Steve Chiou
commited on
Commit
·
19fcf34
1
Parent(s):
5c3c6b0
End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +979 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.01,
|
| 3 |
+
"eval_accuracy": 0.6745283018867925,
|
| 4 |
+
"eval_loss": 0.8912516236305237,
|
| 5 |
+
"eval_runtime": 68.7355,
|
| 6 |
+
"eval_samples_per_second": 6.169,
|
| 7 |
+
"eval_steps_per_second": 1.033
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.01,
|
| 3 |
+
"eval_accuracy": 0.6745283018867925,
|
| 4 |
+
"eval_loss": 0.8912516236305237,
|
| 5 |
+
"eval_runtime": 68.7355,
|
| 6 |
+
"eval_samples_per_second": 6.169,
|
| 7 |
+
"eval_steps_per_second": 1.033
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,979 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6745283018867925,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-engine-subset-20230313/checkpoint-988",
|
| 4 |
+
"epoch": 29.00720720720721,
|
| 5 |
+
"global_step": 1110,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 4.504504504504505e-06,
|
| 13 |
+
"loss": 2.7278,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 9.00900900900901e-06,
|
| 19 |
+
"loss": 2.747,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 25 |
+
"loss": 2.6212,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03,
|
| 30 |
+
"eval_accuracy": 0.37735849056603776,
|
| 31 |
+
"eval_loss": 2.362868070602417,
|
| 32 |
+
"eval_runtime": 69.3989,
|
| 33 |
+
"eval_samples_per_second": 6.11,
|
| 34 |
+
"eval_steps_per_second": 1.023,
|
| 35 |
+
"step": 38
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.0,
|
| 39 |
+
"learning_rate": 1.801801801801802e-05,
|
| 40 |
+
"loss": 2.6599,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.01,
|
| 45 |
+
"learning_rate": 2.2522522522522523e-05,
|
| 46 |
+
"loss": 2.5895,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.02,
|
| 51 |
+
"learning_rate": 2.702702702702703e-05,
|
| 52 |
+
"loss": 2.5383,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.03,
|
| 57 |
+
"learning_rate": 3.153153153153153e-05,
|
| 58 |
+
"loss": 2.455,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.03,
|
| 63 |
+
"eval_accuracy": 0.2169811320754717,
|
| 64 |
+
"eval_loss": 2.3674099445343018,
|
| 65 |
+
"eval_runtime": 70.0897,
|
| 66 |
+
"eval_samples_per_second": 6.049,
|
| 67 |
+
"eval_steps_per_second": 1.013,
|
| 68 |
+
"step": 76
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.0,
|
| 72 |
+
"learning_rate": 3.603603603603604e-05,
|
| 73 |
+
"loss": 2.421,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.01,
|
| 78 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 79 |
+
"loss": 2.4139,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.02,
|
| 84 |
+
"learning_rate": 4.5045045045045046e-05,
|
| 85 |
+
"loss": 2.4999,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.03,
|
| 90 |
+
"learning_rate": 4.954954954954955e-05,
|
| 91 |
+
"loss": 2.4311,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.03,
|
| 96 |
+
"eval_accuracy": 0.3231132075471698,
|
| 97 |
+
"eval_loss": 2.2190816402435303,
|
| 98 |
+
"eval_runtime": 71.2703,
|
| 99 |
+
"eval_samples_per_second": 5.949,
|
| 100 |
+
"eval_steps_per_second": 0.996,
|
| 101 |
+
"step": 114
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.01,
|
| 105 |
+
"learning_rate": 4.954954954954955e-05,
|
| 106 |
+
"loss": 2.5089,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.01,
|
| 111 |
+
"learning_rate": 4.9049049049049054e-05,
|
| 112 |
+
"loss": 2.4986,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.02,
|
| 117 |
+
"learning_rate": 4.854854854854855e-05,
