Commit
•
99530e5
1
Parent(s):
949cb22
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May28_06-55-24_96c9e3e99893/events.out.tfevents.1716898596.96c9e3e99893.24.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +883 -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 [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) 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: 0.95
|
| 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 [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2174
|
| 36 |
+
- Accuracy: 0.95
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 4.09349935387607e+19,
|
| 4 |
+
"train_loss": 0.34581250545650966,
|
| 5 |
+
"train_runtime": 18969.8729,
|
| 6 |
+
"train_samples_per_second": 9.268,
|
| 7 |
+
"train_steps_per_second": 0.579
|
| 8 |
+
}
|
runs/May28_06-55-24_96c9e3e99893/events.out.tfevents.1716898596.96c9e3e99893.24.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c39f902d9d698c496a4b91f92d21dcbd802fb491e36dc45412f9b8d921f6c589
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 4.09349935387607e+19,
|
| 4 |
+
"train_loss": 0.34581250545650966,
|
| 5 |
+
"train_runtime": 18969.8729,
|
| 6 |
+
"train_samples_per_second": 9.268,
|
| 7 |
+
"train_steps_per_second": 0.579
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,883 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.23055487871170044,
|
| 3 |
+
"best_model_checkpoint": "./convnext-base-wd1e-8-4e-5-erasing/checkpoint-10990",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10990,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"grad_norm": 21.871763229370117,
|
| 14 |
+
"learning_rate": 3.999182900797692e-05,
|
| 15 |
+
"loss": 2.4789,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 17.83153533935547,
|
| 21 |
+
"learning_rate": 3.996732270841873e-05,
|
| 22 |
+
"loss": 1.3163,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 19.49209213256836,
|
| 28 |
+
"learning_rate": 3.992650112540325e-05,
|
| 29 |
+
"loss": 1.0315,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36,
|
| 34 |
+
"grad_norm": 33.785457611083984,
|
| 35 |
+
"learning_rate": 3.986939761421341e-05,
|
| 36 |
+
"loss": 0.8006,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.45,
|
| 41 |
+
"grad_norm": 22.69280242919922,
|
| 42 |
+
"learning_rate": 3.9796058834082656e-05,
|
| 43 |
+
"loss": 0.7755,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.55,
|
| 48 |
+
"grad_norm": 17.21114158630371,
|
| 49 |
+
"learning_rate": 3.970654471006971e-05,
|
| 50 |
+
"loss": 0.6705,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"grad_norm": 25.925142288208008,
|
| 56 |
+
"learning_rate": 3.960092838409391e-05,
|
| 57 |
+
"loss": 0.7039,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.73,
|
| 62 |
+
"grad_norm": 9.736983299255371,
|
| 63 |
+
"learning_rate": 3.947929615517096e-05,
|
| 64 |
+
"loss": 0.6441,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.82,
|
| 69 |
+
"grad_norm": 13.611920356750488,
|
| 70 |
+
"learning_rate": 3.93417474088981e-05,
|
| 71 |
+
"loss": 0.6039,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.91,
|
| 76 |
+
"grad_norm": 13.253599166870117,
|
| 77 |
+
"learning_rate": 3.9188394536246174e-05,
|
| 78 |
+
"loss": 0.6036,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.8930417495029821,
|
| 84 |
+
"eval_loss": 0.3736543655395508,
