Commit
•
a837517
1
Parent(s):
21807b5
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May29_14-24-50_5328d81bca58/events.out.tfevents.1717003858.5328d81bca58.24.1 +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-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-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: 0.939484126984127
|
| 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-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2402
|
| 36 |
+
- Accuracy: 0.9395
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.301428412334932e+19,
|
| 4 |
+
"train_loss": 0.4412916103637251,
|
| 5 |
+
"train_runtime": 10918.1842,
|
| 6 |
+
"train_samples_per_second": 16.102,
|
| 7 |
+
"train_steps_per_second": 1.007
|
| 8 |
+
}
|
runs/May29_14-24-50_5328d81bca58/events.out.tfevents.1717003858.5328d81bca58.24.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1929478d716f2959c262546daa657f07ab7b79d5ebaeae95c834b6b634975a3f
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.301428412334932e+19,
|
| 4 |
+
"train_loss": 0.4412916103637251,
|
| 5 |
+
"train_runtime": 10918.1842,
|
| 6 |
+
"train_samples_per_second": 16.102,
|
| 7 |
+
"train_steps_per_second": 1.007
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,883 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.25531044602394104,
|
| 3 |
+
"best_model_checkpoint": "./convnext-tiny-new-1e-4/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": 24.848655700683594,
|
| 14 |
+
"learning_rate": 9.99795725199423e-05,
|
| 15 |
+
"loss": 2.511,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 21.852506637573242,
|
| 21 |
+
"learning_rate": 9.991830677104683e-05,
|
| 22 |
+
"loss": 1.4511,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 14.456836700439453,
|
| 28 |
+
"learning_rate": 9.981625281350813e-05,
|
| 29 |
+
"loss": 1.1871,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36,
|
| 34 |
+
"grad_norm": 25.593276977539062,
|
| 35 |
+
"learning_rate": 9.967349403553353e-05,
|
| 36 |
+
"loss": 1.0097,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.45,
|
| 41 |
+
"grad_norm": 21.799734115600586,
|
| 42 |
+
"learning_rate": 9.949014708520663e-05,
|
| 43 |
+
"loss": 0.9728,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.55,
|
| 48 |
+
"grad_norm": 22.431013107299805,
|
| 49 |
+
"learning_rate": 9.926636177517427e-05,
|
| 50 |
+
"loss": 0.9024,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"grad_norm": 28.28536033630371,
|
| 56 |
+
"learning_rate": 9.900232096023477e-05,
|
| 57 |
+
"loss": 0.8912,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.73,
|
| 62 |
+
"grad_norm": 27.407716751098633,
|
| 63 |
+
"learning_rate": 9.869824038792741e-05,
|
| 64 |
+
"loss": 0.865,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.82,
|
| 69 |
+
"grad_norm": 13.469520568847656,
|
| 70 |
+
"learning_rate": 9.835436852224525e-05,
|
| 71 |
+
"loss": 0.7768,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.91,
|
| 76 |
+
"grad_norm": 17.95415496826172,
|
| 77 |
+
"learning_rate": 9.797098634061542e-05,
|
| 78 |
+
"loss": 0.8432,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.862027833001988,
|
| 84 |
+
"eval_loss": 0.4732176661491394,
|
| 85 |
+
"eval_runtime": 70.5844,
|
| 86 |
+
"eval_samples_per_second": 35.631,
|
| 87 |
+
