End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/May23_13-42-10_2bc4f829fe52/events.out.tfevents.1716472299.2bc4f829fe52.989.11 +3 -0
- train_results.json +8 -0
- trainer_state.json +643 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.6944444444444444
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.8281
|
| 36 |
+
- Accuracy: 0.6944
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 57.142857142857146,
|
| 3 |
+
"eval_accuracy": 0.6944444444444444,
|
| 4 |
+
"eval_loss": 0.8281329870223999,
|
| 5 |
+
"eval_runtime": 0.5522,
|
| 6 |
+
"eval_samples_per_second": 65.19,
|
| 7 |
+
"eval_steps_per_second": 3.622,
|
| 8 |
+
"total_flos": 8.899329213047992e+17,
|
| 9 |
+
"train_loss": 0.6362448835372925,
|
| 10 |
+
"train_runtime": 561.1572,
|
| 11 |
+
"train_samples_per_second": 35.819,
|
| 12 |
+
"train_steps_per_second": 0.178
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 57.142857142857146,
|
| 3 |
+
"eval_accuracy": 0.6944444444444444,
|
| 4 |
+
"eval_loss": 0.8281329870223999,
|
| 5 |
+
"eval_runtime": 0.5522,
|
| 6 |
+
"eval_samples_per_second": 65.19,
|
| 7 |
+
"eval_steps_per_second": 3.622
|
| 8 |
+
}
|
runs/May23_13-42-10_2bc4f829fe52/events.out.tfevents.1716472299.2bc4f829fe52.989.11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ec81c390df17998cf44c7f47375f1d1211aa0527ac677ae5ede4f757274b83e
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 57.142857142857146,
|
| 3 |
+
"total_flos": 8.899329213047992e+17,
|
| 4 |
+
"train_loss": 0.6362448835372925,
|
| 5 |
+
"train_runtime": 561.1572,
|
| 6 |
+
"train_samples_per_second": 35.819,
|
| 7 |
+
"train_steps_per_second": 0.178
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,643 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6944444444444444,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-hasta-65-fold1/checkpoint-70",
|
| 4 |
+
"epoch": 57.142857142857146,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5714285714285714,
|
| 13 |
+
"eval_accuracy": 0.3333333333333333,
|
| 14 |
+
"eval_loss": 1.1951342821121216,
|
| 15 |
+
"eval_runtime": 0.5089,
|
| 16 |
+
"eval_samples_per_second": 70.74,
|
| 17 |
+
"eval_steps_per_second": 3.93,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.7142857142857144,
|
| 22 |
+
"eval_accuracy": 0.3055555555555556,
|
| 23 |
+
"eval_loss": 1.2409210205078125,
|
| 24 |
+
"eval_runtime": 0.5155,
|
| 25 |
+
"eval_samples_per_second": 69.841,
|
| 26 |
+
"eval_steps_per_second": 3.88,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.857142857142857,
|
| 31 |
+
"eval_accuracy": 0.3055555555555556,
|
| 32 |
+
"eval_loss": 1.218138337135315,
|
| 33 |
+
"eval_runtime": 0.5198,
|
| 34 |
+
"eval_samples_per_second": 69.261,
|
| 35 |
+
"eval_steps_per_second": 3.848,
|
| 36 |
+
"step": 5
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.5,
|
| 41 |
+
"eval_loss": 1.1308220624923706,
|
| 42 |
+
"eval_runtime": 0.5152,
|
| 43 |
+
"eval_samples_per_second": 69.87,
|
| 44 |
+
"eval_steps_per_second": 3.882,
|
| 45 |
+
"step": 7
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.571428571428571,
|
| 49 |
+
"eval_accuracy": 0.5277777777777778,
|
| 50 |
+
"eval_loss": 1.1857770681381226,
|
| 51 |
+
"eval_runtime": 0.5007,
|
| 52 |
+
"eval_samples_per_second": 71.904,
|
| 53 |
+
"eval_steps_per_second": 3.995,
|
| 54 |
+
"step": 8
