🍻 cheers
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9521785334750266,
|
| 4 |
+
"eval_loss": 0.21390262246131897,
|
| 5 |
+
"eval_runtime": 40.27,
|
| 6 |
+
"eval_samples_per_second": 23.367,
|
| 7 |
+
"eval_steps_per_second": 2.93,
|
| 8 |
+
"total_flos": 1.651775717862015e+18,
|
| 9 |
+
"train_loss": 0.4871297548483084,
|
| 10 |
+
"train_runtime": 1589.6821,
|
| 11 |
+
"train_samples_per_second": 13.406,
|
| 12 |
+
"train_steps_per_second": 0.838
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9521785334750266,
|
| 4 |
+
"eval_loss": 0.21390262246131897,
|
| 5 |
+
"eval_runtime": 40.27,
|
| 6 |
+
"eval_samples_per_second": 23.367,
|
| 7 |
+
"eval_steps_per_second": 2.93
|
| 8 |
+
}
|
runs/Jul15_18-54-00_8efc67140cef/events.out.tfevents.1657914945.8efc67140cef.6046.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c42ec31335f5e339d21c1c425c36bd0712680f0a46dddc3d74e7509d54568f
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.651775717862015e+18,
|
| 4 |
+
"train_loss": 0.4871297548483084,
|
| 5 |
+
"train_runtime": 1589.6821,
|
| 6 |
+
"train_samples_per_second": 13.406,
|
| 7 |
+
"train_steps_per_second": 0.838
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,940 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.21390262246131897,
|
| 3 |
+
"best_model_checkpoint": "finetuned-indian-food/checkpoint-1300",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 1332,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0001984984984984985,
|
| 13 |
+
"loss": 2.8538,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 0.00019699699699699701,
|
| 19 |
+
"loss": 2.5964,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 0.0001954954954954955,
|
| 25 |
+
"loss": 2.2524,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 0.00019399399399399402,
|
| 31 |
+
"loss": 1.9596,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 0.0001924924924924925,
|
| 37 |
+
"loss": 1.726,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 0.000190990990990991,
|
| 43 |
+
"loss": 1.6152,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 0.0001894894894894895,
|
| 49 |
+
"loss": 1.3396,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 0.000187987987987988,
|
| 55 |
+
"loss": 1.2854,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.27,
|
| 60 |
+
"learning_rate": 0.0001864864864864865,
|
| 61 |
+
"loss": 1.107,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.3,
|
| 66 |
+
"learning_rate": 0.000184984984984985,
|
| 67 |
+
"loss": 1.0846,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.3,
|
| 72 |
+
"eval_accuracy": 0.8554729011689692,
|
| 73 |
+
"eval_loss": 0.9561436772346497,
|
| 74 |
+
"eval_runtime": 39.5068,
|
| 75 |
+
"eval_samples_per_second": 23.819,
|
| 76 |
+
"eval_steps_per_second": 2.987,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.33,
|
| 81 |
+
"learning_rate": 0.0001834834834834835,
|
| 82 |
+
"loss": 0.9812,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.36,
|
| 87 |
+
"learning_rate": 0.000181981981981982,
|
| 88 |
+
"loss": 0.8571,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.39,
|
| 93 |
+
"learning_rate": 0.0001804804804804805,
|
| 94 |
+
"loss": 0.916,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.42,
|
| 99 |
+
"learning_rate": 0.00017897897897897898,
|
| 100 |
+
"loss": 0.9905,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.45,
|
| 105 |
+
"learning_rate": 0.0001774774774774775,
|
| 106 |
+
"loss": 0.7381,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.48,
|
| 111 |
+
"learning_rate": 0.000175975975975976,
|
| 112 |
+
"loss": 0.801,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.51,
