Training in progress, step 1000
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Jul25_04-38-12_d85b605ca0e9/events.out.tfevents.1721882318.d85b605ca0e9.546.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +918 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 17.0,
|
| 3 |
+
"total_flos": 1.333267779734618e+18,
|
| 4 |
+
"train_loss": 0.16752693287151701,
|
| 5 |
+
"train_runtime": 275.2566,
|
| 6 |
+
"train_samples_per_second": 62.502,
|
| 7 |
+
"train_steps_per_second": 3.953
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343248584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83430875cd067277b44370fd56095e9c2e9983de01bc2716a36fcc672a6cd55b
|
| 3 |
size 343248584
|
runs/Jul25_04-38-12_d85b605ca0e9/events.out.tfevents.1721882318.d85b605ca0e9.546.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3e4ba31a2fb7209781b40bf758823c5a53fbeeaa3ee0a76a44f076161dd0635
|
| 3 |
+
size 31150
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 17.0,
|
| 3 |
+
"total_flos": 1.333267779734618e+18,
|
| 4 |
+
"train_loss": 0.16752693287151701,
|
| 5 |
+
"train_runtime": 275.2566,
|
| 6 |
+
"train_samples_per_second": 62.502,
|
| 7 |
+
"train_steps_per_second": 3.953
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,918 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.13913680613040924,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned_v2024-7-24-frost/checkpoint-1000",
|
| 4 |
+
"epoch": 17.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1088,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15625,
|
| 13 |
+
"grad_norm": 0.388886958360672,
|
| 14 |
+
"learning_rate": 1.834862385321101e-05,
|
| 15 |
+
"loss": 0.6876,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3125,
|
| 20 |
+
"grad_norm": 0.43717288970947266,
|
| 21 |
+
"learning_rate": 3.669724770642202e-05,
|
| 22 |
+
"loss": 0.6556,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.46875,
|
| 27 |
+
"grad_norm": 0.41058769822120667,
|
| 28 |
+
"learning_rate": 5.504587155963303e-05,
|
| 29 |
+
"loss": 0.5865,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.625,
|
| 34 |
+
"grad_norm": 0.37728703022003174,
|
| 35 |
+
"learning_rate": 7.339449541284404e-05,
|
| 36 |
+
"loss": 0.5101,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.78125,
|
| 41 |
+
"grad_norm": 0.3225114643573761,
|
| 42 |
+
"learning_rate": 9.174311926605506e-05,
|
| 43 |
+
"loss": 0.4621,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9375,
|
| 48 |
+
"grad_norm": 0.27789732813835144,
|
| 49 |
+
"learning_rate": 0.00011009174311926606,
|
| 50 |
+
"loss": 0.4339,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.09375,
|
| 55 |
+
"grad_norm": 0.3035929501056671,
|
| 56 |
+
"learning_rate": 0.00012844036697247707,
|
| 57 |
+
"loss": 0.3999,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.25,
|
| 62 |
+
"grad_norm": 0.29363128542900085,
|
| 63 |
+
"learning_rate": 0.0001467889908256881,
|
| 64 |
+
"loss": 0.3808,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.40625,
|
| 69 |
+
"grad_norm": 0.2852456867694855,
|
| 70 |
+
"learning_rate": 0.0001651376146788991,
|
| 71 |
+
"loss": 0.356,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.5625,
|
| 76 |
+
"grad_norm": 0.2548869550228119,
|
| 77 |
+
"learning_rate": 0.00018348623853211012,
|
| 78 |
+
"loss": 0.3281,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.5625,
|
| 83 |
+
"eval_accuracy": 0.9008849557522124,
|
| 84 |
+
"eval_f1": 0.6956521739130436,
|
| 85 |
+
"eval_loss": 0.31767982244491577,
|
| 86 |
+
"eval_precision": 0.8767123287671232,
|
| 87 |
