End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec03_17-59-04_DESKTOP-SKBE9FB/events.out.tfevents.1733270806.DESKTOP-SKBE9FB.17260.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +795 -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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss:
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.6739130434782609
|
| 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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.0510
|
| 36 |
+
- Accuracy: 0.6739
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 68.57,
|
| 3 |
+
"eval_accuracy": 0.6739130434782609,
|
| 4 |
+
"eval_loss": 1.0509947538375854,
|
| 5 |
+
"eval_runtime": 0.4916,
|
| 6 |
+
"eval_samples_per_second": 93.569,
|
| 7 |
+
"eval_steps_per_second": 6.102,
|
| 8 |
+
"train_loss": 1.113492695490519,
|
| 9 |
+
"train_runtime": 374.3307,
|
| 10 |
+
"train_samples_per_second": 45.521,
|
| 11 |
+
"train_steps_per_second": 0.641
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 68.57,
|
| 3 |
+
"eval_accuracy": 0.6739130434782609,
|
| 4 |
+
"eval_loss": 1.0509947538375854,
|
| 5 |
+
"eval_runtime": 0.4916,
|
| 6 |
+
"eval_samples_per_second": 93.569,
|
| 7 |
+
"eval_steps_per_second": 6.102
|
| 8 |
+
}
|
runs/Dec03_17-59-04_DESKTOP-SKBE9FB/events.out.tfevents.1733270806.DESKTOP-SKBE9FB.17260.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b164b0a54f5e63625583ce568f6dee04d45d3c0b285cb32673c764979aaf5cc9
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 68.57,
|
| 3 |
+
"train_loss": 1.113492695490519,
|
| 4 |
+
"train_runtime": 374.3307,
|
| 5 |
+
"train_samples_per_second": 45.521,
|
| 6 |
+
"train_steps_per_second": 0.641
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,795 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6739130434782609,
|
| 3 |
+
"best_model_checkpoint": "SW2-DMAE-2\\checkpoint-168",
|
| 4 |
+
"epoch": 68.57142857142857,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 240,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.86,
|
| 13 |
+
"eval_accuracy": 0.10869565217391304,
|
| 14 |
+
"eval_loss": 1.6269055604934692,
|
| 15 |
+
"eval_runtime": 0.2761,
|
| 16 |
+
"eval_samples_per_second": 166.629,
|
| 17 |
+
"eval_steps_per_second": 10.867,
|
| 18 |
+
"step": 3
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.10869565217391304,
|
| 23 |
+
"eval_loss": 1.6078405380249023,
|
| 24 |
+
"eval_runtime": 0.2401,
|
| 25 |
+
"eval_samples_per_second": 191.623,
|
| 26 |
+
"eval_steps_per_second": 12.497,
|
| 27 |
+
"step": 7
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.86,
|
| 31 |
+
"learning_rate": 1.4375e-05,
|
| 32 |
+
"loss": 1.618,
|
| 33 |
+
"step": 10
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.86,
|
| 37 |
+
"eval_accuracy": 0.10869565217391304,
|
| 38 |
+
"eval_loss": 1.585246205329895,
|
| 39 |
+
"eval_runtime": 0.3111,
|
| 40 |
+
"eval_samples_per_second": 147.877,
|
| 41 |
+
"eval_steps_per_second": 9.644,
|
| 42 |
+
"step": 10
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_accuracy": 0.10869565217391304,
|
| 47 |
+
"eval_loss": 1.539771556854248,
|
| 48 |
+
"eval_runtime": 0.2925,
|
| 49 |
+
"eval_samples_per_second": 157.267,
|
| 50 |
+
"eval_steps_per_second": 10.257,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.86,
|
| 55 |
+
"eval_accuracy": 0.10869565217391304,
|
| 56 |
+
"eval_loss": 1.4947997331619263,
|
| 57 |
+
"eval_runtime": 0.2826,
