,
|
| 350 |
+
"loss": 0.7639,
|
| 351 |
+
"step": 780
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 18.96,
|
| 355 |
+
"learning_rate": 0.0004920684629158832,
|
| 356 |
+
"loss": 0.7647,
|
| 357 |
+
"step": 806
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.99,
|
| 361 |
+
"eval_accuracy": 0.9018847006651884,
|
| 362 |
+
"eval_loss": 0.8282992839813232,
|
| 363 |
+
"eval_runtime": 6.784,
|
| 364 |
+
"eval_samples_per_second": 531.841,
|
| 365 |
+
"eval_steps_per_second": 8.402,
|
| 366 |
+
"step": 807
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 19.58,
|
| 370 |
+
"learning_rate": 0.00044975252294341203,
|
| 371 |
+
"loss": 0.7658,
|
| 372 |
+
"step": 832
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.0,
|
| 376 |
+
"eval_accuracy": 0.8891352549889135,
|
| 377 |
+
"eval_loss": 0.8540334105491638,
|
| 378 |
+
"eval_runtime": 6.87,
|
| 379 |
+
"eval_samples_per_second": 525.183,
|
| 380 |
+
"eval_steps_per_second": 8.297,
|
| 381 |
+
"step": 850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 20.19,
|
| 385 |
+
"learning_rate": 0.00040731315504344935,
|
| 386 |
+
"loss": 0.7538,
|
| 387 |
+
"step": 858
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 20.8,
|
| 391 |
+
"learning_rate": 0.00036515133167179504,
|
| 392 |
+
"loss": 0.7442,
|
| 393 |
+
"step": 884
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.99,
|
| 397 |
+
"eval_accuracy": 0.8938470066518847,
|
| 398 |
+
"eval_loss": 0.8362773060798645,
|
| 399 |
+
"eval_runtime": 7.0082,
|
| 400 |
+
"eval_samples_per_second": 514.823,
|
| 401 |
+
"eval_steps_per_second": 8.133,
|
| 402 |
+
"step": 892
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 21.41,
|
| 406 |
+
"learning_rate": 0.000323665403008833,
|
| 407 |
+
"loss": 0.7353,
|
| 408 |
+
"step": 910
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 22.0,
|
| 412 |
+
"eval_accuracy": 0.9016075388026608,
|
| 413 |
+
"eval_loss": 0.8352402448654175,
|
| 414 |
+
"eval_runtime": 6.9197,
|
| 415 |
+
"eval_samples_per_second": 521.408,
|
| 416 |
+
"eval_steps_per_second": 8.237,
|
| 417 |
+
"step": 935
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 22.02,
|
| 421 |
+
"learning_rate": 0.0002832473332972056,
|
| 422 |
+
"loss": 0.7395,
|
| 423 |
+
"step": 936
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.64,
|
| 427 |
+
"learning_rate": 0.000244278997514626,
|
| 428 |
+
"loss": 0.7326,
|
| 429 |
+
"step": 962
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.99,
|
| 433 |
+
"eval_accuracy": 0.9057649667405765,
|
| 434 |
+
"eval_loss": 0.8239282965660095,
|
| 435 |
+
"eval_runtime": 6.561,
|
| 436 |
+
"eval_samples_per_second": 549.915,
|
| 437 |
+
"eval_steps_per_second": 8.688,
|
| 438 |
+
"step": 977
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 23.25,
|
| 442 |
+
"learning_rate": 0.0002071285733713279,
|
| 443 |
+
"loss": 0.7338,
|
| 444 |
+
"step": 988
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.86,
|
| 448 |
+
"learning_rate": 0.0001721470627210114,
|
| 449 |
+
"loss": 0.7224,
|
| 450 |
+
"step": 1014
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 24.0,
|
| 454 |
+
"eval_accuracy": 0.906319290465632,
|
| 455 |
+
"eval_loss": 0.8245892524719238,
|
| 456 |
+
"eval_runtime": 6.5794,
|
| 457 |
+
"eval_samples_per_second": 548.381,
|
| 458 |
+
"eval_steps_per_second": 8.663,
|
| 459 |
+
"step": 1020
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 24.47,
|
| 463 |
+
"learning_rate": 0.00013966497525142913,
|
| 464 |
+
"loss": 0.7165,
|
| 465 |
+
"step": 1040
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 24.99,
|
| 469 |
+
"eval_accuracy": 0.9121396895787139,
|
| 470 |
+
"eval_loss": 0.8174624443054199,
|
| 471 |
+
"eval_runtime": 6.9114,
|
| 472 |
+
"eval_samples_per_second": 522.036,
|
| 473 |
+
"eval_steps_per_second": 8.247,
|
| 474 |
+
"step": 1062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 25.08,
|
| 478 |
+
"learning_rate": 0.00010998920578752054,
|
| 479 |
+
"loss": 0.717,
|
| 480 |
+
"step": 1066
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 25.69,
|
| 484 |
+
"learning_rate": 8.340013471072141e-05,
|
| 485 |
+
"loss": 0.711,
|
| 486 |
+
"step": 1092
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 26.0,
|
| 490 |
+
"eval_accuracy": 0.9121396895787139,
|
| 491 |
+
"eval_loss": 0.8170289397239685,
|
| 492 |
+
"eval_runtime": 6.8654,
|
| 493 |
+
"eval_samples_per_second": 525.535,
|
| 494 |
+
"eval_steps_per_second": 8.303,
|
| 495 |
+
"step": 1105
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 26.31,
|
| 499 |
+
"learning_rate": 6.014897889005363e-05,
|
| 500 |
+
"loss": 0.7115,
|
| 501 |
+
"step": 1118
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.92,
|
| 505 |
+
"learning_rate": 4.0455418153727286e-05,
|
| 506 |
+
"loss": 0.7106,
|
| 507 |
+
"step": 1144
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 26.99,
|
| 511 |
+
"eval_accuracy": 0.914079822616408,
|
| 512 |
+
"eval_loss": 0.8164230585098267,
|
| 513 |
+
"eval_runtime": 6.9054,
|
| 514 |
+
"eval_samples_per_second": 522.493,
|
| 515 |
+
"eval_steps_per_second": 8.254,
|
| 516 |
+
"step": 1147
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 27.53,
|
| 520 |
+
"learning_rate": 2.450551972664773e-05,
|
| 521 |
+
"loss": 0.707,
|
| 522 |
+
"step": 1170
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 28.0,
|
| 526 |
+
"eval_accuracy": 0.9088137472283814,
|
| 527 |
+
"eval_loss": 0.8162174820899963,
|
| 528 |
+
"eval_runtime": 7.0016,
|
| 529 |
+
"eval_samples_per_second": 515.309,
|
| 530 |
+
"eval_steps_per_second": 8.141,
|
| 531 |
+
"step": 1190
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 28.14,
|
| 535 |
+
"learning_rate": 1.244998024400373e-05,
|
| 536 |
+
"loss": 0.7017,
|
| 537 |
+
"step": 1196
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 28.75,
|
| 541 |
+
"learning_rate": 4.402701950610671e-06,
|
| 542 |
+
"loss": 0.702,
|
| 543 |
+
"step": 1222
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 28.99,
|
| 547 |
+
"eval_accuracy": 0.9101995565410199,
|
| 548 |
+
"eval_loss": 0.8174305558204651,
|
| 549 |
+
"eval_runtime": 6.8715,
|
| 550 |
+
"eval_samples_per_second": 525.068,
|
| 551 |
+
"eval_steps_per_second": 8.295,
|
| 552 |
+
"step": 1232
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 29.36,
|
| 556 |
+
"learning_rate": 4.3971653825558924e-07,
|
| 557 |
+
"loss": 0.7063,
|
| 558 |
+
"step": 1248
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 29.65,
|
| 562 |
+
"eval_accuracy": 0.9154656319290465,
|
| 563 |
+
"eval_loss": 0.812396764755249,
|
| 564 |
+
"eval_runtime": 6.8762,
|
| 565 |
+
"eval_samples_per_second": 524.708,
|
| 566 |
+
"eval_steps_per_second": 8.289,
|
| 567 |
+
"step": 1260
|
| 568 |
+
}
|
| 569 |
+
],
|
| 570 |
+
"logging_steps": 26,
|
| 571 |
+
"max_steps": 1260,
|
| 572 |
+
"num_input_tokens_seen": 0,
|
| 573 |
+
"num_train_epochs": 30,
|
| 574 |
+
"save_steps": 500,
|
| 575 |
+
"total_flos": 0.0,
|
| 576 |
+
"train_batch_size": 64,
|
| 577 |
+
"trial_name": null,
|
| 578 |
+
"trial_params": {
|
| 579 |
+
"_wandb": {},
|
| 580 |
+
"assignments": {},
|
| 581 |
+
"learning_rate": 0.0008733775493559538,
|
| 582 |
+
"metric": "eval/loss",
|
| 583 |
+
"warmup_ratio": 0.3328703828976002
|
| 584 |
+
}
|
| 585 |
+
}
|
run-03pb2rjn/checkpoint-1260/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f790c3845918a315719ceecd0fdbf0a1a8fa12de0e64e0248d8e4265fdc5885b
|
| 3 |
+
size 4792
|
run-0t23cnxu/checkpoint-1232/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc2e91bb0a3075ace3f8c0aa7bd38cdf99697cdf1306b87b57d4d565906e666
|
| 3 |
+
size 198025308
|
run-0t23cnxu/checkpoint-1232/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:554e763483561667636a2ac9be6574b6f7dd46f43bb074ac465b3434553487a3
|
| 3 |
+
size 395900602
|
run-0t23cnxu/checkpoint-1232/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f20bd04985262159c8b072ab8016da869887f7af6ed0ffdedf1ca7c0cfc70216
|
| 3 |
+
size 14244
|
run-0t23cnxu/checkpoint-1232/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:417adabfc2f3fb03fb51355107a98ed1a08058242dea66c353b5cc45ab70ace4
|
| 3 |
+
size 1064
|
run-0t23cnxu/checkpoint-1232/trainer_state.json
ADDED
|
@@ -0,0 +1,570 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.916019955654102,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-0t23cnxu/checkpoint-1190",
|
| 4 |
+
"epoch": 28.988235294117647,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1232,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 6.592141778986334e-05,
|
| 14 |
+
"loss": 1.2233,
|
| 15 |
+
"step": 26
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8896895787139689,
|
| 20 |
+
"eval_loss": 0.89235520362854,
|
| 21 |
+
"eval_runtime": 6.9506,
|
| 22 |
+
"eval_samples_per_second": 519.09,
|
| 23 |
+
"eval_steps_per_second": 8.201,
|
| 24 |
+
"step": 42
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.22,
|
| 28 |
+
"learning_rate": 0.00013184283557972668,
|
| 29 |
+
"loss": 0.8733,
|
| 30 |
+
"step": 52
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.84,
|
| 34 |
+
"learning_rate": 0.00019776425336959002,
|
| 35 |
+
"loss": 0.8108,
|
| 36 |
+
"step": 78
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.905210643015521,
|
| 41 |
+
"eval_loss": 0.8281971216201782,
|
| 42 |
+
"eval_runtime": 7.0446,
|
| 43 |
+
"eval_samples_per_second": 512.163,
|
| 44 |
+
"eval_steps_per_second": 8.091,
|
| 45 |
+
"step": 85
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.45,
|
| 49 |
+
"learning_rate": 0.00026368567115945337,
|
| 50 |
+
"loss": 0.8033,
|
| 51 |
+
"step": 104
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.99,
|
| 55 |
+
"eval_accuracy": 0.9060421286031042,
|
| 56 |
+
"eval_loss": 0.835341215133667,
|
| 57 |
+
"eval_runtime": 7.2333,
|
| 58 |
+
"eval_samples_per_second": 498.805,
|
| 59 |
+
"eval_steps_per_second": 7.88,
|
| 60 |
+
"step": 127
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.06,
|
| 64 |
+
"learning_rate": 0.0003296070889493167,
|
| 65 |
+
"loss": 0.7991,
|
| 66 |
+
"step": 130
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.67,
|
| 70 |
+
"learning_rate": 0.00039552850673918005,
|
| 71 |
+
"loss": 0.7927,
|
| 72 |
+
"step": 156
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.3062638580931264,
|
| 77 |
+
"eval_loss": 1.9181619882583618,
|
| 78 |
+
"eval_runtime": 6.8913,
|
| 79 |
+
"eval_samples_per_second": 523.562,
|
| 80 |
+
"eval_steps_per_second": 8.271,
|
| 81 |
+
"step": 170
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.28,
|
| 85 |
+
"learning_rate": 0.00046144992452904344,
|
| 86 |
+
"loss": 0.7921,
|
| 87 |
+
"step": 182
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.89,
|
| 91 |
+
"learning_rate": 0.0005273713423189067,
|
| 92 |
+
"loss": 0.7957,
|
| 93 |
+
"step": 208
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.99,
|
| 97 |
+
"eval_accuracy": 0.8708425720620843,
|
| 98 |
+
"eval_loss": 0.8894914388656616,
|
| 99 |
+
"eval_runtime": 6.783,
|
| 100 |
+
"eval_samples_per_second": 531.919,
|
| 101 |
+
"eval_steps_per_second": 8.403,
|
| 102 |
+
"step": 212
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.51,
|
| 106 |
+
"learning_rate": 0.0005932927601087701,
|
| 107 |
+
"loss": 0.808,
|
| 108 |
+
"step": 234
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.8689024390243902,
|
| 113 |
+
"eval_loss": 0.8922765851020813,
|
| 114 |
+
"eval_runtime": 6.8307,
|
| 115 |
+
"eval_samples_per_second": 528.203,
|
| 116 |
+
"eval_steps_per_second": 8.345,
|
| 117 |
+
"step": 255
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.12,
|
| 121 |
+
"learning_rate": 0.0006592141778986334,
|
| 122 |
+
"loss": 0.8061,
|
| 123 |
+
"step": 260
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.73,
|
| 127 |
+
"learning_rate": 0.0007251355956884968,
|
| 128 |
+
"loss": 0.8088,
|
| 129 |
+
"step": 286
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.99,
|
| 133 |
+
"eval_accuracy": 0.8658536585365854,
|
| 134 |
+
"eval_loss": 0.8844387531280518,
|
| 135 |
+
"eval_runtime": 6.8269,
|
| 136 |
+
"eval_samples_per_second": 528.496,
|
| 137 |
+
"eval_steps_per_second": 8.349,
|
| 138 |
+
"step": 297
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 7.34,
|
| 142 |
+
"learning_rate": 0.0007910570134783601,
|
| 143 |
+
"loss": 0.8271,
|
| 144 |
+
"step": 312
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.95,
|
| 148 |
+
"learning_rate": 0.0008442406306968075,
|
| 149 |
+
"loss": 0.8215,
|
| 150 |
+
"step": 338
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.49057649667405767,
|
| 155 |
+
"eval_loss": 1.415905475616455,
|
| 156 |
+
"eval_runtime": 6.8082,
|
| 157 |
+
"eval_samples_per_second": 529.95,
|
| 158 |
+
"eval_steps_per_second": 8.372,
|
| 159 |
+
"step": 340
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.56,
|
| 163 |
+
"learning_rate": 0.0008419736716673505,
|
| 164 |
+
"loss": 0.8314,
|
| 165 |
+
"step": 364
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.99,
|
| 169 |
+
"eval_accuracy": 0.8508869179600886,
|
| 170 |
+
"eval_loss": 0.925150454044342,
|
| 171 |
+
"eval_runtime": 6.7965,
|
| 172 |
+
"eval_samples_per_second": 530.858,
|
| 173 |
+
"eval_steps_per_second": 8.387,
|
| 174 |
+
"step": 382
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.18,
|
| 178 |
+
"learning_rate": 0.0008364493039611666,
|
| 179 |
+
"loss": 0.8414,
|
| 180 |
+
"step": 390
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.79,
|
| 184 |
+
"learning_rate": 0.0008277103911683624,
|
| 185 |
+
"loss": 0.8306,
|
| 186 |
+
"step": 416
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_accuracy": 0.844789356984479,
|
| 191 |
+
"eval_loss": 0.9613429307937622,
|
| 192 |
+
"eval_runtime": 6.7109,
|
| 193 |
+
"eval_samples_per_second": 537.632,
|
| 194 |
+
"eval_steps_per_second": 8.494,
|
| 195 |
+
"step": 425
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.4,
|
| 199 |
+
"learning_rate": 0.0008158247385466344,
|
| 200 |
+
"loss": 0.8208,
|
| 201 |
+
"step": 442
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.99,
|
| 205 |
+
"eval_accuracy": 0.8561529933481153,
|
| 206 |
+
"eval_loss": 0.9101646542549133,
|
| 207 |
+
"eval_runtime": 6.8804,
|
| 208 |
+
"eval_samples_per_second": 524.39,
|
| 209 |
+
"eval_steps_per_second": 8.284,
|
| 210 |
+
"step": 467
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.01,
|
| 214 |
+
"learning_rate": 0.0008008845669200157,
|
| 215 |
+
"loss": 0.8112,
|
| 216 |
+
"step": 468
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.62,
|
| 220 |
+
"learning_rate": 0.0007830057971371508,
|
| 221 |
+
"loss": 0.8103,
|
| 222 |
+
"step": 494
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_accuracy": 0.866130820399113,
|
| 227 |
+
"eval_loss": 0.8902859687805176,
|
| 228 |
+
"eval_runtime": 6.5342,
|
| 229 |
+
"eval_samples_per_second": 552.175,
|
| 230 |
+
"eval_steps_per_second": 8.723,
|
| 231 |
+
"step": 510
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.24,
|
| 235 |
+
"learning_rate": 0.0007623271506409885,
|
| 236 |
+
"loss": 0.8114,
|
| 237 |
+
"step": 520
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.85,
|
| 241 |
+
"learning_rate": 0.0007390090731285776,
|
| 242 |
+
"loss": 0.8066,
|
| 243 |
+
"step": 546
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.99,
|
| 247 |
+
"eval_accuracy": 0.883869179600887,
|
| 248 |
+
"eval_loss": 0.8509737849235535,
|
| 249 |
+
"eval_runtime": 6.859,