|
| 85 |
+
"eval_runtime": 106.8745,
|
| 86 |
+
"eval_samples_per_second": 23.532,
|
| 87 |
+
"eval_steps_per_second": 1.478,
|
| 88 |
+
"step": 1099
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0,
|
| 92 |
+
"grad_norm": 34.44277572631836,
|
| 93 |
+
"learning_rate": 3.90193628417251e-05,
|
| 94 |
+
"loss": 0.624,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.09,
|
| 99 |
+
"grad_norm": 14.051901817321777,
|
| 100 |
+
"learning_rate": 3.883479044099763e-05,
|
| 101 |
+
"loss": 0.5383,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.18,
|
| 106 |
+
"grad_norm": 23.078445434570312,
|
| 107 |
+
"learning_rate": 3.8634828148025175e-05,
|
| 108 |
+
"loss": 0.507,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.27,
|
| 113 |
+
"grad_norm": 19.300426483154297,
|
| 114 |
+
"learning_rate": 3.841963935183782e-05,
|
| 115 |
+
"loss": 0.4953,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"grad_norm": 22.54229736328125,
|
| 121 |
+
"learning_rate": 3.818939988302927e-05,
|
| 122 |
+
"loss": 0.4969,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.46,
|
| 127 |
+
"grad_norm": 17.774635314941406,
|
| 128 |
+
"learning_rate": 3.7944297870085823e-05,
|
| 129 |
+
"loss": 0.4826,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.55,
|
| 134 |
+
"grad_norm": 13.029126167297363,
|
| 135 |
+
"learning_rate": 3.768453358566675e-05,
|
| 136 |
+
"loss": 0.5326,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.64,
|
| 141 |
+
"grad_norm": 22.84644317626953,
|
| 142 |
+
"learning_rate": 3.741031928296162e-05,
|
| 143 |
+
"loss": 0.4899,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.73,
|
| 148 |
+
"grad_norm": 17.86623764038086,
|
| 149 |
+
"learning_rate": 3.712187902225845e-05,
|
| 150 |
+
"loss": 0.4475,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.82,
|
| 155 |
+
"grad_norm": 15.729595184326172,
|
| 156 |
+
"learning_rate": 3.681944848786418e-05,
|
| 157 |
+
"loss": 0.4841,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.91,
|
| 162 |
+
"grad_norm": 15.516929626464844,
|
| 163 |
+
"learning_rate": 3.6503274795527193e-05,
|
| 164 |
+
"loss": 0.4997,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.0,
|
| 169 |
+
"eval_accuracy": 0.9248508946322067,
|
| 170 |
+
"eval_loss": 0.27299922704696655,
|
| 171 |
+
"eval_runtime": 105.5397,
|
| 172 |
+
"eval_samples_per_second": 23.83,
|
| 173 |
+
"eval_steps_per_second": 1.497,
|
| 174 |
+
"step": 2198
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0,
|
| 178 |
+
"grad_norm": 32.8221321105957,
|
| 179 |
+
"learning_rate": 3.617361629051932e-05,
|
| 180 |
+
"loss": 0.4712,
|
| 181 |
+
"step": 2200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.09,
|
| 185 |
+
"grad_norm": 20.870311737060547,
|
| 186 |
+
"learning_rate": 3.5830742336542e-05,
|
| 187 |
+
"loss": 0.3474,
|
| 188 |
+
"step": 2300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.18,
|
| 192 |
+
"grad_norm": 22.007932662963867,
|
| 193 |
+
"learning_rate": 3.547493309562956e-05,
|
| 194 |
+
"loss": 0.434,
|
| 195 |
+
"step": 2400
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.27,
|
| 199 |
+
"grad_norm": 11.817858695983887,
|
| 200 |
+
"learning_rate": 3.51064792992289e-05,
|
| 201 |
+
"loss": 0.3748,
|
| 202 |
+
"step": 2500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.37,
|
| 206 |
+
"grad_norm": 15.62509536743164,
