Commit
•
e833e43
1
Parent(s):
760618c
Training in progress, epoch 1
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/May04_07-50-27_4f22111e1b44/events.out.tfevents.1714809034.4f22111e1b44.9006.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +868 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 6.302667737382912e+17,
|
| 4 |
+
"train_loss": 0.13929352825309368,
|
| 5 |
+
"train_runtime": 703.6937,
|
| 6 |
+
"train_samples_per_second": 42.177,
|
| 7 |
+
"train_steps_per_second": 1.336
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94302952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:780eabfb1ede8e9e88f021a6b3eb3e36687167bee7cd7ec380ba2499c1df5c17
|
| 3 |
size 94302952
|
runs/May04_07-50-27_4f22111e1b44/events.out.tfevents.1714809034.4f22111e1b44.9006.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d895d001f660732d94a8edaf7b514109fafece53dd472db6f7e499142d751d62
|
| 3 |
+
size 5991
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 6.302667737382912e+17,
|
| 4 |
+
"train_loss": 0.13929352825309368,
|
| 5 |
+
"train_runtime": 703.6937,
|
| 6 |
+
"train_samples_per_second": 42.177,
|
| 7 |
+
"train_steps_per_second": 1.336
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,868 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-student_kaggle/checkpoint-423",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 940,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2127659574468085,
|
| 13 |
+
"grad_norm": 54.35947799682617,
|
| 14 |
+
"learning_rate": 5.319148936170213e-06,
|
| 15 |
+
"loss": 0.9341,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.425531914893617,
|
| 20 |
+
"grad_norm": 34.59556579589844,
|
| 21 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 22 |
+
"loss": 0.9157,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6382978723404256,
|
| 27 |
+
"grad_norm": 42.179847717285156,
|
| 28 |
+
"learning_rate": 1.595744680851064e-05,
|
| 29 |
+
"loss": 0.7801,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.851063829787234,
|
| 34 |
+
"grad_norm": 30.099029541015625,
|
| 35 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 36 |
+
"loss": 0.7142,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.610062893081761,
|
| 42 |
+
"eval_loss": 0.6418222188949585,
|
| 43 |
+
"eval_runtime": 7.6299,
|
| 44 |
+
"eval_samples_per_second": 83.356,
|
| 45 |
+
"eval_steps_per_second": 2.621,
|
| 46 |
+
"step": 47
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.0638297872340425,
|
| 50 |
+
"grad_norm": 48.046546936035156,
|
| 51 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 52 |
+
"loss": 0.7114,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.2765957446808511,
|
| 57 |
+
"grad_norm": 45.94879913330078,
|
| 58 |
+
"learning_rate": 3.191489361702128e-05,
|
| 59 |
+
"loss": 0.6014,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.4893617021276595,
|
| 64 |
+
"grad_norm": 17.69209861755371,
|
| 65 |
+
"learning_rate": 3.723404255319149e-05,
|
| 66 |
+
"loss": 0.4815,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.702127659574468,
|
| 71 |
+
"grad_norm": 18.821670532226562,
|
| 72 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 73 |
+
"loss": 0.463,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.9148936170212765,
|
| 78 |
+
"grad_norm": 23.751588821411133,
|
| 79 |
+
"learning_rate": 4.787234042553192e-05,
|
| 80 |
+
"loss": 0.3351,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.0,
|
| 85 |
+
"eval_accuracy": 0.8946540880503144,
|
| 86 |
+
"eval_loss": 0.25965991616249084,
|
| 87 |
+
"eval_runtime": 7.6659,