|
| 58 |
+
"eval_samples_per_second": 162.793,
|
| 59 |
+
"eval_steps_per_second": 10.617,
|
| 60 |
+
"step": 17
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 5.71,
|
| 64 |
+
"learning_rate": 1.375e-05,
|
| 65 |
+
"loss": 1.5162,
|
| 66 |
+
"step": 20
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 6.0,
|
| 70 |
+
"eval_accuracy": 0.10869565217391304,
|
| 71 |
+
"eval_loss": 1.434383749961853,
|
| 72 |
+
"eval_runtime": 0.2591,
|
| 73 |
+
"eval_samples_per_second": 177.566,
|
| 74 |
+
"eval_steps_per_second": 11.58,
|
| 75 |
+
"step": 21
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.86,
|
| 79 |
+
"eval_accuracy": 0.10869565217391304,
|
| 80 |
+
"eval_loss": 1.3878703117370605,
|
| 81 |
+
"eval_runtime": 0.2371,
|
| 82 |
+
"eval_samples_per_second": 194.049,
|
| 83 |
+
"eval_steps_per_second": 12.655,
|
| 84 |
+
"step": 24
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 8.0,
|
| 88 |
+
"eval_accuracy": 0.17391304347826086,
|
| 89 |
+
"eval_loss": 1.328822135925293,
|
| 90 |
+
"eval_runtime": 0.2481,
|
| 91 |
+
"eval_samples_per_second": 185.442,
|
| 92 |
+
"eval_steps_per_second": 12.094,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.57,
|
| 97 |
+
"learning_rate": 1.3125e-05,
|
| 98 |
+
"loss": 1.3459,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 8.86,
|
| 103 |
+
"eval_accuracy": 0.45652173913043476,
|
| 104 |
+
"eval_loss": 1.2925546169281006,
|
| 105 |
+
"eval_runtime": 0.2481,
|
| 106 |
+
"eval_samples_per_second": 185.442,
|
| 107 |
+
"eval_steps_per_second": 12.094,
|
| 108 |
+
"step": 31
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 10.0,
|
| 112 |
+
"eval_accuracy": 0.45652173913043476,
|
| 113 |
+
"eval_loss": 1.2562181949615479,
|
| 114 |
+
"eval_runtime": 0.2541,
|
| 115 |
+
"eval_samples_per_second": 181.006,
|
| 116 |
+
"eval_steps_per_second": 11.805,
|
| 117 |
+
"step": 35
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 10.86,
|
| 121 |
+
"eval_accuracy": 0.45652173913043476,
|
| 122 |
+
"eval_loss": 1.238446593284607,
|
| 123 |
+
"eval_runtime": 0.2411,
|
| 124 |
+
"eval_samples_per_second": 190.828,
|
| 125 |
+
"eval_steps_per_second": 12.445,
|
| 126 |
+
"step": 38
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 11.43,
|
| 130 |
+
"learning_rate": 1.25e-05,
|
| 131 |
+
"loss": 1.2384,
|
| 132 |
+
"step": 40
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 12.0,
|
| 136 |
+
"eval_accuracy": 0.45652173913043476,
|
| 137 |
+
"eval_loss": 1.2205413579940796,
|
| 138 |
+
"eval_runtime": 0.2537,
|
| 139 |
+
"eval_samples_per_second": 181.326,
|
| 140 |
+
"eval_steps_per_second": 11.826,
|
| 141 |
+
"step": 42
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 12.86,
|
| 145 |
+
"eval_accuracy": 0.45652173913043476,
|
| 146 |
+
"eval_loss": 1.2173599004745483,
|
| 147 |
+
"eval_runtime": 0.2401,
|
| 148 |
+
"eval_samples_per_second": 191.624,
|
| 149 |
+
"eval_steps_per_second": 12.497,
|
| 150 |
+
"step": 45
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 14.0,
|
| 154 |
+
"eval_accuracy": 0.45652173913043476,
|
| 155 |
+
"eval_loss": 1.2131370306015015,
|
| 156 |
+
"eval_runtime": 0.2691,
|
| 157 |
+
"eval_samples_per_second": 170.965,
|
| 158 |
+
"eval_steps_per_second": 11.15,
|
| 159 |
+
"step": 49
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 14.29,
|
| 163 |
+
"learning_rate": 1.1874999999999999e-05,
|
| 164 |
+
"loss": 1.2049,
|
| 165 |
+