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 5.714285714285714,
|
| 58 |
+
"grad_norm": 4.952281475067139,
|
| 59 |
+
"learning_rate": 5e-05,
|
| 60 |
+
"loss": 1.092,
|
| 61 |
+
"step": 10
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.714285714285714,
|
| 65 |
+
"eval_accuracy": 0.3055555555555556,
|
| 66 |
+
"eval_loss": 1.2797729969024658,
|
| 67 |
+
"eval_runtime": 0.5121,
|
| 68 |
+
"eval_samples_per_second": 70.303,
|
| 69 |
+
"eval_steps_per_second": 3.906,
|
| 70 |
+
"step": 10
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 6.857142857142857,
|
| 74 |
+
"eval_accuracy": 0.3611111111111111,
|
| 75 |
+
"eval_loss": 1.0892032384872437,
|
| 76 |
+
"eval_runtime": 0.5025,
|
| 77 |
+
"eval_samples_per_second": 71.636,
|
| 78 |
+
"eval_steps_per_second": 3.98,
|
| 79 |
+
"step": 12
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 8.0,
|
| 83 |
+
"eval_accuracy": 0.3888888888888889,
|
| 84 |
+
"eval_loss": 1.2658005952835083,
|
| 85 |
+
"eval_runtime": 0.5197,
|
| 86 |
+
"eval_samples_per_second": 69.272,
|
| 87 |
+
"eval_steps_per_second": 3.848,
|
| 88 |
+
"step": 14
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 8.571428571428571,
|
| 92 |
+
"eval_accuracy": 0.5,
|
| 93 |
+
"eval_loss": 1.1603169441223145,
|
| 94 |
+
"eval_runtime": 0.5136,
|
| 95 |
+
"eval_samples_per_second": 70.097,
|
| 96 |
+
"eval_steps_per_second": 3.894,
|
| 97 |
+
"step": 15
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 9.714285714285714,
|
| 101 |
+
"eval_accuracy": 0.4166666666666667,
|
| 102 |
+
"eval_loss": 1.0786064863204956,
|
| 103 |
+
"eval_runtime": 0.5166,
|
| 104 |
+
"eval_samples_per_second": 69.688,
|
| 105 |
+
"eval_steps_per_second": 3.872,
|
| 106 |
+
"step": 17
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 10.857142857142858,
|
| 110 |
+
"eval_accuracy": 0.4166666666666667,
|
| 111 |
+
"eval_loss": 1.2399791479110718,
|
| 112 |
+
"eval_runtime": 0.5016,
|
| 113 |
+
"eval_samples_per_second": 71.767,
|
| 114 |
+
"eval_steps_per_second": 3.987,
|
| 115 |
+
"step": 19
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 11.428571428571429,
|
| 119 |
+
"grad_norm": 11.269621849060059,
|
| 120 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 121 |
+
"loss": 0.9727,
|
| 122 |
+
"step": 20
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 12.0,
|
| 126 |
+
"eval_accuracy": 0.3888888888888889,
|
| 127 |
+
"eval_loss": 1.292936086654663,
|
| 128 |
+
"eval_runtime": 0.4771,
|
| 129 |
+
"eval_samples_per_second": 75.46,
|
| 130 |
+
"eval_steps_per_second": 4.192,
|
| 131 |
+
"step": 21
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 12.571428571428571,
|
| 135 |
+
"eval_accuracy": 0.3888888888888889,
|
| 136 |
+
"eval_loss": 1.161321997642517,
|
| 137 |
+
"eval_runtime": 0.497,
|
| 138 |
+
"eval_samples_per_second": 72.439,
|
| 139 |
+
"eval_steps_per_second": 4.024,
|
| 140 |
+
"step": 22
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 13.714285714285714,
|
| 144 |
+
"eval_accuracy": 0.6111111111111112,
|
| 145 |
+
"eval_loss": 0.9838488101959229,
|
| 146 |
+
"eval_runtime": 0.4914,
|
| 147 |
+
"eval_samples_per_second": 73.257,
|
| 148 |
+
"eval_steps_per_second": 4.07,
|
| 149 |
+
"step": 24
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 14.857142857142858,
|
| 153 |
+
"eval_accuracy": 0.3888888888888889,
|
| 154 |