"eval_steps_per_second": 2.238,
|
| 88 |
+
"step": 1099
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0,
|
| 92 |
+
"grad_norm": 28.058094024658203,
|
| 93 |
+
"learning_rate": 9.754840710431274e-05,
|
| 94 |
+
"loss": 0.827,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.09,
|
| 99 |
+
"grad_norm": 10.800704002380371,
|
| 100 |
+
"learning_rate": 9.708697610249406e-05,
|
| 101 |
+
"loss": 0.733,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.18,
|
| 106 |
+
"grad_norm": 17.161815643310547,
|
| 107 |
+
"learning_rate": 9.658707037006294e-05,
|
| 108 |
+
"loss": 0.7117,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.27,
|
| 113 |
+
"grad_norm": 15.4861478805542,
|
| 114 |
+
"learning_rate": 9.604909837959455e-05,
|
| 115 |
+
"loss": 0.6609,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"grad_norm": 20.579856872558594,
|
| 121 |
+
"learning_rate": 9.547349970757317e-05,
|
| 122 |
+
"loss": 0.6396,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.46,
|
| 127 |
+
"grad_norm": 24.0612735748291,
|
| 128 |
+
"learning_rate": 9.486074467521456e-05,
|
| 129 |
+
"loss": 0.6321,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.55,
|
| 134 |
+
"grad_norm": 23.076522827148438,
|
| 135 |
+
"learning_rate": 9.421133396416686e-05,
|
| 136 |
+
"loss": 0.7177,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.64,
|
| 141 |
+
"grad_norm": 24.146862030029297,
|
| 142 |
+
"learning_rate": 9.352579820740405e-05,
|
| 143 |
+
"loss": 0.7033,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.73,
|
| 148 |
+
"grad_norm": 13.88412857055664,
|
| 149 |
+
"learning_rate": 9.280469755564613e-05,
|
| 150 |
+
"loss": 0.637,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.82,
|
| 155 |
+
"grad_norm": 18.419206619262695,
|
| 156 |
+
"learning_rate": 9.204862121966044e-05,
|
| 157 |
+
"loss": 0.6056,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.91,
|
| 162 |
+
"grad_norm": 22.241830825805664,
|
| 163 |
+
"learning_rate": 9.125818698881798e-05,
|
| 164 |
+
"loss": 0.6603,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.0,
|
| 169 |
+
"eval_accuracy": 0.9009940357852882,
|
| 170 |
+
"eval_loss": 0.35555583238601685,
|
| 171 |
+
"eval_runtime": 70.2432,
|
| 172 |
+
"eval_samples_per_second": 35.804,
|
| 173 |
+
"eval_steps_per_second": 2.249,
|
| 174 |
+
"step": 2198
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0,
|
| 178 |
+
"grad_norm": 28.679054260253906,
|
| 179 |
+
"learning_rate": 9.043404072629829e-05,
|
| 180 |
+
"loss": 0.6342,
|
| 181 |
+
"step": 2200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.09,
|
| 185 |
+
"grad_norm": 25.620079040527344,
|
| 186 |
+
"learning_rate": 8.957685584135502e-05,
|
| 187 |
+
"loss": 0.5285,
|
| 188 |
+
"step": 2300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.18,
|
| 192 |
+
"grad_norm": 17.019142150878906,
|
| 193 |
+
"learning_rate": 8.86873327390739e-05,
|
| 194 |
+
"loss": 0.5882,
|
| 195 |
+
"step": 2400
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.27,
|
| 199 |
+
"grad_norm": 15.56048583984375,
|
| 200 |
+
"learning_rate": 8.776619824807224e-05,
|
| 201 |
+
"loss": 0.545,
|
| 202 |
+
"step": 2500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.37,
|
| 206 |
+
"grad_norm": 10.068634033203125,
|
| 207 |
+
"learning_rate": 8.681420502660786e-05,