|
| 250 |
+
"eval_samples_per_second": 526.023,
|
| 251 |
+
"eval_steps_per_second": 8.31,
|
| 252 |
+
"step": 552
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.46,
|
| 256 |
+
"learning_rate": 0.0007132324896522899,
|
| 257 |
+
"loss": 0.789,
|
| 258 |
+
"step": 572
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 14.0,
|
| 262 |
+
"eval_accuracy": 0.8181818181818182,
|
| 263 |
+
"eval_loss": 0.9610012173652649,
|
| 264 |
+
"eval_runtime": 6.7942,
|
| 265 |
+
"eval_samples_per_second": 531.04,
|
| 266 |
+
"eval_steps_per_second": 8.389,
|
| 267 |
+
"step": 595
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 14.07,
|
| 271 |
+
"learning_rate": 0.0006851974008216503,
|
| 272 |
+
"loss": 0.8046,
|
| 273 |
+
"step": 598
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 14.68,
|
| 277 |
+
"learning_rate": 0.0006551213309978434,
|
| 278 |
+
"loss": 0.7871,
|
| 279 |
+
"step": 624
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.99,
|
| 283 |
+
"eval_accuracy": 0.8794345898004434,
|
| 284 |
+
"eval_loss": 0.8511735796928406,
|
| 285 |
+
"eval_runtime": 7.0266,
|
| 286 |
+
"eval_samples_per_second": 513.474,
|
| 287 |
+
"eval_steps_per_second": 8.112,
|
| 288 |
+
"step": 637
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 15.29,
|
| 292 |
+
"learning_rate": 0.000623237640521366,
|
| 293 |
+
"loss": 0.7895,
|
| 294 |
+
"step": 650
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.91,
|
| 298 |
+
"learning_rate": 0.0005897937150682545,
|
| 299 |
+
"loss": 0.7796,
|
| 300 |
+
"step": 676
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.0,
|
| 304 |
+
"eval_accuracy": 0.8941241685144125,
|
| 305 |
+
"eval_loss": 0.8450374007225037,
|
| 306 |
+
"eval_runtime": 6.4133,
|
| 307 |
+
"eval_samples_per_second": 562.585,
|
| 308 |
+
"eval_steps_per_second": 8.888,
|
| 309 |
+
"step": 680
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.52,
|
| 313 |
+
"learning_rate": 0.0005550490461836812,
|
| 314 |
+
"loss": 0.7766,
|
| 315 |
+
"step": 702
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 16.99,
|
| 319 |
+
"eval_accuracy": 0.8919068736141907,
|
| 320 |
+
"eval_loss": 0.84095698595047,
|
| 321 |
+
"eval_runtime": 6.6733,
|
| 322 |
+
"eval_samples_per_second": 540.666,
|
| 323 |
+
"eval_steps_per_second": 8.542,
|
| 324 |
+
"step": 722
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.13,
|
| 328 |
+
"learning_rate": 0.0005192732178860646,
|
| 329 |
+
"loss": 0.7699,
|
| 330 |
+
"step": 728
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.74,
|
| 334 |
+
"learning_rate": 0.00048274381496364333,
|
| 335 |
+
"loss": 0.7682,
|
| 336 |
+
"step": 754
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 18.0,
|
| 340 |
+
"eval_accuracy": 0.9096452328159645,
|
| 341 |
+
"eval_loss": 0.8209763169288635,
|
| 342 |
+
"eval_runtime": 6.9292,
|
| 343 |
+
"eval_samples_per_second": 520.693,
|
| 344 |
+
"eval_steps_per_second": 8.226,
|
| 345 |
+
"step": 765
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 18.35,
|
| 349 |
+
"learning_rate": 0.00044574426919304425,
|
| 350 |
+
"loss": 0.7545,
|
| 351 |
+
"step": 780
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 18.96,
|
| 355 |
+
"learning_rate": 0.00040856166019104657,
|
| 356 |
+
"loss": 0.7493,
|
| 357 |
+
"step": 806
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.99,
|
| 361 |
+
"eval_accuracy": 0.8999445676274944,
|
| 362 |
+
"eval_loss": 0.8305134773254395,
|
| 363 |
+
"eval_runtime": 6.4165,
|
| 364 |
+
"eval_samples_per_second": 562.302,
|
| 365 |
+
"eval_steps_per_second": 8.883,
|
| 366 |
+
"step": 807
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 19.58,
|
| 370 |
+
"learning_rate": 0.00037148448796274085,
|
| 371 |
+
"loss": 0.7647,
|
| 372 |
+
"step": 832
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.0,
|
| 376 |
+
"eval_accuracy": 0.8957871396895787,
|
| 377 |
+
"eval_loss": 0.832939863204956,
|
| 378 |
+
"eval_runtime": 7.1704,
|
| 379 |
+
"eval_samples_per_second": 503.181,
|
| 380 |
+
"eval_steps_per_second": 7.949,
|
| 381 |
+
"step": 850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 20.19,
|
| 385 |
+
"learning_rate": 0.0003348004344288875,
|
| 386 |
+
"loss": 0.7469,
|
| 387 |
+
"step": 858
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 20.8,
|
| 391 |
+
"learning_rate": 0.00029879413130079794,
|
| 392 |
+
"loss": 0.7394,
|
| 393 |
+
"step": 884
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.99,
|
| 397 |
+
"eval_accuracy": 0.9024390243902439,
|
| 398 |
+
"eval_loss": 0.8302128911018372,
|
| 399 |
+
"eval_runtime": 6.5838,
|
| 400 |
+
"eval_samples_per_second": 548.015,
|
| 401 |
+
"eval_steps_per_second": 8.658,
|
| 402 |
+
"step": 892
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 21.41,
|
| 406 |
+
"learning_rate": 0.0002637449516217992,
|
| 407 |
+
"loss": 0.7289,
|
| 408 |
+
"step": 910
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 22.0,
|
| 412 |
+
"eval_accuracy": 0.9068736141906873,
|
| 413 |
+
"eval_loss": 0.8258054852485657,
|
| 414 |
+
"eval_runtime": 7.2067,
|
| 415 |
+
"eval_samples_per_second": 500.644,
|
| 416 |
+
"eval_steps_per_second": 7.909,
|
| 417 |
+
"step": 935
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 22.02,
|
| 421 |
+
"learning_rate": 0.0002299248421107255,
|
| 422 |
+
"loss": 0.7366,
|
| 423 |
+
"step": 936
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.64,
|
| 427 |
+
"learning_rate": 0.00019759621312629024,
|
| 428 |
+
"loss": 0.7284,
|
| 429 |
+
"step": 962
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.99,
|
| 433 |
+
"eval_accuracy": 0.9077050997782705,
|
| 434 |
+
"eval_loss": 0.8189506530761719,
|
| 435 |
+
"eval_runtime": 6.778,
|
| 436 |
+
"eval_samples_per_second": 532.311,
|
| 437 |
+
"eval_steps_per_second": 8.41,
|
| 438 |
+
"step": 977
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 23.25,
|
| 442 |
+
"learning_rate": 0.0001670099026241101,
|
| 443 |
+
"loss": 0.7256,
|
| 444 |
+
"step": 988
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.86,
|
| 448 |
+
"learning_rate": 0.00013840322990405166,
|
| 449 |
+
"loss": 0.7182,
|
| 450 |
+
"step": 1014
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 24.0,
|
| 454 |
+
"eval_accuracy": 0.9107538802660754,
|
| 455 |
+
"eval_loss": 0.8193372488021851,
|
| 456 |
+
"eval_runtime": 6.6489,
|
| 457 |
+
"eval_samples_per_second": 542.643,
|
| 458 |
+
"eval_steps_per_second": 8.573,
|
| 459 |
+
"step": 1020
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 24.47,
|
| 463 |
+
"learning_rate": 0.00011199815424887838,
|
| 464 |
+
"loss": 0.7122,
|
| 465 |
+
"step": 1040
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 24.99,
|
| 469 |
+
"eval_accuracy": 0.9151884700665188,
|
| 470 |
+
"eval_loss": 0.8143371343612671,
|
| 471 |
+
"eval_runtime": 6.823,
|
| 472 |
+
"eval_samples_per_second": 528.798,
|
| 473 |
+
"eval_steps_per_second": 8.354,
|
| 474 |
+
"step": 1062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 25.08,
|
| 478 |
+
"learning_rate": 8.799955274132829e-05,
|
| 479 |
+
"loss": 0.7151,
|
| 480 |
+
"step": 1066
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 25.69,
|
| 484 |
+
"learning_rate": 6.659363062204812e-05,
|
| 485 |
+
"loss": 0.7075,
|
| 486 |
+
"step": 1092
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 26.0,
|
| 490 |
+
"eval_accuracy": 0.9085365853658537,
|
| 491 |
+
"eval_loss": 0.8188567757606506,
|
| 492 |
+
"eval_runtime": 6.7351,
|
| 493 |
+
"eval_samples_per_second": 535.703,
|
| 494 |
+
"eval_steps_per_second": 8.463,
|
| 495 |
+
"step": 1105
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 26.31,
|
| 499 |
+
"learning_rate": 4.794647652242038e-05,
|
| 500 |
+
"loss": 0.7083,
|
| 501 |
+
"step": 1118
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.92,
|
| 505 |
+
"learning_rate": 3.220277378223892e-05,
|
| 506 |
+
"loss": 0.7105,
|
| 507 |
+
"step": 1144
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 26.99,
|
| 511 |
+
"eval_accuracy": 0.9115853658536586,
|
| 512 |
+
"eval_loss": 0.81794673204422,
|
| 513 |
+
"eval_runtime": 7.0537,
|
| 514 |
+
"eval_samples_per_second": 511.506,
|
| 515 |
+
"eval_steps_per_second": 8.081,
|
| 516 |
+
"step": 1147
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 27.53,
|
| 520 |
+
"learning_rate": 1.9484677851123602e-05,
|
| 521 |
+
"loss": 0.7061,
|
| 522 |
+
"step": 1170
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 28.0,
|
| 526 |
+
"eval_accuracy": 0.916019955654102,
|
| 527 |
+
"eval_loss": 0.809096097946167,
|
| 528 |
+
"eval_runtime": 6.7896,
|
| 529 |
+
"eval_samples_per_second": 531.403,
|
| 530 |
+
"eval_steps_per_second": 8.395,
|
| 531 |
+
"step": 1190
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 28.14,
|
| 535 |
+
"learning_rate": 9.890868483920935e-06,
|
| 536 |
+
"loss": 0.7012,
|
| 537 |
+
"step": 1196
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 28.75,
|
| 541 |
+
"learning_rate": 3.4957840841091803e-06,
|
| 542 |
+
"loss": 0.7019,
|
| 543 |
+
"step": 1222
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 28.99,
|
| 547 |
+
"eval_accuracy": 0.9157427937915743,
|
| 548 |
+
"eval_loss": 0.8142038583755493,
|
| 549 |
+
"eval_runtime": 6.8663,
|
| 550 |
+
"eval_samples_per_second": 525.467,
|
| 551 |
+
"eval_steps_per_second": 8.301,
|
| 552 |
+
"step": 1232
|
| 553 |
+
}
|
| 554 |
+
],
|
| 555 |
+
"logging_steps": 26,
|
| 556 |
+
"max_steps": 1260,
|
| 557 |
+
"num_input_tokens_seen": 0,
|
| 558 |
+
"num_train_epochs": 30,
|
| 559 |
+
"save_steps": 500,
|
| 560 |
+
"total_flos": 0.0,
|
| 561 |
+
"train_batch_size": 64,
|
| 562 |
+
"trial_name": null,
|
| 563 |
+
"trial_params": {
|
| 564 |
+
"_wandb": {},
|
| 565 |
+
"assignments": {},
|
| 566 |
+
"learning_rate": 0.0008443012355394036,
|
| 567 |
+
"metric": "eval/loss",
|
| 568 |
+
"warmup_ratio": 0.26422569175932836
|
| 569 |
+
}
|
| 570 |
+
}
|
run-0t23cnxu/checkpoint-1232/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab04088d6a5b249c07af2275e9e3ba21c8e3dcf2db2dbfdad8f76bcc46b0372a
|
| 3 |
+
size 4792
|
run-0t23cnxu/checkpoint-1260/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efb30864fcb2c1e8ee3a05ebc7b87b4da398661551363e04fcdacff154878c5b
|
| 3 |
+
size 198025308
|
run-0t23cnxu/checkpoint-1260/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:102eeec9c08aa585a37266e4dd19307a29a9a19815ce690843f938361252930c
|
| 3 |
+
size 395900602
|
run-0t23cnxu/checkpoint-1260/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deeb0d472f47497c93334cb3948d4032ad244442808af19b401a7a0fea1fe65c
|
| 3 |
+
size 14244
|
run-0t23cnxu/checkpoint-1260/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e04296fca60c05e6440e7b67de679bf2c4bee6f76163acffa199c3cb36d8a67
|
| 3 |
+
size 1064
|
run-0t23cnxu/checkpoint-1260/trainer_state.json
ADDED
|
@@ -0,0 +1,585 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9171286031042128,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-0t23cnxu/checkpoint-1260",
|
| 4 |
+
"epoch": 29.647058823529413,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1260,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 6.592141778986334e-05,
|
| 14 |
+
"loss": 1.2233,
|
| 15 |
+
"step": 26
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8896895787139689,
|
| 20 |
+
"eval_loss": 0.89235520362854,
|
| 21 |
+
"eval_runtime": 6.9506,
|
| 22 |
+
"eval_samples_per_second": 519.09,
|
| 23 |
+
"eval_steps_per_second": 8.201,
|
| 24 |
+
"step": 42
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.22,
|
| 28 |
+
"learning_rate": 0.00013184283557972668,
|
| 29 |
+
"loss": 0.8733,
|
| 30 |
+
"step": 52
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.84,
|
| 34 |
+
"learning_rate": 0.00019776425336959002,
|
| 35 |
+
"loss": 0.8108,
|
| 36 |
+
"step": 78
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.905210643015521,
|
| 41 |
+
"eval_loss": 0.8281971216201782,
|
| 42 |
+
"eval_runtime": 7.0446,
|
| 43 |
+
"eval_samples_per_second": 512.163,
|
| 44 |
+
"eval_steps_per_second": 8.091,
|
| 45 |
+
"step": 85
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.45,
|
| 49 |
+
"learning_rate": 0.00026368567115945337,
|
| 50 |
+
"loss": 0.8033,
|
| 51 |
+
"step": 104
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.99,
|
| 55 |
+
"eval_accuracy": 0.9060421286031042,
|
| 56 |
+
"eval_loss": 0.835341215133667,
|
| 57 |
+
"eval_runtime": 7.2333,
|
| 58 |
+
"eval_samples_per_second": 498.805,
|
| 59 |
+
"eval_steps_per_second": 7.88,
|
| 60 |
+
"step": 127
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.06,
|
| 64 |
+
"learning_rate": 0.0003296070889493167,
|
| 65 |
+
"loss": 0.7991,
|
| 66 |
+
"step": 130
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.67,
|
| 70 |
+
"learning_rate": 0.00039552850673918005,
|
| 71 |
+
"loss": 0.7927,
|
| 72 |
+
"step": 156
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.3062638580931264,
|
| 77 |
+
"eval_loss": 1.9181619882583618,
|
| 78 |
+
"eval_runtime": 6.8913,
|
| 79 |
+
"eval_samples_per_second": 523.562,
|
| 80 |
+
"eval_steps_per_second": 8.271,
|
| 81 |
+
"step": 170
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.28,
|
| 85 |
+
"learning_rate": 0.00046144992452904344,
|
| 86 |
+
"loss": 0.7921,
|
| 87 |
+
"step": 182
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.89,
|
| 91 |
+
"learning_rate": 0.0005273713423189067,
|
| 92 |
+
"loss": 0.7957,
|
| 93 |
+
"step": 208
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.99,
|
| 97 |
+
"eval_accuracy": 0.8708425720620843,
|
| 98 |
+
"eval_loss": 0.8894914388656616,
|
| 99 |
+
"eval_runtime": 6.783,
|
| 100 |
+
"eval_samples_per_second": 531.919,
|
| 101 |
+
"eval_steps_per_second": 8.403,
|
| 102 |
+
"step": 212
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.51,
|
| 106 |
+
"learning_rate": 0.0005932927601087701,
|
| 107 |
+
"loss": 0.808,
|
| 108 |
+
"step": 234
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.8689024390243902,
|
| 113 |
+
"eval_loss": 0.8922765851020813,
|
| 114 |
+
"eval_runtime": 6.8307,
|
| 115 |
+
"eval_samples_per_second": 528.203,
|
| 116 |
+
"eval_steps_per_second": 8.345,
|
| 117 |
+
"step": 255
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.12,
|
| 121 |
+
"learning_rate": 0.0006592141778986334,
|
| 122 |
+
"loss": 0.8061,
|
| 123 |
+
"step": 260
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.73,
|
| 127 |
+
"learning_rate": 0.0007251355956884968,
|
| 128 |
+
"loss": 0.8088,
|
| 129 |
+
"step": 286
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.99,
|
| 133 |
+
"eval_accuracy": 0.8658536585365854,
|
| 134 |
+
"eval_loss": 0.8844387531280518,
|
| 135 |
+
"eval_runtime": 6.8269,
|
| 136 |
+
"eval_samples_per_second": 528.496,
|
| 137 |
+
"eval_steps_per_second": 8.349,
|
| 138 |
+
"step": 297
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 7.34,
|
| 142 |
+
"learning_rate": 0.0007910570134783601,
|
| 143 |
+
"loss": 0.8271,
|
| 144 |
+
"step": 312
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.95,
|
| 148 |
+
"learning_rate": 0.0008442406306968075,
|
| 149 |
+
"loss": 0.8215,
|
| 150 |
+
"step": 338
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.49057649667405767,
|
| 155 |
+
"eval_loss": 1.415905475616455,
|
| 156 |
+
"eval_runtime": 6.8082,
|
| 157 |
+
"eval_samples_per_second": 529.95,
|
| 158 |
+
"eval_steps_per_second": 8.372,
|
| 159 |
+
"step": 340
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.56,
