End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec03_22-26-14_DESKTOP-SKBE9FB/events.out.tfevents.1733287244.DESKTOP-SKBE9FB.2356.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +582 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8317757009345794
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5322
|
| 36 |
+
- Accuracy: 0.8318
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8317757009345794,
|
| 4 |
+
"eval_loss": 0.5321738719940186,
|
| 5 |
+
"eval_runtime": 2.3209,
|
| 6 |
+
"eval_samples_per_second": 46.103,
|
| 7 |
+
"eval_steps_per_second": 3.016,
|
| 8 |
+
"train_loss": 0.3920826520770788,
|
| 9 |
+
"train_runtime": 766.5439,
|
| 10 |
+
"train_samples_per_second": 25.987,
|
| 11 |
+
"train_steps_per_second": 0.417
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8317757009345794,
|
| 4 |
+
"eval_loss": 0.5321738719940186,
|
| 5 |
+
"eval_runtime": 2.3209,
|
| 6 |
+
"eval_samples_per_second": 46.103,
|
| 7 |
+
"eval_steps_per_second": 3.016
|
| 8 |
+
}
|
runs/Dec03_22-26-14_DESKTOP-SKBE9FB/events.out.tfevents.1733287244.DESKTOP-SKBE9FB.2356.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90bd4c5bf891f1a29ce95fe878520baf6da458e115616d2612fa7a5ad395e848
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"train_loss": 0.3920826520770788,
|
| 4 |
+
"train_runtime": 766.5439,
|
| 5 |
+
"train_samples_per_second": 25.987,
|
| 6 |
+
"train_steps_per_second": 0.417
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,582 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8317757009345794,
|
| 3 |
+
"best_model_checkpoint": "BEiT-RHS-NDA\\checkpoint-272",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 320,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.5887850467289719,
|
| 14 |
+
"eval_loss": 0.6851425170898438,
|
| 15 |
+
"eval_runtime": 2.6682,
|
| 16 |
+
"eval_samples_per_second": 40.103,
|
| 17 |
+
"eval_steps_per_second": 2.624,
|
| 18 |
+
"step": 8
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.25,
|
| 22 |
+
"learning_rate": 3.125e-05,
|
| 23 |
+
"loss": 0.6911,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.5887850467289719,
|
| 29 |
+
"eval_loss": 0.6720580458641052,
|
| 30 |
+
"eval_runtime": 2.054,
|
| 31 |
+
"eval_samples_per_second": 52.093,
|
| 32 |
+
"eval_steps_per_second": 3.408,
|
| 33 |
+
"step": 16
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.5,
|
| 37 |
+
"learning_rate": 4.9342105263157894e-05,
|
| 38 |
+
"loss": 0.6739,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.5887850467289719,
|
| 44 |
+
"eval_loss": 0.6504218578338623,
|
| 45 |
+
"eval_runtime": 2.4524,
|
| 46 |
+
"eval_samples_per_second": 43.631,
|
| 47 |
+
"eval_steps_per_second": 2.854,
|
| 48 |
+
"step": 24
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.75,
|
| 52 |
+
"learning_rate": 4.769736842105263e-05,
|
| 53 |
+
"loss": 0.6595,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.5887850467289719,
|
| 59 |
+
"eval_loss": 0.6432350873947144,
|
| 60 |
+
"eval_runtime": 2.1328,
|
| 61 |
+
"eval_samples_per_second": 50.169,
|
| 62 |
+
"eval_steps_per_second": 3.282,
|
| 63 |
+
"step": 32
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"learning_rate": 4.605263157894737e-05,