|
| 208 |
+
"loss": 0.5944,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.46,
|
| 213 |
+
"grad_norm": 15.93220043182373,
|
| 214 |
+
"learning_rate": 8.583213094758261e-05,
|
| 215 |
+
"loss": 0.5378,
|
| 216 |
+
"step": 2700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.55,
|
| 220 |
+
"grad_norm": 16.840496063232422,
|
| 221 |
+
"learning_rate": 8.482077846294308e-05,
|
| 222 |
+
"loss": 0.5597,
|
| 223 |
+
"step": 2800
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.64,
|
| 227 |
+
"grad_norm": 23.36423683166504,
|
| 228 |
+
"learning_rate": 8.378097394799773e-05,
|
| 229 |
+
"loss": 0.5476,
|
| 230 |
+
"step": 2900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.73,
|
| 234 |
+
"grad_norm": 14.018542289733887,
|
| 235 |
+
"learning_rate": 8.271356702618626e-05,
|
| 236 |
+
"loss": 0.5429,
|
| 237 |
+
"step": 3000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.82,
|
| 241 |
+
"grad_norm": 22.620033264160156,
|
| 242 |
+
"learning_rate": 8.161942987485303e-05,
|
| 243 |
+
"loss": 0.5361,
|
| 244 |
+
"step": 3100
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.91,
|
| 248 |
+
"grad_norm": 29.02153778076172,
|
| 249 |
+
"learning_rate": 8.049945651259163e-05,
|
| 250 |
+
"loss": 0.487,
|
| 251 |
+
"step": 3200
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"eval_accuracy": 0.882703777335984,
|
| 256 |
+
"eval_loss": 0.4106706380844116,
|
| 257 |
+
"eval_runtime": 69.7812,
|
| 258 |
+
"eval_samples_per_second": 36.041,
|
| 259 |
+
"eval_steps_per_second": 2.264,
|
| 260 |
+
"step": 3297
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0,
|
| 264 |
+
"grad_norm": 9.186837196350098,
|
| 265 |
+
"learning_rate": 7.935456206874292e-05,
|
| 266 |
+
"loss": 0.5448,
|
| 267 |
+
"step": 3300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.09,
|
| 271 |
+
"grad_norm": 10.694817543029785,
|
| 272 |
+
"learning_rate": 7.818568203564374e-05,
|
| 273 |
+
"loss": 0.4207,
|
| 274 |
+
"step": 3400
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.18,
|
| 278 |
+
"grad_norm": 9.862343788146973,
|
| 279 |
+
"learning_rate": 7.699377150423672e-05,
|
| 280 |
+
"loss": 0.475,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.28,
|
| 285 |
+
"grad_norm": 17.465476989746094,
|
| 286 |
+
"learning_rate": 7.577980438366628e-05,
|
| 287 |
+
"loss": 0.48,
|
| 288 |
+
"step": 3600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.37,
|
| 292 |
+
"grad_norm": 19.368242263793945,
|
| 293 |
+
"learning_rate": 7.454477260549828e-05,
|
| 294 |
+
"loss": 0.4126,
|
| 295 |
+
"step": 3700
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.46,
|
| 299 |
+
"grad_norm": 24.577472686767578,
|
| 300 |
+
"learning_rate": 7.32896853132135e-05,
|
| 301 |
+
"loss": 0.4992,
|
| 302 |
+
"step": 3800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.55,
|
| 306 |
+
"grad_norm": 7.475000381469727,
|
| 307 |
+
"learning_rate": 7.201556803763725e-05,
|
| 308 |
+
"loss": 0.4931,
|
| 309 |
+
"step": 3900
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.64,
|
| 313 |
+
"grad_norm": 13.887510299682617,
|
| 314 |
+
"learning_rate": 7.07234618589791e-05,
|
| 315 |
+
"loss": 0.4909,
|
| 316 |
+
"step": 4000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"grad_norm": 20.115652084350586,
|
| 321 |
+
"learning_rate": 6.94144225561669e-05,