|
| 88 |
+
"eval_samples_per_second": 82.964,
|
| 89 |
+
"eval_steps_per_second": 2.609,
|
| 90 |
+
"step": 94
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.127659574468085,
|
| 94 |
+
"grad_norm": 18.11069679260254,
|
| 95 |
+
"learning_rate": 4.964539007092199e-05,
|
| 96 |
+
"loss": 0.3193,
|
| 97 |
+
"step": 100
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.3404255319148937,
|
| 101 |
+
"grad_norm": 12.397391319274902,
|
| 102 |
+
"learning_rate": 4.905437352245863e-05,
|
| 103 |
+
"loss": 0.2768,
|
| 104 |
+
"step": 110
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.5531914893617023,
|
| 108 |
+
"grad_norm": 16.857635498046875,
|
| 109 |
+
"learning_rate": 4.846335697399527e-05,
|
| 110 |
+
"loss": 0.2594,
|
| 111 |
+
"step": 120
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.7659574468085104,
|
| 115 |
+
"grad_norm": 12.635449409484863,
|
| 116 |
+
"learning_rate": 4.787234042553192e-05,
|
| 117 |
+
"loss": 0.2063,
|
| 118 |
+
"step": 130
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.978723404255319,
|
| 122 |
+
"grad_norm": 15.277303695678711,
|
| 123 |
+
"learning_rate": 4.728132387706856e-05,
|
| 124 |
+
"loss": 0.2574,
|
| 125 |
+
"step": 140
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.0,
|
| 129 |
+
"eval_accuracy": 0.9779874213836478,
|
| 130 |
+
"eval_loss": 0.10460298508405685,
|
| 131 |
+
"eval_runtime": 8.3391,
|
| 132 |
+
"eval_samples_per_second": 76.267,
|
| 133 |
+
"eval_steps_per_second": 2.398,
|
| 134 |
+
"step": 141
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.1914893617021276,
|
| 138 |
+
"grad_norm": 14.497098922729492,
|
| 139 |
+
"learning_rate": 4.669030732860521e-05,
|
| 140 |
+
"loss": 0.2349,
|
| 141 |
+
"step": 150
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.404255319148936,
|
| 145 |
+
"grad_norm": 17.647092819213867,
|
| 146 |
+
"learning_rate": 4.609929078014185e-05,
|
| 147 |
+
"loss": 0.1631,
|
| 148 |
+
"step": 160
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.617021276595745,
|
| 152 |
+
"grad_norm": 12.856146812438965,
|
| 153 |
+
"learning_rate": 4.550827423167849e-05,
|
| 154 |
+
"loss": 0.1675,
|
| 155 |
+
"step": 170
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.829787234042553,
|
| 159 |
+
"grad_norm": 7.248583793640137,
|
| 160 |
+
"learning_rate": 4.491725768321513e-05,
|
| 161 |
+
"loss": 0.1479,
|
| 162 |
+
"step": 180
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.0,
|
| 166 |
+
"eval_accuracy": 0.9874213836477987,
|
| 167 |
+
"eval_loss": 0.061614990234375,
|
| 168 |
+
"eval_runtime": 8.4097,
|
| 169 |
+
"eval_samples_per_second": 75.627,
|
| 170 |
+
"eval_steps_per_second": 2.378,
|
| 171 |
+
"step": 188
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.042553191489362,
|
| 175 |
+
"grad_norm": 25.721847534179688,
|
| 176 |
+
"learning_rate": 4.432624113475177e-05,
|
| 177 |
+
"loss": 0.1528,
|
| 178 |
+
"step": 190
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.25531914893617,
|
| 182 |
+
"grad_norm": 6.252942085266113,
|
| 183 |
+
"learning_rate": 4.373522458628842e-05,
|
| 184 |
+
"loss": 0.145,
|
| 185 |
+
"step": 200
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.468085106382979,
|
| 189 |
+
"grad_norm": 6.672601222991943,
|
| 190 |
+
"learning_rate": 4.3144208037825064e-05,
|
| 191 |
+
"loss": 0.1247,
|
| 192 |
+
"step": 210
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 4.680851063829787,
|
| 196 |
+
"grad_norm": 20.4866886138916,
|
| 197 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 198 |
+
"loss": 0.1405,
|
| 199 |
+
"step": 220