"step": 50
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 14.86,
|
| 169 |
+
"eval_accuracy": 0.45652173913043476,
|
| 170 |
+
"eval_loss": 1.2104469537734985,
|
| 171 |
+
"eval_runtime": 0.2431,
|
| 172 |
+
"eval_samples_per_second": 189.258,
|
| 173 |
+
"eval_steps_per_second": 12.343,
|
| 174 |
+
"step": 52
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 16.0,
|
| 178 |
+
"eval_accuracy": 0.45652173913043476,
|
| 179 |
+
"eval_loss": 1.208552598953247,
|
| 180 |
+
"eval_runtime": 0.2451,
|
| 181 |
+
"eval_samples_per_second": 187.713,
|
| 182 |
+
"eval_steps_per_second": 12.242,
|
| 183 |
+
"step": 56
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 16.86,
|
| 187 |
+
"eval_accuracy": 0.45652173913043476,
|
| 188 |
+
"eval_loss": 1.2076021432876587,
|
| 189 |
+
"eval_runtime": 0.2556,
|
| 190 |
+
"eval_samples_per_second": 179.993,
|
| 191 |
+
"eval_steps_per_second": 11.739,
|
| 192 |
+
"step": 59
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 17.14,
|
| 196 |
+
"learning_rate": 1.125e-05,
|
| 197 |
+
"loss": 1.1815,
|
| 198 |
+
"step": 60
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 18.0,
|
| 202 |
+
"eval_accuracy": 0.45652173913043476,
|
| 203 |
+
"eval_loss": 1.2051774263381958,
|
| 204 |
+
"eval_runtime": 0.2431,
|
| 205 |
+
"eval_samples_per_second": 189.258,
|
| 206 |
+
"eval_steps_per_second": 12.343,
|
| 207 |
+
"step": 63
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 18.86,
|
| 211 |
+
"eval_accuracy": 0.45652173913043476,
|
| 212 |
+
"eval_loss": 1.204942226409912,
|
| 213 |
+
"eval_runtime": 0.3966,
|
| 214 |
+
"eval_samples_per_second": 115.986,
|
| 215 |
+
"eval_steps_per_second": 7.564,
|
| 216 |
+
"step": 66
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 20.0,
|
| 220 |
+
"learning_rate": 1.0625e-05,
|
| 221 |
+
"loss": 1.1826,
|
| 222 |
+
"step": 70
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 20.0,
|
| 226 |
+
"eval_accuracy": 0.45652173913043476,
|
| 227 |
+
"eval_loss": 1.2018660306930542,
|
| 228 |
+
"eval_runtime": 0.3121,
|
| 229 |
+
"eval_samples_per_second": 147.402,
|
| 230 |
+
"eval_steps_per_second": 9.613,
|
| 231 |
+
"step": 70
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 20.86,
|
| 235 |
+
"eval_accuracy": 0.45652173913043476,
|
| 236 |
+
"eval_loss": 1.1960418224334717,
|
| 237 |
+
"eval_runtime": 0.3191,
|
| 238 |
+
"eval_samples_per_second": 144.168,
|
| 239 |
+
"eval_steps_per_second": 9.402,
|
| 240 |
+
"step": 73
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 22.0,
|
| 244 |
+
"eval_accuracy": 0.45652173913043476,
|
| 245 |
+
"eval_loss": 1.1926813125610352,
|
| 246 |
+
"eval_runtime": 0.3096,
|
| 247 |
+
"eval_samples_per_second": 148.592,
|
| 248 |
+
"eval_steps_per_second": 9.691,
|
| 249 |
+
"step": 77
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 22.86,
|
| 253 |
+
"learning_rate": 9.999999999999999e-06,
|
| 254 |
+
"loss": 1.1647,
|
| 255 |
+
"step": 80
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 22.86,
|
| 259 |
+
"eval_accuracy": 0.45652173913043476,
|
| 260 |
+
"eval_loss": 1.1927775144577026,
|
| 261 |
+
"eval_runtime": 0.2491,
|
| 262 |
+
"eval_samples_per_second": 184.697,
|
| 263 |
+
"eval_steps_per_second": 12.045,
|
| 264 |
+
"step": 80
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 24.0,
|
| 268 |
+
"eval_accuracy": 0.45652173913043476,
|
| 269 |
+
"eval_loss": 1.1924192905426025,
|
| 270 |
+
