End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May26_09-28-38_c5415e6f1afd/events.out.tfevents.1716733109.c5415e6f1afd.23.1 +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: 0.9390873015873016
|
| 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: 0.2406
|
| 36 |
+
- Accuracy: 0.9391
|
| 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": 0.25289429932751367,
|
| 5 |
+
"train_runtime": 17079.3849,
|
| 6 |
+
"train_samples_per_second": 10.294,
|
| 7 |
+
"train_steps_per_second": 0.643
|
| 8 |
+
}
|
runs/May26_09-28-38_c5415e6f1afd/events.out.tfevents.1716733109.c5415e6f1afd.23.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c0c2468569b5b2911205eb5e96d6579776388b97534b2d6e66f1fefcda94ea1
|
| 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": 0.25289429932751367,
|
| 5 |
+
"train_runtime": 17079.3849,
|
| 6 |
+
"train_samples_per_second": 10.294,
|
| 7 |
+
"train_steps_per_second": 0.643
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,883 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2340400665998459,
|
| 3 |
+
"best_model_checkpoint": "./convnext-base-3e-5/checkpoint-4396",
|
| 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": 17.956300735473633,
|
| 14 |
+
"learning_rate": 2.999387175598269e-05,
|
| 15 |
+
"loss": 2.4621,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 29.822656631469727,
|
| 21 |
+
"learning_rate": 2.9975492031314045e-05,
|
| 22 |
+
"loss": 1.2937,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 17.655864715576172,
|
| 28 |
+
"learning_rate": 2.994487584405244e-05,
|
| 29 |
+
"loss": 0.9072,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36,
|
| 34 |
+
"grad_norm": 26.621862411499023,
|
| 35 |
+
"learning_rate": 2.990204821066006e-05,
|
| 36 |
+
"loss": 0.6825,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.45,
|
| 41 |
+
"grad_norm": 30.1605224609375,
|
| 42 |
+
"learning_rate": 2.984704412556199e-05,
|
| 43 |
+
"loss": 0.6469,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.55,
|
| 48 |
+
"grad_norm": 20.283042907714844,
|
| 49 |
+
"learning_rate": 2.977990853255228e-05,
|
| 50 |
+
"loss": 0.5517,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"grad_norm": 23.60833740234375,
|
| 56 |
+
"learning_rate": 2.970069628807043e-05,
|
| 57 |
+
"loss": 0.5723,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.73,
|
| 62 |
+
"grad_norm": 33.12726974487305,
|
| 63 |
+
"learning_rate": 2.9609472116378222e-05,
|
| 64 |
+
"loss": 0.5324,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.82,
|
| 69 |
+
"grad_norm": 11.965418815612793,
|
| 70 |
+
"learning_rate": 2.9506310556673573e-05,
|
| 71 |
+
"loss": 0.4686,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.91,
|
| 76 |
+
"grad_norm": 10.123353958129883,
|
| 77 |
+
"learning_rate": 2.9391295902184625e-05,
|
| 78 |
+
"loss": 0.4903,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.8910536779324055,
|
| 84 |
+
"eval_loss": 0.36899805068969727,
|
| 85 |
+
"eval_runtime": 105.6572,
|
| 86 |
+
"eval_samples_per_second": 23.803,
|
| 87 |
+
"eval_steps_per_second": 1.495,
|
| 88 |
+
"step": 1099
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0,
|
| 92 |
+
"grad_norm": 21.59682273864746,
|
| 93 |
+
"learning_rate": 2.9264522131293818e-05,
|
| 94 |