+
"eval_recall": 0.5765765765765766,
|
| 88 |
+
"eval_runtime": 0.9054,
|
| 89 |
+
"eval_samples_per_second": 124.801,
|
| 90 |
+
"eval_steps_per_second": 16.566,
|
| 91 |
+
"step": 100
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.71875,
|
| 95 |
+
"grad_norm": 0.34990283846855164,
|
| 96 |
+
"learning_rate": 0.00019979570990806946,
|
| 97 |
+
"loss": 0.3169,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.875,
|
| 102 |
+
"grad_norm": 0.4318304657936096,
|
| 103 |
+
"learning_rate": 0.00019775280898876404,
|
| 104 |
+
"loss": 0.307,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.03125,
|
| 109 |
+
"grad_norm": 0.4618605077266693,
|
| 110 |
+
"learning_rate": 0.00019570990806945865,
|
| 111 |
+
"loss": 0.2988,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.1875,
|
| 116 |
+
"grad_norm": 0.35013139247894287,
|
| 117 |
+
"learning_rate": 0.00019366700715015323,
|
| 118 |
+
"loss": 0.2962,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.34375,
|
| 123 |
+
"grad_norm": 0.2871937155723572,
|
| 124 |
+
"learning_rate": 0.00019162410623084782,
|
| 125 |
+
"loss": 0.2718,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.5,
|
| 130 |
+
"grad_norm": 0.5972371101379395,
|
| 131 |
+
"learning_rate": 0.0001895812053115424,
|
| 132 |
+
"loss": 0.2724,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.65625,
|
| 137 |
+
"grad_norm": 0.49075496196746826,
|
| 138 |
+
"learning_rate": 0.00018753830439223698,
|
| 139 |
+
"loss": 0.2681,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.8125,
|
| 144 |
+
"grad_norm": 0.23726806044578552,
|
| 145 |
+
"learning_rate": 0.00018549540347293156,
|
| 146 |
+
"loss": 0.2527,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.96875,
|
| 151 |
+
"grad_norm": 0.4829351305961609,
|
| 152 |
+
"learning_rate": 0.00018345250255362615,
|
| 153 |
+
"loss": 0.2484,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.125,
|
| 158 |
+
"grad_norm": 0.3746371567249298,
|
| 159 |
+
"learning_rate": 0.00018140960163432076,
|
| 160 |
+
"loss": 0.2532,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.125,
|
| 165 |
+
"eval_accuracy": 0.9176991150442478,
|
| 166 |
+
"eval_f1": 0.7832167832167832,
|
| 167 |
+
"eval_loss": 0.24235816299915314,
|
| 168 |
+
"eval_precision": 0.8115942028985508,
|
| 169 |
+
"eval_recall": 0.7567567567567568,
|
| 170 |
+
"eval_runtime": 0.8872,
|
| 171 |
+
"eval_samples_per_second": 127.371,
|
| 172 |
+
"eval_steps_per_second": 16.908,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.28125,
|
| 177 |
+
"grad_norm": 0.5272416472434998,
|
| 178 |
+
"learning_rate": 0.00017936670071501534,
|
| 179 |
+
"loss": 0.2438,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.4375,
|
| 184 |
+
"grad_norm": 0.2519098222255707,
|
| 185 |
+
"learning_rate": 0.00017732379979570992,
|
| 186 |
+
"loss": 0.2241,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.59375,
|
| 191 |
+
"grad_norm": 0.22354206442832947,
|
| 192 |
+
"learning_rate": 0.0001752808988764045,
|
| 193 |
+
"loss": 0.223,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.75,
|
| 198 |
+
"grad_norm": 0.32517552375793457,
|
| 199 |
+
"learning_rate": 0.0001732379979570991,
|
| 200 |
+
"loss": 0.2414,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.90625,
|
| 205 |
+
"grad_norm": 0.32100722193717957,
|
| 206 |
+
"learning_rate": 0.00017119509703779367,
|
| 207 |
+
"loss": 0.2188,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.0625,
|
| 212 |
+
"grad_norm": 0.5668182969093323,
|
| 213 |
+
"learning_rate": 0.00016915219611848828,
|
| 214 |
+