|
| 163 |
+
"learning_rate": 0.0008419736716673505,
|
| 164 |
+
"loss": 0.8314,
|
| 165 |
+
"step": 364
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.99,
|
| 169 |
+
"eval_accuracy": 0.8508869179600886,
|
| 170 |
+
"eval_loss": 0.925150454044342,
|
| 171 |
+
"eval_runtime": 6.7965,
|
| 172 |
+
"eval_samples_per_second": 530.858,
|
| 173 |
+
"eval_steps_per_second": 8.387,
|
| 174 |
+
"step": 382
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.18,
|
| 178 |
+
"learning_rate": 0.0008364493039611666,
|
| 179 |
+
"loss": 0.8414,
|
| 180 |
+
"step": 390
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.79,
|
| 184 |
+
"learning_rate": 0.0008277103911683624,
|
| 185 |
+
"loss": 0.8306,
|
| 186 |
+
"step": 416
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_accuracy": 0.844789356984479,
|
| 191 |
+
"eval_loss": 0.9613429307937622,
|
| 192 |
+
"eval_runtime": 6.7109,
|
| 193 |
+
"eval_samples_per_second": 537.632,
|
| 194 |
+
"eval_steps_per_second": 8.494,
|
| 195 |
+
"step": 425
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.4,
|
| 199 |
+
"learning_rate": 0.0008158247385466344,
|
| 200 |
+
"loss": 0.8208,
|
| 201 |
+
"step": 442
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.99,
|
| 205 |
+
"eval_accuracy": 0.8561529933481153,
|
| 206 |
+
"eval_loss": 0.9101646542549133,
|
| 207 |
+
"eval_runtime": 6.8804,
|
| 208 |
+
"eval_samples_per_second": 524.39,
|
| 209 |
+
"eval_steps_per_second": 8.284,
|
| 210 |
+
"step": 467
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.01,
|
| 214 |
+
"learning_rate": 0.0008008845669200157,
|
| 215 |
+
"loss": 0.8112,
|
| 216 |
+
"step": 468
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.62,
|
| 220 |
+
"learning_rate": 0.0007830057971371508,
|
| 221 |
+
"loss": 0.8103,
|
| 222 |
+
"step": 494
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_accuracy": 0.866130820399113,
|
| 227 |
+
"eval_loss": 0.8902859687805176,
|
| 228 |
+
"eval_runtime": 6.5342,
|
| 229 |
+
"eval_samples_per_second": 552.175,
|
| 230 |
+
"eval_steps_per_second": 8.723,
|
| 231 |
+
"step": 510
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.24,
|
| 235 |
+
"learning_rate": 0.0007623271506409885,
|
| 236 |
+
"loss": 0.8114,
|
| 237 |
+
"step": 520
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.85,
|
| 241 |
+
"learning_rate": 0.0007390090731285776,
|
| 242 |
+
"loss": 0.8066,
|
| 243 |
+
"step": 546
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.99,
|
| 247 |
+
"eval_accuracy": 0.883869179600887,
|
| 248 |
+
"eval_loss": 0.8509737849235535,
|
| 249 |
+
"eval_runtime": 6.859,
|
| 250 |
+
"eval_samples_per_second": 526.023,
|
| 251 |
+
"eval_steps_per_second": 8.31,
|
| 252 |
+
"step": 552
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.46,
|
| 256 |
+
"learning_rate": 0.0007132324896522899,
|
| 257 |
+
"loss": 0.789,
|
| 258 |
+
"step": 572
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 14.0,
|
| 262 |
+
"eval_accuracy": 0.8181818181818182,
|
| 263 |
+
"eval_loss": 0.9610012173652649,
|
| 264 |
+
"eval_runtime": 6.7942,
|
| 265 |
+
"eval_samples_per_second": 531.04,
|
| 266 |
+
"eval_steps_per_second": 8.389,
|
| 267 |
+
"step": 595
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 14.07,
|
| 271 |
+
"learning_rate": 0.0006851974008216503,
|
| 272 |
+
"loss": 0.8046,
|
| 273 |
+
"step": 598
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 14.68,
|
| 277 |
+
"learning_rate": 0.0006551213309978434,
|
| 278 |
+
"loss": 0.7871,
|
| 279 |
+
"step": 624
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.99,
|
| 283 |
+
"eval_accuracy": 0.8794345898004434,
|
| 284 |
+
"eval_loss": 0.8511735796928406,
|
| 285 |
+
"eval_runtime": 7.0266,
|
| 286 |
+
"eval_samples_per_second": 513.474,
|
| 287 |
+
"eval_steps_per_second": 8.112,
|
| 288 |
+
"step": 637
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 15.29,
|
| 292 |
+
"learning_rate": 0.000623237640521366,
|
| 293 |
+
"loss": 0.7895,
|
| 294 |
+
"step": 650
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.91,
|
| 298 |
+
"learning_rate": 0.0005897937150682545,
|
| 299 |
+
"loss": 0.7796,
|
| 300 |
+
"step": 676
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.0,
|
| 304 |
+
"eval_accuracy": 0.8941241685144125,
|
| 305 |
+
"eval_loss": 0.8450374007225037,
|
| 306 |
+
"eval_runtime": 6.4133,
|
| 307 |
+
"eval_samples_per_second": 562.585,
|
| 308 |
+
"eval_steps_per_second": 8.888,
|
| 309 |
+
"step": 680
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.52,
|
| 313 |
+
"learning_rate": 0.0005550490461836812,
|
| 314 |
+
"loss": 0.7766,
|
| 315 |
+
"step": 702
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 16.99,
|
| 319 |
+
"eval_accuracy": 0.8919068736141907,
|
| 320 |
+
"eval_loss": 0.84095698595047,
|
| 321 |
+
"eval_runtime": 6.6733,
|
| 322 |
+
"eval_samples_per_second": 540.666,
|
| 323 |
+
"eval_steps_per_second": 8.542,
|
| 324 |
+
"step": 722
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.13,
|
| 328 |
+
"learning_rate": 0.0005192732178860646,
|
| 329 |
+
"loss": 0.7699,
|
| 330 |
+
"step": 728
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.74,
|
| 334 |
+
"learning_rate": 0.00048274381496364333,
|
| 335 |
+
"loss": 0.7682,
|
| 336 |
+
"step": 754
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 18.0,
|
| 340 |
+
"eval_accuracy": 0.9096452328159645,
|
| 341 |
+
"eval_loss": 0.8209763169288635,
|
| 342 |
+
"eval_runtime": 6.9292,
|
| 343 |
+
"eval_samples_per_second": 520.693,
|
| 344 |
+
"eval_steps_per_second": 8.226,
|
| 345 |
+
"step": 765
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 18.35,
|
| 349 |
+
"learning_rate": 0.00044574426919304425,
|
| 350 |
+
"loss": 0.7545,
|
| 351 |
+
"step": 780
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 18.96,
|
| 355 |
+
"learning_rate": 0.00040856166019104657,
|
| 356 |
+
"loss": 0.7493,
|
| 357 |
+
"step": 806
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.99,
|
| 361 |
+
"eval_accuracy": 0.8999445676274944,
|
| 362 |
+
"eval_loss": 0.8305134773254395,
|
| 363 |
+
"eval_runtime": 6.4165,
|
| 364 |
+
"eval_samples_per_second": 562.302,
|
| 365 |
+
"eval_steps_per_second": 8.883,
|
| 366 |
+
"step": 807
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 19.58,
|
| 370 |
+
"learning_rate": 0.00037148448796274085,
|
| 371 |
+
"loss": 0.7647,
|
| 372 |
+
"step": 832
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.0,
|
| 376 |
+
"eval_accuracy": 0.8957871396895787,
|
| 377 |
+
"eval_loss": 0.832939863204956,
|
| 378 |
+
"eval_runtime": 7.1704,
|
| 379 |
+
"eval_samples_per_second": 503.181,
|
| 380 |
+
"eval_steps_per_second": 7.949,
|
| 381 |
+
"step": 850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 20.19,
|
| 385 |
+
"learning_rate": 0.0003348004344288875,
|
| 386 |
+
"loss": 0.7469,
|
| 387 |
+
"step": 858
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 20.8,
|
| 391 |
+
"learning_rate": 0.00029879413130079794,
|
| 392 |
+
"loss": 0.7394,
|
| 393 |
+
"step": 884
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.99,
|
| 397 |
+
"eval_accuracy": 0.9024390243902439,
|
| 398 |
+
"eval_loss": 0.8302128911018372,
|
| 399 |
+
"eval_runtime": 6.5838,
|
| 400 |
+
"eval_samples_per_second": 548.015,
|
| 401 |
+
"eval_steps_per_second": 8.658,
|
| 402 |
+
"step": 892
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 21.41,
|
| 406 |
+
"learning_rate": 0.0002637449516217992,
|
| 407 |
+
"loss": 0.7289,
|
| 408 |
+
"step": 910
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 22.0,
|
| 412 |
+
"eval_accuracy": 0.9068736141906873,
|
| 413 |
+
"eval_loss": 0.8258054852485657,
|
| 414 |
+
"eval_runtime": 7.2067,
|
| 415 |
+
"eval_samples_per_second": 500.644,
|
| 416 |
+
"eval_steps_per_second": 7.909,
|
| 417 |
+
"step": 935
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 22.02,
|
| 421 |
+
"learning_rate": 0.0002299248421107255,
|
| 422 |
+
"loss": 0.7366,
|
| 423 |
+
"step": 936
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.64,
|
| 427 |
+
"learning_rate": 0.00019759621312629024,
|
| 428 |
+
"loss": 0.7284,
|
| 429 |
+
"step": 962
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.99,
|
| 433 |
+
"eval_accuracy": 0.9077050997782705,
|
| 434 |
+
"eval_loss": 0.8189506530761719,
|
| 435 |
+
"eval_runtime": 6.778,
|
| 436 |
+
"eval_samples_per_second": 532.311,
|
| 437 |
+
"eval_steps_per_second": 8.41,
|
| 438 |
+
"step": 977
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 23.25,
|
| 442 |
+
"learning_rate": 0.0001670099026241101,
|
| 443 |
+
"loss": 0.7256,
|
| 444 |
+
"step": 988
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.86,
|
| 448 |
+
"learning_rate": 0.00013840322990405166,
|
| 449 |
+
"loss": 0.7182,
|
| 450 |
+
"step": 1014
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 24.0,
|
| 454 |
+
"eval_accuracy": 0.9107538802660754,
|
| 455 |
+
"eval_loss": 0.8193372488021851,
|
| 456 |
+
"eval_runtime": 6.6489,
|
| 457 |
+
"eval_samples_per_second": 542.643,
|
| 458 |
+
"eval_steps_per_second": 8.573,
|
| 459 |
+
"step": 1020
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 24.47,
|
| 463 |
+
"learning_rate": 0.00011199815424887838,
|
| 464 |
+
"loss": 0.7122,
|
| 465 |
+
"step": 1040
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 24.99,
|
| 469 |
+
"eval_accuracy": 0.9151884700665188,
|
| 470 |
+
"eval_loss": 0.8143371343612671,
|
| 471 |
+
"eval_runtime": 6.823,
|
| 472 |
+
"eval_samples_per_second": 528.798,
|
| 473 |
+
"eval_steps_per_second": 8.354,
|
| 474 |
+
"step": 1062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 25.08,
|
| 478 |
+
"learning_rate": 8.799955274132829e-05,
|
| 479 |
+
"loss": 0.7151,
|
| 480 |
+
"step": 1066
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 25.69,
|
| 484 |
+
"learning_rate": 6.659363062204812e-05,
|
| 485 |
+
"loss": 0.7075,
|
| 486 |
+
"step": 1092
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 26.0,
|
| 490 |
+
"eval_accuracy": 0.9085365853658537,
|
| 491 |
+
"eval_loss": 0.8188567757606506,
|
| 492 |
+
"eval_runtime": 6.7351,
|
| 493 |
+
"eval_samples_per_second": 535.703,
|
| 494 |
+
"eval_steps_per_second": 8.463,
|
| 495 |
+
"step": 1105
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 26.31,
|
| 499 |
+
"learning_rate": 4.794647652242038e-05,
|
| 500 |
+
"loss": 0.7083,
|
| 501 |
+
"step": 1118
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.92,
|
| 505 |
+
"learning_rate": 3.220277378223892e-05,
|
| 506 |
+
"loss": 0.7105,
|
| 507 |
+
"step": 1144
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 26.99,
|
| 511 |
+
"eval_accuracy": 0.9115853658536586,
|
| 512 |
+
"eval_loss": 0.81794673204422,
|
| 513 |
+
"eval_runtime": 7.0537,
|
| 514 |
+
"eval_samples_per_second": 511.506,
|
| 515 |
+
"eval_steps_per_second": 8.081,
|
| 516 |
+
"step": 1147
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 27.53,
|
| 520 |
+
"learning_rate": 1.9484677851123602e-05,
|
| 521 |
+
"loss": 0.7061,
|
| 522 |
+
"step": 1170
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 28.0,
|
| 526 |
+
"eval_accuracy": 0.916019955654102,
|
| 527 |
+
"eval_loss": 0.809096097946167,
|
| 528 |
+
"eval_runtime": 6.7896,
|
| 529 |
+
"eval_samples_per_second": 531.403,
|
| 530 |
+
"eval_steps_per_second": 8.395,
|
| 531 |
+
"step": 1190
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 28.14,
|
| 535 |
+
"learning_rate": 9.890868483920935e-06,
|
| 536 |
+
"loss": 0.7012,
|
| 537 |
+
"step": 1196
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 28.75,
|
| 541 |
+
"learning_rate": 3.4957840841091803e-06,
|
| 542 |
+
"loss": 0.7019,
|
| 543 |
+
"step": 1222
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 28.99,
|
| 547 |
+
"eval_accuracy": 0.9157427937915743,
|
| 548 |
+
"eval_loss": 0.8142038583755493,
|
| 549 |
+
"eval_runtime": 6.8663,
|
| 550 |
+
"eval_samples_per_second": 525.467,
|
| 551 |
+
"eval_steps_per_second": 8.301,
|
| 552 |
+
"step": 1232
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 29.36,
|
| 556 |
+
"learning_rate": 3.4904413594245166e-07,
|
| 557 |
+
"loss": 0.7049,
|
| 558 |
+
"step": 1248
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 29.65,
|
| 562 |
+
"eval_accuracy": 0.9171286031042128,
|
| 563 |
+
"eval_loss": 0.8099156022071838,
|
| 564 |
+
"eval_runtime": 6.6948,
|
| 565 |
+
"eval_samples_per_second": 538.93,
|
| 566 |
+
"eval_steps_per_second": 8.514,
|
| 567 |
+
"step": 1260
|
| 568 |
+
}
|
| 569 |
+
],
|
| 570 |
+
"logging_steps": 26,
|
| 571 |
+
"max_steps": 1260,
|
| 572 |
+
"num_input_tokens_seen": 0,
|
| 573 |
+
"num_train_epochs": 30,
|
| 574 |
+
"save_steps": 500,
|
| 575 |
+
"total_flos": 0.0,
|
| 576 |
+
"train_batch_size": 64,
|
| 577 |
+
"trial_name": null,
|
| 578 |
+
"trial_params": {
|
| 579 |
+
"_wandb": {},
|
| 580 |
+
"assignments": {},
|
| 581 |
+
"learning_rate": 0.0008443012355394036,
|
| 582 |
+
"metric": "eval/loss",
|
| 583 |
+
"warmup_ratio": 0.26422569175932836
|
| 584 |
+
}
|
| 585 |
+
}
|
run-0t23cnxu/checkpoint-1260/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab04088d6a5b249c07af2275e9e3ba21c8e3dcf2db2dbfdad8f76bcc46b0372a
|
| 3 |
+
size 4792
|
run-22pm9fz7/checkpoint-573/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:218a8aeed10478fa490b97ea30aebda7ac73a34263790c45e83a5d756b31772d
|
| 3 |
+
size 198025308
|
run-22pm9fz7/checkpoint-573/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7775b298ddb9c3cb25f0605b6806a8ec3029e0c394c7eeb9e2e8f402b6abc4c
|
| 3 |
+
size 395900602
|
run-22pm9fz7/checkpoint-573/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9102bb312b12c2313ea7585eb813beef5c548592778aaea4ab0516e14ecd38e5
|
| 3 |
+
size 14244
|
run-22pm9fz7/checkpoint-573/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d190657aad44956070319e4cbdc740e546c0b283321e639ed75a4df57212c478
|
| 3 |
+
size 1064
|
run-22pm9fz7/checkpoint-573/trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9190093173009881,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-22pm9fz7/checkpoint-573",
|
| 4 |
+
"epoch": 26.96470588235294,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 573,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 1.2219843366163651e-05,
|
| 14 |
+
"loss": 1.486,
|
| 15 |
+
"step": 13
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8276053215077606,
|
| 20 |
+
"eval_f1": 0.7506333806665745,
|
| 21 |
+
"eval_loss": 1.1113407611846924,
|
| 22 |
+
"eval_precision": 0.6867607734554959,
|
| 23 |
+
"eval_recall": 0.8276053215077606,
|
| 24 |
+
"eval_runtime": 8.3733,
|
| 25 |
+
"eval_samples_per_second": 430.891,
|
| 26 |
+
"eval_steps_per_second": 3.463,
|
| 27 |
+
"step": 21
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.22,
|
| 31 |
+
"learning_rate": 2.4439686732327303e-05,
|
| 32 |
+
"loss": 1.1919,
|
| 33 |
+
"step": 26
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.84,
|
| 37 |
+
"learning_rate": 3.665953009849096e-05,
|
| 38 |
+
"loss": 0.9574,
|
| 39 |
+
"step": 39
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.98,
|
| 43 |
+
"eval_accuracy": 0.8592017738359202,
|
| 44 |
+
"eval_f1": 0.8158688229267518,
|
| 45 |
+
"eval_loss": 0.9284856915473938,
|
| 46 |
+
"eval_precision": 0.8413284596404325,
|
| 47 |
+
"eval_recall": 0.8592017738359202,
|
| 48 |
+
"eval_runtime": 8.4795,
|
| 49 |
+
"eval_samples_per_second": 425.497,
|
| 50 |
+
"eval_steps_per_second": 3.42,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.45,