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.8936170212765955,
|
| 203 |
+
"grad_norm": 19.644893646240234,
|
| 204 |
+
"learning_rate": 4.1962174940898345e-05,
|
| 205 |
+
"loss": 0.1284,
|
| 206 |
+
"step": 230
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.0,
|
| 210 |
+
"eval_accuracy": 0.9952830188679245,
|
| 211 |
+
"eval_loss": 0.02317511849105358,
|
| 212 |
+
"eval_runtime": 10.3441,
|
| 213 |
+
"eval_samples_per_second": 61.485,
|
| 214 |
+
"eval_steps_per_second": 1.933,
|
| 215 |
+
"step": 235
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.1063829787234045,
|
| 219 |
+
"grad_norm": 10.905556678771973,
|
| 220 |
+
"learning_rate": 4.1371158392434986e-05,
|
| 221 |
+
"loss": 0.1178,
|
| 222 |
+
"step": 240
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.319148936170213,
|
| 226 |
+
"grad_norm": 11.02078628540039,
|
| 227 |
+
"learning_rate": 4.078014184397163e-05,
|
| 228 |
+
"loss": 0.1176,
|
| 229 |
+
"step": 250
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 5.531914893617021,
|
| 233 |
+
"grad_norm": 7.510810375213623,
|
| 234 |
+
"learning_rate": 4.018912529550828e-05,
|
| 235 |
+
"loss": 0.0881,
|
| 236 |
+
"step": 260
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.74468085106383,
|
| 240 |
+
"grad_norm": 2.0541610717773438,
|
| 241 |
+
"learning_rate": 3.959810874704492e-05,
|
| 242 |
+
"loss": 0.1274,
|
| 243 |
+
"step": 270
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 5.957446808510638,
|
| 247 |
+
"grad_norm": 7.680713653564453,
|
| 248 |
+
"learning_rate": 3.900709219858156e-05,
|
| 249 |
+
"loss": 0.077,
|
| 250 |
+
"step": 280
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 6.0,
|
| 254 |
+
"eval_accuracy": 0.9952830188679245,
|
| 255 |
+
"eval_loss": 0.015012426301836967,
|
| 256 |
+
"eval_runtime": 8.4118,
|
| 257 |
+
"eval_samples_per_second": 75.608,
|
| 258 |
+
"eval_steps_per_second": 2.378,
|
| 259 |
+
"step": 282
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.170212765957447,
|
| 263 |
+
"grad_norm": 8.117420196533203,
|
| 264 |
+
"learning_rate": 3.84160756501182e-05,
|
| 265 |
+
"loss": 0.172,
|
| 266 |
+
"step": 290
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.382978723404255,
|
| 270 |
+
"grad_norm": 23.871868133544922,
|
| 271 |
+
"learning_rate": 3.782505910165485e-05,
|
| 272 |
+
"loss": 0.0613,
|
| 273 |
+
"step": 300
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.595744680851064,
|
| 277 |
+
"grad_norm": 15.407998085021973,
|
| 278 |
+
"learning_rate": 3.723404255319149e-05,
|
| 279 |
+
"loss": 0.1287,
|
| 280 |
+
"step": 310
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.808510638297872,
|
| 284 |
+
"grad_norm": 6.940992832183838,
|
| 285 |
+
"learning_rate": 3.664302600472813e-05,
|
| 286 |
+
"loss": 0.103,
|
| 287 |
+
"step": 320
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.0,
|
| 291 |
+
"eval_accuracy": 0.9984276729559748,
|
| 292 |
+
"eval_loss": 0.010532047599554062,
|
| 293 |
+
"eval_runtime": 7.9689,
|
| 294 |
+
"eval_samples_per_second": 79.81,
|
| 295 |
+
"eval_steps_per_second": 2.51,
|
| 296 |
+
"step": 329
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.0212765957446805,
|
| 300 |
+
"grad_norm": 4.598968029022217,
|
| 301 |
+
"learning_rate": 3.605200945626478e-05,
|
| 302 |
+
"loss": 0.0906,
|
| 303 |
+
"step": 330
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.23404255319149,
|
| 307 |
+
"grad_norm": 7.53684663772583,
|
| 308 |
+
"learning_rate": 3.546099290780142e-05,
|
| 309 |
+
"loss": 0.0792,
|
| 310 |
+
"step": 340