|
| 207 |
+
"learning_rate": 3.472568201064314e-05,
|
| 208 |
+
"loss": 0.4473,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.46,
|
| 213 |
+
"grad_norm": 29.18074607849121,
|
| 214 |
+
"learning_rate": 3.433285237903305e-05,
|
| 215 |
+
"loss": 0.384,
|
| 216 |
+
"step": 2700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.55,
|
| 220 |
+
"grad_norm": 3.7826242446899414,
|
| 221 |
+
"learning_rate": 3.392831138517724e-05,
|
| 222 |
+
"loss": 0.4136,
|
| 223 |
+
"step": 2800
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.64,
|
| 227 |
+
"grad_norm": 37.68365478515625,
|
| 228 |
+
"learning_rate": 3.3512389579199094e-05,
|
| 229 |
+
"loss": 0.3916,
|
| 230 |
+
"step": 2900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.73,
|
| 234 |
+
"grad_norm": 16.420135498046875,
|
| 235 |
+
"learning_rate": 3.308542681047451e-05,
|
| 236 |
+
"loss": 0.4228,
|
| 237 |
+
"step": 3000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.82,
|
| 241 |
+
"grad_norm": 21.540740966796875,
|
| 242 |
+
"learning_rate": 3.264777194994121e-05,
|
| 243 |
+
"loss": 0.401,
|
| 244 |
+
"step": 3100
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.91,
|
| 248 |
+
"grad_norm": 17.597993850708008,
|
| 249 |
+
"learning_rate": 3.219978260503665e-05,
|
| 250 |
+
"loss": 0.3663,
|
| 251 |
+
"step": 3200
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"eval_accuracy": 0.9260437375745527,
|
| 256 |
+
"eval_loss": 0.26662740111351013,
|
| 257 |
+
"eval_runtime": 105.4604,
|
| 258 |
+
"eval_samples_per_second": 23.848,
|
| 259 |
+
"eval_steps_per_second": 1.498,
|
| 260 |
+
"step": 3297
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0,
|
| 264 |
+
"grad_norm": 7.028054237365723,
|
| 265 |
+
"learning_rate": 3.174182482749717e-05,
|
| 266 |
+
"loss": 0.4076,
|
| 267 |
+
"step": 3300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.09,
|
| 271 |
+
"grad_norm": 6.525599479675293,
|
| 272 |
+
"learning_rate": 3.12742728142575e-05,
|
| 273 |
+
"loss": 0.3146,
|
| 274 |
+
"step": 3400
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.18,
|
| 278 |
+
"grad_norm": 14.01247787475586,
|
| 279 |
+
"learning_rate": 3.079750860169469e-05,
|
| 280 |
+
"loss": 0.3465,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.28,
|
| 285 |
+
"grad_norm": 23.31292152404785,
|
| 286 |
+
"learning_rate": 3.031192175346651e-05,
|
| 287 |
+
"loss": 0.3685,
|
| 288 |
+
"step": 3600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.37,
|
| 292 |
+
"grad_norm": 20.722320556640625,
|
| 293 |
+
"learning_rate": 2.9817909042199313e-05,
|
| 294 |
+
"loss": 0.3136,
|
| 295 |
+
"step": 3700
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.46,
|
| 299 |
+
"grad_norm": 17.478958129882812,
|
| 300 |
+
"learning_rate": 2.93158741252854e-05,
|
| 301 |
+
"loss": 0.3403,
|
| 302 |
+
"step": 3800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.55,
|
| 306 |
+
"grad_norm": 9.703248023986816,
|
| 307 |
+
"learning_rate": 2.8806227215054902e-05,
|
| 308 |
+
"loss": 0.3432,
|
| 309 |
+
"step": 3900
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.64,
|
| 313 |
+
"grad_norm": 11.908836364746094,
|
| 314 |
+
"learning_rate": 2.828938474359164e-05,
|
| 315 |
+
"loss": 0.3695,
|
| 316 |
+
"step": 4000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"grad_norm": 22.338346481323242,