|
| 118 |
+
"loss": 2.3317,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.03,
|
| 123 |
+
"learning_rate": 4.804804804804805e-05,
|
| 124 |
+
"loss": 2.2768,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.03,
|
| 129 |
+
"eval_accuracy": 0.3608490566037736,
|
| 130 |
+
"eval_loss": 2.1226866245269775,
|
| 131 |
+
"eval_runtime": 70.1636,
|
| 132 |
+
"eval_samples_per_second": 6.043,
|
| 133 |
+
"eval_steps_per_second": 1.012,
|
| 134 |
+
"step": 152
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.01,
|
| 138 |
+
"learning_rate": 4.754754754754755e-05,
|
| 139 |
+
"loss": 2.0041,
|
| 140 |
+
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.02,
|
| 144 |
+
"learning_rate": 4.704704704704705e-05,
|
| 145 |
+
"loss": 2.2092,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.03,
|
| 150 |
+
"learning_rate": 4.654654654654655e-05,
|
| 151 |
+
"loss": 1.9442,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.03,
|
| 156 |
+
"learning_rate": 4.604604604604605e-05,
|
| 157 |
+
"loss": 1.7528,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.03,
|
| 162 |
+
"eval_accuracy": 0.4363207547169811,
|
| 163 |
+
"eval_loss": 1.729621171951294,
|
| 164 |
+
"eval_runtime": 69.2109,
|
| 165 |
+
"eval_samples_per_second": 6.126,
|
| 166 |
+
"eval_steps_per_second": 1.026,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.01,
|
| 171 |
+
"learning_rate": 4.5545545545545545e-05,
|
| 172 |
+
"loss": 1.6692,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 5.02,
|
| 177 |
+
"learning_rate": 4.5045045045045046e-05,
|
| 178 |
+
"loss": 1.8567,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 5.03,
|
| 183 |
+
"learning_rate": 4.4544544544544546e-05,
|
| 184 |
+
"loss": 1.5381,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 5.03,
|
| 189 |
+
"eval_accuracy": 0.4339622641509434,
|
| 190 |
+
"eval_loss": 1.5015883445739746,
|
| 191 |
+
"eval_runtime": 71.2754,
|
| 192 |
+
"eval_samples_per_second": 5.949,
|
| 193 |
+
"eval_steps_per_second": 0.996,
|
| 194 |
+
"step": 228
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.0,
|
| 198 |
+
"learning_rate": 4.404404404404405e-05,
|
| 199 |
+
"loss": 1.4846,
|
| 200 |
+
"step": 230
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.01,
|
| 204 |
+
"learning_rate": 4.354354354354355e-05,
|
| 205 |
+
"loss": 1.3143,
|
| 206 |
+
"step": 240
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.02,
|
| 210 |
+
"learning_rate": 4.304304304304305e-05,
|
| 211 |
+
"loss": 1.2959,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.03,
|
| 216 |
+
"learning_rate": 4.254254254254255e-05,
|
| 217 |
+
"loss": 1.407,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.03,
|
| 222 |
+
"eval_accuracy": 0.5448113207547169,
|
| 223 |
+
"eval_loss": 1.2878233194351196,
|
| 224 |
+
"eval_runtime": 70.9118,
|
| 225 |
+
"eval_samples_per_second": 5.979,
|
| 226 |
+
"eval_steps_per_second": 1.001,
|
| 227 |
+
"step": 266
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 7.0,
|
| 231 |
+
"learning_rate": 4.204204204204204e-05,
|
| 232 |
+
"loss": 1.3608,
|
| 233 |
+
"step": 270
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.01,
|
| 237 |
+
"learning_rate": 4.1541541541541544e-05,
|
| 238 |
+
"loss": 1.5729,
|
| 239 |
+
"step": 280
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 7.02,
|
| 243 |
+
"learning_rate": 4.1041041041041045e-05,
|
| 244 |
+
"loss": 1.3095,
|
| 245 |
+
"step": 290
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 7.03,
|
| 249 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 250 |
+