+
"loss": 0.5236,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.09,
|
| 99 |
+
"grad_norm": 8.269460678100586,
|
| 100 |
+
"learning_rate": 2.9126092830748217e-05,
|
| 101 |
+
"loss": 0.3906,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.18,
|
| 106 |
+
"grad_norm": 15.037210464477539,
|
| 107 |
+
"learning_rate": 2.897612111101888e-05,
|
| 108 |
+
"loss": 0.3786,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.27,
|
| 113 |
+
"grad_norm": 11.73908519744873,
|
| 114 |
+
"learning_rate": 2.8814729513878365e-05,
|
| 115 |
+
"loss": 0.3857,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"grad_norm": 22.919809341430664,
|
| 121 |
+
"learning_rate": 2.864204991227195e-05,
|
| 122 |
+
"loss": 0.3413,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.46,
|
| 127 |
+
"grad_norm": 16.75708770751953,
|
| 128 |
+
"learning_rate": 2.8458223402564366e-05,
|
| 129 |
+
"loss": 0.3258,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.55,
|
| 134 |
+
"grad_norm": 13.096406936645508,
|
| 135 |
+
"learning_rate": 2.826340018925006e-05,
|
| 136 |
+
"loss": 0.4003,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.64,
|
| 141 |
+
"grad_norm": 19.19637680053711,
|
| 142 |
+
"learning_rate": 2.8057739462221215e-05,
|
| 143 |
+
"loss": 0.385,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.73,
|
| 148 |
+
"grad_norm": 17.63860321044922,
|
| 149 |
+
"learning_rate": 2.7841409266693838e-05,
|
| 150 |
+
"loss": 0.3486,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.82,
|
| 155 |
+
"grad_norm": 15.726961135864258,
|
| 156 |
+
"learning_rate": 2.761458636589813e-05,
|
| 157 |
+
"loss": 0.3403,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.91,
|
| 162 |
+
"grad_norm": 13.003602027893066,
|
| 163 |
+
"learning_rate": 2.7377456096645395e-05,
|
| 164 |
+
"loss": 0.3615,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.0,
|
| 169 |
+
"eval_accuracy": 0.9168986083499006,
|
| 170 |
+
"eval_loss": 0.2985592782497406,
|
| 171 |
+
"eval_runtime": 106.1115,
|
| 172 |
+
"eval_samples_per_second": 23.701,
|
| 173 |
+
"eval_steps_per_second": 1.489,
|
| 174 |
+
"step": 2198
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0,
|
| 178 |
+
"grad_norm": 31.20207405090332,
|
| 179 |
+
"learning_rate": 2.7130212217889484e-05,
|
| 180 |
+
"loss": 0.353,
|
| 181 |
+
"step": 2200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.09,
|
| 185 |
+
"grad_norm": 17.543489456176758,
|
| 186 |
+
"learning_rate": 2.6873056752406504e-05,
|
| 187 |
+
"loss": 0.307,
|
| 188 |
+
"step": 2300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.18,
|
| 192 |
+
"grad_norm": 16.423120498657227,
|
| 193 |
+
"learning_rate": 2.6606199821722166e-05,
|
| 194 |
+
"loss": 0.2946,
|
| 195 |
+
"step": 2400
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.27,
|
| 199 |
+
"grad_norm": 10.412177085876465,
|
| 200 |
+
"learning_rate": 2.632985947442167e-05,
|
| 201 |
+
"loss": 0.2547,
|
| 202 |
+
"step": 2500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.37,
|
| 206 |
+
"grad_norm": 11.482078552246094,
|
| 207 |
+
"learning_rate": 2.6044261507982356e-05,
|
| 208 |
+
"loss": 0.3145,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.46,
|
| 213 |
+
"grad_norm": 18.31868553161621,
|
| 214 |
+