|
| 55 |
+
"learning_rate": 4.8879373464654605e-05,
|
| 56 |
+
"loss": 0.8789,
|
| 57 |
+
"step": 52
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.96,
|
| 61 |
+
"eval_accuracy": 0.8968957871396895,
|
| 62 |
+
"eval_f1": 0.887994515834578,
|
| 63 |
+
"eval_loss": 0.8563220500946045,
|
| 64 |
+
"eval_precision": 0.888627325917696,
|
| 65 |
+
"eval_recall": 0.8968957871396895,
|
| 66 |
+
"eval_runtime": 8.648,
|
| 67 |
+
"eval_samples_per_second": 417.204,
|
| 68 |
+
"eval_steps_per_second": 3.353,
|
| 69 |
+
"step": 63
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.06,
|
| 73 |
+
"learning_rate": 6.109921683081827e-05,
|
| 74 |
+
"loss": 0.8471,
|
| 75 |
+
"step": 65
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.67,
|
| 79 |
+
"learning_rate": 7.331906019698191e-05,
|
| 80 |
+
"loss": 0.8107,
|
| 81 |
+
"step": 78
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.0,
|
| 85 |
+
"eval_accuracy": 0.9121396895787139,
|
| 86 |
+
"eval_f1": 0.9058964979973173,
|
| 87 |
+
"eval_loss": 0.8172363638877869,
|
| 88 |
+
"eval_precision": 0.9027154396135877,
|
| 89 |
+
"eval_recall": 0.9121396895787139,
|
| 90 |
+
"eval_runtime": 8.0085,
|
| 91 |
+
"eval_samples_per_second": 450.52,
|
| 92 |
+
"eval_steps_per_second": 3.621,
|
| 93 |
+
"step": 85
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.28,
|
| 97 |
+
"learning_rate": 8.553890356314556e-05,
|
| 98 |
+
"loss": 0.8015,
|
| 99 |
+
"step": 91
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.89,
|
| 103 |
+
"learning_rate": 9.775874692930921e-05,
|
| 104 |
+
"loss": 0.7861,
|
| 105 |
+
"step": 104
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.99,
|
| 109 |
+
"eval_accuracy": 0.8849778270509978,
|
| 110 |
+
"eval_f1": 0.8865037130264197,
|
| 111 |
+
"eval_loss": 0.8436875939369202,
|
| 112 |
+
"eval_precision": 0.8932393306490872,
|
| 113 |
+
"eval_recall": 0.8849778270509978,
|
| 114 |
+
"eval_runtime": 8.5752,
|
| 115 |
+
"eval_samples_per_second": 420.749,
|
| 116 |
+
"eval_steps_per_second": 3.382,
|
| 117 |
+
"step": 106
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.51,
|
| 121 |
+
"learning_rate": 0.00010997859029547287,
|
| 122 |
+
"loss": 0.7684,
|
| 123 |
+
"step": 117
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 5.98,
|
| 127 |
+
"eval_accuracy": 0.9124168514412417,
|
| 128 |
+
"eval_f1": 0.9028803793279178,
|
| 129 |
+
"eval_loss": 0.8081041574478149,
|
| 130 |
+
"eval_precision": 0.903857437506207,
|
| 131 |
+
"eval_recall": 0.9124168514412417,
|
| 132 |
+
"eval_runtime": 8.3423,
|
| 133 |
+
"eval_samples_per_second": 432.495,
|
| 134 |
+
"eval_steps_per_second": 3.476,
|
| 135 |
+
"step": 127
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.12,
|
| 139 |
+
"learning_rate": 0.00011842007545068455,
|
| 140 |
+
"loss": 0.7711,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.73,
|
| 145 |
+
"learning_rate": 0.00011810630992573294,
|
| 146 |
+
"loss": 0.7634,
|
| 147 |
+
"step": 143
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.96,
|
| 151 |
+
"eval_accuracy": 0.9149113082039911,
|
| 152 |
+
"eval_f1": 0.9067032873213865,
|
| 153 |
+
"eval_loss": 0.8178200125694275,
|
| 154 |
+
"eval_precision": 0.9055547260013138,
|
| 155 |
+
"eval_recall": 0.9149113082039911,
|
| 156 |
+
"eval_runtime": 8.0759,
|
| 157 |
+
"eval_samples_per_second": 446.762,
|
| 158 |
+
"eval_steps_per_second": 3.591,
|
| 159 |
+
"step": 148
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 7.34,
|
| 163 |
+
"learning_rate": 0.00011740608163483467,
|
| 164 |
+
"loss": 0.7565,
|
| 165 |
+
"step": 156
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 7.95,
|
| 169 |
+
"learning_rate": 0.00011632398602087223,
|
| 170 |
+
"loss": 0.7531,
|
| 171 |
+
"step": 169
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 8.0,
|
| 175 |
+
"eval_accuracy": 0.8070953436807096,
|
| 176 |
+
"eval_f1": 0.8307447955720016,
|
| 177 |
+
"eval_loss": 0.9529986381530762,
|
| 178 |
+
"eval_precision": 0.8811216651383346,
|
| 179 |
+
"eval_recall": 0.8070953436807096,
|
| 180 |
+
"eval_runtime": 8.137,
|
| 181 |
+
"eval_samples_per_second": 443.407,
|
| 182 |
+
"eval_steps_per_second": 3.564,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 8.56,
|
| 187 |
+
"learning_rate": 0.00011486712463722754,
|
| 188 |
+
"loss": 0.746,
|
| 189 |
+
"step": 182
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.99,
|
| 193 |
+
"eval_accuracy": 0.9165742793791575,
|
| 194 |
+
"eval_f1": 0.9088707382436096,
|
| 195 |
+
"eval_loss": 0.8120781779289246,
|
| 196 |
+
"eval_precision": 0.9060999886720389,
|
| 197 |
+
"eval_recall": 0.9165742793791575,
|
| 198 |
+
"eval_runtime": 8.4467,
|
| 199 |
+
"eval_samples_per_second": 427.148,
|
| 200 |
+
"eval_steps_per_second": 3.433,
|
| 201 |
+
"step": 191
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 9.18,
|
| 205 |
+
"learning_rate": 0.0001130450585418631,
|
| 206 |
+
"loss": 0.7441,
|
| 207 |
+
"step": 195
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.79,
|
| 211 |
+
"learning_rate": 0.00011086974555022023,
|
| 212 |
+
"loss": 0.7366,
|
| 213 |
+
"step": 208
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.98,
|
| 217 |
+
"eval_accuracy": 0.8991130820399114,
|
| 218 |
+
"eval_f1": 0.8990952855541333,
|
| 219 |
+
"eval_loss": 0.824906587600708,
|
| 220 |
+
"eval_precision": 0.9061946214416738,
|
| 221 |
+
"eval_recall": 0.8991130820399114,
|
| 222 |
+
"eval_runtime": 8.27,
|
| 223 |
+
"eval_samples_per_second": 436.275,
|
| 224 |
+
"eval_steps_per_second": 3.507,
|
| 225 |
+
"step": 212
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.4,
|
| 229 |
+
"learning_rate": 0.00010835546175873,
|
| 230 |
+
"loss": 0.7323,
|
| 231 |
+
"step": 221
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.96,
|
| 235 |
+
"eval_accuracy": 0.9002217294900222,
|
| 236 |
+
"eval_f1": 0.9012399347617073,
|
| 237 |
+
"eval_loss": 0.8290796279907227,
|
| 238 |
+
"eval_precision": 0.9052326255514389,
|
| 239 |
+
"eval_recall": 0.9002217294900222,
|
| 240 |
+
"eval_runtime": 8.3024,
|
| 241 |
+
"eval_samples_per_second": 434.573,
|
| 242 |
+
"eval_steps_per_second": 3.493,
|
| 243 |
+
"step": 233
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 11.01,
|
| 247 |
+
"learning_rate": 0.00010551870785396043,
|
| 248 |
+
"loss": 0.7313,
|
| 249 |
+
"step": 234
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 11.62,
|
| 253 |
+
"learning_rate": 0.00010237810082227219,
|
| 254 |
+
"loss": 0.725,
|
| 255 |
+
"step": 247
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 12.0,
|
| 259 |
+
"eval_accuracy": 0.9121396895787139,
|
| 260 |
+
"eval_f1": 0.9014249052263176,
|
| 261 |
+
"eval_loss": 0.8157982230186462,
|
| 262 |
+
"eval_precision": 0.9081945289870674,
|
| 263 |
+
"eval_recall": 0.9121396895787139,
|
| 264 |
+
"eval_runtime": 8.2951,
|
| 265 |
+
"eval_samples_per_second": 434.956,
|
| 266 |
+
"eval_steps_per_second": 3.496,
|
| 267 |
+
"step": 255
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 12.24,
|
| 271 |
+
"learning_rate": 9.895425177066865e-05,
|
| 272 |
+
"loss": 0.7242,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.85,
|
| 277 |
+
"learning_rate": 9.526963066067437e-05,
|
| 278 |
+
"loss": 0.7188,
|
| 279 |
+
"step": 273
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 12.99,
|
| 283 |
+
"eval_accuracy": 0.9182372505543237,
|
| 284 |
+
"eval_f1": 0.9146196519587654,
|
| 285 |
+
"eval_loss": 0.8068662285804749,
|
| 286 |
+
"eval_precision": 0.9120081137034548,
|
| 287 |
+
"eval_recall": 0.9182372505543237,
|
| 288 |
+
"eval_runtime": 8.2252,
|
| 289 |
+
"eval_samples_per_second": 438.654,
|
| 290 |
+
"eval_steps_per_second": 3.526,
|
| 291 |
+
"step": 276
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 13.46,
|
| 295 |
+
"learning_rate": 9.134841884296409e-05,
|
| 296 |
+
"loss": 0.7204,
|
| 297 |
+
"step": 286
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.98,
|
| 301 |
+
"eval_accuracy": 0.9168514412416852,
|
| 302 |
+
"eval_f1": 0.9092891599955425,
|
| 303 |
+
"eval_loss": 0.8142066597938538,
|
| 304 |
+
"eval_precision": 0.9095107691249883,
|
| 305 |
+
"eval_recall": 0.9168514412416852,
|
| 306 |
+
"eval_runtime": 8.1951,
|
| 307 |
+
"eval_samples_per_second": 440.263,
|
| 308 |
+
"eval_steps_per_second": 3.539,
|
| 309 |
+
"step": 297
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 14.07,
|
| 313 |
+
"learning_rate": 8.721635036052442e-05,
|
| 314 |
+
"loss": 0.7152,
|
| 315 |
+
"step": 299
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 14.68,
|
| 319 |
+
"learning_rate": 8.290054306184049e-05,
|
| 320 |
+
"loss": 0.7135,
|
| 321 |
+
"step": 312
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 14.96,
|
| 325 |
+
"eval_accuracy": 0.9174057649667405,
|
| 326 |
+
"eval_f1": 0.9103487881551395,
|
| 327 |
+
"eval_loss": 0.8043306469917297,
|
| 328 |
+
"eval_precision": 0.9097246610377273,
|
| 329 |
+
"eval_recall": 0.9174057649667405,
|
| 330 |
+
"eval_runtime": 8.4787,
|
| 331 |
+
"eval_samples_per_second": 425.535,
|
| 332 |
+
"eval_steps_per_second": 3.42,
|
| 333 |
+
"step": 318
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 15.29,
|
| 337 |
+
"learning_rate": 7.842932063247419e-05,
|
| 338 |
+
"loss": 0.7131,
|
| 339 |
+
"step": 325
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.91,
|
| 343 |
+
"learning_rate": 7.383202671300115e-05,
|
| 344 |
+
"loss": 0.7123,
|
| 345 |
+
"step": 338
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 16.0,
|
| 349 |
+
"eval_accuracy": 0.9204545454545454,
|
| 350 |
+
"eval_f1": 0.9125587073196101,
|
| 351 |
+
"eval_loss": 0.80075603723526,
|
| 352 |
+
"eval_precision": 0.9124672143244127,
|
| 353 |
+
"eval_recall": 0.9204545454545454,
|
| 354 |
+
"eval_runtime": 8.2538,
|
| 355 |
+
"eval_samples_per_second": 437.13,
|
| 356 |
+
"eval_steps_per_second": 3.514,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 16.52,
|
| 361 |
+
"learning_rate": 6.913883232320964e-05,
|
| 362 |
+
"loss": 0.7087,
|
| 363 |
+
"step": 351
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 16.99,
|
| 367 |
+
"eval_accuracy": 0.9024390243902439,
|
| 368 |
+
"eval_f1": 0.9037420660128592,
|
| 369 |
+
"eval_loss": 0.82823246717453,
|
| 370 |
+
"eval_precision": 0.9070644554543488,
|
| 371 |
+
"eval_recall": 0.9024390243902439,
|
| 372 |
+
"eval_runtime": 7.9823,
|
| 373 |
+
"eval_samples_per_second": 452.002,
|
| 374 |
+
"eval_steps_per_second": 3.633,
|
| 375 |
+
"step": 361
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 17.13,
|
| 379 |
+
"learning_rate": 6.438053785639281e-05,
|
| 380 |
+
"loss": 0.708,
|
| 381 |
+
"step": 364
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.74,
|
| 385 |
+
"learning_rate": 5.958837094320274e-05,
|
| 386 |
+
"loss": 0.7058,
|
| 387 |
+
"step": 377
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 17.98,
|
| 391 |
+
"eval_accuracy": 0.9221175166297118,
|
| 392 |
+
"eval_f1": 0.918139928004074,
|
| 393 |
+
"eval_loss": 0.8006211519241333,
|
| 394 |
+
"eval_precision": 0.9155745392875521,
|
| 395 |
+
"eval_recall": 0.9221175166297118,
|
| 396 |
+
"eval_runtime": 8.0911,
|
| 397 |
+
"eval_samples_per_second": 445.922,
|
| 398 |
+
"eval_steps_per_second": 3.584,
|
| 399 |
+
"step": 382
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 18.35,
|
| 403 |
+
"learning_rate": 5.479378151164032e-05,
|
| 404 |
+
"loss": 0.7061,
|
| 405 |
+
"step": 390
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.96,
|
| 409 |
+
"learning_rate": 5.0028235388156865e-05,
|
| 410 |
+
"loss": 0.7007,
|
| 411 |
+
"step": 403
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 18.96,
|
| 415 |
+
"eval_accuracy": 0.9162971175166297,
|
| 416 |
+
"eval_f1": 0.911467714185253,
|
| 417 |
+
"eval_loss": 0.8088358640670776,
|
| 418 |
+
"eval_precision": 0.9095502759728672,
|
| 419 |
+
"eval_recall": 0.9162971175166297,
|
| 420 |
+
"eval_runtime": 8.3048,
|
| 421 |
+
"eval_samples_per_second": 434.446,
|
| 422 |
+
"eval_steps_per_second": 3.492,
|
| 423 |
+
"step": 403
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.58,
|
| 427 |
+
"learning_rate": 4.532300779441795e-05,
|
| 428 |
+
"loss": 0.7071,
|
| 429 |
+
"step": 416
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 20.0,
|
| 433 |
+
"eval_accuracy": 0.9174057649667405,
|
| 434 |
+
"eval_f1": 0.9102457116550721,
|
| 435 |
+
"eval_loss": 0.8067628741264343,
|
| 436 |
+
"eval_precision": 0.9095707265020937,
|
| 437 |
+
"eval_recall": 0.9174057649667405,
|
| 438 |
+
"eval_runtime": 8.2606,
|
| 439 |
+
"eval_samples_per_second": 436.772,
|
| 440 |
+
"eval_steps_per_second": 3.511,
|
| 441 |
+
"step": 425
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 20.19,
|
| 445 |
+
"learning_rate": 4.070897809496389e-05,
|
| 446 |
+
"loss": 0.699,
|
| 447 |
+
"step": 429
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 20.8,
|
| 451 |
+
"learning_rate": 3.621642714279302e-05,
|
| 452 |
+
"loss": 0.6963,
|
| 453 |
+
"step": 442
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 20.99,
|
| 457 |
+
"eval_accuracy": 0.9174057649667405,
|
| 458 |
+
"eval_f1": 0.9110921381198841,
|
| 459 |
+
"eval_loss": 0.8131796717643738,
|
| 460 |
+
"eval_precision": 0.9102718845983578,
|
| 461 |
+
"eval_recall": 0.9174057649667405,
|
| 462 |
+
"eval_runtime": 8.5042,
|
| 463 |
+
"eval_samples_per_second": 424.259,
|
| 464 |
+
"eval_steps_per_second": 3.41,
|
| 465 |
+
"step": 446
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.41,
|
| 469 |
+
"learning_rate": 3.18748385528431e-05,
|
| 470 |
+
"loss": 0.6993,
|
| 471 |
+
"step": 455
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.98,
|
| 475 |
+
"eval_accuracy": 0.9165742793791575,
|
| 476 |
+
"eval_f1": 0.9118107776438924,
|
| 477 |
+
"eval_loss": 0.8081905841827393,
|
| 478 |
+
"eval_precision": 0.9099277181845643,
|
| 479 |
+
"eval_recall": 0.9165742793791575,
|
| 480 |
+
"eval_runtime": 8.4643,
|
| 481 |
+
"eval_samples_per_second": 426.259,
|
| 482 |
+
"eval_steps_per_second": 3.426,
|
| 483 |
+
"step": 467
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 22.02,
|
| 487 |
+
"learning_rate": 2.771270520756931e-05,
|
| 488 |
+
"loss": 0.699,
|
| 489 |
+
"step": 468
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 22.64,
|
| 493 |
+
"learning_rate": 2.3757342264479745e-05,
|
| 494 |
+
"loss": 0.695,
|
| 495 |
+
"step": 481
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 22.96,
|
| 499 |
+
"eval_accuracy": 0.9135254988913526,
|
| 500 |
+
"eval_f1": 0.9093429388548893,
|
| 501 |
+
"eval_loss": 0.8111734390258789,
|
| 502 |
+
"eval_precision": 0.9074999707107355,
|
| 503 |
+
"eval_recall": 0.9135254988913526,
|
| 504 |
+
"eval_runtime": 7.9698,
|
| 505 |
+
"eval_samples_per_second": 452.711,
|
| 506 |
+
"eval_steps_per_second": 3.639,
|
| 507 |
+
"step": 488
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.25,
|
| 511 |
+
"learning_rate": 2.0034707892818282e-05,
|
| 512 |
+
"loss": 0.696,
|
| 513 |
+
"step": 494
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 23.86,
|
| 517 |
+
"learning_rate": 1.6569232915860257e-05,
|
| 518 |
+
"loss": 0.6953,
|
| 519 |
+
"step": 507
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 24.0,
|
| 523 |
+
"eval_accuracy": 0.91990022172949,
|
| 524 |
+
"eval_f1": 0.916865936054669,
|
| 525 |
+
"eval_loss": 0.8013141751289368,
|
| 526 |
+
"eval_precision": 0.915740899601062,
|
| 527 |
+
"eval_recall": 0.91990022172949,