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 7.446808510638298,
|
| 314 |
+
"grad_norm": 2.750072479248047,
|
| 315 |
+
"learning_rate": 3.4869976359338065e-05,
|
| 316 |
+
"loss": 0.091,
|
| 317 |
+
"step": 350
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.659574468085106,
|
| 321 |
+
"grad_norm": 4.067008018493652,
|
| 322 |
+
"learning_rate": 3.4278959810874706e-05,
|
| 323 |
+
"loss": 0.0777,
|
| 324 |
+
"step": 360
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.872340425531915,
|
| 328 |
+
"grad_norm": 15.093037605285645,
|
| 329 |
+
"learning_rate": 3.3687943262411347e-05,
|
| 330 |
+
"loss": 0.0922,
|
| 331 |
+
"step": 370
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 8.0,
|
| 335 |
+
"eval_accuracy": 0.9984276729559748,
|
| 336 |
+
"eval_loss": 0.009353628382086754,
|
| 337 |
+
"eval_runtime": 7.7264,
|
| 338 |
+
"eval_samples_per_second": 82.315,
|
| 339 |
+
"eval_steps_per_second": 2.589,
|
| 340 |
+
"step": 376
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 8.085106382978724,
|
| 344 |
+
"grad_norm": 8.675619125366211,
|
| 345 |
+
"learning_rate": 3.309692671394799e-05,
|
| 346 |
+
"loss": 0.1211,
|
| 347 |
+
"step": 380
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 8.297872340425531,
|
| 351 |
+
"grad_norm": 5.723608493804932,
|
| 352 |
+
"learning_rate": 3.2505910165484634e-05,
|
| 353 |
+
"loss": 0.0645,
|
| 354 |
+
"step": 390
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.51063829787234,
|
| 358 |
+
"grad_norm": 8.031245231628418,
|
| 359 |
+
"learning_rate": 3.191489361702128e-05,
|
| 360 |
+
"loss": 0.0787,
|
| 361 |
+
"step": 400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 8.72340425531915,
|
| 365 |
+
"grad_norm": 2.483238935470581,
|
| 366 |
+
"learning_rate": 3.132387706855792e-05,
|
| 367 |
+
"loss": 0.0683,
|
| 368 |
+
"step": 410
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 8.936170212765958,
|
| 372 |
+
"grad_norm": 7.612273216247559,
|
| 373 |
+
"learning_rate": 3.073286052009456e-05,
|
| 374 |
+
"loss": 0.08,
|
| 375 |
+
"step": 420
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 9.0,
|
| 379 |
+
"eval_accuracy": 1.0,
|
| 380 |
+
"eval_loss": 0.00555912172421813,
|
| 381 |
+
"eval_runtime": 8.4427,
|
| 382 |
+
"eval_samples_per_second": 75.331,
|
| 383 |
+
"eval_steps_per_second": 2.369,
|
| 384 |
+
"step": 423
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.148936170212766,
|
| 388 |
+
"grad_norm": 2.0842654705047607,
|
| 389 |
+
"learning_rate": 3.0141843971631207e-05,
|
| 390 |
+
"loss": 0.0812,
|
| 391 |
+
"step": 430
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 9.361702127659575,
|
| 395 |
+
"grad_norm": 17.500883102416992,
|
| 396 |
+
"learning_rate": 2.9550827423167847e-05,
|
| 397 |
+
"loss": 0.0688,
|
| 398 |
+
"step": 440
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 9.574468085106384,
|
| 402 |
+
"grad_norm": 9.671988487243652,
|
| 403 |
+
"learning_rate": 2.895981087470449e-05,
|
| 404 |
+
"loss": 0.0837,
|
| 405 |
+
"step": 450
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 9.787234042553191,
|
| 409 |
+
"grad_norm": 13.061412811279297,
|
| 410 |
+
"learning_rate": 2.836879432624114e-05,
|
| 411 |
+
"loss": 0.1024,
|
| 412 |
+
"step": 460
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 10.0,
|
| 416 |
+
"grad_norm": 11.679757118225098,
|
| 417 |
+
"learning_rate": 2.777777777777778e-05,
|
| 418 |
+
"loss": 0.0492,
|
| 419 |
+
"step": 470
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 10.0,
|
| 423 |
+
"eval_accuracy": 1.0,
|
| 424 |
+
"eval_loss": 0.004496446345001459,
|