"loss": 1.1053,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 7.03,
|
| 255 |
+
"eval_accuracy": 0.4009433962264151,
|
| 256 |
+
"eval_loss": 1.5210211277008057,
|
| 257 |
+
"eval_runtime": 68.6229,
|
| 258 |
+
"eval_samples_per_second": 6.179,
|
| 259 |
+
"eval_steps_per_second": 1.035,
|
| 260 |
+
"step": 304
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 8.01,
|
| 264 |
+
"learning_rate": 4.0040040040040046e-05,
|
| 265 |
+
"loss": 1.2462,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.01,
|
| 270 |
+
"learning_rate": 3.953953953953955e-05,
|
| 271 |
+
"loss": 1.114,
|
| 272 |
+
"step": 320
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 8.02,
|
| 276 |
+
"learning_rate": 3.903903903903904e-05,
|
| 277 |
+
"loss": 1.2971,
|
| 278 |
+
"step": 330
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 8.03,
|
| 282 |
+
"learning_rate": 3.8538538538538534e-05,
|
| 283 |
+
"loss": 1.0893,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 8.03,
|
| 288 |
+
"eval_accuracy": 0.46226415094339623,
|
| 289 |
+
"eval_loss": 1.3901519775390625,
|
| 290 |
+
"eval_runtime": 70.4934,
|
| 291 |
+
"eval_samples_per_second": 6.015,
|
| 292 |
+
"eval_steps_per_second": 1.007,
|
| 293 |
+
"step": 342
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 9.01,
|
| 297 |
+
"learning_rate": 3.8038038038038035e-05,
|
| 298 |
+
"loss": 1.3258,
|
| 299 |
+
"step": 350
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 9.02,
|
| 303 |
+
"learning_rate": 3.7537537537537536e-05,
|
| 304 |
+
"loss": 1.1349,
|
| 305 |
+
"step": 360
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 9.03,
|
| 309 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 310 |
+
"loss": 1.0029,
|
| 311 |
+
"step": 370
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 9.03,
|
| 315 |
+
"learning_rate": 3.653653653653654e-05,
|
| 316 |
+
"loss": 0.8136,
|
| 317 |
+
"step": 380
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.03,
|
| 321 |
+
"eval_accuracy": 0.4033018867924528,
|
| 322 |
+
"eval_loss": 1.6456053256988525,
|
| 323 |
+
"eval_runtime": 71.0727,
|
| 324 |
+
"eval_samples_per_second": 5.966,
|
| 325 |
+
"eval_steps_per_second": 0.999,
|
| 326 |
+
"step": 380
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 10.01,
|
| 330 |
+
"learning_rate": 3.603603603603604e-05,
|
| 331 |
+
"loss": 1.1048,
|
| 332 |
+
"step": 390
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 10.02,
|
| 336 |
+
"learning_rate": 3.553553553553554e-05,
|
| 337 |
+
"loss": 1.2661,
|
| 338 |
+
"step": 400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 10.03,
|
| 342 |
+
"learning_rate": 3.503503503503503e-05,
|
| 343 |
+
"loss": 0.9565,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 10.03,
|
| 348 |
+
"eval_accuracy": 0.5613207547169812,
|
| 349 |
+
"eval_loss": 1.18259859085083,
|
| 350 |
+
"eval_runtime": 70.181,
|
| 351 |
+
"eval_samples_per_second": 6.042,
|
| 352 |
+
"eval_steps_per_second": 1.012,
|
| 353 |
+
"step": 418
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 11.0,
|
| 357 |
+
"learning_rate": 3.453453453453453e-05,
|
| 358 |
+
"loss": 1.0921,
|
| 359 |
+
"step": 420
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 11.01,
|
| 363 |
+
"learning_rate": 3.4034034034034034e-05,
|
| 364 |
+
"loss": 0.7383,
|
| 365 |
+
"step": 430
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 11.02,
|
| 369 |
+
"learning_rate": 3.3533533533533535e-05,
|
| 370 |
+
"loss": 0.926,
|
| 371 |
+
"step": 440
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 11.03,
|
| 375 |
+
"learning_rate": 3.3033033033033035e-05,
|
| 376 |
+