"loss": 0.1933,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.21875,
|
| 219 |
+
"grad_norm": 0.42494627833366394,
|
| 220 |
+
"learning_rate": 0.00016710929519918286,
|
| 221 |
+
"loss": 0.2244,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.375,
|
| 226 |
+
"grad_norm": 0.4030027687549591,
|
| 227 |
+
"learning_rate": 0.00016506639427987742,
|
| 228 |
+
"loss": 0.1939,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 4.53125,
|
| 233 |
+
"grad_norm": 0.3662806749343872,
|
| 234 |
+
"learning_rate": 0.000163023493360572,
|
| 235 |
+
"loss": 0.2117,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.6875,
|
| 240 |
+
"grad_norm": 0.23639629781246185,
|
| 241 |
+
"learning_rate": 0.0001609805924412666,
|
| 242 |
+
"loss": 0.1762,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.6875,
|
| 247 |
+
"eval_accuracy": 0.9407079646017699,
|
| 248 |
+
"eval_f1": 0.8452655889145496,
|
| 249 |
+
"eval_loss": 0.18491290509700775,
|
| 250 |
+
"eval_precision": 0.8672985781990521,
|
| 251 |
+
"eval_recall": 0.8243243243243243,
|
| 252 |
+
"eval_runtime": 1.2006,
|
| 253 |
+
"eval_samples_per_second": 94.116,
|
| 254 |
+
"eval_steps_per_second": 12.493,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.84375,
|
| 259 |
+
"grad_norm": 0.26584741473197937,
|
| 260 |
+
"learning_rate": 0.0001589376915219612,
|
| 261 |
+
"loss": 0.1844,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 5.0,
|
| 266 |
+
"grad_norm": 0.44927456974983215,
|
| 267 |
+
"learning_rate": 0.00015689479060265578,
|
| 268 |
+
"loss": 0.2022,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.15625,
|
| 273 |
+
"grad_norm": 0.24379728734493256,
|
| 274 |
+
"learning_rate": 0.00015485188968335036,
|
| 275 |
+
"loss": 0.185,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.3125,
|
| 280 |
+
"grad_norm": 0.34985587000846863,
|
| 281 |
+
"learning_rate": 0.00015280898876404494,
|
| 282 |
+
"loss": 0.1567,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.46875,
|
| 287 |
+
"grad_norm": 0.325273334980011,
|
| 288 |
+
"learning_rate": 0.00015076608784473953,
|
| 289 |
+
"loss": 0.1658,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.625,
|
| 294 |
+
"grad_norm": 0.26209816336631775,
|
| 295 |
+
"learning_rate": 0.00014872318692543413,
|
| 296 |
+
"loss": 0.1739,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 5.78125,
|
| 301 |
+
"grad_norm": 0.32775962352752686,
|
| 302 |
+
"learning_rate": 0.00014668028600612872,
|
| 303 |
+
"loss": 0.1755,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.9375,
|
| 308 |
+
"grad_norm": 0.2825620174407959,
|
| 309 |
+
"learning_rate": 0.0001446373850868233,
|
| 310 |
+
"loss": 0.1735,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 6.09375,
|
| 315 |
+
"grad_norm": 0.18162801861763,
|
| 316 |
+
"learning_rate": 0.00014259448416751788,
|
| 317 |
+
"loss": 0.1694,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 6.25,
|
| 322 |
+
"grad_norm": 0.3598109483718872,
|
| 323 |
+
"learning_rate": 0.00014055158324821247,
|
| 324 |
+
"loss": 0.1525,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 6.25,
|
| 329 |
+
"eval_accuracy": 0.9256637168141593,
|
| 330 |
+
"eval_f1": 0.8055555555555555,
|
| 331 |
+
"eval_loss": 0.18338988721370697,
|
| 332 |
+
"eval_precision": 0.8285714285714286,
|
| 333 |
+
"eval_recall": 0.7837837837837838,
|
| 334 |
+
"eval_runtime": 0.8607,
|
| 335 |
+
"eval_samples_per_second": 131.29,
|
| 336 |
+
"eval_steps_per_second": 17.428,
|
| 337 |
+
"step": 400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 6.40625,
|
| 341 |
+
"grad_norm": 0.592587947845459,