| 425 |
+
"eval_runtime": 9.0183,
|
| 426 |
+
"eval_samples_per_second": 70.523,
|
| 427 |
+
"eval_steps_per_second": 2.218,
|
| 428 |
+
"step": 470
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 10.212765957446809,
|
| 432 |
+
"grad_norm": 3.253716230392456,
|
| 433 |
+
"learning_rate": 2.7186761229314423e-05,
|
| 434 |
+
"loss": 0.0495,
|
| 435 |
+
"step": 480
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 10.425531914893616,
|
| 439 |
+
"grad_norm": 5.826026916503906,
|
| 440 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 441 |
+
"loss": 0.0266,
|
| 442 |
+
"step": 490
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 10.638297872340425,
|
| 446 |
+
"grad_norm": 9.738965034484863,
|
| 447 |
+
"learning_rate": 2.6004728132387708e-05,
|
| 448 |
+
"loss": 0.0739,
|
| 449 |
+
"step": 500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 10.851063829787234,
|
| 453 |
+
"grad_norm": 9.04916763305664,
|
| 454 |
+
"learning_rate": 2.5413711583924348e-05,
|
| 455 |
+
"loss": 0.0574,
|
| 456 |
+
"step": 510
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 11.0,
|
| 460 |
+
"eval_accuracy": 1.0,
|
| 461 |
+
"eval_loss": 0.004308629781007767,
|
| 462 |
+
"eval_runtime": 8.4135,
|
| 463 |
+
"eval_samples_per_second": 75.593,
|
| 464 |
+
"eval_steps_per_second": 2.377,
|
| 465 |
+
"step": 517
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 11.063829787234043,
|
| 469 |
+
"grad_norm": 11.041916847229004,
|
| 470 |
+
"learning_rate": 2.4822695035460995e-05,
|
| 471 |
+
"loss": 0.0977,
|
| 472 |
+
"step": 520
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 11.27659574468085,
|
| 476 |
+
"grad_norm": 31.96723175048828,
|
| 477 |
+
"learning_rate": 2.4231678486997636e-05,
|
| 478 |
+
"loss": 0.0541,
|
| 479 |
+
"step": 530
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 11.48936170212766,
|
| 483 |
+
"grad_norm": 2.877957344055176,
|
| 484 |
+
"learning_rate": 2.364066193853428e-05,
|
| 485 |
+
"loss": 0.0401,
|
| 486 |
+
"step": 540
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 11.702127659574469,
|
| 490 |
+
"grad_norm": 3.020596742630005,
|
| 491 |
+
"learning_rate": 2.3049645390070924e-05,
|
| 492 |
+
"loss": 0.0284,
|
| 493 |
+
"step": 550
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 11.914893617021276,
|
| 497 |
+
"grad_norm": 7.811126232147217,
|
| 498 |
+
"learning_rate": 2.2458628841607564e-05,
|
| 499 |
+
"loss": 0.0382,
|
| 500 |
+
"step": 560
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 12.0,
|
| 504 |
+
"eval_accuracy": 1.0,
|
| 505 |
+
"eval_loss": 0.0022806336637586355,
|
| 506 |
+
"eval_runtime": 7.7232,
|
| 507 |
+
"eval_samples_per_second": 82.35,
|
| 508 |
+
"eval_steps_per_second": 2.59,
|
| 509 |
+
"step": 564
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 12.127659574468085,
|
| 513 |
+
"grad_norm": 11.633199691772461,
|
| 514 |
+
"learning_rate": 2.186761229314421e-05,
|
| 515 |
+
"loss": 0.0589,
|
| 516 |
+
"step": 570
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 12.340425531914894,
|
| 520 |
+
"grad_norm": 0.3253759443759918,
|
| 521 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 522 |
+
"loss": 0.041,
|
| 523 |
+
"step": 580
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 12.553191489361701,
|
| 527 |
+
"grad_norm": 2.2859044075012207,
|
| 528 |
+
"learning_rate": 2.0685579196217493e-05,
|
| 529 |
+
"loss": 0.0578,
|
| 530 |
+
"step": 590
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 12.76595744680851,
|
| 534 |
+
"grad_norm": 1.5324259996414185,
|
| 535 |
+
"learning_rate": 2.009456264775414e-05,