|
| 68 |
+
"loss": 0.646,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"eval_accuracy": 0.6822429906542056,
|
| 74 |
+
"eval_loss": 0.6316895484924316,
|
| 75 |
+
"eval_runtime": 2.4096,
|
| 76 |
+
"eval_samples_per_second": 44.405,
|
| 77 |
+
"eval_steps_per_second": 2.905,
|
| 78 |
+
"step": 40
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.6915887850467289,
|
| 83 |
+
"eval_loss": 0.617514431476593,
|
| 84 |
+
"eval_runtime": 2.0335,
|
| 85 |
+
"eval_samples_per_second": 52.617,
|
| 86 |
+
"eval_steps_per_second": 3.442,
|
| 87 |
+
"step": 48
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.25,
|
| 91 |
+
"learning_rate": 4.440789473684211e-05,
|
| 92 |
+
"loss": 0.6142,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.6915887850467289,
|
| 98 |
+
"eval_loss": 0.6269640326499939,
|
| 99 |
+
"eval_runtime": 2.0515,
|
| 100 |
+
"eval_samples_per_second": 52.156,
|
| 101 |
+
"eval_steps_per_second": 3.412,
|
| 102 |
+
"step": 56
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.5,
|
| 106 |
+
"learning_rate": 4.2763157894736847e-05,
|
| 107 |
+
"loss": 0.608,
|
| 108 |
+
"step": 60
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.0,
|
| 112 |
+
"eval_accuracy": 0.6915887850467289,
|
| 113 |
+
"eval_loss": 0.6617878675460815,
|
| 114 |
+
"eval_runtime": 2.0447,
|
| 115 |
+
"eval_samples_per_second": 52.331,
|
| 116 |
+
"eval_steps_per_second": 3.424,
|
| 117 |
+
"step": 64
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.75,
|
| 121 |
+
"learning_rate": 4.111842105263158e-05,
|
| 122 |
+
"loss": 0.5927,
|
| 123 |
+
"step": 70
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 9.0,
|
| 127 |
+
"eval_accuracy": 0.6915887850467289,
|
| 128 |
+
"eval_loss": 0.5347260236740112,
|
| 129 |
+
"eval_runtime": 2.139,
|
| 130 |
+
"eval_samples_per_second": 50.023,
|
| 131 |
+
"eval_steps_per_second": 3.273,
|
| 132 |
+
"step": 72
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 137 |
+
"loss": 0.5333,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 10.0,
|
| 142 |
+
"eval_accuracy": 0.6448598130841121,
|
| 143 |
+
"eval_loss": 0.5743899941444397,
|
| 144 |
+
"eval_runtime": 2.1225,
|
| 145 |
+
"eval_samples_per_second": 50.412,
|
| 146 |
+
"eval_steps_per_second": 3.298,
|
| 147 |
+
"step": 80
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 11.0,
|
| 151 |
+
"eval_accuracy": 0.7476635514018691,
|
| 152 |
+
"eval_loss": 0.4974236786365509,
|
| 153 |
+
"eval_runtime": 2.059,
|
| 154 |
+
"eval_samples_per_second": 51.967,
|
| 155 |
+
"eval_steps_per_second": 3.4,
|
| 156 |
+
"step": 88
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.25,
|
| 160 |
+
"learning_rate": 3.7828947368421054e-05,
|
| 161 |
+
"loss": 0.4987,
|
| 162 |
+
"step": 90
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"eval_accuracy": 0.6448598130841121,
|
| 167 |
+
"eval_loss": 0.5970269441604614,
|
| 168 |
+
"eval_runtime": 2.1492,
|
| 169 |
+
"eval_samples_per_second": 49.787,
|
| 170 |
+
"eval_steps_per_second": 3.257,
|
| 171 |
+
"step": 96
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.5,
|
| 175 |
+
"learning_rate": 3.618421052631579e-05,
|
| 176 |
+