|
| 117 |
+
"learning_rate": 0.0001744744744744745,
|
| 118 |
+
"loss": 0.6606,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.54,
|
| 123 |
+
"learning_rate": 0.000172972972972973,
|
| 124 |
+
"loss": 0.7538,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.57,
|
| 129 |
+
"learning_rate": 0.00017147147147147148,
|
| 130 |
+
"loss": 0.6495,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.6,
|
| 135 |
+
"learning_rate": 0.00016996996996997,
|
| 136 |
+
"loss": 0.7894,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.6,
|
| 141 |
+
"eval_accuracy": 0.8926673751328374,
|
| 142 |
+
"eval_loss": 0.587147057056427,
|
| 143 |
+
"eval_runtime": 38.4761,
|
| 144 |
+
"eval_samples_per_second": 24.457,
|
| 145 |
+
"eval_steps_per_second": 3.067,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.63,
|
| 150 |
+
"learning_rate": 0.00016846846846846846,
|
| 151 |
+
"loss": 0.7121,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.66,
|
| 156 |
+
"learning_rate": 0.00016696696696696697,
|
| 157 |
+
"loss": 0.6888,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"learning_rate": 0.00016546546546546546,
|
| 163 |
+
"loss": 0.5768,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.72,
|
| 168 |
+
"learning_rate": 0.00016396396396396395,
|
| 169 |
+
"loss": 0.6568,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.75,
|
| 174 |
+
"learning_rate": 0.00016261261261261262,
|
| 175 |
+
"loss": 0.601,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.78,
|
| 180 |
+
"learning_rate": 0.0001611111111111111,
|
| 181 |
+
"loss": 0.5431,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.81,
|
| 186 |
+
"learning_rate": 0.00015960960960960963,
|
| 187 |
+
"loss": 0.6634,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.84,
|
| 192 |
+
"learning_rate": 0.00015810810810810812,
|
| 193 |
+
"loss": 0.8153,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.87,
|
| 198 |
+
"learning_rate": 0.00015660660660660663,
|
| 199 |
+
"loss": 0.9727,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.9,
|
| 204 |
+
"learning_rate": 0.00015510510510510512,
|
| 205 |
+
"loss": 0.6233,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9,
|
| 210 |
+
"eval_accuracy": 0.9107332624867163,
|
| 211 |
+
"eval_loss": 0.4447122812271118,
|
| 212 |
+
"eval_runtime": 38.3227,
|
| 213 |
+
"eval_samples_per_second": 24.555,
|
| 214 |
+
"eval_steps_per_second": 3.079,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.93,
|
| 219 |
+
"learning_rate": 0.0001536036036036036,
|
| 220 |
+
"loss": 0.578,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.96,
|
| 225 |
+
"learning_rate": 0.00015210210210210212,
|
| 226 |
+
"loss": 0.6366,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.99,
|
| 231 |
+
"learning_rate": 0.0001506006006006006,
|
| 232 |
+
"loss": 0.8622,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.02,
|
| 237 |
+
"learning_rate": 0.00014909909909909913,
|
| 238 |
+
"loss": 0.5957,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.05,
|
| 243 |
+
"learning_rate": 0.00014759759759759762,
|
| 244 |
+
"loss": 0.4458,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.08,
|
| 249 |
+
"learning_rate": 0.0001460960960960961,
|
| 250 |
+
"loss": 0.383,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.11,
|
| 255 |
+
"learning_rate": 0.00014459459459459462,
|
| 256 |
+
"loss": 0.4259,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.14,
|
| 261 |
+
"learning_rate": 0.00014309309309309308,
|
| 262 |
+
"loss": 0.4246,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.17,
|
| 267 |
+
"learning_rate": 0.0001415915915915916,
|