|
| 528 |
+
"eval_runtime": 8.377,
|
| 529 |
+
"eval_samples_per_second": 430.703,
|
| 530 |
+
"eval_steps_per_second": 3.462,
|
| 531 |
+
"step": 510
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 24.47,
|
| 535 |
+
"learning_rate": 1.3383660476840981e-05,
|
| 536 |
+
"loss": 0.6953,
|
| 537 |
+
"step": 520
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 24.99,
|
| 541 |
+
"eval_accuracy": 0.9207317073170732,
|
| 542 |
+
"eval_f1": 0.914589050094206,
|
| 543 |
+
"eval_loss": 0.8078990578651428,
|
| 544 |
+
"eval_precision": 0.9152464196196067,
|
| 545 |
+
"eval_recall": 0.9207317073170732,
|
| 546 |
+
"eval_runtime": 8.115,
|
| 547 |
+
"eval_samples_per_second": 444.608,
|
| 548 |
+
"eval_steps_per_second": 3.574,
|
| 549 |
+
"step": 531
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 25.08,
|
| 553 |
+
"learning_rate": 1.0498896780753623e-05,
|
| 554 |
+
"loss": 0.6945,
|
| 555 |
+
"step": 533
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 25.69,
|
| 559 |
+
"learning_rate": 7.933873891565259e-06,
|
| 560 |
+
"loss": 0.6922,
|
| 561 |
+
"step": 546
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 25.98,
|
| 565 |
+
"eval_accuracy": 0.9226718403547672,
|
| 566 |
+
"eval_f1": 0.9178570407241106,
|
| 567 |
+
"eval_loss": 0.7991681098937988,
|
| 568 |
+
"eval_precision": 0.9160698180928497,
|
| 569 |
+
"eval_recall": 0.9226718403547672,
|
| 570 |
+
"eval_runtime": 8.0279,
|
| 571 |
+
"eval_samples_per_second": 449.434,
|
| 572 |
+
"eval_steps_per_second": 3.612,
|
| 573 |
+
"step": 552
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 26.31,
|
| 577 |
+
"learning_rate": 5.705425485282367e-06,
|
| 578 |
+
"loss": 0.6915,
|
| 579 |
+
"step": 559
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 26.92,
|
| 583 |
+
"learning_rate": 3.828176374270756e-06,
|
| 584 |
+
"loss": 0.6891,
|
| 585 |
+
"step": 572
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 26.96,
|
| 589 |
+
"eval_accuracy": 0.9223946784922394,
|
| 590 |
+
"eval_f1": 0.9190093173009881,
|
| 591 |
+
"eval_loss": 0.8051531910896301,
|
| 592 |
+
"eval_precision": 0.9170832022797123,
|
| 593 |
+
"eval_recall": 0.9223946784922394,
|
| 594 |
+
"eval_runtime": 8.1305,
|
| 595 |
+
"eval_samples_per_second": 443.759,
|
| 596 |
+
"eval_steps_per_second": 3.567,
|
| 597 |
+
"step": 573
|
| 598 |
+
}
|
| 599 |
+
],
|
| 600 |
+
"logging_steps": 13,
|
| 601 |
+
"max_steps": 630,
|
| 602 |
+
"num_input_tokens_seen": 0,
|
| 603 |
+
"num_train_epochs": 30,
|
| 604 |
+
"save_steps": 500,
|
| 605 |
+
"total_flos": 0.0,
|
| 606 |
+
"train_batch_size": 128,
|
| 607 |
+
"trial_name": null,
|
| 608 |
+
"trial_params": {
|
| 609 |
+
"_wandb": {},
|
| 610 |
+
"assignments": {},
|
| 611 |
+
"label_smoothing_factor": 0.04380727559247777,
|
| 612 |
+
"learning_rate": 0.00011843848185666308,
|
| 613 |
+
"metric": "eval/loss",
|
| 614 |
+
"weight_decay": 0.04759846929286333
|
| 615 |
+
}
|
| 616 |
+
}
|
run-22pm9fz7/checkpoint-573/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd44ac72f55da97bd4c201bcd3d83cc4a8480c26354d61666839e3c3964bca85
|
| 3 |
+
size 4792
|
run-22pm9fz7/checkpoint-630/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:251b9dcae8e64bde930b0291bce3a3e77bdd4bd952300070a200d94c5aa5c255
|
| 3 |
+
size 198025308
|
run-22pm9fz7/checkpoint-630/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7719775f550654b470db266cb6c4656645d42c96525e65c36f922760fc1f0481
|
| 3 |
+
size 395900602
|
run-22pm9fz7/checkpoint-630/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bf0590ccc7857c323b9b2e426a89e450fa4acc7c473c28a6f6c37cc9f950c6c
|
| 3 |
+
size 14244
|
run-22pm9fz7/checkpoint-630/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b31486bf2978f7c303d9a41141bea2194c0b81eed86a868b8823cbc64031b3f4
|
| 3 |
+
size 1064
|
run-22pm9fz7/checkpoint-630/trainer_state.json
ADDED
|
@@ -0,0 +1,676 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9190093173009881,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-22pm9fz7/checkpoint-573",
|
| 4 |
+
"epoch": 29.647058823529413,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 630,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 1.2219843366163651e-05,
|
| 14 |
+
"loss": 1.486,
|
| 15 |
+
"step": 13
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8276053215077606,
|
| 20 |
+
"eval_f1": 0.7506333806665745,
|
| 21 |
+
"eval_loss": 1.1113407611846924,
|
| 22 |
+
"eval_precision": 0.6867607734554959,
|
| 23 |
+
"eval_recall": 0.8276053215077606,
|
| 24 |
+
"eval_runtime": 8.3733,
|
| 25 |
+
"eval_samples_per_second": 430.891,
|
| 26 |
+
"eval_steps_per_second": 3.463,
|
| 27 |
+
"step": 21
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.22,
|
| 31 |
+
"learning_rate": 2.4439686732327303e-05,
|
| 32 |
+
"loss": 1.1919,
|
| 33 |
+
"step": 26
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.84,
|
| 37 |
+
"learning_rate": 3.665953009849096e-05,
|
| 38 |
+
"loss": 0.9574,
|
| 39 |
+
"step": 39
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.98,
|
| 43 |
+
"eval_accuracy": 0.8592017738359202,
|
| 44 |
+
"eval_f1": 0.8158688229267518,
|
| 45 |
+
"eval_loss": 0.9284856915473938,
|
| 46 |
+
"eval_precision": 0.8413284596404325,
|
| 47 |
+
"eval_recall": 0.8592017738359202,
|
| 48 |
+
"eval_runtime": 8.4795,
|
| 49 |
+
"eval_samples_per_second": 425.497,
|
| 50 |
+
"eval_steps_per_second": 3.42,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.45,
|
| 55 |
+
"learning_rate": 4.8879373464654605e-05,
|
| 56 |
+
"loss": 0.8789,
|
| 57 |
+
"step": 52
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.96,
|
| 61 |
+
"eval_accuracy": 0.8968957871396895,
|
| 62 |
+
"eval_f1": 0.887994515834578,
|
| 63 |
+
"eval_loss": 0.8563220500946045,
|
| 64 |
+
"eval_precision": 0.888627325917696,
|
| 65 |
+
"eval_recall": 0.8968957871396895,
|
| 66 |
+
"eval_runtime": 8.648,
|
| 67 |
+
"eval_samples_per_second": 417.204,
|
| 68 |
+
"eval_steps_per_second": 3.353,
|
| 69 |
+
"step": 63
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.06,
|
| 73 |
+
"learning_rate": 6.109921683081827e-05,
|
| 74 |
+
"loss": 0.8471,
|
| 75 |
+
"step": 65
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.67,
|
| 79 |
+
"learning_rate": 7.331906019698191e-05,
|
| 80 |
+
"loss": 0.8107,
|
| 81 |
+
"step": 78
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.0,
|
| 85 |
+
"eval_accuracy": 0.9121396895787139,
|
| 86 |
+
"eval_f1": 0.9058964979973173,
|
| 87 |
+
"eval_loss": 0.8172363638877869,
|
| 88 |
+
"eval_precision": 0.9027154396135877,
|
| 89 |
+
"eval_recall": 0.9121396895787139,
|
| 90 |
+
"eval_runtime": 8.0085,
|
| 91 |
+
"eval_samples_per_second": 450.52,
|
| 92 |
+
"eval_steps_per_second": 3.621,
|
| 93 |
+
"step": 85
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.28,
|
| 97 |
+
"learning_rate": 8.553890356314556e-05,
|
| 98 |
+
"loss": 0.8015,
|
| 99 |
+
"step": 91
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.89,
|
| 103 |
+
"learning_rate": 9.775874692930921e-05,
|
| 104 |
+
"loss": 0.7861,
|
| 105 |
+
"step": 104
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.99,
|
| 109 |
+
"eval_accuracy": 0.8849778270509978,
|
| 110 |
+
"eval_f1": 0.8865037130264197,
|
| 111 |
+
"eval_loss": 0.8436875939369202,
|
| 112 |
+
"eval_precision": 0.8932393306490872,
|
| 113 |
+
"eval_recall": 0.8849778270509978,
|
| 114 |
+
"eval_runtime": 8.5752,
|
| 115 |
+
"eval_samples_per_second": 420.749,
|
| 116 |
+
"eval_steps_per_second": 3.382,
|
| 117 |
+
"step": 106
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.51,
|
| 121 |
+
"learning_rate": 0.00010997859029547287,
|
| 122 |
+
"loss": 0.7684,
|
| 123 |
+
"step": 117
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 5.98,
|
| 127 |
+
"eval_accuracy": 0.9124168514412417,
|
| 128 |
+
"eval_f1": 0.9028803793279178,
|
| 129 |
+
"eval_loss": 0.8081041574478149,
|
| 130 |
+
"eval_precision": 0.903857437506207,
|
| 131 |
+
"eval_recall": 0.9124168514412417,
|
| 132 |
+
"eval_runtime": 8.3423,
|
| 133 |
+
"eval_samples_per_second": 432.495,
|
| 134 |
+
"eval_steps_per_second": 3.476,
|
| 135 |
+
"step": 127
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.12,
|
| 139 |
+
"learning_rate": 0.00011842007545068455,
|
| 140 |
+
"loss": 0.7711,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.73,
|
| 145 |
+
"learning_rate": 0.00011810630992573294,
|
| 146 |
+
"loss": 0.7634,
|
| 147 |
+
"step": 143
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.96,
|
| 151 |
+
"eval_accuracy": 0.9149113082039911,
|
| 152 |
+
"eval_f1": 0.9067032873213865,
|
| 153 |
+
"eval_loss": 0.8178200125694275,
|
| 154 |
+
"eval_precision": 0.9055547260013138,
|
| 155 |
+
"eval_recall": 0.9149113082039911,
|
| 156 |
+
"eval_runtime": 8.0759,
|
| 157 |
+
"eval_samples_per_second": 446.762,
|
| 158 |
+
"eval_steps_per_second": 3.591,
|
| 159 |
+
"step": 148
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 7.34,
|
| 163 |
+
"learning_rate": 0.00011740608163483467,
|
| 164 |
+
"loss": 0.7565,
|
| 165 |
+
"step": 156
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 7.95,
|
| 169 |
+
"learning_rate": 0.00011632398602087223,
|
| 170 |
+
"loss": 0.7531,
|
| 171 |
+
"step": 169
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 8.0,
|
| 175 |
+
"eval_accuracy": 0.8070953436807096,
|
| 176 |
+
"eval_f1": 0.8307447955720016,
|
| 177 |
+
"eval_loss": 0.9529986381530762,
|
| 178 |
+
"eval_precision": 0.8811216651383346,
|
| 179 |
+
"eval_recall": 0.8070953436807096,
|
| 180 |
+
"eval_runtime": 8.137,
|
| 181 |
+
"eval_samples_per_second": 443.407,
|
| 182 |
+
"eval_steps_per_second": 3.564,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 8.56,
|
| 187 |
+
"learning_rate": 0.00011486712463722754,
|
| 188 |
+
"loss": 0.746,
|
| 189 |
+
"step": 182
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.99,
|
| 193 |
+
"eval_accuracy": 0.9165742793791575,
|
| 194 |
+
"eval_f1": 0.9088707382436096,
|
| 195 |
+
"eval_loss": 0.8120781779289246,
|
| 196 |
+
"eval_precision": 0.9060999886720389,
|
| 197 |
+
"eval_recall": 0.9165742793791575,
|
| 198 |
+
"eval_runtime": 8.4467,
|
| 199 |
+
"eval_samples_per_second": 427.148,
|
| 200 |
+
"eval_steps_per_second": 3.433,
|
| 201 |
+
"step": 191
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 9.18,
|
| 205 |
+
"learning_rate": 0.0001130450585418631,
|
| 206 |
+
"loss": 0.7441,
|
| 207 |
+
"step": 195
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.79,
|
| 211 |
+
"learning_rate": 0.00011086974555022023,
|
| 212 |
+
"loss": 0.7366,
|
| 213 |
+
"step": 208
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.98,
|
| 217 |
+
"eval_accuracy": 0.8991130820399114,
|
| 218 |
+
"eval_f1": 0.8990952855541333,
|
| 219 |
+
"eval_loss": 0.824906587600708,
|
| 220 |
+
"eval_precision": 0.9061946214416738,
|
| 221 |
+
"eval_recall": 0.8991130820399114,
|
| 222 |
+
"eval_runtime": 8.27,
|
| 223 |
+
"eval_samples_per_second": 436.275,
|
| 224 |
+
"eval_steps_per_second": 3.507,
|
| 225 |
+
"step": 212
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.4,
|
| 229 |
+
"learning_rate": 0.00010835546175873,
|
| 230 |
+
"loss": 0.7323,
|
| 231 |
+
"step": 221
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.96,
|
| 235 |
+
"eval_accuracy": 0.9002217294900222,
|
| 236 |
+
"eval_f1": 0.9012399347617073,
|
| 237 |
+
"eval_loss": 0.8290796279907227,
|
| 238 |
+
"eval_precision": 0.9052326255514389,
|
| 239 |
+
"eval_recall": 0.9002217294900222,
|
| 240 |
+
"eval_runtime": 8.3024,
|
| 241 |
+
"eval_samples_per_second": 434.573,
|
| 242 |
+
"eval_steps_per_second": 3.493,
|
| 243 |
+
"step": 233
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 11.01,
|
| 247 |
+
"learning_rate": 0.00010551870785396043,
|
| 248 |
+
"loss": 0.7313,
|
| 249 |
+
"step": 234
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 11.62,
|
| 253 |
+
"learning_rate": 0.00010237810082227219,
|
| 254 |
+
"loss": 0.725,
|
| 255 |
+
"step": 247
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 12.0,
|
| 259 |
+
"eval_accuracy": 0.9121396895787139,
|
| 260 |
+
"eval_f1": 0.9014249052263176,
|
| 261 |
+
"eval_loss": 0.8157982230186462,
|
| 262 |
+
"eval_precision": 0.9081945289870674,
|
| 263 |
+
"eval_recall": 0.9121396895787139,
|
| 264 |
+
"eval_runtime": 8.2951,
|
| 265 |
+
"eval_samples_per_second": 434.956,
|
| 266 |
+
"eval_steps_per_second": 3.496,
|
| 267 |
+
"step": 255
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 12.24,
|
| 271 |
+
"learning_rate": 9.895425177066865e-05,
|
| 272 |
+
"loss": 0.7242,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.85,
|
| 277 |
+
"learning_rate": 9.526963066067437e-05,
|
| 278 |
+
"loss": 0.7188,
|
| 279 |
+
"step": 273
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 12.99,
|
| 283 |
+
"eval_accuracy": 0.9182372505543237,
|
| 284 |
+
"eval_f1": 0.9146196519587654,
|
| 285 |
+
"eval_loss": 0.8068662285804749,
|
| 286 |
+
"eval_precision": 0.9120081137034548,
|
| 287 |
+
"eval_recall": 0.9182372505543237,
|
| 288 |
+
"eval_runtime": 8.2252,
|
| 289 |
+
"eval_samples_per_second": 438.654,
|
| 290 |
+
"eval_steps_per_second": 3.526,
|
| 291 |
+
"step": 276
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 13.46,
|
| 295 |
+
"learning_rate": 9.134841884296409e-05,
|
| 296 |
+
"loss": 0.7204,
|
| 297 |
+
"step": 286
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.98,
|
| 301 |
+
"eval_accuracy": 0.9168514412416852,
|
| 302 |
+
"eval_f1": 0.9092891599955425,
|
| 303 |
+
"eval_loss": 0.8142066597938538,
|
| 304 |
+
"eval_precision": 0.9095107691249883,
|
| 305 |
+
"eval_recall": 0.9168514412416852,
|
| 306 |
+
"eval_runtime": 8.1951,
|
| 307 |
+
"eval_samples_per_second": 440.263,
|
| 308 |
+
"eval_steps_per_second": 3.539,
|
| 309 |
+
"step": 297
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 14.07,
|
| 313 |
+
"learning_rate": 8.721635036052442e-05,
|
| 314 |
+
"loss": 0.7152,
|
| 315 |
+
"step": 299
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 14.68,
|
| 319 |
+
"learning_rate": 8.290054306184049e-05,
|
| 320 |
+
"loss": 0.7135,
|
| 321 |
+
"step": 312
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 14.96,
|
| 325 |
+
"eval_accuracy": 0.9174057649667405,
|
| 326 |
+
"eval_f1": 0.9103487881551395,
|
| 327 |
+
"eval_loss": 0.8043306469917297,
|
| 328 |
+
"eval_precision": 0.9097246610377273,
|
| 329 |
+
"eval_recall": 0.9174057649667405,
|
| 330 |
+
"eval_runtime": 8.4787,
|
| 331 |
+
"eval_samples_per_second": 425.535,
|
| 332 |
+
"eval_steps_per_second": 3.42,
|
| 333 |
+
"step": 318
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 15.29,
|
| 337 |
+
"learning_rate": 7.842932063247419e-05,
|
| 338 |
+
"loss": 0.7131,
|
| 339 |
+
"step": 325
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.91,
|
| 343 |
+
"learning_rate": 7.383202671300115e-05,
|
| 344 |
+
"loss": 0.7123,
|
| 345 |
+
"step": 338
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 16.0,
|
| 349 |
+
"eval_accuracy": 0.9204545454545454,
|
| 350 |
+
"eval_f1": 0.9125587073196101,
|
| 351 |
+
"eval_loss": 0.80075603723526,
|
| 352 |
+
"eval_precision": 0.9124672143244127,
|
| 353 |
+
"eval_recall": 0.9204545454545454,
|
| 354 |
+
"eval_runtime": 8.2538,
|
| 355 |
+
"eval_samples_per_second": 437.13,
|
| 356 |
+
"eval_steps_per_second": 3.514,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 16.52,
|
| 361 |
+
"learning_rate": 6.913883232320964e-05,
|
| 362 |
+
"loss": 0.7087,