"loss": 1.0147,
|
| 377 |
+
"step": 450
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 11.03,
|
| 381 |
+
"eval_accuracy": 0.5117924528301887,
|
| 382 |
+
"eval_loss": 1.2098637819290161,
|
| 383 |
+
"eval_runtime": 70.8824,
|
| 384 |
+
"eval_samples_per_second": 5.982,
|
| 385 |
+
"eval_steps_per_second": 1.002,
|
| 386 |
+
"step": 456
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 12.0,
|
| 390 |
+
"learning_rate": 3.2532532532532536e-05,
|
| 391 |
+
"loss": 0.9178,
|
| 392 |
+
"step": 460
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 12.01,
|
| 396 |
+
"learning_rate": 3.203203203203203e-05,
|
| 397 |
+
"loss": 0.8994,
|
| 398 |
+
"step": 470
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 12.02,
|
| 402 |
+
"learning_rate": 3.153153153153153e-05,
|
| 403 |
+
"loss": 0.8648,
|
| 404 |
+
"step": 480
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 12.03,
|
| 408 |
+
"learning_rate": 3.103103103103103e-05,
|
| 409 |
+
"loss": 0.9125,
|
| 410 |
+
"step": 490
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 12.03,
|
| 414 |
+
"eval_accuracy": 0.5495283018867925,
|
| 415 |
+
"eval_loss": 1.1849919557571411,
|
| 416 |
+
"eval_runtime": 70.4782,
|
| 417 |
+
"eval_samples_per_second": 6.016,
|
| 418 |
+
"eval_steps_per_second": 1.007,
|
| 419 |
+
"step": 494
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 13.01,
|
| 423 |
+
"learning_rate": 3.053053053053053e-05,
|
| 424 |
+
"loss": 0.8926,
|
| 425 |
+
"step": 500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 13.01,
|
| 429 |
+
"learning_rate": 3.0030030030030033e-05,
|
| 430 |
+
"loss": 0.8618,
|
| 431 |
+
"step": 510
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 13.02,
|
| 435 |
+
"learning_rate": 2.952952952952953e-05,
|
| 436 |
+
"loss": 0.8057,
|
| 437 |
+
"step": 520
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 13.03,
|
| 441 |
+
"learning_rate": 2.902902902902903e-05,
|
| 442 |
+
"loss": 0.7091,
|
| 443 |
+
"step": 530
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 13.03,
|
| 447 |
+
"eval_accuracy": 0.535377358490566,
|
| 448 |
+
"eval_loss": 1.2324182987213135,
|
| 449 |
+
"eval_runtime": 70.9353,
|
| 450 |
+
"eval_samples_per_second": 5.977,
|
| 451 |
+
"eval_steps_per_second": 1.001,
|
| 452 |
+
"step": 532
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 14.01,
|
| 456 |
+
"learning_rate": 2.852852852852853e-05,
|
| 457 |
+
"loss": 0.74,
|
| 458 |
+
"step": 540
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 14.02,
|
| 462 |
+
"learning_rate": 2.8028028028028032e-05,
|
| 463 |
+
"loss": 0.7484,
|
| 464 |
+
"step": 550
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 14.03,
|
| 468 |
+
"learning_rate": 2.752752752752753e-05,
|
| 469 |
+
"loss": 0.7962,
|
| 470 |
+
"step": 560
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 14.03,
|
| 474 |
+
"learning_rate": 2.702702702702703e-05,
|
| 475 |
+
"loss": 0.7361,
|
| 476 |
+
"step": 570
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 14.03,
|
| 480 |
+
"eval_accuracy": 0.6226415094339622,
|
| 481 |
+
"eval_loss": 1.022481083869934,
|
| 482 |
+
"eval_runtime": 70.6845,
|
| 483 |
+
"eval_samples_per_second": 5.998,
|
| 484 |
+
"eval_steps_per_second": 1.004,
|
| 485 |
+
"step": 570
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 15.01,
|
| 489 |
+
"learning_rate": 2.652652652652653e-05,
|
| 490 |
+
"loss": 0.8396,
|
| 491 |
+
"step": 580
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 15.02,
|
| 495 |
+
"learning_rate": 2.6026026026026028e-05,
|
| 496 |
+
"loss": 0.7193,
|
| 497 |
+
"step": 590