| 268 |
+
"loss": 0.3343,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.2,
|
| 273 |
+
"learning_rate": 0.0001400900900900901,
|
| 274 |
+
"loss": 0.3619,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.2,
|
| 279 |
+
"eval_accuracy": 0.8937300743889479,
|
| 280 |
+
"eval_loss": 0.4354824125766754,
|
| 281 |
+
"eval_runtime": 37.6727,
|
| 282 |
+
"eval_samples_per_second": 24.978,
|
| 283 |
+
"eval_steps_per_second": 3.132,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.23,
|
| 288 |
+
"learning_rate": 0.00013858858858858858,
|
| 289 |
+
"loss": 0.5238,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.26,
|
| 294 |
+
"learning_rate": 0.0001370870870870871,
|
| 295 |
+
"loss": 0.5456,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.29,
|
| 300 |
+
"learning_rate": 0.00013558558558558558,
|
| 301 |
+
"loss": 0.5347,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.32,
|
| 306 |
+
"learning_rate": 0.0001340840840840841,
|
| 307 |
+
"loss": 0.3739,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.35,
|
| 312 |
+
"learning_rate": 0.00013258258258258258,
|
| 313 |
+
"loss": 0.392,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.38,
|
| 318 |
+
"learning_rate": 0.00013108108108108107,
|
| 319 |
+
"loss": 0.5306,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.41,
|
| 324 |
+
"learning_rate": 0.0001295795795795796,
|
| 325 |
+
"loss": 0.4171,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.44,
|
| 330 |
+
"learning_rate": 0.00012807807807807808,
|
| 331 |
+
"loss": 0.3715,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.47,
|
| 336 |
+
"learning_rate": 0.00012657657657657657,
|
| 337 |
+
"loss": 0.5192,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.5,
|
| 342 |
+
"learning_rate": 0.00012507507507507508,
|
| 343 |
+
"loss": 0.34,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.5,
|
| 348 |
+
"eval_accuracy": 0.9117959617428267,
|
| 349 |
+
"eval_loss": 0.3712367117404938,
|
| 350 |
+
"eval_runtime": 37.8371,
|
| 351 |
+
"eval_samples_per_second": 24.87,
|
| 352 |
+
"eval_steps_per_second": 3.119,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.53,
|
| 357 |
+
"learning_rate": 0.00012357357357357357,
|
| 358 |
+
"loss": 0.5209,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.56,
|
| 363 |
+
"learning_rate": 0.00012207207207207209,
|
| 364 |
+
"loss": 0.4896,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.59,
|
| 369 |
+
"learning_rate": 0.00012057057057057057,
|
| 370 |
+
"loss": 0.5666,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.62,
|
| 375 |
+
"learning_rate": 0.00011906906906906908,
|
| 376 |
+
"loss": 0.3288,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.65,
|
| 381 |
+
"learning_rate": 0.00011756756756756758,
|
| 382 |
+
"loss": 0.4315,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.68,
|
| 387 |
+
"learning_rate": 0.00011606606606606607,
|
| 388 |
+
"loss": 0.4185,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.71,
|
| 393 |
+
"learning_rate": 0.00011456456456456457,
|
| 394 |
+
"loss": 0.2794,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.74,
|
| 399 |
+
"learning_rate": 0.00011306306306306307,
|
| 400 |
+
"loss": 0.3125,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.77,
|
| 405 |
+
"learning_rate": 0.00011156156156156157,
|
| 406 |
+
"loss": 0.3229,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.8,
|
| 411 |
+
"learning_rate": 0.00011006006006006006,
|
| 412 |
+
"loss": 0.3413,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.8,
|
| 417 |
+
"eval_accuracy": 0.8916046758767269,
|
| 418 |
+
"eval_loss": 0.40877240896224976,
|
| 419 |
+