|
| 342 |
+
"learning_rate": 0.00013850868232890705,
|
| 343 |
+
"loss": 0.1518,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.5625,
|
| 348 |
+
"grad_norm": 0.1838444322347641,
|
| 349 |
+
"learning_rate": 0.00013646578140960163,
|
| 350 |
+
"loss": 0.161,
|
| 351 |
+
"step": 420
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.71875,
|
| 355 |
+
"grad_norm": 0.326659232378006,
|
| 356 |
+
"learning_rate": 0.00013442288049029624,
|
| 357 |
+
"loss": 0.1603,
|
| 358 |
+
"step": 430
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.875,
|
| 362 |
+
"grad_norm": 0.45708832144737244,
|
| 363 |
+
"learning_rate": 0.00013237997957099082,
|
| 364 |
+
"loss": 0.1609,
|
| 365 |
+
"step": 440
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.03125,
|
| 369 |
+
"grad_norm": 0.17103692889213562,
|
| 370 |
+
"learning_rate": 0.0001303370786516854,
|
| 371 |
+
"loss": 0.1263,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 7.1875,
|
| 376 |
+
"grad_norm": 0.40236711502075195,
|
| 377 |
+
"learning_rate": 0.00012829417773238,
|
| 378 |
+
"loss": 0.1386,
|
| 379 |
+
"step": 460
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 7.34375,
|
| 383 |
+
"grad_norm": 0.5935817360877991,
|
| 384 |
+
"learning_rate": 0.00012625127681307457,
|
| 385 |
+
"loss": 0.1419,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 7.5,
|
| 390 |
+
"grad_norm": 0.42183375358581543,
|
| 391 |
+
"learning_rate": 0.00012420837589376916,
|
| 392 |
+
"loss": 0.1296,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 7.65625,
|
| 397 |
+
"grad_norm": 0.28589242696762085,
|
| 398 |
+
"learning_rate": 0.00012216547497446374,
|
| 399 |
+
"loss": 0.1298,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 7.8125,
|
| 404 |
+
"grad_norm": 0.14183469116687775,
|
| 405 |
+
"learning_rate": 0.00012012257405515832,
|
| 406 |
+
"loss": 0.1447,
|
| 407 |
+
"step": 500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 7.8125,
|
| 411 |
+
"eval_accuracy": 0.9415929203539823,
|
| 412 |
+
"eval_f1": 0.8472222222222222,
|
| 413 |
+
"eval_loss": 0.16118969023227692,
|
| 414 |
+
"eval_precision": 0.8714285714285714,
|
| 415 |
+
"eval_recall": 0.8243243243243243,
|
| 416 |
+
"eval_runtime": 0.9028,
|
| 417 |
+
"eval_samples_per_second": 125.167,
|
| 418 |
+
"eval_steps_per_second": 16.615,
|
| 419 |
+
"step": 500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.96875,
|
| 423 |
+
"grad_norm": 0.4977594017982483,
|
| 424 |
+
"learning_rate": 0.0001180796731358529,
|
| 425 |
+
"loss": 0.1385,
|
| 426 |
+
"step": 510
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 8.125,
|
| 430 |
+
"grad_norm": 0.6004766225814819,
|
| 431 |
+
"learning_rate": 0.0001160367722165475,
|
| 432 |
+
"loss": 0.1532,
|
| 433 |
+
"step": 520
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 8.28125,
|
| 437 |
+
"grad_norm": 0.20785477757453918,
|
| 438 |
+
"learning_rate": 0.00011399387129724208,
|
| 439 |
+
"loss": 0.1329,
|
| 440 |
+
"step": 530
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.4375,
|
| 444 |
+
"grad_norm": 0.30308064818382263,
|
| 445 |
+
"learning_rate": 0.00011195097037793667,
|
| 446 |
+
"loss": 0.1351,
|
| 447 |
+
"step": 540
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 8.59375,
|
| 451 |
+
"grad_norm": 0.40658825635910034,
|
| 452 |
+
"learning_rate": 0.00010990806945863126,
|
| 453 |
+
"loss": 0.1289,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 8.75,
|
| 458 |
+
"grad_norm": 0.15297789871692657,
|
| 459 |
+
"learning_rate": 0.00010786516853932584,
|
| 460 |
+