|
| 321 |
+
"learning_rate": 2.7765769022466762e-05,
|
| 322 |
+
"loss": 0.3569,
|
| 323 |
+
"step": 4100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.82,
|
| 327 |
+
"grad_norm": 3.3628461360931396,
|
| 328 |
+
"learning_rate": 2.723580789766831e-05,
|
| 329 |
+
"loss": 0.3324,
|
| 330 |
+
"step": 4200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.91,
|
| 334 |
+
"grad_norm": 17.76543617248535,
|
| 335 |
+
"learning_rate": 2.669993440000862e-05,
|
| 336 |
+
"loss": 0.3176,
|
| 337 |
+
"step": 4300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.0,
|
| 341 |
+
"eval_accuracy": 0.9391650099403579,
|
| 342 |
+
"eval_loss": 0.2379751056432724,
|
| 343 |
+
"eval_runtime": 105.9425,
|
| 344 |
+
"eval_samples_per_second": 23.739,
|
| 345 |
+
"eval_steps_per_second": 1.491,
|
| 346 |
+
"step": 4396
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.0,
|
| 350 |
+
"grad_norm": 13.366058349609375,
|
| 351 |
+
"learning_rate": 2.6158586391295163e-05,
|
| 352 |
+
"loss": 0.2818,
|
| 353 |
+
"step": 4400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.09,
|
| 357 |
+
"grad_norm": 10.28676700592041,
|
| 358 |
+
"learning_rate": 2.5612206206554034e-05,
|
| 359 |
+
"loss": 0.2891,
|
| 360 |
+
"step": 4500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.19,
|
| 364 |
+
"grad_norm": 15.261099815368652,
|
| 365 |
+
"learning_rate": 2.5061240292598336e-05,
|
| 366 |
+
"loss": 0.3196,
|
| 367 |
+
"step": 4600
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.28,
|
| 371 |
+
"grad_norm": 23.628677368164062,
|
| 372 |
+
"learning_rate": 2.4506138843236867e-05,
|
| 373 |
+
"loss": 0.2921,
|
| 374 |
+
"step": 4700
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.37,
|
| 378 |
+
"grad_norm": 28.432357788085938,
|
| 379 |
+
"learning_rate": 2.3947355431421094e-05,
|
| 380 |
+
"loss": 0.2641,
|
| 381 |
+
"step": 4800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.46,
|
| 385 |
+
"grad_norm": 13.766435623168945,
|
| 386 |
+
"learning_rate": 2.3385346638631082e-05,
|
| 387 |
+
"loss": 0.2599,
|
| 388 |
+
"step": 4900
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.55,
|
| 392 |
+
"grad_norm": 17.775606155395508,
|
| 393 |
+
"learning_rate": 2.2820571681803108e-05,
|
| 394 |
+
"loss": 0.2917,
|
| 395 |
+
"step": 5000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.64,
|
| 399 |
+
"grad_norm": 34.89625549316406,
|
| 400 |
+
"learning_rate": 2.225349203810388e-05,
|
| 401 |
+
"loss": 0.2867,
|
| 402 |
+
"step": 5100
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.73,
|
| 406 |
+
"grad_norm": 20.649389266967773,
|
| 407 |
+
"learning_rate": 2.16845710678579e-05,
|
| 408 |
+
"loss": 0.3066,
|
| 409 |
+
"step": 5200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.82,
|
| 413 |
+
"grad_norm": 11.82371711730957,
|
| 414 |
+
"learning_rate": 2.111427363593615e-05,
|
| 415 |
+
"loss": 0.302,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.91,
|
| 420 |
+
"grad_norm": 18.50792694091797,
|
| 421 |
+
"learning_rate": 2.0543065731915316e-05,
|
| 422 |
+
"loss": 0.305,
|
| 423 |
+
"step": 5400
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.0,
|
| 427 |
+
"eval_accuracy": 0.9371769383697813,
|
| 428 |
+
"eval_loss": 0.24580277502536774,
|
| 429 |
+
"eval_runtime": 106.0764,
|
| 430 |
+
"eval_samples_per_second": 23.709,
|
| 431 |
+