|
| 536 |
+
"loss": 0.0312,
|
| 537 |
+
"step": 600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 12.97872340425532,
|
| 541 |
+
"grad_norm": 6.985143661499023,
|
| 542 |
+
"learning_rate": 1.950354609929078e-05,
|
| 543 |
+
"loss": 0.0666,
|
| 544 |
+
"step": 610
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 13.0,
|
| 548 |
+
"eval_accuracy": 1.0,
|
| 549 |
+
"eval_loss": 0.0022491966374218464,
|
| 550 |
+
"eval_runtime": 8.1081,
|
| 551 |
+
"eval_samples_per_second": 78.44,
|
| 552 |
+
"eval_steps_per_second": 2.467,
|
| 553 |
+
"step": 611
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 13.191489361702128,
|
| 557 |
+
"grad_norm": 8.847366333007812,
|
| 558 |
+
"learning_rate": 1.8912529550827425e-05,
|
| 559 |
+
"loss": 0.0539,
|
| 560 |
+
"step": 620
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 13.404255319148936,
|
| 564 |
+
"grad_norm": 10.476814270019531,
|
| 565 |
+
"learning_rate": 1.8321513002364065e-05,
|
| 566 |
+
"loss": 0.0369,
|
| 567 |
+
"step": 630
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 13.617021276595745,
|
| 571 |
+
"grad_norm": 5.339621067047119,
|
| 572 |
+
"learning_rate": 1.773049645390071e-05,
|
| 573 |
+
"loss": 0.0308,
|
| 574 |
+
"step": 640
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 13.829787234042554,
|
| 578 |
+
"grad_norm": 14.648975372314453,
|
| 579 |
+
"learning_rate": 1.7139479905437353e-05,
|
| 580 |
+
"loss": 0.0477,
|
| 581 |
+
"step": 650
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 14.0,
|
| 585 |
+
"eval_accuracy": 1.0,
|
| 586 |
+
"eval_loss": 0.0021932125091552734,
|
| 587 |
+
"eval_runtime": 8.4493,
|
| 588 |
+
"eval_samples_per_second": 75.272,
|
| 589 |
+
"eval_steps_per_second": 2.367,
|
| 590 |
+
"step": 658
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 14.042553191489361,
|
| 594 |
+
"grad_norm": 5.510159969329834,
|
| 595 |
+
"learning_rate": 1.6548463356973994e-05,
|
| 596 |
+
"loss": 0.028,
|
| 597 |
+
"step": 660
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 14.25531914893617,
|
| 601 |
+
"grad_norm": 5.803068161010742,
|
| 602 |
+
"learning_rate": 1.595744680851064e-05,
|
| 603 |
+
"loss": 0.0522,
|
| 604 |
+
"step": 670
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 14.46808510638298,
|
| 608 |
+
"grad_norm": 1.1623107194900513,
|
| 609 |
+
"learning_rate": 1.536643026004728e-05,
|
| 610 |
+
"loss": 0.0481,
|
| 611 |
+
"step": 680
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 14.680851063829786,
|
| 615 |
+
"grad_norm": 12.495600700378418,
|
| 616 |
+
"learning_rate": 1.4775413711583924e-05,
|
| 617 |
+
"loss": 0.0588,
|
| 618 |
+
"step": 690
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 14.893617021276595,
|
| 622 |
+
"grad_norm": 3.4236888885498047,
|
| 623 |
+
"learning_rate": 1.418439716312057e-05,
|
| 624 |
+
"loss": 0.0614,
|
| 625 |
+
"step": 700
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 15.0,
|
| 629 |
+
"eval_accuracy": 1.0,
|
| 630 |
+
"eval_loss": 0.002270177938044071,
|
| 631 |
+
"eval_runtime": 8.5563,
|
| 632 |
+
"eval_samples_per_second": 74.331,
|
| 633 |
+
"eval_steps_per_second": 2.337,
|
| 634 |
+
"step": 705
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 15.106382978723405,
|
| 638 |
+
"grad_norm": 11.681058883666992,
|
| 639 |
+
"learning_rate": 1.3593380614657212e-05,
|
| 640 |
+
"loss": 0.0674,
|
| 641 |
+
"step": 710
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 15.319148936170214,
|
| 645 |
+
"grad_norm": 1.846946120262146,
|
| 646 |
+
"learning_rate": 1.3002364066193854e-05,
|
| 647 |
+