"loss": 0.1353,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 8.90625,
|
| 465 |
+
"grad_norm": 0.2919471859931946,
|
| 466 |
+
"learning_rate": 0.00010582226762002043,
|
| 467 |
+
"loss": 0.1215,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 9.0625,
|
| 472 |
+
"grad_norm": 0.23703481256961823,
|
| 473 |
+
"learning_rate": 0.00010377936670071502,
|
| 474 |
+
"loss": 0.1107,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 9.21875,
|
| 479 |
+
"grad_norm": 0.15953165292739868,
|
| 480 |
+
"learning_rate": 0.0001017364657814096,
|
| 481 |
+
"loss": 0.1349,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.375,
|
| 486 |
+
"grad_norm": 0.2888895869255066,
|
| 487 |
+
"learning_rate": 9.969356486210419e-05,
|
| 488 |
+
"loss": 0.1114,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.375,
|
| 493 |
+
"eval_accuracy": 0.9433628318584071,
|
| 494 |
+
"eval_f1": 0.8545454545454546,
|
| 495 |
+
"eval_loss": 0.15215742588043213,
|
| 496 |
+
"eval_precision": 0.8623853211009175,
|
| 497 |
+
"eval_recall": 0.8468468468468469,
|
| 498 |
+
"eval_runtime": 0.8895,
|
| 499 |
+
"eval_samples_per_second": 127.032,
|
| 500 |
+
"eval_steps_per_second": 16.863,
|
| 501 |
+
"step": 600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.53125,
|
| 505 |
+
"grad_norm": 0.23866873979568481,
|
| 506 |
+
"learning_rate": 9.765066394279879e-05,
|
| 507 |
+
"loss": 0.1097,
|
| 508 |
+
"step": 610
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 9.6875,
|
| 512 |
+
"grad_norm": 0.2734706997871399,
|
| 513 |
+
"learning_rate": 9.560776302349337e-05,
|
| 514 |
+
"loss": 0.1096,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.84375,
|
| 519 |
+
"grad_norm": 0.5498181581497192,
|
| 520 |
+
"learning_rate": 9.356486210418795e-05,
|
| 521 |
+
"loss": 0.1039,
|
| 522 |
+
"step": 630
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 10.0,
|
| 526 |
+
"grad_norm": 0.17813219130039215,
|
| 527 |
+
"learning_rate": 9.152196118488255e-05,
|
| 528 |
+
"loss": 0.1002,
|
| 529 |
+
"step": 640
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 10.15625,
|
| 533 |
+
"grad_norm": 0.34687340259552,
|
| 534 |
+
"learning_rate": 8.947906026557712e-05,
|
| 535 |
+
"loss": 0.1164,
|
| 536 |
+
"step": 650
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 10.3125,
|
| 540 |
+
"grad_norm": 0.18163448572158813,
|
| 541 |
+
"learning_rate": 8.743615934627171e-05,
|
| 542 |
+
"loss": 0.1038,
|
| 543 |
+
"step": 660
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 10.46875,
|
| 547 |
+
"grad_norm": 0.2275228351354599,
|
| 548 |
+
"learning_rate": 8.53932584269663e-05,
|
| 549 |
+
"loss": 0.1165,
|
| 550 |
+
"step": 670
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 10.625,
|
| 554 |
+
"grad_norm": 0.3568095862865448,
|
| 555 |
+
"learning_rate": 8.335035750766088e-05,
|
| 556 |
+
"loss": 0.0986,
|
| 557 |
+
"step": 680
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 10.78125,
|
| 561 |
+
"grad_norm": 0.2227988988161087,
|
| 562 |
+
"learning_rate": 8.130745658835548e-05,
|
| 563 |
+
"loss": 0.1139,
|
| 564 |
+
"step": 690
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 10.9375,
|
| 568 |
+
"grad_norm": 0.3007115423679352,
|
| 569 |
+
"learning_rate": 7.926455566905006e-05,
|
| 570 |
+
"loss": 0.1004,
|
| 571 |
+
"step": 700
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 10.9375,
|
| 575 |
+
"eval_accuracy": 0.9451327433628318,
|
| 576 |
+
"eval_f1": 0.8571428571428571,
|
| 577 |
+
"eval_loss": 0.15245945751667023,
|
| 578 |
+
"eval_precision": 0.8773584905660378,
|
| 579 |
+
"eval_recall": 0.8378378378378378,