"eval_runtime": 0.2991,
|
| 271 |
+
"eval_samples_per_second": 153.812,
|
| 272 |
+
"eval_steps_per_second": 10.031,
|
| 273 |
+
"step": 84
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 24.86,
|
| 277 |
+
"eval_accuracy": 0.45652173913043476,
|
| 278 |
+
"eval_loss": 1.1902908086776733,
|
| 279 |
+
"eval_runtime": 0.3005,
|
| 280 |
+
"eval_samples_per_second": 153.097,
|
| 281 |
+
"eval_steps_per_second": 9.985,
|
| 282 |
+
"step": 87
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 25.71,
|
| 286 |
+
"learning_rate": 9.375000000000001e-06,
|
| 287 |
+
"loss": 1.1568,
|
| 288 |
+
"step": 90
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 26.0,
|
| 292 |
+
"eval_accuracy": 0.45652173913043476,
|
| 293 |
+
"eval_loss": 1.1878631114959717,
|
| 294 |
+
"eval_runtime": 0.2861,
|
| 295 |
+
"eval_samples_per_second": 160.803,
|
| 296 |
+
"eval_steps_per_second": 10.487,
|
| 297 |
+
"step": 91
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 26.86,
|
| 301 |
+
"eval_accuracy": 0.45652173913043476,
|
| 302 |
+
"eval_loss": 1.1913325786590576,
|
| 303 |
+
"eval_runtime": 0.2806,
|
| 304 |
+
"eval_samples_per_second": 163.951,
|
| 305 |
+
"eval_steps_per_second": 10.692,
|
| 306 |
+
"step": 94
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 28.0,
|
| 310 |
+
"eval_accuracy": 0.4782608695652174,
|
| 311 |
+
"eval_loss": 1.204640507698059,
|
| 312 |
+
"eval_runtime": 0.2621,
|
| 313 |
+
"eval_samples_per_second": 175.533,
|
| 314 |
+
"eval_steps_per_second": 11.448,
|
| 315 |
+
"step": 98
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 28.57,
|
| 319 |
+
"learning_rate": 8.750000000000001e-06,
|
| 320 |
+
"loss": 1.1432,
|
| 321 |
+
"step": 100
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 28.86,
|
| 325 |
+
"eval_accuracy": 0.4782608695652174,
|
| 326 |
+
"eval_loss": 1.193393588066101,
|
| 327 |
+
"eval_runtime": 0.2361,
|
| 328 |
+
"eval_samples_per_second": 194.871,
|
| 329 |
+
"eval_steps_per_second": 12.709,
|
| 330 |
+
"step": 101
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 30.0,
|
| 334 |
+
"eval_accuracy": 0.4782608695652174,
|
| 335 |
+
"eval_loss": 1.166512131690979,
|
| 336 |
+
"eval_runtime": 0.2421,
|
| 337 |
+
"eval_samples_per_second": 190.04,
|
| 338 |
+
"eval_steps_per_second": 12.394,
|
| 339 |
+
"step": 105
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 30.86,
|
| 343 |
+
"eval_accuracy": 0.4782608695652174,
|
| 344 |
+
"eval_loss": 1.1600818634033203,
|
| 345 |
+
"eval_runtime": 0.2381,
|
| 346 |
+
"eval_samples_per_second": 193.234,
|
| 347 |
+
"eval_steps_per_second": 12.602,
|
| 348 |
+
"step": 108
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 31.43,
|
| 352 |
+
"learning_rate": 8.125e-06,
|
| 353 |
+
"loss": 1.1112,
|
| 354 |
+
"step": 110
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 32.0,
|
| 358 |
+
"eval_accuracy": 0.5,
|
| 359 |
+
"eval_loss": 1.1623895168304443,
|
| 360 |
+
"eval_runtime": 0.2801,
|
| 361 |
+
"eval_samples_per_second": 164.249,
|
| 362 |
+
"eval_steps_per_second": 10.712,
|
| 363 |
+
"step": 112
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 32.86,
|
| 367 |
+
"eval_accuracy": 0.5217391304347826,
|
| 368 |
+
"eval_loss": 1.1663668155670166,
|
| 369 |
+
"eval_runtime": 0.3126,
|
| 370 |
+
"eval_samples_per_second": 147.162,
|
| 371 |
+
"eval_steps_per_second": 9.597,
|
| 372 |
+
"step": 115
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 34.0,