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 15.03,
|
| 501 |
+
"learning_rate": 2.552552552552553e-05,
|
| 502 |
+
"loss": 0.6979,
|
| 503 |
+
"step": 600
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 15.03,
|
| 507 |
+
"eval_accuracy": 0.5589622641509434,
|
| 508 |
+
"eval_loss": 1.0737839937210083,
|
| 509 |
+
"eval_runtime": 69.8991,
|
| 510 |
+
"eval_samples_per_second": 6.066,
|
| 511 |
+
"eval_steps_per_second": 1.016,
|
| 512 |
+
"step": 608
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 16.0,
|
| 516 |
+
"learning_rate": 2.502502502502503e-05,
|
| 517 |
+
"loss": 0.6869,
|
| 518 |
+
"step": 610
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 16.01,
|
| 522 |
+
"learning_rate": 2.4524524524524527e-05,
|
| 523 |
+
"loss": 0.6704,
|
| 524 |
+
"step": 620
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 16.02,
|
| 528 |
+
"learning_rate": 2.4024024024024024e-05,
|
| 529 |
+
"loss": 0.8011,
|
| 530 |
+
"step": 630
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 16.03,
|
| 534 |
+
"learning_rate": 2.3523523523523525e-05,
|
| 535 |
+
"loss": 0.5265,
|
| 536 |
+
"step": 640
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 16.03,
|
| 540 |
+
"eval_accuracy": 0.5872641509433962,
|
| 541 |
+
"eval_loss": 1.1062343120574951,
|
| 542 |
+
"eval_runtime": 70.6095,
|
| 543 |
+
"eval_samples_per_second": 6.005,
|
| 544 |
+
"eval_steps_per_second": 1.006,
|
| 545 |
+
"step": 646
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 17.0,
|
| 549 |
+
"learning_rate": 2.3023023023023026e-05,
|
| 550 |
+
"loss": 0.6415,
|
| 551 |
+
"step": 650
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 17.01,
|
| 555 |
+
"learning_rate": 2.2522522522522523e-05,
|
| 556 |
+
"loss": 0.7402,
|
| 557 |
+
"step": 660
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 17.02,
|
| 561 |
+
"learning_rate": 2.2022022022022024e-05,
|
| 562 |
+
"loss": 0.6275,
|
| 563 |
+
"step": 670
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 17.03,
|
| 567 |
+
"learning_rate": 2.1521521521521524e-05,
|
| 568 |
+
"loss": 0.5651,
|
| 569 |
+
"step": 680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 17.03,
|
| 573 |
+
"eval_accuracy": 0.5801886792452831,
|
| 574 |
+
"eval_loss": 1.1402446031570435,
|
| 575 |
+
"eval_runtime": 70.0342,
|
| 576 |
+
"eval_samples_per_second": 6.054,
|
| 577 |
+
"eval_steps_per_second": 1.014,
|
| 578 |
+
"step": 684
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 18.01,
|
| 582 |
+
"learning_rate": 2.102102102102102e-05,
|
| 583 |
+
"loss": 0.5542,
|
| 584 |
+
"step": 690
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 18.01,
|
| 588 |
+
"learning_rate": 2.0520520520520522e-05,
|
| 589 |
+
"loss": 0.6903,
|
| 590 |
+
"step": 700
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 18.02,
|
| 594 |
+
"learning_rate": 2.0020020020020023e-05,
|
| 595 |
+
"loss": 0.7,
|
| 596 |
+
"step": 710
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 18.03,
|
| 600 |
+
"learning_rate": 1.951951951951952e-05,
|
| 601 |
+
"loss": 0.7182,
|
| 602 |
+
"step": 720
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 18.03,
|
| 606 |
+
"eval_accuracy": 0.5801886792452831,
|
| 607 |
+
"eval_loss": 1.097399115562439,
|
| 608 |
+
"eval_runtime": 70.689,
|
| 609 |
+
"eval_samples_per_second": 5.998,
|
| 610 |
+
"eval_steps_per_second": 1.004,
|
| 611 |
+
"step": 722
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 19.01,
|
| 615 |
+
"learning_rate": 1.9019019019019018e-05,
|
| 616 |
+
"loss": 0.5921,
|
| 617 |
+
"step": 730
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 19.02,