+
"eval_loss": 1.2316433191299438,
|
| 155 |
+
"eval_runtime": 0.4927,
|
| 156 |
+
"eval_samples_per_second": 73.074,
|
| 157 |
+
"eval_steps_per_second": 4.06,
|
| 158 |
+
"step": 26
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 16.0,
|
| 162 |
+
"eval_accuracy": 0.4722222222222222,
|
| 163 |
+
"eval_loss": 1.151979923248291,
|
| 164 |
+
"eval_runtime": 0.5114,
|
| 165 |
+
"eval_samples_per_second": 70.402,
|
| 166 |
+
"eval_steps_per_second": 3.911,
|
| 167 |
+
"step": 28
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 16.571428571428573,
|
| 171 |
+
"eval_accuracy": 0.5555555555555556,
|
| 172 |
+
"eval_loss": 1.034508466720581,
|
| 173 |
+
"eval_runtime": 0.4983,
|
| 174 |
+
"eval_samples_per_second": 72.244,
|
| 175 |
+
"eval_steps_per_second": 4.014,
|
| 176 |
+
"step": 29
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 17.142857142857142,
|
| 180 |
+
"grad_norm": 8.270461082458496,
|
| 181 |
+
"learning_rate": 3.888888888888889e-05,
|
| 182 |
+
"loss": 0.8844,
|
| 183 |
+
"step": 30
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 17.714285714285715,
|
| 187 |
+
"eval_accuracy": 0.5,
|
| 188 |
+
"eval_loss": 0.999970555305481,
|
| 189 |
+
"eval_runtime": 0.5004,
|
| 190 |
+
"eval_samples_per_second": 71.949,
|
| 191 |
+
"eval_steps_per_second": 3.997,
|
| 192 |
+
"step": 31
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 18.857142857142858,
|
| 196 |
+
"eval_accuracy": 0.5277777777777778,
|
| 197 |
+
"eval_loss": 0.9932595491409302,
|
| 198 |
+
"eval_runtime": 0.506,
|
| 199 |
+
"eval_samples_per_second": 71.149,
|
| 200 |
+
"eval_steps_per_second": 3.953,
|
| 201 |
+
"step": 33
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 20.0,
|
| 205 |
+
"eval_accuracy": 0.5555555555555556,
|
| 206 |
+
"eval_loss": 1.0511807203292847,
|
| 207 |
+
"eval_runtime": 0.5024,
|
| 208 |
+
"eval_samples_per_second": 71.658,
|
| 209 |
+
"eval_steps_per_second": 3.981,
|
| 210 |
+
"step": 35
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 20.571428571428573,
|
| 214 |
+
"eval_accuracy": 0.5555555555555556,
|
| 215 |
+
"eval_loss": 0.9949522018432617,
|
| 216 |
+
"eval_runtime": 0.498,
|
| 217 |
+
"eval_samples_per_second": 72.292,
|
| 218 |
+
"eval_steps_per_second": 4.016,
|
| 219 |
+
"step": 36
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 21.714285714285715,
|
| 223 |
+
"eval_accuracy": 0.4722222222222222,
|
| 224 |
+
"eval_loss": 0.9621425271034241,
|
| 225 |
+
"eval_runtime": 0.5011,
|
| 226 |
+
"eval_samples_per_second": 71.845,
|
| 227 |
+
"eval_steps_per_second": 3.991,
|
| 228 |
+
"step": 38
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 22.857142857142858,
|
| 232 |
+
"grad_norm": 9.892123222351074,
|
| 233 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 234 |
+
"loss": 0.7447,
|
| 235 |
+
"step": 40
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 22.857142857142858,
|
| 239 |
+
"eval_accuracy": 0.5277777777777778,
|
| 240 |
+
"eval_loss": 0.8811734318733215,
|
| 241 |
+
"eval_runtime": 0.5013,
|
| 242 |
+
"eval_samples_per_second": 71.816,
|
| 243 |
+
"eval_steps_per_second": 3.99,
|
| 244 |
+
"step": 40
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 24.0,
|
| 248 |
+
"eval_accuracy": 0.5833333333333334,
|
| 249 |
+
"eval_loss": 1.024406909942627,
|
| 250 |
+
"eval_runtime": 0.4975,
|
| 251 |
+