|
| 322 |
+
"loss": 0.4814,
|
| 323 |
+
"step": 4100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.82,
|
| 327 |
+
"grad_norm": 14.20095443725586,
|
| 328 |
+
"learning_rate": 6.808951974417078e-05,
|
| 329 |
+
"loss": 0.457,
|
| 330 |
+
"step": 4200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.91,
|
| 334 |
+
"grad_norm": 29.256624221801758,
|
| 335 |
+
"learning_rate": 6.674983600002155e-05,
|
| 336 |
+
"loss": 0.4369,
|
| 337 |
+
"step": 4300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.0,
|
| 341 |
+
"eval_accuracy": 0.9172962226640159,
|
| 342 |
+
"eval_loss": 0.3118807375431061,
|
| 343 |
+
"eval_runtime": 70.2783,
|
| 344 |
+
"eval_samples_per_second": 35.786,
|
| 345 |
+
"eval_steps_per_second": 2.248,
|
| 346 |
+
"step": 4396
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.0,
|
| 350 |
+
"grad_norm": 10.440736770629883,
|
| 351 |
+
"learning_rate": 6.539646597823791e-05,
|
| 352 |
+
"loss": 0.4036,
|
| 353 |
+
"step": 4400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.09,
|
| 357 |
+
"grad_norm": 14.221583366394043,
|
| 358 |
+
"learning_rate": 6.403051551638508e-05,
|
| 359 |
+
"loss": 0.3902,
|
| 360 |
+
"step": 4500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.19,
|
| 364 |
+
"grad_norm": 18.483789443969727,
|
| 365 |
+
"learning_rate": 6.265310073149584e-05,
|
| 366 |
+
"loss": 0.4096,
|
| 367 |
+
"step": 4600
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.28,
|
| 371 |
+
"grad_norm": 27.6778564453125,
|
| 372 |
+
"learning_rate": 6.126534710809216e-05,
|
| 373 |
+
"loss": 0.3778,
|
| 374 |
+
"step": 4700
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.37,
|
| 378 |
+
"grad_norm": 18.118946075439453,
|
| 379 |
+
"learning_rate": 5.9868388578552734e-05,
|
| 380 |
+
"loss": 0.356,
|
| 381 |
+
"step": 4800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.46,
|
| 385 |
+
"grad_norm": 27.71598243713379,
|
| 386 |
+
"learning_rate": 5.8463366596577706e-05,
|
| 387 |
+
"loss": 0.3544,
|
| 388 |
+
"step": 4900
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.55,
|
| 392 |
+
"grad_norm": 10.941313743591309,
|
| 393 |
+
"learning_rate": 5.705142920450777e-05,
|
| 394 |
+
"loss": 0.4005,
|
| 395 |
+
"step": 5000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.64,
|
| 399 |
+
"grad_norm": 20.2288818359375,
|
| 400 |
+
"learning_rate": 5.5633730095259695e-05,
|
| 401 |
+
"loss": 0.4007,
|
| 402 |
+
"step": 5100
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.73,
|
| 406 |
+
"grad_norm": 13.51459789276123,
|
| 407 |
+
"learning_rate": 5.421142766964474e-05,
|
| 408 |
+
"loss": 0.411,
|
| 409 |
+
"step": 5200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.82,
|
| 413 |
+
"grad_norm": 10.38302993774414,
|
| 414 |
+
"learning_rate": 5.278568408984037e-05,
|
| 415 |
+
"loss": 0.4178,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.91,
|
| 420 |
+
"grad_norm": 7.628846168518066,
|
| 421 |
+
"learning_rate": 5.135766432978829e-05,
|
| 422 |
+
"loss": 0.3791,
|
| 423 |
+
"step": 5400
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.0,
|
| 427 |
+
"eval_accuracy": 0.9196819085487078,
|
| 428 |
+
"eval_loss": 0.3082761764526367,
|
| 429 |
+
"eval_runtime": 71.5388,
|
| 430 |
+
"eval_samples_per_second": 35.156,
|
| 431 |
+