|
| 363 |
+
"step": 351
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 16.99,
|
| 367 |
+
"eval_accuracy": 0.9024390243902439,
|
| 368 |
+
"eval_f1": 0.9037420660128592,
|
| 369 |
+
"eval_loss": 0.82823246717453,
|
| 370 |
+
"eval_precision": 0.9070644554543488,
|
| 371 |
+
"eval_recall": 0.9024390243902439,
|
| 372 |
+
"eval_runtime": 7.9823,
|
| 373 |
+
"eval_samples_per_second": 452.002,
|
| 374 |
+
"eval_steps_per_second": 3.633,
|
| 375 |
+
"step": 361
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 17.13,
|
| 379 |
+
"learning_rate": 6.438053785639281e-05,
|
| 380 |
+
"loss": 0.708,
|
| 381 |
+
"step": 364
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.74,
|
| 385 |
+
"learning_rate": 5.958837094320274e-05,
|
| 386 |
+
"loss": 0.7058,
|
| 387 |
+
"step": 377
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 17.98,
|
| 391 |
+
"eval_accuracy": 0.9221175166297118,
|
| 392 |
+
"eval_f1": 0.918139928004074,
|
| 393 |
+
"eval_loss": 0.8006211519241333,
|
| 394 |
+
"eval_precision": 0.9155745392875521,
|
| 395 |
+
"eval_recall": 0.9221175166297118,
|
| 396 |
+
"eval_runtime": 8.0911,
|
| 397 |
+
"eval_samples_per_second": 445.922,
|
| 398 |
+
"eval_steps_per_second": 3.584,
|
| 399 |
+
"step": 382
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 18.35,
|
| 403 |
+
"learning_rate": 5.479378151164032e-05,
|
| 404 |
+
"loss": 0.7061,
|
| 405 |
+
"step": 390
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.96,
|
| 409 |
+
"learning_rate": 5.0028235388156865e-05,
|
| 410 |
+
"loss": 0.7007,
|
| 411 |
+
"step": 403
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 18.96,
|
| 415 |
+
"eval_accuracy": 0.9162971175166297,
|
| 416 |
+
"eval_f1": 0.911467714185253,
|
| 417 |
+
"eval_loss": 0.8088358640670776,
|
| 418 |
+
"eval_precision": 0.9095502759728672,
|
| 419 |
+
"eval_recall": 0.9162971175166297,
|
| 420 |
+
"eval_runtime": 8.3048,
|
| 421 |
+
"eval_samples_per_second": 434.446,
|
| 422 |
+
"eval_steps_per_second": 3.492,
|
| 423 |
+
"step": 403
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.58,
|
| 427 |
+
"learning_rate": 4.532300779441795e-05,
|
| 428 |
+
"loss": 0.7071,
|
| 429 |
+
"step": 416
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 20.0,
|
| 433 |
+
"eval_accuracy": 0.9174057649667405,
|
| 434 |
+
"eval_f1": 0.9102457116550721,
|
| 435 |
+
"eval_loss": 0.8067628741264343,
|
| 436 |
+
"eval_precision": 0.9095707265020937,
|
| 437 |
+
"eval_recall": 0.9174057649667405,
|
| 438 |
+
"eval_runtime": 8.2606,
|
| 439 |
+
"eval_samples_per_second": 436.772,
|
| 440 |
+
"eval_steps_per_second": 3.511,
|
| 441 |
+
"step": 425
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 20.19,
|
| 445 |
+
"learning_rate": 4.070897809496389e-05,
|
| 446 |
+
"loss": 0.699,
|
| 447 |
+
"step": 429
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 20.8,
|
| 451 |
+
"learning_rate": 3.621642714279302e-05,
|
| 452 |
+
"loss": 0.6963,
|
| 453 |
+
"step": 442
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 20.99,
|
| 457 |
+
"eval_accuracy": 0.9174057649667405,
|
| 458 |
+
"eval_f1": 0.9110921381198841,
|
| 459 |
+
"eval_loss": 0.8131796717643738,
|
| 460 |
+
"eval_precision": 0.9102718845983578,
|
| 461 |
+
"eval_recall": 0.9174057649667405,
|
| 462 |
+
"eval_runtime": 8.5042,
|
| 463 |
+
"eval_samples_per_second": 424.259,
|
| 464 |
+
"eval_steps_per_second": 3.41,
|
| 465 |
+
"step": 446
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.41,
|
| 469 |
+
"learning_rate": 3.18748385528431e-05,
|
| 470 |
+
"loss": 0.6993,
|
| 471 |
+
"step": 455
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.98,
|
| 475 |
+
"eval_accuracy": 0.9165742793791575,
|
| 476 |
+
"eval_f1": 0.9118107776438924,
|
| 477 |
+
"eval_loss": 0.8081905841827393,
|
| 478 |
+
"eval_precision": 0.9099277181845643,
|
| 479 |
+
"eval_recall": 0.9165742793791575,
|
| 480 |
+
"eval_runtime": 8.4643,
|
| 481 |
+
"eval_samples_per_second": 426.259,
|
| 482 |
+
"eval_steps_per_second": 3.426,
|
| 483 |
+
"step": 467
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 22.02,
|
| 487 |
+
"learning_rate": 2.771270520756931e-05,
|
| 488 |
+
"loss": 0.699,
|
| 489 |
+
"step": 468
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 22.64,
|
| 493 |
+
"learning_rate": 2.3757342264479745e-05,
|
| 494 |
+
"loss": 0.695,
|
| 495 |
+
"step": 481
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 22.96,
|
| 499 |
+
"eval_accuracy": 0.9135254988913526,
|
| 500 |
+
"eval_f1": 0.9093429388548893,
|
| 501 |
+
"eval_loss": 0.8111734390258789,
|
| 502 |
+
"eval_precision": 0.9074999707107355,
|
| 503 |
+
"eval_recall": 0.9135254988913526,
|
| 504 |
+
"eval_runtime": 7.9698,
|
| 505 |
+
"eval_samples_per_second": 452.711,
|
| 506 |
+
"eval_steps_per_second": 3.639,
|
| 507 |
+
"step": 488
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.25,
|
| 511 |
+
"learning_rate": 2.0034707892818282e-05,
|
| 512 |
+
"loss": 0.696,
|
| 513 |
+
"step": 494
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 23.86,
|
| 517 |
+
"learning_rate": 1.6569232915860257e-05,
|
| 518 |
+
"loss": 0.6953,
|
| 519 |
+
"step": 507
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 24.0,
|
| 523 |
+
"eval_accuracy": 0.91990022172949,
|
| 524 |
+
"eval_f1": 0.916865936054669,
|
| 525 |
+
"eval_loss": 0.8013141751289368,
|
| 526 |
+
"eval_precision": 0.915740899601062,
|
| 527 |
+
"eval_recall": 0.91990022172949,
|
| 528 |
+
"eval_runtime": 8.377,
|
| 529 |
+
"eval_samples_per_second": 430.703,
|
| 530 |
+
"eval_steps_per_second": 3.462,
|
| 531 |
+
"step": 510
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 24.47,
|
| 535 |
+
"learning_rate": 1.3383660476840981e-05,
|
| 536 |
+
"loss": 0.6953,
|
| 537 |
+
"step": 520
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 24.99,
|
| 541 |
+
"eval_accuracy": 0.9207317073170732,
|
| 542 |
+
"eval_f1": 0.914589050094206,
|
| 543 |
+
"eval_loss": 0.8078990578651428,
|
| 544 |
+
"eval_precision": 0.9152464196196067,
|
| 545 |
+
"eval_recall": 0.9207317073170732,
|
| 546 |
+
"eval_runtime": 8.115,
|
| 547 |
+
"eval_samples_per_second": 444.608,
|
| 548 |
+
"eval_steps_per_second": 3.574,
|
| 549 |
+
"step": 531
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 25.08,
|
| 553 |
+
"learning_rate": 1.0498896780753623e-05,
|
| 554 |
+
"loss": 0.6945,
|
| 555 |
+
"step": 533
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 25.69,
|
| 559 |
+
"learning_rate": 7.933873891565259e-06,
|
| 560 |
+
"loss": 0.6922,
|
| 561 |
+
"step": 546
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 25.98,
|
| 565 |
+
"eval_accuracy": 0.9226718403547672,
|
| 566 |
+
"eval_f1": 0.9178570407241106,
|
| 567 |
+
"eval_loss": 0.7991681098937988,
|
| 568 |
+
"eval_precision": 0.9160698180928497,
|
| 569 |
+
"eval_recall": 0.9226718403547672,
|
| 570 |
+
"eval_runtime": 8.0279,
|
| 571 |
+
"eval_samples_per_second": 449.434,
|
| 572 |
+
"eval_steps_per_second": 3.612,
|
| 573 |
+
"step": 552
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 26.31,
|
| 577 |
+
"learning_rate": 5.705425485282367e-06,
|
| 578 |
+
"loss": 0.6915,
|
| 579 |
+
"step": 559
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 26.92,
|
| 583 |
+
"learning_rate": 3.828176374270756e-06,
|
| 584 |
+
"loss": 0.6891,
|
| 585 |
+
"step": 572
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 26.96,
|
| 589 |
+
"eval_accuracy": 0.9223946784922394,
|
| 590 |
+
"eval_f1": 0.9190093173009881,
|
| 591 |
+
"eval_loss": 0.8051531910896301,
|
| 592 |
+
"eval_precision": 0.9170832022797123,
|
| 593 |
+
"eval_recall": 0.9223946784922394,
|
| 594 |
+
"eval_runtime": 8.1305,
|
| 595 |
+
"eval_samples_per_second": 443.759,
|
| 596 |
+
"eval_steps_per_second": 3.567,
|
| 597 |
+
"step": 573
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 27.53,
|
| 601 |
+
"learning_rate": 2.3144465278575693e-06,
|
| 602 |
+
"loss": 0.6926,
|
| 603 |
+
"step": 585
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 28.0,
|
| 607 |
+
"eval_accuracy": 0.9149113082039911,
|
| 608 |
+
"eval_f1": 0.9109826412632926,
|
| 609 |
+
"eval_loss": 0.8063508868217468,
|
| 610 |
+
"eval_precision": 0.9094636475940526,
|
| 611 |
+
"eval_recall": 0.9149113082039911,
|
| 612 |
+
"eval_runtime": 8.2034,
|
| 613 |
+
"eval_samples_per_second": 439.816,
|
| 614 |
+
"eval_steps_per_second": 3.535,
|
| 615 |
+
"step": 595
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 28.14,
|
| 619 |
+
"learning_rate": 1.1741702191065044e-06,
|
| 620 |
+
"loss": 0.6939,
|
| 621 |
+
"step": 598
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 28.75,
|
| 625 |
+
"learning_rate": 4.1483082838826053e-07,
|
| 626 |
+
"loss": 0.6932,
|
| 627 |
+
"step": 611
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 28.99,
|
| 631 |
+
"eval_accuracy": 0.9226718403547672,
|
| 632 |
+
"eval_f1": 0.9176131090408187,
|
| 633 |
+
"eval_loss": 0.8002130389213562,
|
| 634 |
+
"eval_precision": 0.9141152774640595,
|
| 635 |
+
"eval_recall": 0.9226718403547672,
|
| 636 |
+
"eval_runtime": 8.3732,
|
| 637 |
+
"eval_samples_per_second": 430.898,
|
| 638 |
+
"eval_steps_per_second": 3.463,
|
| 639 |
+
"step": 616
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 29.36,
|
| 643 |
+
"learning_rate": 4.14117316158514e-08,
|
| 644 |
+
"loss": 0.695,
|
| 645 |
+
"step": 624
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 29.65,
|
| 649 |
+
"eval_accuracy": 0.9223946784922394,
|
| 650 |
+
"eval_f1": 0.9182832502545885,
|
| 651 |
+
"eval_loss": 0.8041395545005798,
|
| 652 |
+
"eval_precision": 0.9178198224542571,
|
| 653 |
+
"eval_recall": 0.9223946784922394,
|
| 654 |
+
"eval_runtime": 8.142,
|
| 655 |
+
"eval_samples_per_second": 443.134,
|
| 656 |
+
"eval_steps_per_second": 3.562,
|
| 657 |
+
"step": 630
|
| 658 |
+
}
|
| 659 |
+
],
|
| 660 |
+
"logging_steps": 13,
|
| 661 |
+
"max_steps": 630,
|
| 662 |
+
"num_input_tokens_seen": 0,
|
| 663 |
+
"num_train_epochs": 30,
|
| 664 |
+
"save_steps": 500,
|
| 665 |
+
"total_flos": 0.0,
|
| 666 |
+
"train_batch_size": 128,
|
| 667 |
+
"trial_name": null,
|
| 668 |
+
"trial_params": {
|
| 669 |
+
"_wandb": {},
|
| 670 |
+
"assignments": {},
|
| 671 |
+
"label_smoothing_factor": 0.04380727559247777,
|
| 672 |
+
"learning_rate": 0.00011843848185666308,
|
| 673 |
+
"metric": "eval/loss",
|
| 674 |
+
"weight_decay": 0.04759846929286333
|
| 675 |
+
}
|
| 676 |
+
}
|
run-22pm9fz7/checkpoint-630/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd44ac72f55da97bd4c201bcd3d83cc4a8480c26354d61666839e3c3964bca85
|
| 3 |
+
size 4792
|
run-2787ye3h/checkpoint-1147/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:756a7990e7702b773466531078bb3fe9016548435c2876cd65cae0c9ab2236cb
|
| 3 |
+
size 198025308
|
run-2787ye3h/checkpoint-1147/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb84fa967a9ded82440d1c6f3316c7c9fc0d7c5bfbc68c4202ac2de0ff056359
|
| 3 |
+
size 395900602
|
run-2787ye3h/checkpoint-1147/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf2d43d63184b1920f250efdd6f38efa027691f238090c0a0b0f43317419a2de
|
| 3 |
+
size 14244
|
run-2787ye3h/checkpoint-1147/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a440e59de37db302633fa345da2c0920b23c9b167bc8e7ac5218b25bb8dc0d7e
|
| 3 |
+
size 1064
|
run-2787ye3h/checkpoint-1147/trainer_state.json
ADDED
|
@@ -0,0 +1,534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9273835920177383,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-2787ye3h/checkpoint-1147",
|
| 4 |
+
"epoch": 26.988235294117647,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1147,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 3.626442337305279e-05,
|
| 14 |
+
"loss": 1.293,
|
| 15 |
+
"step": 26
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8755543237250555,
|
| 20 |
+
"eval_loss": 0.9349600672721863,
|
| 21 |
+
"eval_runtime": 6.9886,
|
| 22 |
+
"eval_samples_per_second": 516.266,
|
| 23 |
+
"eval_steps_per_second": 8.156,
|
| 24 |
+
"step": 42
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.22,
|
| 28 |
+
"learning_rate": 7.252884674610559e-05,
|
| 29 |
+
"loss": 0.9064,
|
| 30 |
+
"step": 52
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.84,
|
| 34 |
+
"learning_rate": 0.00010879327011915836,
|
| 35 |
+
"loss": 0.8316,
|
| 36 |
+
"step": 78
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.914079822616408,
|
| 41 |
+
"eval_loss": 0.8049944639205933,
|
| 42 |
+
"eval_runtime": 6.9141,
|
| 43 |
+
"eval_samples_per_second": 521.829,
|
| 44 |
+
"eval_steps_per_second": 8.244,
|
| 45 |
+
"step": 85
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.45,
|
| 49 |
+
"learning_rate": 0.00014505769349221117,
|
| 50 |
+
"loss": 0.7997,
|
| 51 |
+
"step": 104
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.99,
|
| 55 |
+
"eval_accuracy": 0.9126940133037694,
|
| 56 |
+
"eval_loss": 0.8133141398429871,
|
| 57 |
+
"eval_runtime": 6.6693,
|
| 58 |
+
"eval_samples_per_second": 540.987,
|
| 59 |
+
"eval_steps_per_second": 8.547,
|
| 60 |
+
"step": 127
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.06,
|
| 64 |
+
"learning_rate": 0.00018132211686526395,
|
| 65 |
+
"loss": 0.7971,
|
| 66 |
+
"step": 130
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.67,
|
| 70 |
+
"learning_rate": 0.00018108536618532123,
|
| 71 |
+
"loss": 0.7806,
|
| 72 |
+
"step": 156
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.9182372505543237,
|
| 77 |
+
"eval_loss": 0.8043554425239563,
|
| 78 |
+
"eval_runtime": 6.9887,
|
| 79 |
+
"eval_samples_per_second": 516.26,
|
| 80 |
+
"eval_steps_per_second": 8.156,
|
| 81 |
+
"step": 170
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.28,
|
| 85 |
+
"learning_rate": 0.00018037635063854584,
|
| 86 |
+
"loss": 0.7788,
|
| 87 |
+
"step": 182
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.89,
|
| 91 |
+
"learning_rate": 0.00017919877324618395,
|
| 92 |
+
"loss": 0.764,
|
| 93 |
+
"step": 208
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.99,
|
| 97 |
+
"eval_accuracy": 0.917960088691796,
|
| 98 |
+
"eval_loss": 0.7976019382476807,
|
| 99 |
+
"eval_runtime": 6.7358,
|
| 100 |
+
"eval_samples_per_second": 535.642,
|
| 101 |
+
"eval_steps_per_second": 8.462,
|
| 102 |
+
"step": 212
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.51,
|
| 106 |
+
"learning_rate": 0.00017755878421766717,
|
| 107 |
+
"loss": 0.7658,
|
| 108 |
+
"step": 234
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.9016075388026608,
|
| 113 |
+
"eval_loss": 0.8304137587547302,
|
| 114 |
+
"eval_runtime": 6.8918,
|
| 115 |
+
"eval_samples_per_second": 523.522,
|
| 116 |
+
"eval_steps_per_second": 8.271,
|
| 117 |
+
"step": 255
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.12,
|
| 121 |
+
"learning_rate": 0.00017546494882951695,
|
| 122 |
+
"loss": 0.751,
|
| 123 |
+
"step": 260
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.73,
|
| 127 |
+
"learning_rate": 0.00017292820269092213,
|
| 128 |
+
"loss": 0.7533,
|
| 129 |
+
"step": 286
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.99,
|
| 133 |
+
"eval_accuracy": 0.9049334811529933,
|
| 134 |
+
"eval_loss": 0.8278865218162537,
|
| 135 |
+
"eval_runtime": 6.9038,
|
| 136 |
+
"eval_samples_per_second": 522.607,
|
| 137 |
+
"eval_steps_per_second": 8.256,
|
| 138 |
+
"step": 297
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 7.34,
|
| 142 |
+
"learning_rate": 0.00016996179462962718,
|
| 143 |
+
"loss": 0.747,
|
| 144 |