|
| 376 |
+
"eval_accuracy": 0.5,
|
| 377 |
+
"eval_loss": 1.1692047119140625,
|
| 378 |
+
"eval_runtime": 0.2586,
|
| 379 |
+
"eval_samples_per_second": 177.904,
|
| 380 |
+
"eval_steps_per_second": 11.602,
|
| 381 |
+
"step": 119
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 34.29,
|
| 385 |
+
"learning_rate": 7.5e-06,
|
| 386 |
+
"loss": 1.1132,
|
| 387 |
+
"step": 120
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 34.86,
|
| 391 |
+
"eval_accuracy": 0.5434782608695652,
|
| 392 |
+
"eval_loss": 1.1513336896896362,
|
| 393 |
+
"eval_runtime": 0.2416,
|
| 394 |
+
"eval_samples_per_second": 190.427,
|
| 395 |
+
"eval_steps_per_second": 12.419,
|
| 396 |
+
"step": 122
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 36.0,
|
| 400 |
+
"eval_accuracy": 0.5869565217391305,
|
| 401 |
+
"eval_loss": 1.1384443044662476,
|
| 402 |
+
"eval_runtime": 0.2461,
|
| 403 |
+
"eval_samples_per_second": 186.95,
|
| 404 |
+
"eval_steps_per_second": 12.192,
|
| 405 |
+
"step": 126
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 36.86,
|
| 409 |
+
"eval_accuracy": 0.6086956521739131,
|
| 410 |
+
"eval_loss": 1.127366542816162,
|
| 411 |
+
"eval_runtime": 0.2446,
|
| 412 |
+
"eval_samples_per_second": 188.091,
|
| 413 |
+
"eval_steps_per_second": 12.267,
|
| 414 |
+
"step": 129
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 37.14,
|
| 418 |
+
"learning_rate": 6.875e-06,
|
| 419 |
+
"loss": 1.0642,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 38.0,
|
| 424 |
+
"eval_accuracy": 0.5869565217391305,
|
| 425 |
+
"eval_loss": 1.1442575454711914,
|
| 426 |
+
"eval_runtime": 0.2586,
|
| 427 |
+
"eval_samples_per_second": 177.903,
|
| 428 |
+
"eval_steps_per_second": 11.602,
|
| 429 |
+
"step": 133
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 38.86,
|
| 433 |
+
"eval_accuracy": 0.5,
|
| 434 |
+
"eval_loss": 1.1651057004928589,
|
| 435 |
+
"eval_runtime": 0.2496,
|
| 436 |
+
"eval_samples_per_second": 184.324,
|
| 437 |
+
"eval_steps_per_second": 12.021,
|
| 438 |
+
"step": 136
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 40.0,
|
| 442 |
+
"learning_rate": 6.25e-06,
|
| 443 |
+
"loss": 1.0439,
|
| 444 |
+
"step": 140
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 40.0,
|
| 448 |
+
"eval_accuracy": 0.5,
|
| 449 |
+
"eval_loss": 1.149288296699524,
|
| 450 |
+
"eval_runtime": 0.2441,
|
| 451 |
+
"eval_samples_per_second": 188.478,
|
| 452 |
+
"eval_steps_per_second": 12.292,
|
| 453 |
+
"step": 140
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 40.86,
|
| 457 |
+
"eval_accuracy": 0.5217391304347826,
|
| 458 |
+
"eval_loss": 1.1330839395523071,
|
| 459 |
+
"eval_runtime": 0.2811,
|
| 460 |
+
"eval_samples_per_second": 163.664,
|
| 461 |
+
"eval_steps_per_second": 10.674,
|
| 462 |
+
"step": 143
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 42.0,
|
| 466 |
+
"eval_accuracy": 0.5869565217391305,
|
| 467 |
+
"eval_loss": 1.1032251119613647,
|
| 468 |
+
"eval_runtime": 0.2521,
|
| 469 |
+
"eval_samples_per_second": 182.499,
|
| 470 |
+
"eval_steps_per_second": 11.902,
|
| 471 |
+
"step": 147
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 42.86,
|
| 475 |
+
"learning_rate": 5.625e-06,
|
| 476 |
+
"loss": 1.0362,
|
| 477 |
+
"step": 150
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 42.86,
|
| 481 |
+
"eval_accuracy": 0.6304347826086957,
|
| 482 |
+
"eval_loss": 1.0988132953643799,
|
| 483 |