"eval_samples_per_second": 72.357,
|
| 252 |
+
"eval_steps_per_second": 4.02,
|
| 253 |
+
"step": 42
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 24.571428571428573,
|
| 257 |
+
"eval_accuracy": 0.5833333333333334,
|
| 258 |
+
"eval_loss": 1.0124177932739258,
|
| 259 |
+
"eval_runtime": 0.5032,
|
| 260 |
+
"eval_samples_per_second": 71.543,
|
| 261 |
+
"eval_steps_per_second": 3.975,
|
| 262 |
+
"step": 43
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 25.714285714285715,
|
| 266 |
+
"eval_accuracy": 0.6388888888888888,
|
| 267 |
+
"eval_loss": 0.8907694220542908,
|
| 268 |
+
"eval_runtime": 0.501,
|
| 269 |
+
"eval_samples_per_second": 71.85,
|
| 270 |
+
"eval_steps_per_second": 3.992,
|
| 271 |
+
"step": 45
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 26.857142857142858,
|
| 275 |
+
"eval_accuracy": 0.5833333333333334,
|
| 276 |
+
"eval_loss": 0.8184720873832703,
|
| 277 |
+
"eval_runtime": 0.5096,
|
| 278 |
+
"eval_samples_per_second": 70.643,
|
| 279 |
+
"eval_steps_per_second": 3.925,
|
| 280 |
+
"step": 47
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 28.0,
|
| 284 |
+
"eval_accuracy": 0.5555555555555556,
|
| 285 |
+
"eval_loss": 0.9408966898918152,
|
| 286 |
+
"eval_runtime": 0.499,
|
| 287 |
+
"eval_samples_per_second": 72.139,
|
| 288 |
+
"eval_steps_per_second": 4.008,
|
| 289 |
+
"step": 49
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 28.571428571428573,
|
| 293 |
+
"grad_norm": 6.166210174560547,
|
| 294 |
+
"learning_rate": 2.777777777777778e-05,
|
| 295 |
+
"loss": 0.6176,
|
| 296 |
+
"step": 50
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 28.571428571428573,
|
| 300 |
+
"eval_accuracy": 0.5555555555555556,
|
| 301 |
+
"eval_loss": 1.0401257276535034,
|
| 302 |
+
"eval_runtime": 0.5125,
|
| 303 |
+
"eval_samples_per_second": 70.249,
|
| 304 |
+
"eval_steps_per_second": 3.903,
|
| 305 |
+
"step": 50
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 29.714285714285715,
|
| 309 |
+
"eval_accuracy": 0.5555555555555556,
|
| 310 |
+
"eval_loss": 1.0988928079605103,
|
| 311 |
+
"eval_runtime": 0.4975,
|
| 312 |
+
"eval_samples_per_second": 72.356,
|
| 313 |
+
"eval_steps_per_second": 4.02,
|
| 314 |
+
"step": 52
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 30.857142857142858,
|
| 318 |
+
"eval_accuracy": 0.5833333333333334,
|
| 319 |
+
"eval_loss": 0.9102041721343994,
|
| 320 |
+
"eval_runtime": 0.4988,
|
| 321 |
+
"eval_samples_per_second": 72.176,
|
| 322 |
+
"eval_steps_per_second": 4.01,
|
| 323 |
+
"step": 54
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 32.0,
|
| 327 |
+
"eval_accuracy": 0.5833333333333334,
|
| 328 |
+
"eval_loss": 0.8855189681053162,
|
| 329 |
+
"eval_runtime": 0.5026,
|
| 330 |
+
"eval_samples_per_second": 71.634,
|
| 331 |
+
"eval_steps_per_second": 3.98,
|
| 332 |
+
"step": 56
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 32.57142857142857,
|
| 336 |
+
"eval_accuracy": 0.5555555555555556,
|
| 337 |
+
"eval_loss": 0.8973506093025208,
|
| 338 |
+
"eval_runtime": 0.4968,
|
| 339 |
+
"eval_samples_per_second": 72.468,
|
| 340 |
+
"eval_steps_per_second": 4.026,
|
| 341 |
+
"step": 57
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 33.714285714285715,
|
| 345 |
+
"eval_accuracy": 0.6111111111111112,
|
| 346 |
+
"eval_loss": 0.9418532848358154,
|
| 347 |
+