"loss": 0.5421,
|
| 177 |
+
"step": 100
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"eval_accuracy": 0.7383177570093458,
|
| 182 |
+
"eval_loss": 0.5137068629264832,
|
| 183 |
+
"eval_runtime": 2.4494,
|
| 184 |
+
"eval_samples_per_second": 43.684,
|
| 185 |
+
"eval_steps_per_second": 2.858,
|
| 186 |
+
"step": 104
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 13.75,
|
| 190 |
+
"learning_rate": 3.4539473684210524e-05,
|
| 191 |
+
"loss": 0.4881,
|
| 192 |
+
"step": 110
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 14.0,
|
| 196 |
+
"eval_accuracy": 0.7663551401869159,
|
| 197 |
+
"eval_loss": 0.47269827127456665,
|
| 198 |
+
"eval_runtime": 2.4181,
|
| 199 |
+
"eval_samples_per_second": 44.249,
|
| 200 |
+
"eval_steps_per_second": 2.895,
|
| 201 |
+
"step": 112
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"learning_rate": 3.289473684210527e-05,
|
| 206 |
+
"loss": 0.4408,
|
| 207 |
+
"step": 120
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 15.0,
|
| 211 |
+
"eval_accuracy": 0.7663551401869159,
|
| 212 |
+
"eval_loss": 0.5161357522010803,
|
| 213 |
+
"eval_runtime": 2.086,
|
| 214 |
+
"eval_samples_per_second": 51.295,
|
| 215 |
+
"eval_steps_per_second": 3.356,
|
| 216 |
+
"step": 120
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 16.0,
|
| 220 |
+
"eval_accuracy": 0.6915887850467289,
|
| 221 |
+
"eval_loss": 0.6732468008995056,
|
| 222 |
+
"eval_runtime": 2.0757,
|
| 223 |
+
"eval_samples_per_second": 51.548,
|
| 224 |
+
"eval_steps_per_second": 3.372,
|
| 225 |
+
"step": 128
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.25,
|
| 229 |
+
"learning_rate": 3.125e-05,
|
| 230 |
+
"loss": 0.4923,
|
| 231 |
+
"step": 130
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.0,
|
| 235 |
+
"eval_accuracy": 0.7009345794392523,
|
| 236 |
+
"eval_loss": 0.6567767262458801,
|
| 237 |
+
"eval_runtime": 2.0563,
|
| 238 |
+
"eval_samples_per_second": 52.036,
|
| 239 |
+
"eval_steps_per_second": 3.404,
|
| 240 |
+
"step": 136
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 17.5,
|
| 244 |
+
"learning_rate": 2.9605263157894735e-05,
|
| 245 |
+
"loss": 0.4135,
|
| 246 |
+
"step": 140
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.7009345794392523,
|
| 251 |
+
"eval_loss": 0.665261447429657,
|
| 252 |
+
"eval_runtime": 2.454,
|
| 253 |
+
"eval_samples_per_second": 43.602,
|
| 254 |
+
"eval_steps_per_second": 2.852,
|
| 255 |
+
"step": 144
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 18.75,
|
| 259 |
+
"learning_rate": 2.7960526315789477e-05,
|
| 260 |
+
"loss": 0.4308,
|
| 261 |
+
"step": 150
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"eval_accuracy": 0.719626168224299,
|
| 266 |
+
"eval_loss": 0.6031992435455322,
|
| 267 |
+
"eval_runtime": 2.0319,
|
| 268 |
+
"eval_samples_per_second": 52.66,
|
| 269 |
+
"eval_steps_per_second": 3.445,
|
| 270 |
+
"step": 152
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 20.0,
|
| 274 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 275 |
+
"loss": 0.3837,
|
| 276 |
+
"step": 160
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 20.0,
|
| 280 |
+
"eval_accuracy": 0.8037383177570093,
|
| 281 |
+