"eval_runtime": 39.2551,
|
| 420 |
+
"eval_samples_per_second": 23.971,
|
| 421 |
+
"eval_steps_per_second": 3.006,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.83,
|
| 426 |
+
"learning_rate": 0.00010855855855855856,
|
| 427 |
+
"loss": 0.3967,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.86,
|
| 432 |
+
"learning_rate": 0.00010705705705705707,
|
| 433 |
+
"loss": 0.32,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.89,
|
| 438 |
+
"learning_rate": 0.00010555555555555557,
|
| 439 |
+
"loss": 0.3256,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.92,
|
| 444 |
+
"learning_rate": 0.0001042042042042042,
|
| 445 |
+
"loss": 0.4024,
|
| 446 |
+
"step": 640
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.95,
|
| 450 |
+
"learning_rate": 0.0001027027027027027,
|
| 451 |
+
"loss": 0.4209,
|
| 452 |
+
"step": 650
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.98,
|
| 456 |
+
"learning_rate": 0.0001012012012012012,
|
| 457 |
+
"loss": 0.3888,
|
| 458 |
+
"step": 660
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.01,
|
| 462 |
+
"learning_rate": 9.96996996996997e-05,
|
| 463 |
+
"loss": 0.3793,
|
| 464 |
+
"step": 670
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.04,
|
| 468 |
+
"learning_rate": 9.81981981981982e-05,
|
| 469 |
+
"loss": 0.3094,
|
| 470 |
+
"step": 680
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.07,
|
| 474 |
+
"learning_rate": 9.66966966966967e-05,
|
| 475 |
+
"loss": 0.3613,
|
| 476 |
+
"step": 690
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.1,
|
| 480 |
+
"learning_rate": 9.51951951951952e-05,
|
| 481 |
+
"loss": 0.3619,
|
| 482 |
+
"step": 700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.1,
|
| 486 |
+
"eval_accuracy": 0.9043570669500531,
|
| 487 |
+
"eval_loss": 0.37407416105270386,
|
| 488 |
+
"eval_runtime": 39.0938,
|
| 489 |
+
"eval_samples_per_second": 24.07,
|
| 490 |
+
"eval_steps_per_second": 3.018,
|
| 491 |
+
"step": 700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.13,
|
| 495 |
+
"learning_rate": 9.36936936936937e-05,
|
| 496 |
+
"loss": 0.3051,
|
| 497 |
+
"step": 710
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.16,
|
| 501 |
+
"learning_rate": 9.219219219219219e-05,
|
| 502 |
+
"loss": 0.4062,
|
| 503 |
+
"step": 720
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.19,
|
| 507 |
+
"learning_rate": 9.069069069069069e-05,
|
| 508 |
+
"loss": 0.3811,
|
| 509 |
+
"step": 730
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.22,
|
| 513 |
+
"learning_rate": 8.918918918918919e-05,
|
| 514 |
+
"loss": 0.3118,
|
| 515 |
+
"step": 740
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.25,
|
| 519 |
+
"learning_rate": 8.76876876876877e-05,
|
| 520 |
+
"loss": 0.3014,
|
| 521 |
+
"step": 750
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.28,
|
| 525 |
+
"learning_rate": 8.61861861861862e-05,
|
| 526 |
+
"loss": 0.2404,
|
| 527 |
+
"step": 760
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.31,
|
| 531 |
+
"learning_rate": 8.468468468468469e-05,
|
| 532 |
+
"loss": 0.3802,
|
| 533 |
+
"step": 770
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.34,
|
| 537 |
+
"learning_rate": 8.318318318318319e-05,
|
| 538 |
+
"loss": 0.3222,
|
| 539 |
+
"step": 780
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.37,
|
| 543 |
+
"learning_rate": 8.168168168168169e-05,
|
| 544 |
+
"loss": 0.2459,
|
| 545 |
+
"step": 790
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.4,
|
| 549 |
+
"learning_rate": 8.018018018018019e-05,
|
| 550 |
+
"loss": 0.2135,
|
| 551 |
+
"step": 800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.4,
|