"eval_steps_per_second": 2.209,
|
| 432 |
+
"step": 5495
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.0,
|
| 436 |
+
"grad_norm": 15.286186218261719,
|
| 437 |
+
"learning_rate": 4.9928535223295344e-05,
|
| 438 |
+
"loss": 0.3914,
|
| 439 |
+
"step": 5500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.1,
|
| 443 |
+
"grad_norm": 19.06636619567871,
|
| 444 |
+
"learning_rate": 4.849946451061443e-05,
|
| 445 |
+
"loss": 0.3268,
|
| 446 |
+
"step": 5600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.19,
|
| 450 |
+
"grad_norm": 16.880006790161133,
|
| 451 |
+
"learning_rate": 4.707161988428495e-05,
|
| 452 |
+
"loss": 0.3184,
|
| 453 |
+
"step": 5700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.28,
|
| 457 |
+
"grad_norm": 10.349203109741211,
|
| 458 |
+
"learning_rate": 4.564616803501205e-05,
|
| 459 |
+
"loss": 0.3417,
|
| 460 |
+
"step": 5800
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.37,
|
| 464 |
+
"grad_norm": 17.491863250732422,
|
| 465 |
+
"learning_rate": 4.4224273698364735e-05,
|
| 466 |
+
"loss": 0.3218,
|
| 467 |
+
"step": 5900
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.46,
|
| 471 |
+
"grad_norm": 9.212013244628906,
|
| 472 |
+
"learning_rate": 4.2807098703071255e-05,
|
| 473 |
+
"loss": 0.3143,
|
| 474 |
+
"step": 6000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.55,
|
| 478 |
+
"grad_norm": 19.431245803833008,
|
| 479 |
+
"learning_rate": 4.1395801021689746e-05,
|
| 480 |
+
"loss": 0.3262,
|
| 481 |
+
"step": 6100
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.64,
|
| 485 |
+
"grad_norm": 16.24408531188965,
|
| 486 |
+
"learning_rate": 3.999153382442995e-05,
|
| 487 |
+
"loss": 0.2885,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.73,
|
| 492 |
+
"grad_norm": 23.65041732788086,
|
| 493 |
+
"learning_rate": 3.859544453689853e-05,
|
| 494 |
+
"loss": 0.3555,
|
| 495 |
+
"step": 6300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.82,
|
| 499 |
+
"grad_norm": 10.8707275390625,
|
| 500 |
+
"learning_rate": 3.7208673902538706e-05,
|
| 501 |
+
"loss": 0.3404,
|
| 502 |
+
"step": 6400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.91,
|
| 506 |
+
"grad_norm": 18.250511169433594,
|
| 507 |
+
"learning_rate": 3.583235505052955e-05,
|
| 508 |
+
"loss": 0.3342,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.0,
|
| 513 |
+
"eval_accuracy": 0.9296222664015904,
|
| 514 |
+
"eval_loss": 0.28032296895980835,
|
| 515 |
+
"eval_runtime": 79.2042,
|
| 516 |
+
"eval_samples_per_second": 31.753,
|
| 517 |
+
"eval_steps_per_second": 1.995,
|
| 518 |
+
"step": 6594
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.01,
|
| 522 |
+
"grad_norm": 6.232498645782471,
|
| 523 |
+
"learning_rate": 3.446761256990723e-05,
|
| 524 |
+
"loss": 0.3301,
|
| 525 |
+
"step": 6600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.1,
|
| 529 |
+
"grad_norm": 19.711963653564453,
|
| 530 |
+
"learning_rate": 3.311556159066397e-05,
|
| 531 |
+
"loss": 0.2638,
|
| 532 |
+
"step": 6700
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.19,
|
| 536 |
+
"grad_norm": 11.230116844177246,
|
| 537 |
+
"learning_rate": 3.177730687257639e-05,
|
| 538 |
+
"loss": 0.312,
|
| 539 |
+
"step": 6800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.28,
|
| 543 |
+
"grad_norm": 9.200843811035156,
|