"learning_rate": 2.5749639284274782e-05,
|
| 215 |
+
"loss": 0.2831,
|
| 216 |
+
"step": 2700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.55,
|
| 220 |
+
"grad_norm": 1.5178425312042236,
|
| 221 |
+
"learning_rate": 2.5446233538882924e-05,
|
| 222 |
+
"loss": 0.294,
|
| 223 |
+
"step": 2800
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.64,
|
| 227 |
+
"grad_norm": 14.94119644165039,
|
| 228 |
+
"learning_rate": 2.513429218439932e-05,
|
| 229 |
+
"loss": 0.306,
|
| 230 |
+
"step": 2900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.73,
|
| 234 |
+
"grad_norm": 16.603517532348633,
|
| 235 |
+
"learning_rate": 2.4814070107855878e-05,
|
| 236 |
+
"loss": 0.2681,
|
| 237 |
+
"step": 3000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.82,
|
| 241 |
+
"grad_norm": 17.19023895263672,
|
| 242 |
+
"learning_rate": 2.448582896245591e-05,
|
| 243 |
+
"loss": 0.2738,
|
| 244 |
+
"step": 3100
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.91,
|
| 248 |
+
"grad_norm": 16.443864822387695,
|
| 249 |
+
"learning_rate": 2.4149836953777488e-05,
|
| 250 |
+
"loss": 0.2686,
|
| 251 |
+
"step": 3200
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"eval_accuracy": 0.9304174950298211,
|
| 256 |
+
"eval_loss": 0.26619353890419006,
|
| 257 |
+
"eval_runtime": 105.8407,
|
| 258 |
+
"eval_samples_per_second": 23.762,
|
| 259 |
+
"eval_steps_per_second": 1.493,
|
| 260 |
+
"step": 3297
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0,
|
| 264 |
+
"grad_norm": 18.363679885864258,
|
| 265 |
+
"learning_rate": 2.3806368620622876e-05,
|
| 266 |
+
"loss": 0.2955,
|
| 267 |
+
"step": 3300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.09,
|
| 271 |
+
"grad_norm": 6.975516319274902,
|
| 272 |
+
"learning_rate": 2.345570461069312e-05,
|
| 273 |
+
"loss": 0.2085,
|
| 274 |
+
"step": 3400
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.18,
|
| 278 |
+
"grad_norm": 3.4055590629577637,
|
| 279 |
+
"learning_rate": 2.3098131451271016e-05,
|
| 280 |
+
"loss": 0.2276,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.28,
|
| 285 |
+
"grad_norm": 16.472017288208008,
|
| 286 |
+
"learning_rate": 2.2733941315099883e-05,
|
| 287 |
+
"loss": 0.2423,
|
| 288 |
+
"step": 3600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.37,
|
| 292 |
+
"grad_norm": 9.783247947692871,
|
| 293 |
+
"learning_rate": 2.2363431781649483e-05,
|
| 294 |
+
"loss": 0.2187,
|
| 295 |
+
"step": 3700
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.46,
|
| 299 |
+
"grad_norm": 20.065593719482422,
|
| 300 |
+
"learning_rate": 2.1986905593964048e-05,
|
| 301 |
+
"loss": 0.1958,
|
| 302 |
+
"step": 3800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.55,
|
| 306 |
+
"grad_norm": 9.611791610717773,
|
| 307 |
+
"learning_rate": 2.1604670411291174e-05,
|
| 308 |
+
"loss": 0.2657,
|
| 309 |
+
"step": 3900
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.64,
|
| 313 |
+
"grad_norm": 7.389467239379883,
|
| 314 |
+
"learning_rate": 2.121703855769373e-05,
|
| 315 |
+
"loss": 0.2479,
|
| 316 |
+
"step": 4000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"grad_norm": 7.945903301239014,
|
| 321 |
+
"learning_rate": 2.0824326766850072e-05,
|
| 322 |
+
"loss": 0.2279,
|
| 323 |
+