|
| 621 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 622 |
+
"loss": 0.5428,
|
| 623 |
+
"step": 740
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 19.03,
|
| 627 |
+
"learning_rate": 1.801801801801802e-05,
|
| 628 |
+
"loss": 0.7289,
|
| 629 |
+
"step": 750
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 19.03,
|
| 633 |
+
"learning_rate": 1.7517517517517516e-05,
|
| 634 |
+
"loss": 0.6582,
|
| 635 |
+
"step": 760
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 19.03,
|
| 639 |
+
"eval_accuracy": 0.6179245283018868,
|
| 640 |
+
"eval_loss": 1.0529001951217651,
|
| 641 |
+
"eval_runtime": 70.8949,
|
| 642 |
+
"eval_samples_per_second": 5.981,
|
| 643 |
+
"eval_steps_per_second": 1.001,
|
| 644 |
+
"step": 760
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 20.01,
|
| 648 |
+
"learning_rate": 1.7017017017017017e-05,
|
| 649 |
+
"loss": 0.5001,
|
| 650 |
+
"step": 770
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 20.02,
|
| 654 |
+
"learning_rate": 1.6516516516516518e-05,
|
| 655 |
+
"loss": 0.5387,
|
| 656 |
+
"step": 780
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 20.03,
|
| 660 |
+
"learning_rate": 1.6016016016016015e-05,
|
| 661 |
+
"loss": 0.5709,
|
| 662 |
+
"step": 790
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 20.03,
|
| 666 |
+
"eval_accuracy": 0.6344339622641509,
|
| 667 |
+
"eval_loss": 0.965450644493103,
|
| 668 |
+
"eval_runtime": 69.2205,
|
| 669 |
+
"eval_samples_per_second": 6.125,
|
| 670 |
+
"eval_steps_per_second": 1.026,
|
| 671 |
+
"step": 798
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 21.0,
|
| 675 |
+
"learning_rate": 1.5515515515515516e-05,
|
| 676 |
+
"loss": 0.7102,
|
| 677 |
+
"step": 800
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 21.01,
|
| 681 |
+
"learning_rate": 1.5015015015015016e-05,
|
| 682 |
+
"loss": 0.4746,
|
| 683 |
+
"step": 810
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 21.02,
|
| 687 |
+
"learning_rate": 1.4514514514514515e-05,
|
| 688 |
+
"loss": 0.611,
|
| 689 |
+
"step": 820
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 21.03,
|
| 693 |
+
"learning_rate": 1.4014014014014016e-05,
|
| 694 |
+
"loss": 0.4808,
|
| 695 |
+
"step": 830
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 21.03,
|
| 699 |
+
"eval_accuracy": 0.6226415094339622,
|
| 700 |
+
"eval_loss": 1.0440747737884521,
|
| 701 |
+
"eval_runtime": 70.6133,
|
| 702 |
+
"eval_samples_per_second": 6.005,
|
| 703 |
+
"eval_steps_per_second": 1.005,
|
| 704 |
+
"step": 836
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 22.0,
|
| 708 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 709 |
+
"loss": 0.5081,
|
| 710 |
+
"step": 840
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 22.01,
|
| 714 |
+
"learning_rate": 1.3013013013013014e-05,
|
| 715 |
+
"loss": 0.6717,
|
| 716 |
+
"step": 850
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 22.02,
|
| 720 |
+
"learning_rate": 1.2512512512512515e-05,
|
| 721 |
+
"loss": 0.343,
|
| 722 |
+
"step": 860
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 22.03,
|
| 726 |
+
"learning_rate": 1.2012012012012012e-05,
|
| 727 |
+
"loss": 0.5816,
|
| 728 |
+
"step": 870
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 22.03,
|
| 732 |
+
"eval_accuracy": 0.6438679245283019,
|
| 733 |
+
"eval_loss": 0.9445228576660156,
|
| 734 |
+
"eval_runtime": 70.5922,
|
| 735 |
+
"eval_samples_per_second": 6.006,
|
| 736 |
+
"eval_steps_per_second": 1.006,
|
| 737 |
+
"step": 874
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 23.01,
|
| 741 |
+