|
| 580 |
+
"eval_runtime": 1.1963,
|
| 581 |
+
"eval_samples_per_second": 94.461,
|
| 582 |
+
"eval_steps_per_second": 12.539,
|
| 583 |
+
"step": 700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 11.09375,
|
| 587 |
+
"grad_norm": 0.2825964689254761,
|
| 588 |
+
"learning_rate": 7.722165474974464e-05,
|
| 589 |
+
"loss": 0.1071,
|
| 590 |
+
"step": 710
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 11.25,
|
| 594 |
+
"grad_norm": 0.2866518795490265,
|
| 595 |
+
"learning_rate": 7.517875383043922e-05,
|
| 596 |
+
"loss": 0.0797,
|
| 597 |
+
"step": 720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 11.40625,
|
| 601 |
+
"grad_norm": 0.40209805965423584,
|
| 602 |
+
"learning_rate": 7.313585291113382e-05,
|
| 603 |
+
"loss": 0.0919,
|
| 604 |
+
"step": 730
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 11.5625,
|
| 608 |
+
"grad_norm": 0.22357816994190216,
|
| 609 |
+
"learning_rate": 7.10929519918284e-05,
|
| 610 |
+
"loss": 0.0862,
|
| 611 |
+
"step": 740
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 11.71875,
|
| 615 |
+
"grad_norm": 0.21823176741600037,
|
| 616 |
+
"learning_rate": 6.905005107252299e-05,
|
| 617 |
+
"loss": 0.0921,
|
| 618 |
+
"step": 750
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 11.875,
|
| 622 |
+
"grad_norm": 0.37442561984062195,
|
| 623 |
+
"learning_rate": 6.700715015321757e-05,
|
| 624 |
+
"loss": 0.0926,
|
| 625 |
+
"step": 760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 12.03125,
|
| 629 |
+
"grad_norm": 0.10888390988111496,
|
| 630 |
+
"learning_rate": 6.496424923391215e-05,
|
| 631 |
+
"loss": 0.0758,
|
| 632 |
+
"step": 770
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 12.1875,
|
| 636 |
+
"grad_norm": 0.30619969964027405,
|
| 637 |
+
"learning_rate": 6.292134831460675e-05,
|
| 638 |
+
"loss": 0.0824,
|
| 639 |
+
"step": 780
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.34375,
|
| 643 |
+
"grad_norm": 0.2507191598415375,
|
| 644 |
+
"learning_rate": 6.087844739530133e-05,
|
| 645 |
+
"loss": 0.0815,
|
| 646 |
+
"step": 790
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 12.5,
|
| 650 |
+
"grad_norm": 0.1795010268688202,
|
| 651 |
+
"learning_rate": 5.883554647599592e-05,
|
| 652 |
+
"loss": 0.0831,
|
| 653 |
+
"step": 800
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 12.5,
|
| 657 |
+
"eval_accuracy": 0.9513274336283186,
|
| 658 |
+
"eval_f1": 0.8741418764302059,
|
| 659 |
+
"eval_loss": 0.14417380094528198,
|
| 660 |
+
"eval_precision": 0.8883720930232558,
|
| 661 |
+
"eval_recall": 0.8603603603603603,
|
| 662 |
+
"eval_runtime": 0.9097,
|
| 663 |
+
"eval_samples_per_second": 124.22,
|
| 664 |
+
"eval_steps_per_second": 16.489,
|
| 665 |
+
"step": 800
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 12.65625,
|
| 669 |
+
"grad_norm": 0.3208577334880829,
|
| 670 |
+
"learning_rate": 5.67926455566905e-05,
|
| 671 |
+
"loss": 0.0759,
|
| 672 |
+
"step": 810
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 12.8125,
|
| 676 |
+
"grad_norm": 0.13223229348659515,
|
| 677 |
+
"learning_rate": 5.474974463738509e-05,
|
| 678 |
+
"loss": 0.087,
|
| 679 |
+
"step": 820
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 12.96875,
|
| 683 |
+
"grad_norm": 0.25973808765411377,
|
| 684 |
+
"learning_rate": 5.270684371807968e-05,
|
| 685 |
+
"loss": 0.0919,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 13.125,
|
| 690 |
+
"grad_norm": 0.2930574417114258,
|
| 691 |
+
"learning_rate": 5.0663942798774264e-05,
|
| 692 |
+
"loss": 0.0826,
|
| 693 |
+
"step": 840