"eval_steps_per_second": 1.489,
|
| 432 |
+
"step": 5495
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.0,
|
| 436 |
+
"grad_norm": 17.39256477355957,
|
| 437 |
+
"learning_rate": 1.997141408931814e-05,
|
| 438 |
+
"loss": 0.2981,
|
| 439 |
+
"step": 5500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.1,
|
| 443 |
+
"grad_norm": 15.757665634155273,
|
| 444 |
+
"learning_rate": 1.9399785804245775e-05,
|
| 445 |
+
"loss": 0.237,
|
| 446 |
+
"step": 5600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.19,
|
| 450 |
+
"grad_norm": 13.927785873413086,
|
| 451 |
+
"learning_rate": 1.8828647953713982e-05,
|
| 452 |
+
"loss": 0.2281,
|
| 453 |
+
"step": 5700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.28,
|
| 457 |
+
"grad_norm": 27.117650985717773,
|
| 458 |
+
"learning_rate": 1.825846721400482e-05,
|
| 459 |
+
"loss": 0.2586,
|
| 460 |
+
"step": 5800
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.37,
|
| 464 |
+
"grad_norm": 29.655193328857422,
|
| 465 |
+
"learning_rate": 1.7689709479345895e-05,
|
| 466 |
+
"loss": 0.2595,
|
| 467 |
+
"step": 5900
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.46,
|
| 471 |
+
"grad_norm": 12.67216968536377,
|
| 472 |
+
"learning_rate": 1.7122839481228503e-05,
|
| 473 |
+
"loss": 0.2449,
|
| 474 |
+
"step": 6000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.55,
|
| 478 |
+
"grad_norm": 15.060705184936523,
|
| 479 |
+
"learning_rate": 1.65583204086759e-05,
|
| 480 |
+
"loss": 0.2558,
|
| 481 |
+
"step": 6100
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.64,
|
| 485 |
+
"grad_norm": 35.11772918701172,
|
| 486 |
+
"learning_rate": 1.599661352977198e-05,
|
| 487 |
+
"loss": 0.2148,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.73,
|
| 492 |
+
"grad_norm": 13.670873641967773,
|
| 493 |
+
"learning_rate": 1.543817781475941e-05,
|
| 494 |
+
"loss": 0.2593,
|
| 495 |
+
"step": 6300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.82,
|
| 499 |
+
"grad_norm": 16.197233200073242,
|
| 500 |
+
"learning_rate": 1.4883469561015482e-05,
|
| 501 |
+
"loss": 0.2482,
|
| 502 |
+
"step": 6400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.91,
|
| 506 |
+
"grad_norm": 26.83169937133789,
|
| 507 |
+
"learning_rate": 1.433294202021182e-05,
|
| 508 |
+
"loss": 0.2489,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.0,
|
| 513 |
+
"eval_accuracy": 0.945924453280318,
|
| 514 |
+
"eval_loss": 0.23894770443439484,
|
| 515 |
+
"eval_runtime": 105.5878,
|
| 516 |
+
"eval_samples_per_second": 23.819,
|
| 517 |
+
"eval_steps_per_second": 1.496,
|
| 518 |
+
"step": 6594
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.01,
|
| 522 |
+
"grad_norm": 15.461714744567871,
|
| 523 |
+
"learning_rate": 1.378704502796289e-05,
|
| 524 |
+
"loss": 0.2724,
|
| 525 |
+
"step": 6600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.1,
|
| 529 |
+
"grad_norm": 13.98656177520752,
|
| 530 |
+
"learning_rate": 1.3246224636265588e-05,
|
| 531 |
+
"loss": 0.2111,
|
| 532 |
+
"step": 6700
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.19,
|
| 536 |
+
"grad_norm": 11.368219375610352,
|
| 537 |
+
"learning_rate": 1.2710922749030558e-05,
|
| 538 |
+
"loss": 0.2428,
|
| 539 |
+
"step": 6800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.28,
|
| 543 |
+
"grad_norm": 12.15278434753418,
|
| 544 |
+
"learning_rate": 1.2181576761002872e-05,