+
"step": 312
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.95,
|
| 148 |
+
"learning_rate": 0.00016658121749642477,
|
| 149 |
+
"loss": 0.7294,
|
| 150 |
+
"step": 338
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.9054878048780488,
|
| 155 |
+
"eval_loss": 0.8298162817955017,
|
| 156 |
+
"eval_runtime": 6.8854,
|
| 157 |
+
"eval_samples_per_second": 524.008,
|
| 158 |
+
"eval_steps_per_second": 8.278,
|
| 159 |
+
"step": 340
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.56,
|
| 163 |
+
"learning_rate": 0.0001628041272496441,
|
| 164 |
+
"loss": 0.7325,
|
| 165 |
+
"step": 364
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.99,
|
| 169 |
+
"eval_accuracy": 0.9174057649667405,
|
| 170 |
+
"eval_loss": 0.8046008944511414,
|
| 171 |
+
"eval_runtime": 6.8095,
|
| 172 |
+
"eval_samples_per_second": 529.85,
|
| 173 |
+
"eval_steps_per_second": 8.371,
|
| 174 |
+
"step": 382
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.18,
|
| 178 |
+
"learning_rate": 0.0001586502507422381,
|
| 179 |
+
"loss": 0.737,
|
| 180 |
+
"step": 390
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.79,
|
| 184 |
+
"learning_rate": 0.0001541412826930757,
|
| 185 |
+
"loss": 0.7235,
|
| 186 |
+
"step": 416
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_accuracy": 0.917960088691796,
|
| 191 |
+
"eval_loss": 0.8011636734008789,
|
| 192 |
+
"eval_runtime": 7.0572,
|
| 193 |
+
"eval_samples_per_second": 511.252,
|
| 194 |
+
"eval_steps_per_second": 8.077,
|
| 195 |
+
"step": 425
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.4,
|
| 199 |
+
"learning_rate": 0.00014930077238053366,
|
| 200 |
+
"loss": 0.7212,
|
| 201 |
+
"step": 442
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.99,
|
| 205 |
+
"eval_accuracy": 0.9154656319290465,
|
| 206 |
+
"eval_loss": 0.8091404438018799,
|
| 207 |
+
"eval_runtime": 6.6144,
|
| 208 |
+
"eval_samples_per_second": 545.478,
|
| 209 |
+
"eval_steps_per_second": 8.618,
|
| 210 |
+
"step": 467
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.01,
|
| 214 |
+
"learning_rate": 0.00014415400065016071,
|
| 215 |
+
"loss": 0.7204,
|
| 216 |
+
"step": 468
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.62,
|
| 220 |
+
"learning_rate": 0.00013872784787877452,
|
| 221 |
+
"loss": 0.7154,
|
| 222 |
+
"step": 494
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_accuracy": 0.8747228381374723,
|
| 227 |
+
"eval_loss": 0.8664525747299194,
|
| 228 |
+
"eval_runtime": 6.7378,
|
| 229 |
+
"eval_samples_per_second": 535.484,
|
| 230 |
+
"eval_steps_per_second": 8.46,
|
| 231 |
+
"step": 510
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.24,
|
| 235 |
+
"learning_rate": 0.00013305065358458295,
|
| 236 |
+
"loss": 0.7148,
|
| 237 |
+
"step": 520
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.85,
|
| 241 |
+
"learning_rate": 0.00012715206841655379,
|
| 242 |
+
"loss": 0.7122,
|
| 243 |
+
"step": 546
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.99,
|
| 247 |
+
"eval_accuracy": 0.9154656319290465,
|
| 248 |
+
"eval_loss": 0.8063619136810303,
|
| 249 |
+
"eval_runtime": 6.798,
|
| 250 |
+
"eval_samples_per_second": 530.746,
|
| 251 |
+
"eval_steps_per_second": 8.385,
|
| 252 |
+
"step": 552
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.46,
|
| 256 |
+
"learning_rate": 0.00012106289929605711,
|
| 257 |
+
"loss": 0.7096,
|
| 258 |
+
"step": 572
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 14.0,
|
| 262 |
+
"eval_accuracy": 0.9162971175166297,
|
| 263 |
+
"eval_loss": 0.8059455752372742,
|
| 264 |
+
"eval_runtime": 6.7495,
|
| 265 |
+
"eval_samples_per_second": 534.558,
|
| 266 |
+
"eval_steps_per_second": 8.445,
|
| 267 |
+
"step": 595
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 14.07,
|
| 271 |
+
"learning_rate": 0.00011481494851956916,
|
| 272 |
+
"loss": 0.7157,
|
| 273 |
+
"step": 598
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 14.68,
|
| 277 |
+
"learning_rate": 0.0001084408476627666,
|
| 278 |
+
"loss": 0.7021,
|
| 279 |
+
"step": 624
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.99,
|
| 283 |
+
"eval_accuracy": 0.9212860310421286,
|
| 284 |
+
"eval_loss": 0.8017489314079285,
|
| 285 |
+
"eval_runtime": 6.9058,
|
| 286 |
+
"eval_samples_per_second": 522.457,
|
| 287 |
+
"eval_steps_per_second": 8.254,
|
| 288 |
+
"step": 637
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 15.29,
|
| 292 |
+
"learning_rate": 0.0001019738871534904,
|
| 293 |
+
"loss": 0.7021,
|
| 294 |
+
"step": 650
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.91,
|
| 298 |
+
"learning_rate": 9.544784240368045e-05,
|
| 299 |
+
"loss": 0.7002,
|
| 300 |
+
"step": 676
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.0,
|
| 304 |
+
"eval_accuracy": 0.9157427937915743,
|
| 305 |
+
"eval_loss": 0.816520631313324,
|
| 306 |
+
"eval_runtime": 6.8,
|
| 307 |
+
"eval_samples_per_second": 530.585,
|
| 308 |
+
"eval_steps_per_second": 8.382,
|
| 309 |
+
"step": 680
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.52,
|
| 313 |
+
"learning_rate": 8.889679740835216e-05,
|
| 314 |
+
"loss": 0.705,
|
| 315 |
+
"step": 702
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 16.99,
|
| 319 |
+
"eval_accuracy": 0.9196230598669624,
|
| 320 |
+
"eval_loss": 0.8022974133491516,
|
| 321 |
+
"eval_runtime": 6.9057,
|
| 322 |
+
"eval_samples_per_second": 522.468,
|
| 323 |
+
"eval_steps_per_second": 8.254,
|
| 324 |
+
"step": 722
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.13,
|
| 328 |
+
"learning_rate": 8.235496673291634e-05,
|
| 329 |
+
"loss": 0.7031,
|
| 330 |
+
"step": 728
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.74,
|
| 334 |
+
"learning_rate": 7.585651681856075e-05,
|
| 335 |
+
"loss": 0.6987,
|
| 336 |
+
"step": 754
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 18.0,
|
| 340 |
+
"eval_accuracy": 0.9154656319290465,
|
| 341 |
+
"eval_loss": 0.8067501783370972,
|
| 342 |
+
"eval_runtime": 6.7889,
|
| 343 |
+
"eval_samples_per_second": 531.457,
|
| 344 |
+
"eval_steps_per_second": 8.396,
|
| 345 |
+
"step": 765
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 18.35,
|
| 349 |
+
"learning_rate": 6.943538753897311e-05,
|
| 350 |
+
"loss": 0.6986,
|
| 351 |
+
"step": 780
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 18.96,
|
| 355 |
+
"learning_rate": 6.312511494037267e-05,
|
| 356 |
+
"loss": 0.698,
|
| 357 |
+
"step": 806
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.99,
|
| 361 |
+
"eval_accuracy": 0.9262749445676275,
|
| 362 |
+
"eval_loss": 0.7983365058898926,
|
| 363 |
+
"eval_runtime": 6.7297,
|
| 364 |
+
"eval_samples_per_second": 536.129,
|
| 365 |
+
"eval_steps_per_second": 8.47,
|
| 366 |
+
"step": 807
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 19.58,
|
| 370 |
+
"learning_rate": 5.695865609063774e-05,
|
| 371 |
+
"loss": 0.6899,
|
| 372 |
+
"step": 832
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.0,
|
| 376 |
+
"eval_accuracy": 0.9174057649667405,
|
| 377 |
+
"eval_loss": 0.8008666038513184,
|
| 378 |
+
"eval_runtime": 6.6376,
|
| 379 |
+
"eval_samples_per_second": 543.571,
|
| 380 |
+
"eval_steps_per_second": 8.587,
|
| 381 |
+
"step": 850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 20.19,
|
| 385 |
+
"learning_rate": 5.0968216952300726e-05,
|
| 386 |
+
"loss": 0.6935,
|
| 387 |
+
"step": 858
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 20.8,
|
| 391 |
+
"learning_rate": 4.518508417838943e-05,
|
| 392 |
+
"loss": 0.6922,
|
| 393 |
+
"step": 884
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.99,
|
| 397 |
+
"eval_accuracy": 0.9221175166297118,
|
| 398 |
+
"eval_loss": 0.8021017909049988,
|
| 399 |
+
"eval_runtime": 6.9244,
|
| 400 |
+
"eval_samples_per_second": 521.053,
|
| 401 |
+
"eval_steps_per_second": 8.232,
|
| 402 |
+
"step": 892
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 21.41,
|
| 406 |
+
"learning_rate": 3.9639461709605394e-05,
|
| 407 |
+
"loss": 0.6895,
|
| 408 |
+
"step": 910
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 22.0,
|
| 412 |
+
"eval_accuracy": 0.9240576496674058,
|
| 413 |
+
"eval_loss": 0.7964810729026794,
|
| 414 |
+
"eval_runtime": 6.7682,
|
| 415 |
+
"eval_samples_per_second": 533.077,
|
| 416 |
+
"eval_steps_per_second": 8.422,
|
| 417 |
+
"step": 935
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 22.02,
|
| 421 |
+
"learning_rate": 3.436031302625408e-05,
|
| 422 |
+
"loss": 0.6875,
|
| 423 |
+
"step": 936
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.64,
|
| 427 |
+
"learning_rate": 2.937520987880715e-05,
|
| 428 |
+
"loss": 0.6865,
|
| 429 |
+
"step": 962
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.99,
|
| 433 |
+
"eval_accuracy": 0.9229490022172949,
|
| 434 |
+
"eval_loss": 0.7992194294929504,
|
| 435 |
+
"eval_runtime": 6.8278,
|
| 436 |
+
"eval_samples_per_second": 528.427,
|
| 437 |
+
"eval_steps_per_second": 8.348,
|
| 438 |
+
"step": 977
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 23.25,
|
| 442 |
+
"learning_rate": 2.4710188287142336e-05,
|
| 443 |
+
"loss": 0.6886,
|
| 444 |
+
"step": 988
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.86,
|
| 448 |
+
"learning_rate": 2.0389612560542293e-05,
|
| 449 |
+
"loss": 0.6874,
|
| 450 |
+
"step": 1014
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 24.0,
|
| 454 |
+
"eval_accuracy": 0.9243348115299335,
|
| 455 |
+
"eval_loss": 0.794614851474762,
|
| 456 |
+
"eval_runtime": 7.0369,
|
| 457 |
+
"eval_samples_per_second": 512.726,
|
| 458 |
+
"eval_steps_per_second": 8.1,
|
| 459 |
+
"step": 1020
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 24.47,
|
| 463 |
+
"learning_rate": 1.6436048048644487e-05,
|
| 464 |
+
"loss": 0.6936,
|
| 465 |
+
"step": 1040
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 24.99,
|
| 469 |
+
"eval_accuracy": 0.924889135254989,
|
| 470 |
+
"eval_loss": 0.7939379811286926,
|
| 471 |
+
"eval_runtime": 6.7889,
|
| 472 |
+
"eval_samples_per_second": 531.455,
|
| 473 |
+
"eval_steps_per_second": 8.396,
|
| 474 |
+
"step": 1062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 25.08,
|
| 478 |
+
"learning_rate": 1.2870143287933509e-05,
|
| 479 |
+
"loss": 0.6864,
|
| 480 |
+
"step": 1066
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 25.69,
|
| 484 |
+
"learning_rate": 9.710522159297248e-06,
|
| 485 |
+
"loss": 0.6875,
|
| 486 |
+
"step": 1092
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 26.0,
|
| 490 |
+
"eval_accuracy": 0.926829268292683,
|
| 491 |
+
"eval_loss": 0.7930501699447632,
|
| 492 |
+
"eval_runtime": 6.6519,
|
| 493 |
+
"eval_samples_per_second": 542.402,
|
| 494 |
+
"eval_steps_per_second": 8.569,
|
| 495 |
+
"step": 1105
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 26.31,
|
| 499 |
+
"learning_rate": 6.9736866198824056e-06,
|
| 500 |
+
"loss": 0.6869,
|
| 501 |
+
"step": 1118
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.92,
|
| 505 |
+
"learning_rate": 4.67393051725817e-06,
|
| 506 |
+
"loss": 0.6863,
|
| 507 |
+
"step": 1144
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 26.99,
|
| 511 |
+
"eval_accuracy": 0.9273835920177383,
|
| 512 |
+
"eval_loss": 0.7957404851913452,
|
| 513 |
+
"eval_runtime": 6.6539,
|
| 514 |
+
"eval_samples_per_second": 542.236,
|
| 515 |
+
"eval_steps_per_second": 8.566,
|
| 516 |
+
"step": 1147
|
| 517 |
+
}
|
| 518 |
+
],
|
| 519 |
+
"logging_steps": 26,
|
| 520 |
+
"max_steps": 1260,
|
| 521 |
+
"num_input_tokens_seen": 0,
|
| 522 |
+
"num_train_epochs": 30,
|
| 523 |
+
"save_steps": 500,
|
| 524 |
+
"total_flos": 0.0,
|
| 525 |
+
"train_batch_size": 64,
|
| 526 |
+
"trial_name": null,
|
| 527 |
+
"trial_params": {
|
| 528 |
+
"_wandb": {},
|
| 529 |
+
"assignments": {},
|
| 530 |
+
"learning_rate": 0.00018132211686526395,
|
| 531 |
+
"metric": "eval/loss",
|
| 532 |
+
"warmup_ratio": 0.1030284831764748
|
| 533 |
+
}
|
| 534 |
+
}
|
run-2787ye3h/checkpoint-1147/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94e2659a8bb759e9044d294378560379668c25ab4ec4cf4e84f05ca8f53c3df5
|
| 3 |
+
size 4792
|
run-2787ye3h/checkpoint-1260/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b604effb42ed0baafcac2b4065eccab0998e410df650f41d83ee6e33df57430a
|
| 3 |
+
size 198025308
|
run-2787ye3h/checkpoint-1260/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7923d81e79b6942020b1e84cafe77e6444202c34dc4ce3ca5698683ce6e57f8d
|
| 3 |
+
size 395900602
|
run-2787ye3h/checkpoint-1260/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deeb0d472f47497c93334cb3948d4032ad244442808af19b401a7a0fea1fe65c
|
| 3 |
+
size 14244
|
run-2787ye3h/checkpoint-1260/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61b5c1cff843287d42e8d539aeaf3ec7dfa105711e1497176ca7268775886c4f
|
| 3 |
+
size 1064
|
run-2787ye3h/checkpoint-1260/trainer_state.json
ADDED
|
@@ -0,0 +1,585 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9273835920177383,
|
| 3 |
+
"best_model_checkpoint": "/home/hoan/projects/nsfw/models/efficientvit_l1.r224_in1k/run-2787ye3h/checkpoint-1147",
|
| 4 |
+
"epoch": 29.647058823529413,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1260,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.61,
|
| 13 |
+
"learning_rate": 3.626442337305279e-05,
|
| 14 |
+
"loss": 1.293,
|
| 15 |
+
"step": 26
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.8755543237250555,
|
| 20 |
+
"eval_loss": 0.9349600672721863,
|
| 21 |
+
"eval_runtime": 6.9886,
|
| 22 |
+
"eval_samples_per_second": 516.266,
|
| 23 |
+
"eval_steps_per_second": 8.156,
|
| 24 |
+
"step": 42
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.22,
|
| 28 |
+
"learning_rate": 7.252884674610559e-05,
|
| 29 |
+
"loss": 0.9064,
|
| 30 |
+
"step": 52
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.84,
|
| 34 |
+
"learning_rate": 0.00010879327011915836,
|
| 35 |
+
"loss": 0.8316,
|
| 36 |
+
"step": 78
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.914079822616408,
|
| 41 |
+
"eval_loss": 0.8049944639205933,
|
| 42 |
+
"eval_runtime": 6.9141,
|
| 43 |
+
"eval_samples_per_second": 521.829,
|
| 44 |
+
"eval_steps_per_second": 8.244,
|
| 45 |
+
"step": 85
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.45,
|
| 49 |
+
"learning_rate": 0.00014505769349221117,
|
| 50 |
+
"loss": 0.7997,
|
| 51 |
+
"step": 104
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.99,
|
| 55 |
+
"eval_accuracy": 0.9126940133037694,
|
| 56 |
+
"eval_loss": 0.8133141398429871,
|
| 57 |
+
"eval_runtime": 6.6693,
|
| 58 |
+
"eval_samples_per_second": 540.987,
|
| 59 |
+
"eval_steps_per_second": 8.547,
|
| 60 |
+
"step": 127
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.06,
|
| 64 |
+
"learning_rate": 0.00018132211686526395,
|
| 65 |
+
"loss": 0.7971,
|
| 66 |
+
"step": 130
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.67,
|
| 70 |
+
"learning_rate": 0.00018108536618532123,
|
| 71 |
+
"loss": 0.7806,
|
| 72 |
+
"step": 156
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.9182372505543237,
|
| 77 |
+
"eval_loss": 0.8043554425239563,
|
| 78 |
+
"eval_runtime": 6.9887,
|
| 79 |
+
"eval_samples_per_second": 516.26,
|
| 80 |
+
"eval_steps_per_second": 8.156,
|
| 81 |
+
"step": 170
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.28,
|
| 85 |
+
"learning_rate": 0.00018037635063854584,
|
| 86 |
+
"loss": 0.7788,
|
| 87 |
+
"step": 182
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.89,
|
| 91 |
+
"learning_rate": 0.00017919877324618395,