"step": 4100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.82,
|
| 327 |
+
"grad_norm": 0.05080638453364372,
|
| 328 |
+
"learning_rate": 2.042685592325123e-05,
|
| 329 |
+
"loss": 0.2171,
|
| 330 |
+
"step": 4200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.91,
|
| 334 |
+
"grad_norm": 8.823617935180664,
|
| 335 |
+
"learning_rate": 2.0024950800006463e-05,
|
| 336 |
+
"loss": 0.246,
|
| 337 |
+
"step": 4300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.0,
|
| 341 |
+
"eval_accuracy": 0.9395626242544731,
|
| 342 |
+
"eval_loss": 0.2340400665998459,
|
| 343 |
+
"eval_runtime": 106.7505,
|
| 344 |
+
"eval_samples_per_second": 23.56,
|
| 345 |
+
"eval_steps_per_second": 1.48,
|
| 346 |
+
"step": 4396
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.0,
|
| 350 |
+
"grad_norm": 8.573821067810059,
|
| 351 |
+
"learning_rate": 1.961893979347137e-05,
|
| 352 |
+
"loss": 0.2168,
|
| 353 |
+
"step": 4400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.09,
|
| 357 |
+
"grad_norm": 12.596579551696777,
|
| 358 |
+
"learning_rate": 1.9209154654915524e-05,
|
| 359 |
+
"loss": 0.1946,
|
| 360 |
+
"step": 4500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.19,
|
| 364 |
+
"grad_norm": 15.590298652648926,
|
| 365 |
+
"learning_rate": 1.879593021944875e-05,
|
| 366 |
+
"loss": 0.2028,
|
| 367 |
+
"step": 4600
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.28,
|
| 371 |
+
"grad_norm": 20.42356300354004,
|
| 372 |
+
"learning_rate": 1.837960413242765e-05,
|
| 373 |
+
"loss": 0.1985,
|
| 374 |
+
"step": 4700
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.37,
|
| 378 |
+
"grad_norm": 1.106755018234253,
|
| 379 |
+
"learning_rate": 1.796051657356582e-05,
|
| 380 |
+
"loss": 0.1907,
|
| 381 |
+
"step": 4800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.46,
|
| 385 |
+
"grad_norm": 4.9287495613098145,
|
| 386 |
+
"learning_rate": 1.7539009978973312e-05,
|
| 387 |
+
"loss": 0.1858,
|
| 388 |
+
"step": 4900
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.55,
|
| 392 |
+
"grad_norm": 25.559234619140625,
|
| 393 |
+
"learning_rate": 1.711542876135233e-05,
|
| 394 |
+
"loss": 0.1694,
|
| 395 |
+
"step": 5000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.64,
|
| 399 |
+
"grad_norm": 22.039155960083008,
|
| 400 |
+
"learning_rate": 1.669011902857791e-05,
|
| 401 |
+
"loss": 0.1891,
|
| 402 |
+
"step": 5100
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.73,
|
| 406 |
+
"grad_norm": 3.6209306716918945,
|
| 407 |
+
"learning_rate": 1.6263428300893422e-05,
|
| 408 |
+
"loss": 0.1981,
|
| 409 |
+
"step": 5200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.82,
|
| 413 |
+
"grad_norm": 30.3158016204834,
|
| 414 |
+
"learning_rate": 1.5835705226952112e-05,
|
| 415 |
+
"loss": 0.1867,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.91,
|
| 420 |
+
"grad_norm": 32.05391311645508,
|
| 421 |
+
"learning_rate": 1.540729929893649e-05,
|
| 422 |
+
"loss": 0.201,
|
| 423 |
+
"step": 5400
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.0,
|
| 427 |
+
"eval_accuracy": 0.9411530815109344,
|
| 428 |
+
"eval_loss": 0.25883305072784424,
|
| 429 |
+
"eval_runtime": 105.5526,
|
| 430 |
+
"eval_samples_per_second": 23.827,
|
| 431 |
+
"eval_steps_per_second": 1.497,
|
| 432 |
+
"step": 5495