|
| 545 |
+
"loss": 0.2478,
|
| 546 |
+
"step": 6900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.37,
|
| 550 |
+
"grad_norm": 2.1350884437561035,
|
| 551 |
+
"learning_rate": 1.1658619200367073e-05,
|
| 552 |
+
"loss": 0.2005,
|
| 553 |
+
"step": 7000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.46,
|
| 557 |
+
"grad_norm": 0.2970704138278961,
|
| 558 |
+
"learning_rate": 1.1142477375328796e-05,
|
| 559 |
+
"loss": 0.2369,
|
| 560 |
+
"step": 7100
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.55,
|
| 564 |
+
"grad_norm": 11.124874114990234,
|
| 565 |
+
"learning_rate": 1.0633573024961584e-05,
|
| 566 |
+
"loss": 0.2222,
|
| 567 |
+
"step": 7200
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.64,
|
| 571 |
+
"grad_norm": 12.277088165283203,
|
| 572 |
+
"learning_rate": 1.013232197460415e-05,
|
| 573 |
+
"loss": 0.2092,
|
| 574 |
+
"step": 7300
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.73,
|
| 578 |
+
"grad_norm": 26.41246223449707,
|
| 579 |
+
"learning_rate": 9.639133796089901e-06,
|
| 580 |
+
"loss": 0.2214,
|
| 581 |
+
"step": 7400
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.82,
|
| 585 |
+
"grad_norm": 4.2534918785095215,
|
| 586 |
+
"learning_rate": 9.154411473086087e-06,
|
| 587 |
+
"loss": 0.1903,
|
| 588 |
+
"step": 7500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.92,
|
| 592 |
+
"grad_norm": 0.8372716307640076,
|
| 593 |
+
"learning_rate": 8.678551071816193e-06,
|
| 594 |
+
"loss": 0.2356,
|
| 595 |
+
"step": 7600
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.0,
|
| 599 |
+
"eval_accuracy": 0.9451292246520875,
|
| 600 |
+
"eval_loss": 0.24236075580120087,
|
| 601 |
+
"eval_runtime": 105.4122,
|
| 602 |
+
"eval_samples_per_second": 23.859,
|
| 603 |
+
"eval_steps_per_second": 1.499,
|
| 604 |
+
"step": 7693
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.01,
|
| 608 |
+
"grad_norm": 21.71571159362793,
|
| 609 |
+
"learning_rate": 8.211941417434488e-06,
|
| 610 |
+
"loss": 0.1892,
|
| 611 |
+
"step": 7700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.1,
|
| 615 |
+
"grad_norm": 35.81491470336914,
|
| 616 |
+
"learning_rate": 7.754963776317355e-06,
|
| 617 |
+
"loss": 0.2233,
|
| 618 |
+
"step": 7800
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.19,
|
| 622 |
+
"grad_norm": 14.517807960510254,
|
| 623 |
+
"learning_rate": 7.307991544530839e-06,
|
| 624 |
+
"loss": 0.184,
|
| 625 |
+
"step": 7900
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.28,
|
| 629 |
+
"grad_norm": 4.057854652404785,
|
| 630 |
+
"learning_rate": 6.871389942728983e-06,
|
| 631 |
+
"loss": 0.2041,
|
| 632 |
+
"step": 8000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.37,
|
| 636 |
+
"grad_norm": 9.720903396606445,
|
| 637 |
+
"learning_rate": 6.445515717732332e-06,
|
| 638 |
+
"loss": 0.1968,
|
| 639 |
+
"step": 8100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.46,
|
| 643 |
+
"grad_norm": 8.159006118774414,
|
| 644 |
+
"learning_rate": 6.03071685103043e-06,
|
| 645 |
+
"loss": 0.204,
|
| 646 |
+
"step": 8200
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.55,
|
| 650 |
+
"grad_norm": 7.216451168060303,
|
| 651 |
+
"learning_rate": 5.627332274446377e-06,
|
| 652 |
+
"loss": 0.1778,
|
| 653 |
+
"step": 8300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.64,
|