| 544 |
+
"learning_rate": 3.0453941902507177e-05,
|
| 545 |
+
"loss": 0.3046,
|
| 546 |
+
"step": 6900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.37,
|
| 550 |
+
"grad_norm": 18.336387634277344,
|
| 551 |
+
"learning_rate": 2.914654800091768e-05,
|
| 552 |
+
"loss": 0.2505,
|
| 553 |
+
"step": 7000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.46,
|
| 557 |
+
"grad_norm": 4.870161533355713,
|
| 558 |
+
"learning_rate": 2.7856193438321986e-05,
|
| 559 |
+
"loss": 0.3136,
|
| 560 |
+
"step": 7100
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.55,
|
| 564 |
+
"grad_norm": 8.88219165802002,
|
| 565 |
+
"learning_rate": 2.6583932562403957e-05,
|
| 566 |
+
"loss": 0.2656,
|
| 567 |
+
"step": 7200
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.64,
|
| 571 |
+
"grad_norm": 12.868867874145508,
|
| 572 |
+
"learning_rate": 2.5330804936510373e-05,
|
| 573 |
+
"loss": 0.2714,
|
| 574 |
+
"step": 7300
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.73,
|
| 578 |
+
"grad_norm": 26.35186767578125,
|
| 579 |
+
"learning_rate": 2.409783449022475e-05,
|
| 580 |
+
"loss": 0.2675,
|
| 581 |
+
"step": 7400
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.82,
|
| 585 |
+
"grad_norm": 13.712077140808105,
|
| 586 |
+
"learning_rate": 2.2886028682715217e-05,
|
| 587 |
+
"loss": 0.2664,
|
| 588 |
+
"step": 7500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.92,
|
| 592 |
+
"grad_norm": 0.8319320678710938,
|
| 593 |
+
"learning_rate": 2.169637767954048e-05,
|
| 594 |
+
"loss": 0.2803,
|
| 595 |
+
"step": 7600
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.0,
|
| 599 |
+
"eval_accuracy": 0.9339960238568589,
|
| 600 |
+
"eval_loss": 0.26732343435287476,
|
| 601 |
+
"eval_runtime": 70.0882,
|
| 602 |
+
"eval_samples_per_second": 35.883,
|
| 603 |
+
"eval_steps_per_second": 2.254,
|
| 604 |
+
"step": 7693
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.01,
|
| 608 |
+
"grad_norm": 15.552393913269043,
|
| 609 |
+
"learning_rate": 2.052985354358622e-05,
|
| 610 |
+
"loss": 0.2109,
|
| 611 |
+
"step": 7700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.1,
|
| 615 |
+
"grad_norm": 15.977888107299805,
|
| 616 |
+
"learning_rate": 1.9387409440793386e-05,
|
| 617 |
+
"loss": 0.2315,
|
| 618 |
+
"step": 7800
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.19,
|
| 622 |
+
"grad_norm": 12.987915992736816,
|
| 623 |
+
"learning_rate": 1.82699788613271e-05,
|
| 624 |
+
"loss": 0.2421,
|
| 625 |
+
"step": 7900
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.28,
|
| 629 |
+
"grad_norm": 7.147055625915527,
|
| 630 |
+
"learning_rate": 1.7178474856822456e-05,
|
| 631 |
+
"loss": 0.2454,
|
| 632 |
+
"step": 8000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.37,
|
| 636 |
+
"grad_norm": 25.91172981262207,
|
| 637 |
+
"learning_rate": 1.611378929433083e-05,
|
| 638 |
+
"loss": 0.2504,
|
| 639 |
+
"step": 8100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.46,
|
| 643 |
+
"grad_norm": 12.569241523742676,
|
| 644 |
+
"learning_rate": 1.5076792127576073e-05,
|
| 645 |
+
"loss": 0.2338,
|
| 646 |
+
"step": 8200
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.55,
|
| 650 |
+
"grad_norm": 19.739892959594727,
|
| 651 |
+
"learning_rate": 1.4068330686115943e-05,
|
| 652 |
+
"loss": 0.2161,
|
| 653 |