"loss": 0.0415,
|
| 648 |
+
"step": 720
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 15.53191489361702,
|
| 652 |
+
"grad_norm": 8.939858436584473,
|
| 653 |
+
"learning_rate": 1.2411347517730498e-05,
|
| 654 |
+
"loss": 0.0189,
|
| 655 |
+
"step": 730
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 15.74468085106383,
|
| 659 |
+
"grad_norm": 3.521784782409668,
|
| 660 |
+
"learning_rate": 1.182033096926714e-05,
|
| 661 |
+
"loss": 0.0585,
|
| 662 |
+
"step": 740
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 15.957446808510639,
|
| 666 |
+
"grad_norm": 1.9891993999481201,
|
| 667 |
+
"learning_rate": 1.1229314420803782e-05,
|
| 668 |
+
"loss": 0.0282,
|
| 669 |
+
"step": 750
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.0,
|
| 673 |
+
"eval_accuracy": 1.0,
|
| 674 |
+
"eval_loss": 0.0013930280692875385,
|
| 675 |
+
"eval_runtime": 8.1789,
|
| 676 |
+
"eval_samples_per_second": 77.761,
|
| 677 |
+
"eval_steps_per_second": 2.445,
|
| 678 |
+
"step": 752
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 16.170212765957448,
|
| 682 |
+
"grad_norm": 7.0705246925354,
|
| 683 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 684 |
+
"loss": 0.0508,
|
| 685 |
+
"step": 760
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 16.382978723404257,
|
| 689 |
+
"grad_norm": 11.365514755249023,
|
| 690 |
+
"learning_rate": 1.004728132387707e-05,
|
| 691 |
+
"loss": 0.0393,
|
| 692 |
+
"step": 770
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 16.595744680851062,
|
| 696 |
+
"grad_norm": 8.82397747039795,
|
| 697 |
+
"learning_rate": 9.456264775413712e-06,
|
| 698 |
+
"loss": 0.0509,
|
| 699 |
+
"step": 780
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 16.80851063829787,
|
| 703 |
+
"grad_norm": 5.013731002807617,
|
| 704 |
+
"learning_rate": 8.865248226950355e-06,
|
| 705 |
+
"loss": 0.0659,
|
| 706 |
+
"step": 790
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 17.0,
|
| 710 |
+
"eval_accuracy": 1.0,
|
| 711 |
+
"eval_loss": 0.0016287014586851,
|
| 712 |
+
"eval_runtime": 7.6703,
|
| 713 |
+
"eval_samples_per_second": 82.917,
|
| 714 |
+
"eval_steps_per_second": 2.607,
|
| 715 |
+
"step": 799
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 17.02127659574468,
|
| 719 |
+
"grad_norm": 2.8596644401550293,
|
| 720 |
+
"learning_rate": 8.274231678486997e-06,
|
| 721 |
+
"loss": 0.0285,
|
| 722 |
+
"step": 800
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 17.23404255319149,
|
| 726 |
+
"grad_norm": 10.184608459472656,
|
| 727 |
+
"learning_rate": 7.68321513002364e-06,
|
| 728 |
+
"loss": 0.062,
|
| 729 |
+
"step": 810
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 17.4468085106383,
|
| 733 |
+
"grad_norm": 6.029819011688232,
|
| 734 |
+
"learning_rate": 7.092198581560285e-06,
|
| 735 |
+
"loss": 0.0672,
|
| 736 |
+
"step": 820
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 17.659574468085108,
|
| 740 |
+
"grad_norm": 0.9212875366210938,
|
| 741 |
+
"learning_rate": 6.501182033096927e-06,
|
| 742 |
+
"loss": 0.0404,
|
| 743 |
+
"step": 830
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 17.872340425531917,
|
| 747 |
+
"grad_norm": 0.5147794485092163,
|
| 748 |
+
"learning_rate": 5.91016548463357e-06,
|
| 749 |
+
"loss": 0.0586,
|
| 750 |
+
"step": 840
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 18.0,
|
| 754 |
+
"eval_accuracy": 1.0,
|
| 755 |
+
"eval_loss": 0.0009691208251751959,
|
| 756 |
+
"eval_runtime": 8.4381,
|
| 757 |
+
"eval_samples_per_second": 75.373,
|
| 758 |
+
"eval_steps_per_second": 2.37,
|
| 759 |
+
"step": 846