| 657 |
+
"grad_norm": 16.071630477905273,
|
| 658 |
+
"learning_rate": 5.2356915931959086e-06,
|
| 659 |
+
"loss": 0.2121,
|
| 660 |
+
"step": 8400
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.73,
|
| 664 |
+
"grad_norm": 2.6936397552490234,
|
| 665 |
+
"learning_rate": 4.856114816567281e-06,
|
| 666 |
+
"loss": 0.1652,
|
| 667 |
+
"step": 8500
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.83,
|
| 671 |
+
"grad_norm": 13.142534255981445,
|
| 672 |
+
"learning_rate": 4.488912096441886e-06,
|
| 673 |
+
"loss": 0.1989,
|
| 674 |
+
"step": 8600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.92,
|
| 678 |
+
"grad_norm": 1.0733413696289062,
|
| 679 |
+
"learning_rate": 4.13438347386943e-06,
|
| 680 |
+
"loss": 0.1678,
|
| 681 |
+
"step": 8700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.0,
|
| 685 |
+
"eval_accuracy": 0.9439363817097416,
|
| 686 |
+
"eval_loss": 0.23690353333950043,
|
| 687 |
+
"eval_runtime": 105.711,
|
| 688 |
+
"eval_samples_per_second": 23.791,
|
| 689 |
+
"eval_steps_per_second": 1.495,
|
| 690 |
+
"step": 8792
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 8.01,
|
| 694 |
+
"grad_norm": 17.58012580871582,
|
| 695 |
+
"learning_rate": 3.7928186339045982e-06,
|
| 696 |
+
"loss": 0.1947,
|
| 697 |
+
"step": 8800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.1,
|
| 701 |
+
"grad_norm": 20.622407913208008,
|
| 702 |
+
"learning_rate": 3.464496668905677e-06,
|
| 703 |
+
"loss": 0.1857,
|
| 704 |
+
"step": 8900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.19,
|
| 708 |
+
"grad_norm": 0.7151262164115906,
|
| 709 |
+
"learning_rate": 3.14968585048836e-06,
|
| 710 |
+
"loss": 0.1732,
|
| 711 |
+
"step": 9000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.28,
|
| 715 |
+
"grad_norm": 8.048576354980469,
|
| 716 |
+
"learning_rate": 2.848643410321257e-06,
|
| 717 |
+
"loss": 0.1318,
|
| 718 |
+
"step": 9100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.37,
|
| 722 |
+
"grad_norm": 0.751136064529419,
|
| 723 |
+
"learning_rate": 2.561615329942089e-06,
|
| 724 |
+
"loss": 0.1989,
|
| 725 |
+
"step": 9200
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.46,
|
| 729 |
+
"grad_norm": 3.61799693107605,
|
| 730 |
+
"learning_rate": 2.288836139766373e-06,
|
| 731 |
+
"loss": 0.1495,
|
| 732 |
+
"step": 9300
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.55,
|
| 736 |
+
"grad_norm": 12.693122863769531,
|
| 737 |
+
"learning_rate": 2.0305287274528073e-06,
|
| 738 |
+
"loss": 0.1762,
|
| 739 |
+
"step": 9400
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 8.64,
|
| 743 |
+
"grad_norm": 9.484522819519043,
|
| 744 |
+
"learning_rate": 1.7869041557819456e-06,
|
| 745 |
+
"loss": 0.1923,
|
| 746 |
+
"step": 9500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.74,
|
| 750 |
+
"grad_norm": 24.0538330078125,
|
| 751 |
+
"learning_rate": 1.558161490196961e-06,
|
| 752 |
+
"loss": 0.1779,
|
| 753 |
+
"step": 9600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.83,
|
| 757 |
+
"grad_norm": 1.2370848655700684,
|
| 758 |
+
"learning_rate": 1.34448763614744e-06,
|
| 759 |
+
"loss": 0.2347,
|
| 760 |
+
"step": 9700
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.92,
|
| 764 |
+
"grad_norm": 18.4951229095459,
|
| 765 |
+
"learning_rate": 1.1460571863690762e-06,
|
| 766 |
+
"loss": 0.1565,
|
| 767 |
+