+
"eval_runtime": 0.2916,
|
| 484 |
+
"eval_samples_per_second": 157.767,
|
| 485 |
+
"eval_steps_per_second": 10.289,
|
| 486 |
+
"step": 150
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 44.0,
|
| 490 |
+
"eval_accuracy": 0.5869565217391305,
|
| 491 |
+
"eval_loss": 1.1092532873153687,
|
| 492 |
+
"eval_runtime": 0.2506,
|
| 493 |
+
"eval_samples_per_second": 183.583,
|
| 494 |
+
"eval_steps_per_second": 11.973,
|
| 495 |
+
"step": 154
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 44.86,
|
| 499 |
+
"eval_accuracy": 0.5869565217391305,
|
| 500 |
+
"eval_loss": 1.1101136207580566,
|
| 501 |
+
"eval_runtime": 0.22,
|
| 502 |
+
"eval_samples_per_second": 209.044,
|
| 503 |
+
"eval_steps_per_second": 13.633,
|
| 504 |
+
"step": 157
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 45.71,
|
| 508 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 509 |
+
"loss": 1.0177,
|
| 510 |
+
"step": 160
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 46.0,
|
| 514 |
+
"eval_accuracy": 0.6304347826086957,
|
| 515 |
+
"eval_loss": 1.0903021097183228,
|
| 516 |
+
"eval_runtime": 0.3931,
|
| 517 |
+
"eval_samples_per_second": 117.022,
|
| 518 |
+
"eval_steps_per_second": 7.632,
|
| 519 |
+
"step": 161
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 46.86,
|
| 523 |
+
"eval_accuracy": 0.6521739130434783,
|
| 524 |
+
"eval_loss": 1.069130301475525,
|
| 525 |
+
"eval_runtime": 0.4281,
|
| 526 |
+
"eval_samples_per_second": 107.447,
|
| 527 |
+
"eval_steps_per_second": 7.007,
|
| 528 |
+
"step": 164
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 48.0,
|
| 532 |
+
"eval_accuracy": 0.6739130434782609,
|
| 533 |
+
"eval_loss": 1.0509947538375854,
|
| 534 |
+
"eval_runtime": 0.2701,
|
| 535 |
+
"eval_samples_per_second": 170.332,
|
| 536 |
+
"eval_steps_per_second": 11.109,
|
| 537 |
+
"step": 168
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 48.57,
|
| 541 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 542 |
+
"loss": 1.0,
|
| 543 |
+
"step": 170
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 48.86,
|
| 547 |
+
"eval_accuracy": 0.6521739130434783,
|
| 548 |
+
"eval_loss": 1.0451492071151733,
|
| 549 |
+
"eval_runtime": 0.2466,
|
| 550 |
+
"eval_samples_per_second": 186.563,
|
| 551 |
+
"eval_steps_per_second": 12.167,
|
| 552 |
+
"step": 171
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 50.0,
|
| 556 |
+
"eval_accuracy": 0.6521739130434783,
|
| 557 |
+
"eval_loss": 1.0425117015838623,
|
| 558 |
+
"eval_runtime": 0.2591,
|
| 559 |
+
"eval_samples_per_second": 177.566,
|
| 560 |
+
"eval_steps_per_second": 11.58,
|
| 561 |
+
"step": 175
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 50.86,
|
| 565 |
+
"eval_accuracy": 0.6086956521739131,
|
| 566 |
+
"eval_loss": 1.0512455701828003,
|
| 567 |
+
"eval_runtime": 0.2671,
|
| 568 |
+
"eval_samples_per_second": 172.246,
|
| 569 |
+
"eval_steps_per_second": 11.233,
|
| 570 |
+
"step": 178
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 51.43,
|
| 574 |
+
"learning_rate": 3.75e-06,
|
| 575 |
+
"loss": 0.9636,
|
| 576 |
+
"step": 180
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 52.0,
|
| 580 |
+
"eval_accuracy": 0.6304347826086957,
|
| 581 |
+
"eval_loss": 1.044124722480774,
|
| 582 |
+
"eval_runtime": 0.2541,
|
| 583 |
+
"eval_samples_per_second": 181.062,
|
| 584 |
+
"eval_steps_per_second": 11.808,
|
| 585 |
+
"step": 182