|
| 92 |
+
"loss": 0.764,
|
| 93 |
+
"step": 208
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.99,
|
| 97 |
+
"eval_accuracy": 0.917960088691796,
|
| 98 |
+
"eval_loss": 0.7976019382476807,
|
| 99 |
+
"eval_runtime": 6.7358,
|
| 100 |
+
"eval_samples_per_second": 535.642,
|
| 101 |
+
"eval_steps_per_second": 8.462,
|
| 102 |
+
"step": 212
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.51,
|
| 106 |
+
"learning_rate": 0.00017755878421766717,
|
| 107 |
+
"loss": 0.7658,
|
| 108 |
+
"step": 234
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.9016075388026608,
|
| 113 |
+
"eval_loss": 0.8304137587547302,
|
| 114 |
+
"eval_runtime": 6.8918,
|
| 115 |
+
"eval_samples_per_second": 523.522,
|
| 116 |
+
"eval_steps_per_second": 8.271,
|
| 117 |
+
"step": 255
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.12,
|
| 121 |
+
"learning_rate": 0.00017546494882951695,
|
| 122 |
+
"loss": 0.751,
|
| 123 |
+
"step": 260
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.73,
|
| 127 |
+
"learning_rate": 0.00017292820269092213,
|
| 128 |
+
"loss": 0.7533,
|
| 129 |
+
"step": 286
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.99,
|
| 133 |
+
"eval_accuracy": 0.9049334811529933,
|
| 134 |
+
"eval_loss": 0.8278865218162537,
|
| 135 |
+
"eval_runtime": 6.9038,
|
| 136 |
+
"eval_samples_per_second": 522.607,
|
| 137 |
+
"eval_steps_per_second": 8.256,
|
| 138 |
+
"step": 297
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 7.34,
|
| 142 |
+
"learning_rate": 0.00016996179462962718,
|
| 143 |
+
"loss": 0.747,
|
| 144 |
+
"step": 312
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.95,
|
| 148 |
+
"learning_rate": 0.00016658121749642477,
|
| 149 |
+
"loss": 0.7294,
|
| 150 |
+
"step": 338
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.9054878048780488,
|
| 155 |
+
"eval_loss": 0.8298162817955017,
|
| 156 |
+
"eval_runtime": 6.8854,
|
| 157 |
+
"eval_samples_per_second": 524.008,
|
| 158 |
+
"eval_steps_per_second": 8.278,
|
| 159 |
+
"step": 340
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.56,
|
| 163 |
+
"learning_rate": 0.0001628041272496441,
|
| 164 |
+
"loss": 0.7325,
|
| 165 |
+
"step": 364
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.99,
|
| 169 |
+
"eval_accuracy": 0.9174057649667405,
|
| 170 |
+
"eval_loss": 0.8046008944511414,
|
| 171 |
+
"eval_runtime": 6.8095,
|
| 172 |
+
"eval_samples_per_second": 529.85,
|
| 173 |
+
"eval_steps_per_second": 8.371,
|
| 174 |
+
"step": 382
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.18,
|
| 178 |
+
"learning_rate": 0.0001586502507422381,
|
| 179 |
+
"loss": 0.737,
|
| 180 |
+
"step": 390
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.79,
|
| 184 |
+
"learning_rate": 0.0001541412826930757,
|
| 185 |
+
"loss": 0.7235,
|
| 186 |
+
"step": 416
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_accuracy": 0.917960088691796,
|
| 191 |
+
"eval_loss": 0.8011636734008789,
|
| 192 |
+
"eval_runtime": 7.0572,
|
| 193 |
+
"eval_samples_per_second": 511.252,
|
| 194 |
+
"eval_steps_per_second": 8.077,
|
| 195 |
+
"step": 425
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.4,
|
| 199 |
+
"learning_rate": 0.00014930077238053366,
|
| 200 |
+
"loss": 0.7212,
|
| 201 |
+
"step": 442
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.99,
|
| 205 |
+
"eval_accuracy": 0.9154656319290465,
|
| 206 |
+
"eval_loss": 0.8091404438018799,
|
| 207 |
+
"eval_runtime": 6.6144,
|
| 208 |
+
"eval_samples_per_second": 545.478,
|
| 209 |
+
"eval_steps_per_second": 8.618,
|
| 210 |
+
"step": 467
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.01,
|
| 214 |
+
"learning_rate": 0.00014415400065016071,
|
| 215 |
+
"loss": 0.7204,
|
| 216 |
+
"step": 468
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.62,
|
| 220 |
+
"learning_rate": 0.00013872784787877452,
|
| 221 |
+
"loss": 0.7154,
|
| 222 |
+
"step": 494
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_accuracy": 0.8747228381374723,
|
| 227 |
+
"eval_loss": 0.8664525747299194,
|
| 228 |
+
"eval_runtime": 6.7378,
|
| 229 |
+
"eval_samples_per_second": 535.484,
|
| 230 |
+
"eval_steps_per_second": 8.46,
|
| 231 |
+
"step": 510
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.24,
|
| 235 |
+
"learning_rate": 0.00013305065358458295,
|
| 236 |
+
"loss": 0.7148,
|
| 237 |
+
"step": 520
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 12.85,
|
| 241 |
+
"learning_rate": 0.00012715206841655379,
|
| 242 |
+
"loss": 0.7122,
|
| 243 |
+
"step": 546
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.99,
|
| 247 |
+
"eval_accuracy": 0.9154656319290465,
|
| 248 |
+
"eval_loss": 0.8063619136810303,
|
| 249 |
+
"eval_runtime": 6.798,
|
| 250 |
+
"eval_samples_per_second": 530.746,
|
| 251 |
+
"eval_steps_per_second": 8.385,
|
| 252 |
+
"step": 552
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.46,
|
| 256 |
+
"learning_rate": 0.00012106289929605711,
|
| 257 |
+
"loss": 0.7096,
|
| 258 |
+
"step": 572
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 14.0,
|
| 262 |
+
"eval_accuracy": 0.9162971175166297,
|
| 263 |
+
"eval_loss": 0.8059455752372742,
|
| 264 |
+
"eval_runtime": 6.7495,
|
| 265 |
+
"eval_samples_per_second": 534.558,
|
| 266 |
+
"eval_steps_per_second": 8.445,
|
| 267 |
+
"step": 595
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 14.07,
|
| 271 |
+
"learning_rate": 0.00011481494851956916,
|
| 272 |
+
"loss": 0.7157,
|
| 273 |
+
"step": 598
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 14.68,
|
| 277 |
+
"learning_rate": 0.0001084408476627666,
|
| 278 |
+
"loss": 0.7021,
|
| 279 |
+
"step": 624
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.99,
|
| 283 |
+
"eval_accuracy": 0.9212860310421286,
|
| 284 |
+
"eval_loss": 0.8017489314079285,
|
| 285 |
+
"eval_runtime": 6.9058,
|
| 286 |
+
"eval_samples_per_second": 522.457,
|
| 287 |
+
"eval_steps_per_second": 8.254,
|
| 288 |
+
"step": 637
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 15.29,
|
| 292 |
+
"learning_rate": 0.0001019738871534904,
|
| 293 |
+
"loss": 0.7021,
|
| 294 |
+
"step": 650
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.91,
|
| 298 |
+
"learning_rate": 9.544784240368045e-05,
|
| 299 |
+
"loss": 0.7002,
|
| 300 |
+
"step": 676
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.0,
|
| 304 |
+
"eval_accuracy": 0.9157427937915743,
|
| 305 |
+
"eval_loss": 0.816520631313324,
|
| 306 |
+
"eval_runtime": 6.8,
|
| 307 |
+
"eval_samples_per_second": 530.585,
|
| 308 |
+
"eval_steps_per_second": 8.382,
|
| 309 |
+
"step": 680
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.52,
|
| 313 |
+
"learning_rate": 8.889679740835216e-05,
|
| 314 |
+
"loss": 0.705,
|
| 315 |
+
"step": 702
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 16.99,
|
| 319 |
+
"eval_accuracy": 0.9196230598669624,
|
| 320 |
+
"eval_loss": 0.8022974133491516,
|
| 321 |
+
"eval_runtime": 6.9057,
|
| 322 |
+
"eval_samples_per_second": 522.468,
|
| 323 |
+
"eval_steps_per_second": 8.254,
|
| 324 |
+
"step": 722
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.13,
|
| 328 |
+
"learning_rate": 8.235496673291634e-05,
|
| 329 |
+
"loss": 0.7031,
|
| 330 |
+
"step": 728
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 17.74,
|
| 334 |
+
"learning_rate": 7.585651681856075e-05,
|
| 335 |
+
"loss": 0.6987,
|
| 336 |
+
"step": 754
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 18.0,
|
| 340 |
+
"eval_accuracy": 0.9154656319290465,
|
| 341 |
+
"eval_loss": 0.8067501783370972,
|
| 342 |
+
"eval_runtime": 6.7889,
|
| 343 |
+
"eval_samples_per_second": 531.457,
|
| 344 |
+
"eval_steps_per_second": 8.396,
|
| 345 |
+
"step": 765
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 18.35,
|
| 349 |
+
"learning_rate": 6.943538753897311e-05,
|
| 350 |
+
"loss": 0.6986,
|
| 351 |
+
"step": 780
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 18.96,
|
| 355 |
+
"learning_rate": 6.312511494037267e-05,
|
| 356 |
+
"loss": 0.698,
|
| 357 |
+
"step": 806
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 18.99,
|
| 361 |
+
"eval_accuracy": 0.9262749445676275,
|
| 362 |
+
"eval_loss": 0.7983365058898926,
|
| 363 |
+
"eval_runtime": 6.7297,
|
| 364 |
+
"eval_samples_per_second": 536.129,
|
| 365 |
+
"eval_steps_per_second": 8.47,
|
| 366 |
+
"step": 807
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 19.58,
|
| 370 |
+
"learning_rate": 5.695865609063774e-05,
|
| 371 |
+
"loss": 0.6899,
|
| 372 |
+
"step": 832
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.0,
|
| 376 |
+
"eval_accuracy": 0.9174057649667405,
|
| 377 |
+
"eval_loss": 0.8008666038513184,
|
| 378 |
+
"eval_runtime": 6.6376,
|
| 379 |
+
"eval_samples_per_second": 543.571,
|
| 380 |
+
"eval_steps_per_second": 8.587,
|
| 381 |
+
"step": 850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 20.19,
|
| 385 |
+
"learning_rate": 5.0968216952300726e-05,
|
| 386 |
+
"loss": 0.6935,
|
| 387 |
+
"step": 858
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 20.8,
|
| 391 |
+
"learning_rate": 4.518508417838943e-05,
|
| 392 |
+
"loss": 0.6922,
|
| 393 |
+
"step": 884
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.99,
|
| 397 |
+
"eval_accuracy": 0.9221175166297118,
|
| 398 |
+
"eval_loss": 0.8021017909049988,
|
| 399 |
+
"eval_runtime": 6.9244,
|
| 400 |
+
"eval_samples_per_second": 521.053,
|
| 401 |
+
"eval_steps_per_second": 8.232,
|
| 402 |
+
"step": 892
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 21.41,
|
| 406 |
+
"learning_rate": 3.9639461709605394e-05,
|
| 407 |
+
"loss": 0.6895,
|
| 408 |
+
"step": 910
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 22.0,
|
| 412 |
+
"eval_accuracy": 0.9240576496674058,
|
| 413 |
+
"eval_loss": 0.7964810729026794,
|
| 414 |
+
"eval_runtime": 6.7682,
|
| 415 |
+
"eval_samples_per_second": 533.077,
|
| 416 |
+
"eval_steps_per_second": 8.422,
|
| 417 |
+
"step": 935
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 22.02,
|
| 421 |
+
"learning_rate": 3.436031302625408e-05,
|
| 422 |
+
"loss": 0.6875,
|
| 423 |
+
"step": 936
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.64,
|
| 427 |
+
"learning_rate": 2.937520987880715e-05,
|
| 428 |
+
"loss": 0.6865,
|
| 429 |
+
"step": 962
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.99,
|
| 433 |
+
"eval_accuracy": 0.9229490022172949,
|
| 434 |
+
"eval_loss": 0.7992194294929504,
|
| 435 |
+
"eval_runtime": 6.8278,
|
| 436 |
+
"eval_samples_per_second": 528.427,
|
| 437 |
+
"eval_steps_per_second": 8.348,
|
| 438 |
+
"step": 977
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 23.25,
|
| 442 |
+
"learning_rate": 2.4710188287142336e-05,
|
| 443 |
+
"loss": 0.6886,
|
| 444 |
+
"step": 988
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.86,
|
| 448 |
+
"learning_rate": 2.0389612560542293e-05,
|
| 449 |
+
"loss": 0.6874,
|
| 450 |
+
"step": 1014
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 24.0,
|
| 454 |
+
"eval_accuracy": 0.9243348115299335,
|
| 455 |
+
"eval_loss": 0.794614851474762,
|
| 456 |
+
"eval_runtime": 7.0369,
|
| 457 |
+
"eval_samples_per_second": 512.726,
|
| 458 |
+
"eval_steps_per_second": 8.1,
|
| 459 |
+
"step": 1020
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 24.47,
|
| 463 |
+
"learning_rate": 1.6436048048644487e-05,
|
| 464 |
+
"loss": 0.6936,
|
| 465 |
+
"step": 1040
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 24.99,
|
| 469 |
+
"eval_accuracy": 0.924889135254989,
|
| 470 |
+
"eval_loss": 0.7939379811286926,
|
| 471 |
+
"eval_runtime": 6.7889,
|
| 472 |
+
"eval_samples_per_second": 531.455,
|
| 473 |
+
"eval_steps_per_second": 8.396,
|
| 474 |
+
"step": 1062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 25.08,
|
| 478 |
+
"learning_rate": 1.2870143287933509e-05,
|
| 479 |
+
"loss": 0.6864,
|
| 480 |
+
"step": 1066
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 25.69,
|
| 484 |
+
"learning_rate": 9.710522159297248e-06,
|
| 485 |
+
"loss": 0.6875,
|
| 486 |
+
"step": 1092
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 26.0,
|
| 490 |
+
"eval_accuracy": 0.926829268292683,
|
| 491 |
+
"eval_loss": 0.7930501699447632,
|
| 492 |
+
"eval_runtime": 6.6519,
|
| 493 |
+
"eval_samples_per_second": 542.402,
|
| 494 |
+
"eval_steps_per_second": 8.569,
|
| 495 |
+
"step": 1105
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 26.31,
|
| 499 |
+
"learning_rate": 6.9736866198824056e-06,
|
| 500 |
+
"loss": 0.6869,
|
| 501 |
+
"step": 1118
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.92,
|
| 505 |
+
"learning_rate": 4.67393051725817e-06,
|
| 506 |
+
"loss": 0.6863,
|
| 507 |
+
"step": 1144
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 26.99,
|
| 511 |
+
"eval_accuracy": 0.9273835920177383,
|
| 512 |
+
"eval_loss": 0.7957404851913452,
|
| 513 |
+
"eval_runtime": 6.6539,
|
| 514 |
+
"eval_samples_per_second": 542.236,
|
| 515 |
+
"eval_steps_per_second": 8.566,
|
| 516 |
+
"step": 1147
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 27.53,
|
| 520 |
+
"learning_rate": 2.823264936016118e-06,
|
| 521 |
+
"loss": 0.6844,
|
| 522 |
+
"step": 1170
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 28.0,
|
| 526 |
+
"eval_accuracy": 0.9237804878048781,
|
| 527 |
+
"eval_loss": 0.7975443005561829,
|
| 528 |
+
"eval_runtime": 6.6662,
|
| 529 |
+
"eval_samples_per_second": 541.236,
|
| 530 |
+
"eval_steps_per_second": 8.551,
|
| 531 |
+
"step": 1190
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 28.14,
|
| 535 |
+
"learning_rate": 1.4313554667037497e-06,
|
| 536 |
+
"loss": 0.6868,
|
| 537 |
+
"step": 1196
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 28.75,
|
| 541 |
+
"learning_rate": 5.054717247209873e-07,
|
| 542 |
+
"loss": 0.6883,
|
| 543 |
+
"step": 1222
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 28.99,
|
| 547 |
+
"eval_accuracy": 0.9254434589800443,
|
| 548 |
+
"eval_loss": 0.7970326542854309,
|
| 549 |
+
"eval_runtime": 6.7789,
|
| 550 |
+
"eval_samples_per_second": 532.24,
|
| 551 |
+
"eval_steps_per_second": 8.408,
|
| 552 |
+
"step": 1232
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 29.36,
|
| 556 |
+
"learning_rate": 5.0449382830818864e-08,
|
| 557 |
+
"loss": 0.6866,
|
| 558 |
+
"step": 1248
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 29.65,
|
| 562 |
+
"eval_accuracy": 0.9210088691796009,
|
| 563 |
+
"eval_loss": 0.8019540309906006,
|
| 564 |
+
"eval_runtime": 6.7841,
|
| 565 |
+
"eval_samples_per_second": 531.828,
|
| 566 |
+
"eval_steps_per_second": 8.402,
|
| 567 |
+
"step": 1260
|
| 568 |
+
}
|
| 569 |
+
],
|
| 570 |
+
"logging_steps": 26,
|
| 571 |
+
"max_steps": 1260,
|
| 572 |
+
"num_input_tokens_seen": 0,
|
| 573 |
+
"num_train_epochs": 30,
|
| 574 |
+
"save_steps": 500,
|
| 575 |
+
"total_flos": 0.0,
|
| 576 |
+
"train_batch_size": 64,
|
| 577 |
+
"trial_name": null,
|
| 578 |
+
"trial_params": {
|
| 579 |
+
"_wandb": {},
|
| 580 |
+
"assignments": {},
|
| 581 |
+
"learning_rate": 0.00018132211686526395,
|
| 582 |
+
"metric": "eval/loss",
|
| 583 |
+
"warmup_ratio": 0.1030284831764748
|
| 584 |
+
}
|
| 585 |
+
}
|
run-2787ye3h/checkpoint-1260/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94e2659a8bb759e9044d294378560379668c25ab4ec4cf4e84f05ca8f53c3df5
|
| 3 |
+
size 4792
|
run-29h0ichm/checkpoint-1232/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db5f61d12178aef4ec9a1782f92b84ca6d8a9ec28e8f6601801840b106bc002c
|
| 3 |
+
size 198025308
|