+
"step": 8300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.64,
|
| 657 |
+
"grad_norm": 9.218408584594727,
|
| 658 |
+
"learning_rate": 1.308922898298977e-05,
|
| 659 |
+
"loss": 0.2329,
|
| 660 |
+
"step": 8400
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.73,
|
| 664 |
+
"grad_norm": 2.0763704776763916,
|
| 665 |
+
"learning_rate": 1.2140287041418203e-05,
|
| 666 |
+
"loss": 0.2085,
|
| 667 |
+
"step": 8500
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.83,
|
| 671 |
+
"grad_norm": 11.455533981323242,
|
| 672 |
+
"learning_rate": 1.1222280241104716e-05,
|
| 673 |
+
"loss": 0.2561,
|
| 674 |
+
"step": 8600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.92,
|
| 678 |
+
"grad_norm": 3.408818006515503,
|
| 679 |
+
"learning_rate": 1.0335958684673574e-05,
|
| 680 |
+
"loss": 0.2118,
|
| 681 |
+
"step": 8700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.0,
|
| 685 |
+
"eval_accuracy": 0.9320079522862823,
|
| 686 |
+
"eval_loss": 0.2637202739715576,
|
| 687 |
+
"eval_runtime": 74.3067,
|
| 688 |
+
"eval_samples_per_second": 33.846,
|
| 689 |
+
"eval_steps_per_second": 2.126,
|
| 690 |
+
"step": 8792
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 8.01,
|
| 694 |
+
"grad_norm": 10.710466384887695,
|
| 695 |
+
"learning_rate": 9.482046584761495e-06,
|
| 696 |
+
"loss": 0.2045,
|
| 697 |
+
"step": 8800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.1,
|
| 701 |
+
"grad_norm": 14.385254859924316,
|
| 702 |
+
"learning_rate": 8.661241672264192e-06,
|
| 703 |
+
"loss": 0.2176,
|
| 704 |
+
"step": 8900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.19,
|
| 708 |
+
"grad_norm": 10.243017196655273,
|
| 709 |
+
"learning_rate": 7.874214626220899e-06,
|
| 710 |
+
"loss": 0.2099,
|
| 711 |
+
"step": 9000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.28,
|
| 715 |
+
"grad_norm": 6.018984317779541,
|
| 716 |
+
"learning_rate": 7.1216085258031414e-06,
|
| 717 |
+
"loss": 0.1686,
|
| 718 |
+
"step": 9100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.37,
|
| 722 |
+
"grad_norm": 1.289069652557373,
|
| 723 |
+
"learning_rate": 6.404038324855222e-06,
|
| 724 |
+
"loss": 0.2214,
|
| 725 |
+
"step": 9200
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.46,
|
| 729 |
+
"grad_norm": 2.6374850273132324,
|
| 730 |
+
"learning_rate": 5.7220903494159316e-06,
|
| 731 |
+
"loss": 0.1675,
|
| 732 |
+
"step": 9300
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.55,
|
| 736 |
+
"grad_norm": 2.8265738487243652,
|
| 737 |
+
"learning_rate": 5.076321818632018e-06,
|
| 738 |
+
"loss": 0.2129,
|
| 739 |
+
"step": 9400
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 8.64,
|
| 743 |
+
"grad_norm": 11.41331958770752,
|
| 744 |
+
"learning_rate": 4.467260389454864e-06,
|
| 745 |
+
"loss": 0.2097,
|
| 746 |
+
"step": 9500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.74,
|
| 750 |
+
"grad_norm": 22.140159606933594,
|
| 751 |
+
"learning_rate": 3.895403725492402e-06,
|
| 752 |
+
"loss": 0.2099,
|
| 753 |
+
"step": 9600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.83,
|
| 757 |
+
"grad_norm": 7.952567100524902,
|
| 758 |
+
"learning_rate": 3.3612190903686005e-06,
|
| 759 |
+
"loss": 0.2438,
|
| 760 |
+
"step": 9700
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.92,
|
| 764 |
+