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 52.86,
|
| 589 |
+
"eval_accuracy": 0.6521739130434783,
|
| 590 |
+
"eval_loss": 1.0401920080184937,
|
| 591 |
+
"eval_runtime": 0.2676,
|
| 592 |
+
"eval_samples_per_second": 171.917,
|
| 593 |
+
"eval_steps_per_second": 11.212,
|
| 594 |
+
"step": 185
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 54.0,
|
| 598 |
+
"eval_accuracy": 0.6521739130434783,
|
| 599 |
+
"eval_loss": 1.0161322355270386,
|
| 600 |
+
"eval_runtime": 0.2421,
|
| 601 |
+
"eval_samples_per_second": 190.039,
|
| 602 |
+
"eval_steps_per_second": 12.394,
|
| 603 |
+
"step": 189
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 54.29,
|
| 607 |
+
"learning_rate": 3.125e-06,
|
| 608 |
+
"loss": 0.9744,
|
| 609 |
+
"step": 190
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 54.86,
|
| 613 |
+
"eval_accuracy": 0.6521739130434783,
|
| 614 |
+
"eval_loss": 1.0072776079177856,
|
| 615 |
+
"eval_runtime": 0.3861,
|
| 616 |
+
"eval_samples_per_second": 119.144,
|
| 617 |
+
"eval_steps_per_second": 7.77,
|
| 618 |
+
"step": 192
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 56.0,
|
| 622 |
+
"eval_accuracy": 0.6521739130434783,
|
| 623 |
+
"eval_loss": 1.0047576427459717,
|
| 624 |
+
"eval_runtime": 0.2431,
|
| 625 |
+
"eval_samples_per_second": 189.257,
|
| 626 |
+
"eval_steps_per_second": 12.343,
|
| 627 |
+
"step": 196
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 56.86,
|
| 631 |
+
"eval_accuracy": 0.6521739130434783,
|
| 632 |
+
"eval_loss": 0.9993048310279846,
|
| 633 |
+
"eval_runtime": 0.2251,
|
| 634 |
+
"eval_samples_per_second": 204.398,
|
| 635 |
+
"eval_steps_per_second": 13.33,
|
| 636 |
+
"step": 199
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 57.14,
|
| 640 |
+
"learning_rate": 2.4999999999999998e-06,
|
| 641 |
+
"loss": 0.9233,
|
| 642 |
+
"step": 200
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 58.0,
|
| 646 |
+
"eval_accuracy": 0.6521739130434783,
|
| 647 |
+
"eval_loss": 0.9939430952072144,
|
| 648 |
+
"eval_runtime": 0.2431,
|
| 649 |
+
"eval_samples_per_second": 189.258,
|
| 650 |
+
"eval_steps_per_second": 12.343,
|
| 651 |
+
"step": 203
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 58.86,
|
| 655 |
+
"eval_accuracy": 0.6521739130434783,
|
| 656 |
+
"eval_loss": 0.9938895106315613,
|
| 657 |
+
"eval_runtime": 0.2396,
|
| 658 |
+
"eval_samples_per_second": 192.017,
|
| 659 |
+
"eval_steps_per_second": 12.523,
|
| 660 |
+
"step": 206
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 60.0,
|
| 664 |
+
"learning_rate": 1.875e-06,
|
| 665 |
+
"loss": 0.9452,
|
| 666 |
+
"step": 210
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 60.0,
|
| 670 |
+
"eval_accuracy": 0.6521739130434783,
|
| 671 |
+
"eval_loss": 0.9975183010101318,
|
| 672 |
+
"eval_runtime": 0.2521,
|
| 673 |
+
"eval_samples_per_second": 182.499,
|
| 674 |
+
"eval_steps_per_second": 11.902,
|
| 675 |
+
"step": 210
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 60.86,
|
| 679 |
+
"eval_accuracy": 0.6086956521739131,
|
| 680 |
+
"eval_loss": 0.998058557510376,
|
| 681 |
+
"eval_runtime": 0.2471,
|
| 682 |
+
"eval_samples_per_second": 186.193,
|
| 683 |
+
"eval_steps_per_second": 12.143,
|
| 684 |
+
"step": 213
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 62.0,
|
| 688 |
+
"eval_accuracy": 0.6086956521739131,
|
| 689 |
+
"eval_loss": 0.9985237121582031,
|
| 690 |
+
"eval_runtime": 0.2421,
|