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.0,
|
| 436 |
+
"grad_norm": 1.146540641784668,
|
| 437 |
+
"learning_rate": 1.4978560566988603e-05,
|
| 438 |
+
"loss": 0.1906,
|
| 439 |
+
"step": 5500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.1,
|
| 443 |
+
"grad_norm": 15.014126777648926,
|
| 444 |
+
"learning_rate": 1.454983935318433e-05,
|
| 445 |
+
"loss": 0.1563,
|
| 446 |
+
"step": 5600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.19,
|
| 450 |
+
"grad_norm": 7.286404609680176,
|
| 451 |
+
"learning_rate": 1.4121485965285485e-05,
|
| 452 |
+
"loss": 0.1526,
|
| 453 |
+
"step": 5700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.28,
|
| 457 |
+
"grad_norm": 19.885345458984375,
|
| 458 |
+
"learning_rate": 1.3693850410503614e-05,
|
| 459 |
+
"loss": 0.1482,
|
| 460 |
+
"step": 5800
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.37,
|
| 464 |
+
"grad_norm": 0.03801773115992546,
|
| 465 |
+
"learning_rate": 1.326728210950942e-05,
|
| 466 |
+
"loss": 0.1619,
|
| 467 |
+
"step": 5900
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.46,
|
| 471 |
+
"grad_norm": 0.256340354681015,
|
| 472 |
+
"learning_rate": 1.2842129610921378e-05,
|
| 473 |
+
"loss": 0.1431,
|
| 474 |
+
"step": 6000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.55,
|
| 478 |
+
"grad_norm": 6.246147632598877,
|
| 479 |
+
"learning_rate": 1.2418740306506923e-05,
|
| 480 |
+
"loss": 0.194,
|
| 481 |
+
"step": 6100
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.64,
|
| 485 |
+
"grad_norm": 0.7258792519569397,
|
| 486 |
+
"learning_rate": 1.1997460147328984e-05,
|
| 487 |
+
"loss": 0.1388,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.73,
|
| 492 |
+
"grad_norm": 5.175995826721191,
|
| 493 |
+
"learning_rate": 1.1578633361069559e-05,
|
| 494 |
+
"loss": 0.1943,
|
| 495 |
+
"step": 6300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.82,
|
| 499 |
+
"grad_norm": 5.505824089050293,
|
| 500 |
+
"learning_rate": 1.1162602170761611e-05,
|
| 501 |
+
"loss": 0.1617,
|
| 502 |
+
"step": 6400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.91,
|
| 506 |
+
"grad_norm": 22.753047943115234,
|
| 507 |
+
"learning_rate": 1.0749706515158863e-05,
|
| 508 |
+
"loss": 0.1757,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.0,
|
| 513 |
+
"eval_accuracy": 0.9439363817097416,
|
| 514 |
+
"eval_loss": 0.2435537427663803,
|
| 515 |
+
"eval_runtime": 105.5095,
|
| 516 |
+
"eval_samples_per_second": 23.837,
|
| 517 |
+
"eval_steps_per_second": 1.497,
|
| 518 |
+
"step": 6594
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.01,
|
| 522 |
+
"grad_norm": 17.974355697631836,
|
| 523 |
+
"learning_rate": 1.0340283770972167e-05,
|
| 524 |
+
"loss": 0.1683,
|
| 525 |
+
"step": 6600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.1,
|
| 529 |
+
"grad_norm": 26.32249641418457,
|
| 530 |
+
"learning_rate": 9.93466847719919e-06,
|
| 531 |
+
"loss": 0.1313,
|
| 532 |
+
"step": 6700
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.19,
|
| 536 |
+
"grad_norm": 8.388775825500488,
|
| 537 |
+
"learning_rate": 9.533192061772919e-06,
|
| 538 |
+
"loss": 0.1363,
|
| 539 |
+
"step": 6800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.28,
|
| 543 |
+
"grad_norm": 15.968542098999023,