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 13.28125,
|
| 697 |
+
"grad_norm": 0.28331613540649414,
|
| 698 |
+
"learning_rate": 4.862104187946885e-05,
|
| 699 |
+
"loss": 0.0703,
|
| 700 |
+
"step": 850
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 13.4375,
|
| 704 |
+
"grad_norm": 0.5403579473495483,
|
| 705 |
+
"learning_rate": 4.657814096016344e-05,
|
| 706 |
+
"loss": 0.0877,
|
| 707 |
+
"step": 860
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 13.59375,
|
| 711 |
+
"grad_norm": 0.24780268967151642,
|
| 712 |
+
"learning_rate": 4.453524004085802e-05,
|
| 713 |
+
"loss": 0.0783,
|
| 714 |
+
"step": 870
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 13.75,
|
| 718 |
+
"grad_norm": 0.43411558866500854,
|
| 719 |
+
"learning_rate": 4.24923391215526e-05,
|
| 720 |
+
"loss": 0.0809,
|
| 721 |
+
"step": 880
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 13.90625,
|
| 725 |
+
"grad_norm": 0.33748045563697815,
|
| 726 |
+
"learning_rate": 4.044943820224719e-05,
|
| 727 |
+
"loss": 0.0875,
|
| 728 |
+
"step": 890
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 14.0625,
|
| 732 |
+
"grad_norm": 0.18760047852993011,
|
| 733 |
+
"learning_rate": 3.840653728294178e-05,
|
| 734 |
+
"loss": 0.0654,
|
| 735 |
+
"step": 900
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 14.0625,
|
| 739 |
+
"eval_accuracy": 0.9495575221238938,
|
| 740 |
+
"eval_f1": 0.8689655172413793,
|
| 741 |
+
"eval_loss": 0.13779258728027344,
|
| 742 |
+
"eval_precision": 0.8873239436619719,
|
| 743 |
+
"eval_recall": 0.8513513513513513,
|
| 744 |
+
"eval_runtime": 0.8895,
|
| 745 |
+
"eval_samples_per_second": 127.038,
|
| 746 |
+
"eval_steps_per_second": 16.863,
|
| 747 |
+
"step": 900
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 14.21875,
|
| 751 |
+
"grad_norm": 0.15740624070167542,
|
| 752 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 753 |
+
"loss": 0.0729,
|
| 754 |
+
"step": 910
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 14.375,
|
| 758 |
+
"grad_norm": 0.21466964483261108,
|
| 759 |
+
"learning_rate": 3.4320735444330954e-05,
|
| 760 |
+
"loss": 0.0613,
|
| 761 |
+
"step": 920
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 14.53125,
|
| 765 |
+
"grad_norm": 0.32680827379226685,
|
| 766 |
+
"learning_rate": 3.2277834525025536e-05,
|
| 767 |
+
"loss": 0.0636,
|
| 768 |
+
"step": 930
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 14.6875,
|
| 772 |
+
"grad_norm": 0.14597666263580322,
|
| 773 |
+
"learning_rate": 3.0234933605720123e-05,
|
| 774 |
+
"loss": 0.0758,
|
| 775 |
+
"step": 940
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 14.84375,
|
| 779 |
+
"grad_norm": 0.1691855937242508,
|
| 780 |
+
"learning_rate": 2.819203268641471e-05,
|
| 781 |
+
"loss": 0.0788,
|
| 782 |
+
"step": 950
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 15.0,
|
| 786 |
+
"grad_norm": 0.6366788148880005,
|
| 787 |
+
"learning_rate": 2.61491317671093e-05,
|
| 788 |
+
"loss": 0.0775,
|
| 789 |
+
"step": 960
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 15.15625,
|
| 793 |
+
"grad_norm": 0.4018935561180115,
|
| 794 |
+
"learning_rate": 2.410623084780388e-05,
|
| 795 |
+
"loss": 0.0616,
|
| 796 |
+
"step": 970
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 15.3125,
|
| 800 |
+
"grad_norm": 0.2861553728580475,
|
| 801 |
+
"learning_rate": 2.2063329928498467e-05,
|
| 802 |
+
"loss": 0.0648,
|
| 803 |
+
"step": 980
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 15.46875,
|
| 807 |
+
"grad_norm": 0.14629952609539032,
|
| 808 |
+
"learning_rate": 2.0020429009193057e-05,