"eval_runtime": 0.4995,
|
| 348 |
+
"eval_samples_per_second": 72.073,
|
| 349 |
+
"eval_steps_per_second": 4.004,
|
| 350 |
+
"step": 59
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 34.285714285714285,
|
| 354 |
+
"grad_norm": 10.520373344421387,
|
| 355 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 356 |
+
"loss": 0.4929,
|
| 357 |
+
"step": 60
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 34.857142857142854,
|
| 361 |
+
"eval_accuracy": 0.5833333333333334,
|
| 362 |
+
"eval_loss": 0.9471322298049927,
|
| 363 |
+
"eval_runtime": 0.5068,
|
| 364 |
+
"eval_samples_per_second": 71.029,
|
| 365 |
+
"eval_steps_per_second": 3.946,
|
| 366 |
+
"step": 61
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 36.0,
|
| 370 |
+
"eval_accuracy": 0.5833333333333334,
|
| 371 |
+
"eval_loss": 0.8608690500259399,
|
| 372 |
+
"eval_runtime": 0.4977,
|
| 373 |
+
"eval_samples_per_second": 72.332,
|
| 374 |
+
"eval_steps_per_second": 4.018,
|
| 375 |
+
"step": 63
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 36.57142857142857,
|
| 379 |
+
"eval_accuracy": 0.5833333333333334,
|
| 380 |
+
"eval_loss": 0.8558059334754944,
|
| 381 |
+
"eval_runtime": 0.4937,
|
| 382 |
+
"eval_samples_per_second": 72.92,
|
| 383 |
+
"eval_steps_per_second": 4.051,
|
| 384 |
+
"step": 64
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 37.714285714285715,
|
| 388 |
+
"eval_accuracy": 0.5555555555555556,
|
| 389 |
+
"eval_loss": 0.8449121117591858,
|
| 390 |
+
"eval_runtime": 0.5013,
|
| 391 |
+
"eval_samples_per_second": 71.82,
|
| 392 |
+
"eval_steps_per_second": 3.99,
|
| 393 |
+
"step": 66
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 38.857142857142854,
|
| 397 |
+
"eval_accuracy": 0.6666666666666666,
|
| 398 |
+
"eval_loss": 0.8136334419250488,
|
| 399 |
+
"eval_runtime": 0.4944,
|
| 400 |
+
"eval_samples_per_second": 72.811,
|
| 401 |
+
"eval_steps_per_second": 4.045,
|
| 402 |
+
"step": 68
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 40.0,
|
| 406 |
+
"grad_norm": 11.665092468261719,
|
| 407 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 408 |
+
"loss": 0.463,
|
| 409 |
+
"step": 70
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 40.0,
|
| 413 |
+
"eval_accuracy": 0.6944444444444444,
|
| 414 |
+
"eval_loss": 0.8281329870223999,
|
| 415 |
+
"eval_runtime": 0.5025,
|
| 416 |
+
"eval_samples_per_second": 71.639,
|
| 417 |
+
"eval_steps_per_second": 3.98,
|
| 418 |
+
"step": 70
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 40.57142857142857,
|
| 422 |
+
"eval_accuracy": 0.6944444444444444,
|
| 423 |
+
"eval_loss": 0.8226919770240784,
|
| 424 |
+
"eval_runtime": 0.5104,
|
| 425 |
+
"eval_samples_per_second": 70.529,
|
| 426 |
+
"eval_steps_per_second": 3.918,
|
| 427 |
+
"step": 71
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 41.714285714285715,
|
| 431 |
+
"eval_accuracy": 0.5833333333333334,
|
| 432 |
+
"eval_loss": 0.8322837352752686,
|
| 433 |
+
"eval_runtime": 0.4973,
|
| 434 |
+
"eval_samples_per_second": 72.392,
|
| 435 |
+
"eval_steps_per_second": 4.022,
|
| 436 |
+
"step": 73
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 42.857142857142854,
|
| 440 |
+
"eval_accuracy": 0.5833333333333334,
|
| 441 |
+
"eval_loss": 0.8435983657836914,
|
| 442 |
+
"eval_runtime": 0.4888,
|
| 443 |
+
"eval_samples_per_second": 73.644,