"eval_loss": 0.44923561811447144,
|
| 282 |
+
"eval_runtime": 2.1355,
|
| 283 |
+
"eval_samples_per_second": 50.106,
|
| 284 |
+
"eval_steps_per_second": 3.278,
|
| 285 |
+
"step": 160
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 21.0,
|
| 289 |
+
"eval_accuracy": 0.794392523364486,
|
| 290 |
+
"eval_loss": 0.454855740070343,
|
| 291 |
+
"eval_runtime": 2.1041,
|
| 292 |
+
"eval_samples_per_second": 50.854,
|
| 293 |
+
"eval_steps_per_second": 3.327,
|
| 294 |
+
"step": 168
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 21.25,
|
| 298 |
+
"learning_rate": 2.4671052631578947e-05,
|
| 299 |
+
"loss": 0.3297,
|
| 300 |
+
"step": 170
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 22.0,
|
| 304 |
+
"eval_accuracy": 0.7663551401869159,
|
| 305 |
+
"eval_loss": 0.5525509715080261,
|
| 306 |
+
"eval_runtime": 2.3723,
|
| 307 |
+
"eval_samples_per_second": 45.104,
|
| 308 |
+
"eval_steps_per_second": 2.951,
|
| 309 |
+
"step": 176
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.5,
|
| 313 |
+
"learning_rate": 2.3026315789473685e-05,
|
| 314 |
+
"loss": 0.3264,
|
| 315 |
+
"step": 180
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 23.0,
|
| 319 |
+
"eval_accuracy": 0.794392523364486,
|
| 320 |
+
"eval_loss": 0.5171772241592407,
|
| 321 |
+
"eval_runtime": 2.1842,
|
| 322 |
+
"eval_samples_per_second": 48.989,
|
| 323 |
+
"eval_steps_per_second": 3.205,
|
| 324 |
+
"step": 184
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 23.75,
|
| 328 |
+
"learning_rate": 2.1381578947368423e-05,
|
| 329 |
+
"loss": 0.3487,
|
| 330 |
+
"step": 190
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 24.0,
|
| 334 |
+
"eval_accuracy": 0.7663551401869159,
|
| 335 |
+
"eval_loss": 0.5104933381080627,
|
| 336 |
+
"eval_runtime": 2.1764,
|
| 337 |
+
"eval_samples_per_second": 49.164,
|
| 338 |
+
"eval_steps_per_second": 3.216,
|
| 339 |
+
"step": 192
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 25.0,
|
| 343 |
+
"learning_rate": 1.9736842105263158e-05,
|
| 344 |
+
"loss": 0.2892,
|
| 345 |
+
"step": 200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"eval_accuracy": 0.7757009345794392,
|
| 350 |
+
"eval_loss": 0.4565769135951996,
|
| 351 |
+
"eval_runtime": 2.1452,
|
| 352 |
+
"eval_samples_per_second": 49.879,
|
| 353 |
+
"eval_steps_per_second": 3.263,
|
| 354 |
+
"step": 200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 26.0,
|
| 358 |
+
"eval_accuracy": 0.794392523364486,
|
| 359 |
+
"eval_loss": 0.523303747177124,
|
| 360 |
+
"eval_runtime": 2.1458,
|
| 361 |
+
"eval_samples_per_second": 49.865,
|
| 362 |
+
"eval_steps_per_second": 3.262,
|
| 363 |
+
"step": 208
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 26.25,
|
| 367 |
+
"learning_rate": 1.8092105263157896e-05,
|
| 368 |
+
"loss": 0.2505,
|
| 369 |
+
"step": 210
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 27.0,
|
| 373 |
+
"eval_accuracy": 0.794392523364486,
|
| 374 |
+
"eval_loss": 0.4817139804363251,
|
| 375 |
+
"eval_runtime": 2.0456,
|
| 376 |
+
"eval_samples_per_second": 52.308,
|
| 377 |
+
"eval_steps_per_second": 3.422,
|
| 378 |
+
"step": 216
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 27.5,