|
| 809 |
+
"loss": 0.0687,
|
| 810 |
+
"step": 990
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 15.625,
|
| 814 |
+
"grad_norm": 0.18827380239963531,
|
| 815 |
+
"learning_rate": 1.797752808988764e-05,
|
| 816 |
+
"loss": 0.0583,
|
| 817 |
+
"step": 1000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 15.625,
|
| 821 |
+
"eval_accuracy": 0.9530973451327434,
|
| 822 |
+
"eval_f1": 0.8798185941043084,
|
| 823 |
+
"eval_loss": 0.13913680613040924,
|
| 824 |
+
"eval_precision": 0.8858447488584474,
|
| 825 |
+
"eval_recall": 0.8738738738738738,
|
| 826 |
+
"eval_runtime": 1.128,
|
| 827 |
+
"eval_samples_per_second": 100.175,
|
| 828 |
+
"eval_steps_per_second": 13.298,
|
| 829 |
+
"step": 1000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 15.78125,
|
| 833 |
+
"grad_norm": 0.4585842788219452,
|
| 834 |
+
"learning_rate": 1.593462717058223e-05,
|
| 835 |
+
"loss": 0.061,
|
| 836 |
+
"step": 1010
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 15.9375,
|
| 840 |
+
"grad_norm": 0.20938844978809357,
|
| 841 |
+
"learning_rate": 1.3891726251276812e-05,
|
| 842 |
+
"loss": 0.0682,
|
| 843 |
+
"step": 1020
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 16.09375,
|
| 847 |
+
"grad_norm": 0.1632617712020874,
|
| 848 |
+
"learning_rate": 1.18488253319714e-05,
|
| 849 |
+
"loss": 0.065,
|
| 850 |
+
"step": 1030
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 16.25,
|
| 854 |
+
"grad_norm": 0.25956493616104126,
|
| 855 |
+
"learning_rate": 9.805924412665986e-06,
|
| 856 |
+
"loss": 0.0761,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 16.40625,
|
| 861 |
+
"grad_norm": 0.17571082711219788,
|
| 862 |
+
"learning_rate": 7.763023493360572e-06,
|
| 863 |
+
"loss": 0.0676,
|
| 864 |
+
"step": 1050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 16.5625,
|
| 868 |
+
"grad_norm": 0.1871979534626007,
|
| 869 |
+
"learning_rate": 5.720122574055159e-06,
|
| 870 |
+
"loss": 0.0663,
|
| 871 |
+
"step": 1060
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 16.71875,
|
| 875 |
+
"grad_norm": 0.18988612294197083,
|
| 876 |
+
"learning_rate": 3.677221654749745e-06,
|
| 877 |
+
"loss": 0.0608,
|
| 878 |
+
"step": 1070
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 16.875,
|
| 882 |
+
"grad_norm": 0.18478451669216156,
|
| 883 |
+
"learning_rate": 1.6343207354443311e-06,
|
| 884 |
+
"loss": 0.0511,
|
| 885 |
+
"step": 1080
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 17.0,
|
| 889 |
+
"step": 1088,
|
| 890 |
+
"total_flos": 1.333267779734618e+18,
|
| 891 |
+
"train_loss": 0.16752693287151701,
|
| 892 |
+
"train_runtime": 275.2566,
|
| 893 |
+
"train_samples_per_second": 62.502,
|
| 894 |
+
"train_steps_per_second": 3.953
|
| 895 |
+
}
|
| 896 |
+
],
|
| 897 |
+
"logging_steps": 10,
|
| 898 |
+
"max_steps": 1088,
|
| 899 |
+
"num_input_tokens_seen": 0,
|
| 900 |
+
"num_train_epochs": 17,
|
| 901 |
+
"save_steps": 500,
|
| 902 |
+
"stateful_callbacks": {
|
| 903 |
+
"TrainerControl": {
|
| 904 |
+
"args": {
|
| 905 |
+
"should_epoch_stop": false,
|
| 906 |
+
"should_evaluate": false,
|
| 907 |
+
"should_log": false,
|
| 908 |
+
"should_save": true,
|
| 909 |
+
"should_training_stop": true
|
| 910 |
+
},
|
| 911 |
+
"attributes": {}
|
| 912 |
+
}
|
| 913 |
+
},
|
| 914 |
+
"total_flos": 1.333267779734618e+18,
|
| 915 |
+
"train_batch_size": 16,
|
| 916 |
+
"trial_name": null,
|
| 917 |
+
"trial_params": null
|
| 918 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0929cc3c8fd963acaabc5e79cef7ef6ed9cc06e7d16d1c8702a5eda3b45072d
|
| 3 |
size 5176
|