"grad_norm": 19.06670379638672,
|
| 765 |
+
"learning_rate": 2.86514296592269e-06,
|
| 766 |
+
"loss": 0.1706,
|
| 767 |
+
"step": 9800
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 9.0,
|
| 771 |
+
"eval_accuracy": 0.9347912524850894,
|
| 772 |
+
"eval_loss": 0.25745028257369995,
|
| 773 |
+
"eval_runtime": 74.1249,
|
| 774 |
+
"eval_samples_per_second": 33.929,
|
| 775 |
+
"eval_steps_per_second": 2.132,
|
| 776 |
+
"step": 9891
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 9.01,
|
| 780 |
+
"grad_norm": 16.285367965698242,
|
| 781 |
+
"learning_rate": 2.407580695560252e-06,
|
| 782 |
+
"loss": 0.1872,
|
| 783 |
+
"step": 9900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.1,
|
| 787 |
+
"grad_norm": 5.482550621032715,
|
| 788 |
+
"learning_rate": 1.9889061530473986e-06,
|
| 789 |
+
"loss": 0.1863,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.19,
|
| 794 |
+
"grad_norm": 8.077670097351074,
|
| 795 |
+
"learning_rate": 1.6094614370188499e-06,
|
| 796 |
+
"loss": 0.1759,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 9.28,
|
| 801 |
+
"grad_norm": 14.164857864379883,
|
| 802 |
+
"learning_rate": 1.269556591449389e-06,
|
| 803 |
+
"loss": 0.1768,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.37,
|
| 808 |
+
"grad_norm": 16.639026641845703,
|
| 809 |
+
"learning_rate": 9.694693523171927e-07,
|
| 810 |
+
"loss": 0.2211,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 9.46,
|
| 815 |
+
"grad_norm": 13.088668823242188,
|
| 816 |
+
"learning_rate": 7.094449206659748e-07,
|
| 817 |
+
"loss": 0.1891,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.55,
|
| 822 |
+
"grad_norm": 7.857825756072998,
|
| 823 |
+
"learning_rate": 4.896957622514298e-07,
|
| 824 |
+
"loss": 0.2362,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.65,
|
| 829 |
+
"grad_norm": 16.95376968383789,
|
| 830 |
+
"learning_rate": 3.104014339355921e-07,
|
| 831 |
+
"loss": 0.2201,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 9.74,
|
| 836 |
+
"grad_norm": 11.055394172668457,
|
| 837 |
+
"learning_rate": 1.7170843697111304e-07,
|
| 838 |
+
"loss": 0.2139,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.83,
|
| 843 |
+
"grad_norm": 8.469569206237793,
|
| 844 |
+
"learning_rate": 7.37300972951771e-08,
|
| 845 |
+
"loss": 0.2026,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 9.92,
|
| 850 |
+
"grad_norm": 18.598886489868164,
|
| 851 |
+
"learning_rate": 1.654647293098388e-08,
|
| 852 |
+
"loss": 0.1995,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 10.0,
|
| 857 |
+
"eval_accuracy": 0.9375745526838967,
|
| 858 |
+
"eval_loss": 0.25531044602394104,
|
| 859 |
+
"eval_runtime": 73.7798,
|
| 860 |
+
"eval_samples_per_second": 34.088,
|
| 861 |
+
"eval_steps_per_second": 2.142,
|
| 862 |
+
"step": 10990
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 10.0,
|
| 866 |
+
"step": 10990,
|
| 867 |
+
"total_flos": 1.301428412334932e+19,
|
| 868 |
+
"train_loss": 0.4412916103637251,
|
| 869 |
+
"train_runtime": 10918.1842,
|
| 870 |
+
"train_samples_per_second": 16.102,
|
| 871 |
+
"train_steps_per_second": 1.007
|
| 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": 1.301428412334932e+19,
|
| 880 |
+
"train_batch_size": 16,
|
| 881 |
+
"trial_name": null,
|
| 882 |
+
"trial_params": null
|
| 883 |
+
}
|