|
| 544 |
+
"learning_rate": 9.136182570752153e-06,
|
| 545 |
+
"loss": 0.1241,
|
| 546 |
+
"step": 6900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.37,
|
| 550 |
+
"grad_norm": 0.21214519441127777,
|
| 551 |
+
"learning_rate": 8.743964400275304e-06,
|
| 552 |
+
"loss": 0.1201,
|
| 553 |
+
"step": 7000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.46,
|
| 557 |
+
"grad_norm": 0.1043318435549736,
|
| 558 |
+
"learning_rate": 8.356858031496596e-06,
|
| 559 |
+
"loss": 0.1438,
|
| 560 |
+
"step": 7100
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.55,
|
| 564 |
+
"grad_norm": 0.6806092858314514,
|
| 565 |
+
"learning_rate": 7.975179768721187e-06,
|
| 566 |
+
"loss": 0.13,
|
| 567 |
+
"step": 7200
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.64,
|
| 571 |
+
"grad_norm": 0.5344202518463135,
|
| 572 |
+
"learning_rate": 7.599241480953112e-06,
|
| 573 |
+
"loss": 0.1393,
|
| 574 |
+
"step": 7300
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.73,
|
| 578 |
+
"grad_norm": 28.392440795898438,
|
| 579 |
+
"learning_rate": 7.229350347067426e-06,
|
| 580 |
+
"loss": 0.1441,
|
| 581 |
+
"step": 7400
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.82,
|
| 585 |
+
"grad_norm": 21.353750228881836,
|
| 586 |
+
"learning_rate": 6.865808604814564e-06,
|
| 587 |
+
"loss": 0.1211,
|
| 588 |
+
"step": 7500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.92,
|
| 592 |
+
"grad_norm": 3.2531442642211914,
|
| 593 |
+
"learning_rate": 6.508913303862144e-06,
|
| 594 |
+
"loss": 0.1699,
|
| 595 |
+
"step": 7600
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.0,
|
| 599 |
+
"eval_accuracy": 0.9443339960238568,
|
| 600 |
+
"eval_loss": 0.2558170557022095,
|
| 601 |
+
"eval_runtime": 106.0537,
|
| 602 |
+
"eval_samples_per_second": 23.714,
|
| 603 |
+
"eval_steps_per_second": 1.49,
|
| 604 |
+
"step": 7693
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.01,
|
| 608 |
+
"grad_norm": 27.954816818237305,
|
| 609 |
+
"learning_rate": 6.1589560630758656e-06,
|
| 610 |
+
"loss": 0.1067,
|
| 611 |
+
"step": 7700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.1,
|
| 615 |
+
"grad_norm": 12.10332202911377,
|
| 616 |
+
"learning_rate": 5.8162228322380155e-06,
|
| 617 |
+
"loss": 0.1084,
|
| 618 |
+
"step": 7800
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.19,
|
| 622 |
+
"grad_norm": 1.8917927742004395,
|
| 623 |
+
"learning_rate": 5.480993658398129e-06,
|
| 624 |
+
"loss": 0.1441,
|
| 625 |
+
"step": 7900
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.28,
|
| 629 |
+
"grad_norm": 0.24689602851867676,
|
| 630 |
+
"learning_rate": 5.153542457046737e-06,
|
| 631 |
+
"loss": 0.1006,
|
| 632 |
+
"step": 8000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.37,
|
| 636 |
+
"grad_norm": 3.907996416091919,
|
| 637 |
+
"learning_rate": 4.834136788299248e-06,
|
| 638 |
+
"loss": 0.1243,
|
| 639 |
+
"step": 8100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.46,
|
| 643 |
+
"grad_norm": 0.24271999299526215,
|
| 644 |
+
"learning_rate": 4.523037638272822e-06,
|
| 645 |
+
"loss": 0.0981,
|
| 646 |
+
"step": 8200
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.55,
|
| 650 |
+
"grad_norm": 20.29511833190918,
|
| 651 |
+
"learning_rate": 4.220499205834783e-06,