| 691 |
+
"eval_samples_per_second": 190.04,
|
| 692 |
+
"eval_steps_per_second": 12.394,
|
| 693 |
+
"step": 217
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 62.86,
|
| 697 |
+
"learning_rate": 1.2499999999999999e-06,
|
| 698 |
+
"loss": 0.9183,
|
| 699 |
+
"step": 220
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 62.86,
|
| 703 |
+
"eval_accuracy": 0.6086956521739131,
|
| 704 |
+
"eval_loss": 0.9968777298927307,
|
| 705 |
+
"eval_runtime": 0.2391,
|
| 706 |
+
"eval_samples_per_second": 192.425,
|
| 707 |
+
"eval_steps_per_second": 12.549,
|
| 708 |
+
"step": 220
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 64.0,
|
| 712 |
+
"eval_accuracy": 0.6304347826086957,
|
| 713 |
+
"eval_loss": 0.99575275182724,
|
| 714 |
+
"eval_runtime": 0.2351,
|
| 715 |
+
"eval_samples_per_second": 195.701,
|
| 716 |
+
"eval_steps_per_second": 12.763,
|
| 717 |
+
"step": 224
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 64.86,
|
| 721 |
+
"eval_accuracy": 0.6086956521739131,
|
| 722 |
+
"eval_loss": 0.9928344488143921,
|
| 723 |
+
"eval_runtime": 0.2406,
|
| 724 |
+
"eval_samples_per_second": 191.216,
|
| 725 |
+
"eval_steps_per_second": 12.471,
|
| 726 |
+
"step": 227
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 65.71,
|
| 730 |
+
"learning_rate": 6.249999999999999e-07,
|
| 731 |
+
"loss": 0.9449,
|
| 732 |
+
"step": 230
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 66.0,
|
| 736 |
+
"eval_accuracy": 0.6086956521739131,
|
| 737 |
+
"eval_loss": 0.9906012415885925,
|
| 738 |
+
"eval_runtime": 0.2456,
|
| 739 |
+
"eval_samples_per_second": 187.316,
|
| 740 |
+
"eval_steps_per_second": 12.216,
|
| 741 |
+
"step": 231
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 66.86,
|
| 745 |
+
"eval_accuracy": 0.6304347826086957,
|
| 746 |
+
"eval_loss": 0.9892796874046326,
|
| 747 |
+
"eval_runtime": 0.2501,
|
| 748 |
+
"eval_samples_per_second": 183.959,
|
| 749 |
+
"eval_steps_per_second": 11.997,
|
| 750 |
+
"step": 234
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 68.0,
|
| 754 |
+
"eval_accuracy": 0.6521739130434783,
|
| 755 |
+
"eval_loss": 0.9880576133728027,
|
| 756 |
+
"eval_runtime": 0.2471,
|
| 757 |
+
"eval_samples_per_second": 186.193,
|
| 758 |
+
"eval_steps_per_second": 12.143,
|
| 759 |
+
"step": 238
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 68.57,
|
| 763 |
+
"learning_rate": 0.0,
|
| 764 |
+
"loss": 0.9154,
|
| 765 |
+
"step": 240
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 68.57,
|
| 769 |
+
"eval_accuracy": 0.6521739130434783,
|
| 770 |
+
"eval_loss": 0.9880411028862,
|
| 771 |
+
"eval_runtime": 0.2566,
|
| 772 |
+
"eval_samples_per_second": 179.291,
|
| 773 |
+
"eval_steps_per_second": 11.693,
|
| 774 |
+
"step": 240
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 68.57,
|
| 778 |
+
"step": 240,
|
| 779 |
+
"total_flos": 4.754181186964685e+17,
|
| 780 |
+
"train_loss": 1.113492695490519,
|
| 781 |
+
"train_runtime": 374.3307,
|
| 782 |
+
"train_samples_per_second": 45.521,
|
| 783 |
+
"train_steps_per_second": 0.641
|
| 784 |
+
}
|
| 785 |
+
],
|
| 786 |
+
"logging_steps": 10,
|
| 787 |
+
"max_steps": 240,
|
| 788 |
+
"num_input_tokens_seen": 0,
|
| 789 |
+
"num_train_epochs": 80,
|
| 790 |
+
"save_steps": 500,
|
| 791 |
+
"total_flos": 4.754181186964685e+17,
|
| 792 |
+
"train_batch_size": 16,
|
| 793 |
+
"trial_name": null,
|
| 794 |
+
"trial_params": null
|
| 795 |
+
}
|