|
| 382 |
+
"learning_rate": 1.6447368421052635e-05,
|
| 383 |
+
"loss": 0.2542,
|
| 384 |
+
"step": 220
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 28.0,
|
| 388 |
+
"eval_accuracy": 0.8037383177570093,
|
| 389 |
+
"eval_loss": 0.5034652948379517,
|
| 390 |
+
"eval_runtime": 2.3168,
|
| 391 |
+
"eval_samples_per_second": 46.184,
|
| 392 |
+
"eval_steps_per_second": 3.021,
|
| 393 |
+
"step": 224
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 28.75,
|
| 397 |
+
"learning_rate": 1.4802631578947368e-05,
|
| 398 |
+
"loss": 0.2285,
|
| 399 |
+
"step": 230
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 29.0,
|
| 403 |
+
"eval_accuracy": 0.794392523364486,
|
| 404 |
+
"eval_loss": 0.5281862616539001,
|
| 405 |
+
"eval_runtime": 2.1165,
|
| 406 |
+
"eval_samples_per_second": 50.556,
|
| 407 |
+
"eval_steps_per_second": 3.307,
|
| 408 |
+
"step": 232
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 30.0,
|
| 412 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 413 |
+
"loss": 0.2053,
|
| 414 |
+
"step": 240
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 30.0,
|
| 418 |
+
"eval_accuracy": 0.8130841121495327,
|
| 419 |
+
"eval_loss": 0.5637905597686768,
|
| 420 |
+
"eval_runtime": 2.1396,
|
| 421 |
+
"eval_samples_per_second": 50.009,
|
| 422 |
+
"eval_steps_per_second": 3.272,
|
| 423 |
+
"step": 240
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 31.0,
|
| 427 |
+
"eval_accuracy": 0.7570093457943925,
|
| 428 |
+
"eval_loss": 0.6189974546432495,
|
| 429 |
+
"eval_runtime": 2.2612,
|
| 430 |
+
"eval_samples_per_second": 47.32,
|
| 431 |
+
"eval_steps_per_second": 3.096,
|
| 432 |
+
"step": 248
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 31.25,
|
| 436 |
+
"learning_rate": 1.1513157894736843e-05,
|
| 437 |
+
"loss": 0.2205,
|
| 438 |
+
"step": 250
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 32.0,
|
| 442 |
+
"eval_accuracy": 0.7850467289719626,
|
| 443 |
+
"eval_loss": 0.614178478717804,
|
| 444 |
+
"eval_runtime": 2.5358,
|
| 445 |
+
"eval_samples_per_second": 42.196,
|
| 446 |
+
"eval_steps_per_second": 2.761,
|
| 447 |
+
"step": 256
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 32.5,
|
| 451 |
+
"learning_rate": 9.868421052631579e-06,
|
| 452 |
+
"loss": 0.2081,
|
| 453 |
+
"step": 260
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 33.0,
|
| 457 |
+
"eval_accuracy": 0.7850467289719626,
|
| 458 |
+
"eval_loss": 0.575212836265564,
|
| 459 |
+
"eval_runtime": 2.0662,
|
| 460 |
+
"eval_samples_per_second": 51.787,
|
| 461 |
+
"eval_steps_per_second": 3.388,
|
| 462 |
+
"step": 264
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.75,
|
| 466 |
+
"learning_rate": 8.223684210526317e-06,
|
| 467 |
+
"loss": 0.2075,
|
| 468 |
+
"step": 270
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 34.0,
|
| 472 |
+
"eval_accuracy": 0.8317757009345794,
|
| 473 |
+
"eval_loss": 0.5321738719940186,
|
| 474 |
+
"eval_runtime": 2.1157,
|
| 475 |
+
"eval_samples_per_second": 50.573,
|
| 476 |
+
"eval_steps_per_second": 3.309,
|
| 477 |
+
"step": 272
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 35.0,
|
| 481 |
+
"learning_rate": 6.578947368421053e-06,