|
| 652 |
+
"loss": 0.1046,
|
| 653 |
+
"step": 8300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.64,
|
| 657 |
+
"grad_norm": 2.0506038665771484,
|
| 658 |
+
"learning_rate": 3.926768694896931e-06,
|
| 659 |
+
"loss": 0.1175,
|
| 660 |
+
"step": 8400
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.73,
|
| 664 |
+
"grad_norm": 0.33996373414993286,
|
| 665 |
+
"learning_rate": 3.6420861124254607e-06,
|
| 666 |
+
"loss": 0.1491,
|
| 667 |
+
"step": 8500
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.83,
|
| 671 |
+
"grad_norm": 0.5826025605201721,
|
| 672 |
+
"learning_rate": 3.3666840723314145e-06,
|
| 673 |
+
"loss": 0.1164,
|
| 674 |
+
"step": 8600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.92,
|
| 678 |
+
"grad_norm": 3.4220075607299805,
|
| 679 |
+
"learning_rate": 3.1007876054020724e-06,
|
| 680 |
+
"loss": 0.1178,
|
| 681 |
+
"step": 8700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.0,
|
| 685 |
+
"eval_accuracy": 0.9479125248508946,
|
| 686 |
+
"eval_loss": 0.2512185275554657,
|
| 687 |
+
"eval_runtime": 105.3589,
|
| 688 |
+
"eval_samples_per_second": 23.871,
|
| 689 |
+
"eval_steps_per_second": 1.5,
|
| 690 |
+
"step": 8792
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 8.01,
|
| 694 |
+
"grad_norm": 5.513002395629883,
|
| 695 |
+
"learning_rate": 2.8446139754284486e-06,
|
| 696 |
+
"loss": 0.1009,
|
| 697 |
+
"step": 8800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.1,
|
| 701 |
+
"grad_norm": 15.36313533782959,
|
| 702 |
+
"learning_rate": 2.5983725016792574e-06,
|
| 703 |
+
"loss": 0.1245,
|
| 704 |
+
"step": 8900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.19,
|
| 708 |
+
"grad_norm": 3.3562428951263428,
|
| 709 |
+
"learning_rate": 2.36226438786627e-06,
|
| 710 |
+
"loss": 0.1124,
|
| 711 |
+
"step": 9000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.28,
|
| 715 |
+
"grad_norm": 28.229764938354492,
|
| 716 |
+
"learning_rate": 2.1364825577409424e-06,
|
| 717 |
+
"loss": 0.0913,
|
| 718 |
+
"step": 9100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.37,
|
| 722 |
+
"grad_norm": 3.830212116241455,
|
| 723 |
+
"learning_rate": 1.9212114974565664e-06,
|
| 724 |
+
"loss": 0.1226,
|
| 725 |
+
"step": 9200
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.46,
|
| 729 |
+
"grad_norm": 0.01726786606013775,
|
| 730 |
+
"learning_rate": 1.7166271048247796e-06,
|
| 731 |
+
"loss": 0.0825,
|
| 732 |
+
"step": 9300
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.55,
|
| 736 |
+
"grad_norm": 10.166333198547363,
|
| 737 |
+
"learning_rate": 1.5228965455896054e-06,
|
| 738 |
+
"loss": 0.0989,
|
| 739 |
+
"step": 9400
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 8.64,
|
| 743 |
+
"grad_norm": 18.327802658081055,
|
| 744 |
+
"learning_rate": 1.3401781168364591e-06,
|
| 745 |
+
"loss": 0.105,
|
| 746 |
+
"step": 9500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.74,
|
| 750 |
+
"grad_norm": 0.282446950674057,
|
| 751 |
+
"learning_rate": 1.1686211176477208e-06,
|
| 752 |
+
"loss": 0.1097,
|
| 753 |
+
"step": 9600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.83,
|
| 757 |
+
"grad_norm": 21.263484954833984,
|
| 758 |
+
"learning_rate": 1.00836572711058e-06,
|
| 759 |
+
"loss": 0.1297,
|