| 555 |
+
"eval_accuracy": 0.9160467587672688,
|
| 556 |
+
"eval_loss": 0.328594833612442,
|
| 557 |
+
"eval_runtime": 38.4594,
|
| 558 |
+
"eval_samples_per_second": 24.467,
|
| 559 |
+
"eval_steps_per_second": 3.068,
|
| 560 |
+
"step": 800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.43,
|
| 564 |
+
"learning_rate": 7.867867867867868e-05,
|
| 565 |
+
"loss": 0.2152,
|
| 566 |
+
"step": 810
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.46,
|
| 570 |
+
"learning_rate": 7.717717717717718e-05,
|
| 571 |
+
"loss": 0.2621,
|
| 572 |
+
"step": 820
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.49,
|
| 576 |
+
"learning_rate": 7.567567567567568e-05,
|
| 577 |
+
"loss": 0.2118,
|
| 578 |
+
"step": 830
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.52,
|
| 582 |
+
"learning_rate": 7.417417417417419e-05,
|
| 583 |
+
"loss": 0.2826,
|
| 584 |
+
"step": 840
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.55,
|
| 588 |
+
"learning_rate": 7.267267267267268e-05,
|
| 589 |
+
"loss": 0.4047,
|
| 590 |
+
"step": 850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.58,
|
| 594 |
+
"learning_rate": 7.117117117117116e-05,
|
| 595 |
+
"loss": 0.4956,
|
| 596 |
+
"step": 860
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.61,
|
| 600 |
+
"learning_rate": 6.966966966966967e-05,
|
| 601 |
+
"loss": 0.2431,
|
| 602 |
+
"step": 870
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.64,
|
| 606 |
+
"learning_rate": 6.816816816816817e-05,
|
| 607 |
+
"loss": 0.2189,
|
| 608 |
+
"step": 880
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.67,
|
| 612 |
+
"learning_rate": 6.666666666666667e-05,
|
| 613 |
+
"loss": 0.2455,
|
| 614 |
+
"step": 890
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.7,
|
| 618 |
+
"learning_rate": 6.516516516516516e-05,
|
| 619 |
+
"loss": 0.2166,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.7,
|
| 624 |
+
"eval_accuracy": 0.9415515409139213,
|
| 625 |
+
"eval_loss": 0.2758049964904785,
|
| 626 |
+
"eval_runtime": 38.181,
|
| 627 |
+
"eval_samples_per_second": 24.646,
|
| 628 |
+
"eval_steps_per_second": 3.091,
|
| 629 |
+
"step": 900
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.73,
|
| 633 |
+
"learning_rate": 6.366366366366366e-05,
|
| 634 |
+
"loss": 0.2648,
|
| 635 |
+
"step": 910
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.76,
|
| 639 |
+
"learning_rate": 6.216216216216216e-05,
|
| 640 |
+
"loss": 0.2233,
|
| 641 |
+
"step": 920
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.79,
|
| 645 |
+
"learning_rate": 6.0660660660660665e-05,
|
| 646 |
+
"loss": 0.2876,
|
| 647 |
+
"step": 930
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.82,
|
| 651 |
+
"learning_rate": 5.915915915915916e-05,
|
| 652 |
+
"loss": 0.3385,
|
| 653 |
+
"step": 940
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.85,
|
| 657 |
+
"learning_rate": 5.765765765765766e-05,
|
| 658 |
+
"loss": 0.2823,
|
| 659 |
+
"step": 950
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.88,
|
| 663 |
+
"learning_rate": 5.615615615615616e-05,
|
| 664 |
+
"loss": 0.135,
|
| 665 |
+
"step": 960
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.91,
|
| 669 |
+
"learning_rate": 5.465465465465466e-05,
|
| 670 |
+
"loss": 0.289,
|
| 671 |
+
"step": 970
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.94,
|
| 675 |
+
"learning_rate": 5.3153153153153155e-05,
|
| 676 |
+
"loss": 0.2228,
|
| 677 |
+
"step": 980
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.97,
|
| 681 |
+
"learning_rate": 5.165165165165166e-05,
|
| 682 |
+
"loss": 0.3221,
|
| 683 |
+
"step": 990
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.0,