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 18.085106382978722,
|
| 763 |
+
"grad_norm": 3.351142406463623,
|
| 764 |
+
"learning_rate": 5.319148936170213e-06,
|
| 765 |
+
"loss": 0.0333,
|
| 766 |
+
"step": 850
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 18.29787234042553,
|
| 770 |
+
"grad_norm": 7.570976257324219,
|
| 771 |
+
"learning_rate": 4.728132387706856e-06,
|
| 772 |
+
"loss": 0.0401,
|
| 773 |
+
"step": 860
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 18.51063829787234,
|
| 777 |
+
"grad_norm": 6.660007953643799,
|
| 778 |
+
"learning_rate": 4.137115839243498e-06,
|
| 779 |
+
"loss": 0.0329,
|
| 780 |
+
"step": 870
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 18.72340425531915,
|
| 784 |
+
"grad_norm": 11.373592376708984,
|
| 785 |
+
"learning_rate": 3.5460992907801423e-06,
|
| 786 |
+
"loss": 0.0523,
|
| 787 |
+
"step": 880
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 18.93617021276596,
|
| 791 |
+
"grad_norm": 4.553757667541504,
|
| 792 |
+
"learning_rate": 2.955082742316785e-06,
|
| 793 |
+
"loss": 0.0557,
|
| 794 |
+
"step": 890
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 19.0,
|
| 798 |
+
"eval_accuracy": 1.0,
|
| 799 |
+
"eval_loss": 0.0012750416062772274,
|
| 800 |
+
"eval_runtime": 8.3957,
|
| 801 |
+
"eval_samples_per_second": 75.753,
|
| 802 |
+
"eval_steps_per_second": 2.382,
|
| 803 |
+
"step": 893
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 19.148936170212767,
|
| 807 |
+
"grad_norm": 1.8293001651763916,
|
| 808 |
+
"learning_rate": 2.364066193853428e-06,
|
| 809 |
+
"loss": 0.0248,
|
| 810 |
+
"step": 900
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 19.361702127659573,
|
| 814 |
+
"grad_norm": 3.5974695682525635,
|
| 815 |
+
"learning_rate": 1.7730496453900712e-06,
|
| 816 |
+
"loss": 0.0298,
|
| 817 |
+
"step": 910
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 19.574468085106382,
|
| 821 |
+
"grad_norm": 4.631837844848633,
|
| 822 |
+
"learning_rate": 1.182033096926714e-06,
|
| 823 |
+
"loss": 0.0272,
|
| 824 |
+
"step": 920
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 19.78723404255319,
|
| 828 |
+
"grad_norm": 1.5552431344985962,
|
| 829 |
+
"learning_rate": 5.91016548463357e-07,
|
| 830 |
+
"loss": 0.0281,
|
| 831 |
+
"step": 930
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 20.0,
|
| 835 |
+
"grad_norm": 5.388515949249268,
|
| 836 |
+
"learning_rate": 0.0,
|
| 837 |
+
"loss": 0.07,
|
| 838 |
+
"step": 940
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 20.0,
|
| 842 |
+
"eval_accuracy": 1.0,
|
| 843 |
+
"eval_loss": 0.001178326434455812,
|
| 844 |
+
"eval_runtime": 8.4555,
|
| 845 |
+
"eval_samples_per_second": 75.217,
|
| 846 |
+
"eval_steps_per_second": 2.365,
|
| 847 |
+
"step": 940
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 20.0,
|
| 851 |
+
"step": 940,
|
| 852 |
+
"total_flos": 6.302667737382912e+17,
|
| 853 |
+
"train_loss": 0.13929352825309368,
|
| 854 |
+
"train_runtime": 703.6937,
|
| 855 |
+
"train_samples_per_second": 42.177,
|
| 856 |
+
"train_steps_per_second": 1.336
|
| 857 |
+
}
|
| 858 |
+
],
|
| 859 |
+
"logging_steps": 10,
|
| 860 |
+
"max_steps": 940,
|
| 861 |
+
"num_input_tokens_seen": 0,
|
| 862 |
+
"num_train_epochs": 20,
|
| 863 |
+
"save_steps": 500,
|
| 864 |
+
"total_flos": 6.302667737382912e+17,
|
| 865 |
+
"train_batch_size": 32,
|
| 866 |
+
"trial_name": null,
|
| 867 |
+
"trial_params": null
|
| 868 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e86333774fdc2cb3ed0a9195f9238c2f5423847f1665b9f8b4b6f56508f38d3c
|
| 3 |
size 5048
|