"step": 9800
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 9.0,
|
| 771 |
+
"eval_accuracy": 0.9499005964214712,
|
| 772 |
+
"eval_loss": 0.23227240145206451,
|
| 773 |
+
"eval_runtime": 105.2417,
|
| 774 |
+
"eval_samples_per_second": 23.897,
|
| 775 |
+
"eval_steps_per_second": 1.501,
|
| 776 |
+
"step": 9891
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 9.01,
|
| 780 |
+
"grad_norm": 12.973793983459473,
|
| 781 |
+
"learning_rate": 9.63032278224101e-07,
|
| 782 |
+
"loss": 0.1495,
|
| 783 |
+
"step": 9900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.1,
|
| 787 |
+
"grad_norm": 7.522297382354736,
|
| 788 |
+
"learning_rate": 7.955624612189594e-07,
|
| 789 |
+
"loss": 0.1573,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.19,
|
| 794 |
+
"grad_norm": 15.810741424560547,
|
| 795 |
+
"learning_rate": 6.4378457480754e-07,
|
| 796 |
+
"loss": 0.1692,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 9.28,
|
| 801 |
+
"grad_norm": 15.419889450073242,
|
| 802 |
+
"learning_rate": 5.078226365797556e-07,
|
| 803 |
+
"loss": 0.1387,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.37,
|
| 808 |
+
"grad_norm": 10.454876899719238,
|
| 809 |
+
"learning_rate": 3.877877409268771e-07,
|
| 810 |
+
"loss": 0.1696,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 9.46,
|
| 815 |
+
"grad_norm": 0.05530254915356636,
|
| 816 |
+
"learning_rate": 2.837779682663899e-07,
|
| 817 |
+
"loss": 0.1417,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.55,
|
| 822 |
+
"grad_norm": 14.749571800231934,
|
| 823 |
+
"learning_rate": 1.958783049005719e-07,
|
| 824 |
+
"loss": 0.1799,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.65,
|
| 829 |
+
"grad_norm": 32.72957992553711,
|
| 830 |
+
"learning_rate": 1.2416057357423684e-07,
|
| 831 |
+
"loss": 0.1893,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 9.74,
|
| 836 |
+
"grad_norm": 26.80739974975586,
|
| 837 |
+
"learning_rate": 6.868337478844523e-08,
|
| 838 |
+
"loss": 0.1796,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.83,
|
| 843 |
+
"grad_norm": 9.608071327209473,
|
| 844 |
+
"learning_rate": 2.9492038918070844e-08,
|
| 845 |
+
"loss": 0.178,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 9.92,
|
| 850 |
+
"grad_norm": 13.889327049255371,
|
| 851 |
+
"learning_rate": 6.618589172393553e-09,
|
| 852 |
+
"loss": 0.1643,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 10.0,
|
| 857 |
+
"eval_accuracy": 0.9502982107355865,
|
| 858 |
+
"eval_loss": 0.23055487871170044,
|
| 859 |
+
"eval_runtime": 105.2963,
|
| 860 |
+
"eval_samples_per_second": 23.885,
|
| 861 |
+
"eval_steps_per_second": 1.501,
|
| 862 |
+
"step": 10990
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 10.0,
|
| 866 |
+
"step": 10990,
|
| 867 |
+
"total_flos": 4.09349935387607e+19,
|
| 868 |
+
"train_loss": 0.34581250545650966,
|
| 869 |
+
"train_runtime": 18969.8729,
|
| 870 |
+
"train_samples_per_second": 9.268,
|
| 871 |
+
"train_steps_per_second": 0.579
|
| 872 |
+
}
|
| 873 |
+
],
|
| 874 |
+
"logging_steps": 100,
|
| 875 |
+
"max_steps": 10990,
|
| 876 |
+
"num_input_tokens_seen": 0,
|
| 877 |
+
"num_train_epochs": 10,
|
| 878 |
+
"save_steps": 500,
|
| 879 |
+
"total_flos": 4.09349935387607e+19,
|
| 880 |
+
"train_batch_size": 16,
|
| 881 |
+
"trial_name": null,
|
| 882 |
+
"trial_params": null
|
| 883 |
+
}
|