|
| 687 |
+
"learning_rate": 5.015015015015015e-05,
|
| 688 |
+
"loss": 0.1557,
|
| 689 |
+
"step": 1000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.0,
|
| 693 |
+
"eval_accuracy": 0.9330499468650372,
|
| 694 |
+
"eval_loss": 0.2679324150085449,
|
| 695 |
+
"eval_runtime": 37.7775,
|
| 696 |
+
"eval_samples_per_second": 24.909,
|
| 697 |
+
"eval_steps_per_second": 3.124,
|
| 698 |
+
"step": 1000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.03,
|
| 702 |
+
"learning_rate": 4.8648648648648654e-05,
|
| 703 |
+
"loss": 0.1808,
|
| 704 |
+
"step": 1010
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.06,
|
| 708 |
+
"learning_rate": 4.714714714714715e-05,
|
| 709 |
+
"loss": 0.2742,
|
| 710 |
+
"step": 1020
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.09,
|
| 714 |
+
"learning_rate": 4.5645645645645645e-05,
|
| 715 |
+
"loss": 0.147,
|
| 716 |
+
"step": 1030
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.12,
|
| 720 |
+
"learning_rate": 4.414414414414415e-05,
|
| 721 |
+
"loss": 0.248,
|
| 722 |
+
"step": 1040
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.15,
|
| 726 |
+
"learning_rate": 4.264264264264264e-05,
|
| 727 |
+
"loss": 0.1214,
|
| 728 |
+
"step": 1050
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.18,
|
| 732 |
+
"learning_rate": 4.1141141141141144e-05,
|
| 733 |
+
"loss": 0.352,
|
| 734 |
+
"step": 1060
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.21,
|
| 738 |
+
"learning_rate": 3.963963963963964e-05,
|
| 739 |
+
"loss": 0.2441,
|
| 740 |
+
"step": 1070
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.24,
|
| 744 |
+
"learning_rate": 3.813813813813814e-05,
|
| 745 |
+
"loss": 0.2205,
|
| 746 |
+
"step": 1080
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.27,
|
| 750 |
+
"learning_rate": 3.663663663663664e-05,
|
| 751 |
+
"loss": 0.1925,
|
| 752 |
+
"step": 1090
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.3,
|
| 756 |
+
"learning_rate": 3.513513513513514e-05,
|
| 757 |
+
"loss": 0.1115,
|
| 758 |
+
"step": 1100
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.3,
|
| 762 |
+
"eval_accuracy": 0.9362380446333688,
|
| 763 |
+
"eval_loss": 0.2528650462627411,
|
| 764 |
+
"eval_runtime": 38.8623,
|
| 765 |
+
"eval_samples_per_second": 24.214,
|
| 766 |
+
"eval_steps_per_second": 3.036,
|
| 767 |
+
"step": 1100
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.33,
|
| 771 |
+
"learning_rate": 3.3633633633633635e-05,
|
| 772 |
+
"loss": 0.2245,
|
| 773 |
+
"step": 1110
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.36,
|
| 777 |
+
"learning_rate": 3.213213213213213e-05,
|
| 778 |
+
"loss": 0.2538,
|
| 779 |
+
"step": 1120
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.39,
|
| 783 |
+
"learning_rate": 3.063063063063063e-05,
|
| 784 |
+
"loss": 0.1725,
|
| 785 |
+
"step": 1130
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.42,
|
| 789 |
+
"learning_rate": 2.912912912912913e-05,
|
| 790 |
+
"loss": 0.3009,
|
| 791 |
+
"step": 1140
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 3.45,
|
| 795 |
+
"learning_rate": 2.762762762762763e-05,
|
| 796 |
+
"loss": 0.3042,
|
| 797 |
+
"step": 1150
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.48,
|
| 801 |
+
"learning_rate": 2.6126126126126128e-05,
|
| 802 |
+
"loss": 0.1748,
|
| 803 |
+
"step": 1160
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.51,
|
| 807 |
+
"learning_rate": 2.4624624624624627e-05,
|
| 808 |
+
"loss": 0.1229,
|
| 809 |
+
"step": 1170
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.54,
|
| 813 |
+
"learning_rate": 2.3123123123123125e-05,
|
| 814 |
+