"learning_rate": 1.1511511511511513e-05,
|
| 742 |
+
"loss": 0.4179,
|
| 743 |
+
"step": 880
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 23.01,
|
| 747 |
+
"learning_rate": 1.1011011011011012e-05,
|
| 748 |
+
"loss": 0.4346,
|
| 749 |
+
"step": 890
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 23.02,
|
| 753 |
+
"learning_rate": 1.051051051051051e-05,
|
| 754 |
+
"loss": 0.4038,
|
| 755 |
+
"step": 900
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 23.03,
|
| 759 |
+
"learning_rate": 1.0010010010010011e-05,
|
| 760 |
+
"loss": 0.5057,
|
| 761 |
+
"step": 910
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 23.03,
|
| 765 |
+
"eval_accuracy": 0.6320754716981132,
|
| 766 |
+
"eval_loss": 1.0248113870620728,
|
| 767 |
+
"eval_runtime": 71.1172,
|
| 768 |
+
"eval_samples_per_second": 5.962,
|
| 769 |
+
"eval_steps_per_second": 0.998,
|
| 770 |
+
"step": 912
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 24.01,
|
| 774 |
+
"learning_rate": 9.509509509509509e-06,
|
| 775 |
+
"loss": 0.393,
|
| 776 |
+
"step": 920
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 24.02,
|
| 780 |
+
"learning_rate": 9.00900900900901e-06,
|
| 781 |
+
"loss": 0.4297,
|
| 782 |
+
"step": 930
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 24.03,
|
| 786 |
+
"learning_rate": 8.508508508508508e-06,
|
| 787 |
+
"loss": 0.5053,
|
| 788 |
+
"step": 940
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 24.03,
|
| 792 |
+
"learning_rate": 8.008008008008007e-06,
|
| 793 |
+
"loss": 0.6253,
|
| 794 |
+
"step": 950
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 24.03,
|
| 798 |
+
"eval_accuracy": 0.660377358490566,
|
| 799 |
+
"eval_loss": 0.9517852067947388,
|
| 800 |
+
"eval_runtime": 70.664,
|
| 801 |
+
"eval_samples_per_second": 6.0,
|
| 802 |
+
"eval_steps_per_second": 1.005,
|
| 803 |
+
"step": 950
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 25.01,
|
| 807 |
+
"learning_rate": 7.507507507507508e-06,
|
| 808 |
+
"loss": 0.4143,
|
| 809 |
+
"step": 960
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 25.02,
|
| 813 |
+
"learning_rate": 7.007007007007008e-06,
|
| 814 |
+
"loss": 0.6003,
|
| 815 |
+
"step": 970
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 25.03,
|
| 819 |
+
"learning_rate": 6.506506506506507e-06,
|
| 820 |
+
"loss": 0.6841,
|
| 821 |
+
"step": 980
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 25.03,
|
| 825 |
+
"eval_accuracy": 0.6745283018867925,
|
| 826 |
+
"eval_loss": 0.8912516236305237,
|
| 827 |
+
"eval_runtime": 70.8493,
|
| 828 |
+
"eval_samples_per_second": 5.985,
|
| 829 |
+
"eval_steps_per_second": 1.002,
|
| 830 |
+
"step": 988
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 26.0,
|
| 834 |
+
"learning_rate": 6.006006006006006e-06,
|
| 835 |
+
"loss": 0.2104,
|
| 836 |
+
"step": 990
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 26.01,
|
| 840 |
+
"learning_rate": 5.505505505505506e-06,
|
| 841 |
+
"loss": 0.6054,
|
| 842 |
+
"step": 1000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 26.02,
|
| 846 |
+
"learning_rate": 5.005005005005006e-06,
|
| 847 |
+
"loss": 0.6045,
|
| 848 |
+
"step": 1010
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 26.03,
|
| 852 |
+
"learning_rate": 4.504504504504505e-06,
|
| 853 |
+
"loss": 0.5933,
|
| 854 |
+
"step": 1020
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 26.03,
|
| 858 |
+
"eval_accuracy": 0.6438679245283019,
|
| 859 |
+
"eval_loss": 0.9012843370437622,
|
| 860 |
+
"eval_runtime": 71.2482,
|
| 861 |
+
"eval_samples_per_second": 5.951,
|
| 862 |
+