| 760 |
+
"step": 9700
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.92,
|
| 764 |
+
"grad_norm": 4.42637825012207,
|
| 765 |
+
"learning_rate": 8.595428897768071e-07,
|
| 766 |
+
"loss": 0.1167,
|
| 767 |
+
"step": 9800
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 9.0,
|
| 771 |
+
"eval_accuracy": 0.9479125248508946,
|
| 772 |
+
"eval_loss": 0.2536466717720032,
|
| 773 |
+
"eval_runtime": 105.7662,
|
| 774 |
+
"eval_samples_per_second": 23.779,
|
| 775 |
+
"eval_steps_per_second": 1.494,
|
| 776 |
+
"step": 9891
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 9.01,
|
| 780 |
+
"grad_norm": 9.55751895904541,
|
| 781 |
+
"learning_rate": 7.222742086680756e-07,
|
| 782 |
+
"loss": 0.1121,
|
| 783 |
+
"step": 9900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.1,
|
| 787 |
+
"grad_norm": 0.058909401297569275,
|
| 788 |
+
"learning_rate": 5.966718459142196e-07,
|
| 789 |
+
"loss": 0.0856,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.19,
|
| 794 |
+
"grad_norm": 27.23402214050293,
|
| 795 |
+
"learning_rate": 4.82838431105655e-07,
|
| 796 |
+
"loss": 0.1041,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 9.28,
|
| 801 |
+
"grad_norm": 0.20296531915664673,
|
| 802 |
+
"learning_rate": 3.808669774348167e-07,
|
| 803 |
+
"loss": 0.1079,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.37,
|
| 808 |
+
"grad_norm": 0.6779181957244873,
|
| 809 |
+
"learning_rate": 2.908408056951578e-07,
|
| 810 |
+
"loss": 0.0855,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 9.46,
|
| 815 |
+
"grad_norm": 0.20246420800685883,
|
| 816 |
+
"learning_rate": 2.1283347619979243e-07,
|
| 817 |
+
"loss": 0.0715,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.55,
|
| 822 |
+
"grad_norm": 0.13543924689292908,
|
| 823 |
+
"learning_rate": 1.4690872867542892e-07,
|
| 824 |
+
"loss": 0.1181,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.65,
|
| 829 |
+
"grad_norm": 12.729443550109863,
|
| 830 |
+
"learning_rate": 9.312043018067762e-08,
|
| 831 |
+
"loss": 0.1114,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 9.74,
|
| 836 |
+
"grad_norm": 11.665053367614746,
|
| 837 |
+
"learning_rate": 5.1512531091333914e-08,
|
| 838 |
+
"loss": 0.131,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.83,
|
| 843 |
+
"grad_norm": 5.462090969085693,
|
| 844 |
+
"learning_rate": 2.211902918855313e-08,
|
| 845 |
+
"loss": 0.1174,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 9.92,
|
| 850 |
+
"grad_norm": 8.030549049377441,
|
| 851 |
+
"learning_rate": 4.963941879295164e-09,
|
| 852 |
+
"loss": 0.0889,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 10.0,
|
| 857 |
+
"eval_accuracy": 0.9495029821073558,
|
| 858 |
+
"eval_loss": 0.25355264544487,
|
| 859 |
+
"eval_runtime": 105.6261,
|
| 860 |
+
"eval_samples_per_second": 23.81,
|
| 861 |
+
"eval_steps_per_second": 1.496,
|
| 862 |
+
"step": 10990
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 10.0,
|
| 866 |
+
"step": 10990,
|
| 867 |
+
"total_flos": 4.09349935387607e+19,
|
| 868 |
+
"train_loss": 0.25289429932751367,
|
| 869 |
+
"train_runtime": 17079.3849,
|
| 870 |
+
"train_samples_per_second": 10.294,
|
| 871 |
+
"train_steps_per_second": 0.643
|
| 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 |
+
}
|