"loss": 0.2376,
|
| 815 |
+
"step": 1180
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.57,
|
| 819 |
+
"learning_rate": 2.1621621621621624e-05,
|
| 820 |
+
"loss": 0.2025,
|
| 821 |
+
"step": 1190
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.6,
|
| 825 |
+
"learning_rate": 2.012012012012012e-05,
|
| 826 |
+
"loss": 0.1571,
|
| 827 |
+
"step": 1200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.6,
|
| 831 |
+
"eval_accuracy": 0.946865037194474,
|
| 832 |
+
"eval_loss": 0.23596596717834473,
|
| 833 |
+
"eval_runtime": 38.9005,
|
| 834 |
+
"eval_samples_per_second": 24.19,
|
| 835 |
+
"eval_steps_per_second": 3.033,
|
| 836 |
+
"step": 1200
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.63,
|
| 840 |
+
"learning_rate": 1.8618618618618618e-05,
|
| 841 |
+
"loss": 0.0491,
|
| 842 |
+
"step": 1210
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.66,
|
| 846 |
+
"learning_rate": 1.7117117117117117e-05,
|
| 847 |
+
"loss": 0.1921,
|
| 848 |
+
"step": 1220
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.69,
|
| 852 |
+
"learning_rate": 1.5615615615615616e-05,
|
| 853 |
+
"loss": 0.1733,
|
| 854 |
+
"step": 1230
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.72,
|
| 858 |
+
"learning_rate": 1.4114114114114116e-05,
|
| 859 |
+
"loss": 0.1822,
|
| 860 |
+
"step": 1240
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.75,
|
| 864 |
+
"learning_rate": 1.2612612612612611e-05,
|
| 865 |
+
"loss": 0.2661,
|
| 866 |
+
"step": 1250
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.78,
|
| 870 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 871 |
+
"loss": 0.1566,
|
| 872 |
+
"step": 1260
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.81,
|
| 876 |
+
"learning_rate": 9.60960960960961e-06,
|
| 877 |
+
"loss": 0.1764,
|
| 878 |
+
"step": 1270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.84,
|
| 882 |
+
"learning_rate": 8.108108108108109e-06,
|
| 883 |
+
"loss": 0.1824,
|
| 884 |
+
"step": 1280
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.87,
|
| 888 |
+
"learning_rate": 6.606606606606607e-06,
|
| 889 |
+
"loss": 0.122,
|
| 890 |
+
"step": 1290
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.9,
|
| 894 |
+
"learning_rate": 5.105105105105106e-06,
|
| 895 |
+
"loss": 0.1079,
|
| 896 |
+
"step": 1300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.9,
|
| 900 |
+
"eval_accuracy": 0.9521785334750266,
|
| 901 |
+
"eval_loss": 0.21390262246131897,
|
| 902 |
+
"eval_runtime": 38.2092,
|
| 903 |
+
"eval_samples_per_second": 24.628,
|
| 904 |
+
"eval_steps_per_second": 3.088,
|
| 905 |
+
"step": 1300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.93,
|
| 909 |
+
"learning_rate": 3.603603603603604e-06,
|
| 910 |
+
"loss": 0.1973,
|
| 911 |
+
"step": 1310
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.96,
|
| 915 |
+
"learning_rate": 2.102102102102102e-06,
|
| 916 |
+
"loss": 0.0976,
|
| 917 |
+
"step": 1320
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.99,
|
| 921 |
+
"learning_rate": 6.006006006006006e-07,
|
| 922 |
+
"loss": 0.1724,
|
| 923 |
+
"step": 1330
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.0,
|
| 927 |
+
"step": 1332,
|
| 928 |
+
"total_flos": 1.651775717862015e+18,
|
| 929 |
+
"train_loss": 0.4871297548483084,
|
| 930 |
+
"train_runtime": 1589.6821,
|
| 931 |
+
"train_samples_per_second": 13.406,
|
| 932 |
+
"train_steps_per_second": 0.838
|
| 933 |
+
}
|
| 934 |
+
],
|
| 935 |
+
"max_steps": 1332,
|
| 936 |
+
"num_train_epochs": 4,
|
| 937 |
+
"total_flos": 1.651775717862015e+18,
|
| 938 |
+
"trial_name": null,
|
| 939 |
+
"trial_params": null
|
| 940 |
+
}
|