"eval_steps_per_second": 0.997,
|
| 863 |
+
"step": 1026
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 27.0,
|
| 867 |
+
"learning_rate": 4.004004004004004e-06,
|
| 868 |
+
"loss": 0.4052,
|
| 869 |
+
"step": 1030
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 27.01,
|
| 873 |
+
"learning_rate": 3.503503503503504e-06,
|
| 874 |
+
"loss": 0.4422,
|
| 875 |
+
"step": 1040
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 27.02,
|
| 879 |
+
"learning_rate": 3.003003003003003e-06,
|
| 880 |
+
"loss": 0.4861,
|
| 881 |
+
"step": 1050
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 27.03,
|
| 885 |
+
"learning_rate": 2.502502502502503e-06,
|
| 886 |
+
"loss": 0.389,
|
| 887 |
+
"step": 1060
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 27.03,
|
| 891 |
+
"eval_accuracy": 0.6627358490566038,
|
| 892 |
+
"eval_loss": 0.9089723229408264,
|
| 893 |
+
"eval_runtime": 71.3879,
|
| 894 |
+
"eval_samples_per_second": 5.939,
|
| 895 |
+
"eval_steps_per_second": 0.995,
|
| 896 |
+
"step": 1064
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 28.01,
|
| 900 |
+
"learning_rate": 2.002002002002002e-06,
|
| 901 |
+
"loss": 0.4572,
|
| 902 |
+
"step": 1070
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 28.01,
|
| 906 |
+
"learning_rate": 1.5015015015015015e-06,
|
| 907 |
+
"loss": 0.213,
|
| 908 |
+
"step": 1080
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 28.02,
|
| 912 |
+
"learning_rate": 1.001001001001001e-06,
|
| 913 |
+
"loss": 0.6041,
|
| 914 |
+
"step": 1090
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 28.03,
|
| 918 |
+
"learning_rate": 5.005005005005005e-07,
|
| 919 |
+
"loss": 0.3705,
|
| 920 |
+
"step": 1100
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 28.03,
|
| 924 |
+
"eval_accuracy": 0.6721698113207547,
|
| 925 |
+
"eval_loss": 0.8935866355895996,
|
| 926 |
+
"eval_runtime": 70.2956,
|
| 927 |
+
"eval_samples_per_second": 6.032,
|
| 928 |
+
"eval_steps_per_second": 1.01,
|
| 929 |
+
"step": 1102
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 29.01,
|
| 933 |
+
"learning_rate": 0.0,
|
| 934 |
+
"loss": 0.6043,
|
| 935 |
+
"step": 1110
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 29.01,
|
| 939 |
+
"eval_accuracy": 0.6721698113207547,
|
| 940 |
+
"eval_loss": 0.8942137956619263,
|
| 941 |
+
"eval_runtime": 69.8197,
|
| 942 |
+
"eval_samples_per_second": 6.073,
|
| 943 |
+
"eval_steps_per_second": 1.017,
|
| 944 |
+
"step": 1110
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 29.01,
|
| 948 |
+
"step": 1110,
|
| 949 |
+
"total_flos": 8.191332105366897e+18,
|
| 950 |
+
"train_loss": 1.059841639716346,
|
| 951 |
+
"train_runtime": 5977.6934,
|
| 952 |
+
"train_samples_per_second": 1.114,
|
| 953 |
+
"train_steps_per_second": 0.186
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 29.01,
|
| 957 |
+
"eval_accuracy": 0.6745283018867925,
|
| 958 |
+
"eval_loss": 0.8912516236305237,
|
| 959 |
+
"eval_runtime": 68.8583,
|
| 960 |
+
"eval_samples_per_second": 6.158,
|
| 961 |
+
"eval_steps_per_second": 1.031,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 29.01,
|
| 966 |
+
"eval_accuracy": 0.6745283018867925,
|
| 967 |
+
"eval_loss": 0.8912516236305237,
|
| 968 |
+
"eval_runtime": 68.7355,
|
| 969 |
+
"eval_samples_per_second": 6.169,
|
| 970 |
+
"eval_steps_per_second": 1.033,
|
| 971 |
+
"step": 1110
|
| 972 |
+
}
|
| 973 |
+
],
|
| 974 |
+
"max_steps": 1110,
|
| 975 |
+
"num_train_epochs": 9223372036854775807,
|
| 976 |
+
"total_flos": 8.191332105366897e+18,
|
| 977 |
+
"trial_name": null,
|
| 978 |
+
"trial_params": null
|
| 979 |
+
}
|