|
| 482 |
+
"loss": 0.2286,
|
| 483 |
+
"step": 280
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 35.0,
|
| 487 |
+
"eval_accuracy": 0.794392523364486,
|
| 488 |
+
"eval_loss": 0.5312566161155701,
|
| 489 |
+
"eval_runtime": 2.4167,
|
| 490 |
+
"eval_samples_per_second": 44.276,
|
| 491 |
+
"eval_steps_per_second": 2.897,
|
| 492 |
+
"step": 280
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 36.0,
|
| 496 |
+
"eval_accuracy": 0.8130841121495327,
|
| 497 |
+
"eval_loss": 0.5189207792282104,
|
| 498 |
+
"eval_runtime": 2.2397,
|
| 499 |
+
"eval_samples_per_second": 47.773,
|
| 500 |
+
"eval_steps_per_second": 3.125,
|
| 501 |
+
"step": 288
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 36.25,
|
| 505 |
+
"learning_rate": 4.9342105263157895e-06,
|
| 506 |
+
"loss": 0.2008,
|
| 507 |
+
"step": 290
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 37.0,
|
| 511 |
+
"eval_accuracy": 0.7850467289719626,
|
| 512 |
+
"eval_loss": 0.5589626431465149,
|
| 513 |
+
"eval_runtime": 2.5429,
|
| 514 |
+
"eval_samples_per_second": 42.078,
|
| 515 |
+
"eval_steps_per_second": 2.753,
|
| 516 |
+
"step": 296
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 37.5,
|
| 520 |
+
"learning_rate": 3.2894736842105265e-06,
|
| 521 |
+
"loss": 0.1884,
|
| 522 |
+
"step": 300
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 38.0,
|
| 526 |
+
"eval_accuracy": 0.794392523364486,
|
| 527 |
+
"eval_loss": 0.5488373041152954,
|
| 528 |
+
"eval_runtime": 2.042,
|
| 529 |
+
"eval_samples_per_second": 52.399,
|
| 530 |
+
"eval_steps_per_second": 3.428,
|
| 531 |
+
"step": 304
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 38.75,
|
| 535 |
+
"learning_rate": 1.6447368421052632e-06,
|
| 536 |
+
"loss": 0.1819,
|
| 537 |
+
"step": 310
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 39.0,
|
| 541 |
+
"eval_accuracy": 0.8037383177570093,
|
| 542 |
+
"eval_loss": 0.556251585483551,
|
| 543 |
+
"eval_runtime": 2.015,
|
| 544 |
+
"eval_samples_per_second": 53.102,
|
| 545 |
+
"eval_steps_per_second": 3.474,
|
| 546 |
+
"step": 312
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 40.0,
|
| 550 |
+
"learning_rate": 0.0,
|
| 551 |
+
"loss": 0.1698,
|
| 552 |
+
"step": 320
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 40.0,
|
| 556 |
+
"eval_accuracy": 0.794392523364486,
|
| 557 |
+
"eval_loss": 0.5678603053092957,
|
| 558 |
+
"eval_runtime": 2.1445,
|
| 559 |
+
"eval_samples_per_second": 49.894,
|
| 560 |
+
"eval_steps_per_second": 3.264,
|
| 561 |
+
"step": 320
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"step": 320,
|
| 566 |
+
"total_flos": 1.5429806632629043e+18,
|
| 567 |
+
"train_loss": 0.3920826520770788,
|
| 568 |
+
"train_runtime": 766.5439,
|
| 569 |
+
"train_samples_per_second": 25.987,
|
| 570 |
+
"train_steps_per_second": 0.417
|
| 571 |
+
}
|
| 572 |
+
],
|
| 573 |
+
"logging_steps": 10,
|
| 574 |
+
"max_steps": 320,
|
| 575 |
+
"num_input_tokens_seen": 0,
|
| 576 |
+
"num_train_epochs": 40,
|
| 577 |
+
"save_steps": 500,
|
| 578 |
+
"total_flos": 1.5429806632629043e+18,
|
| 579 |
+
"train_batch_size": 16,
|
| 580 |
+
"trial_name": null,
|
| 581 |
+
"trial_params": null
|
| 582 |
+
}
|