|
| 444 |
+
"eval_steps_per_second": 4.091,
|
| 445 |
+
"step": 75
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 44.0,
|
| 449 |
+
"eval_accuracy": 0.5833333333333334,
|
| 450 |
+
"eval_loss": 0.839017927646637,
|
| 451 |
+
"eval_runtime": 0.4935,
|
| 452 |
+
"eval_samples_per_second": 72.953,
|
| 453 |
+
"eval_steps_per_second": 4.053,
|
| 454 |
+
"step": 77
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 44.57142857142857,
|
| 458 |
+
"eval_accuracy": 0.6111111111111112,
|
| 459 |
+
"eval_loss": 0.8580043911933899,
|
| 460 |
+
"eval_runtime": 0.4996,
|
| 461 |
+
"eval_samples_per_second": 72.055,
|
| 462 |
+
"eval_steps_per_second": 4.003,
|
| 463 |
+
"step": 78
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 45.714285714285715,
|
| 467 |
+
"grad_norm": 5.9656195640563965,
|
| 468 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 469 |
+
"loss": 0.3995,
|
| 470 |
+
"step": 80
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 45.714285714285715,
|
| 474 |
+
"eval_accuracy": 0.6111111111111112,
|
| 475 |
+
"eval_loss": 0.9374995827674866,
|
| 476 |
+
"eval_runtime": 0.5119,
|
| 477 |
+
"eval_samples_per_second": 70.321,
|
| 478 |
+
"eval_steps_per_second": 3.907,
|
| 479 |
+
"step": 80
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 46.857142857142854,
|
| 483 |
+
"eval_accuracy": 0.5555555555555556,
|
| 484 |
+
"eval_loss": 0.9897011518478394,
|
| 485 |
+
"eval_runtime": 0.5037,
|
| 486 |
+
"eval_samples_per_second": 71.47,
|
| 487 |
+
"eval_steps_per_second": 3.971,
|
| 488 |
+
"step": 82
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 48.0,
|
| 492 |
+
"eval_accuracy": 0.5555555555555556,
|
| 493 |
+
"eval_loss": 0.9784960150718689,
|
| 494 |
+
"eval_runtime": 0.4971,
|
| 495 |
+
"eval_samples_per_second": 72.425,
|
| 496 |
+
"eval_steps_per_second": 4.024,
|
| 497 |
+
"step": 84
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 48.57142857142857,
|
| 501 |
+
"eval_accuracy": 0.6388888888888888,
|
| 502 |
+
"eval_loss": 0.9335712790489197,
|
| 503 |
+
"eval_runtime": 0.5144,
|
| 504 |
+
"eval_samples_per_second": 69.989,
|
| 505 |
+
"eval_steps_per_second": 3.888,
|
| 506 |
+
"step": 85
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 49.714285714285715,
|
| 510 |
+
"eval_accuracy": 0.6388888888888888,
|
| 511 |
+
"eval_loss": 0.8504276275634766,
|
| 512 |
+
"eval_runtime": 0.5039,
|
| 513 |
+
"eval_samples_per_second": 71.439,
|
| 514 |
+
"eval_steps_per_second": 3.969,
|
| 515 |
+
"step": 87
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 50.857142857142854,
|
| 519 |
+
"eval_accuracy": 0.6666666666666666,
|
| 520 |
+
"eval_loss": 0.8450478911399841,
|
| 521 |
+
"eval_runtime": 0.5024,
|
| 522 |
+
"eval_samples_per_second": 71.65,
|
| 523 |
+
"eval_steps_per_second": 3.981,
|
| 524 |
+
"step": 89
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 51.42857142857143,
|
| 528 |
+
"grad_norm": 10.226240158081055,
|
| 529 |
+
"learning_rate": 5.555555555555556e-06,
|
| 530 |
+
"loss": 0.3697,
|
| 531 |
+
"step": 90
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 52.0,
|
| 535 |
+
"eval_accuracy": 0.6388888888888888,
|
| 536 |
+
"eval_loss": 0.8530892133712769,
|
| 537 |
+
"eval_runtime": 0.5051,
|
| 538 |
+
"eval_samples_per_second": 71.274,
|
| 539 |
+
"eval_steps_per_second": 3.96,
|
| 540 |
+
"step": 91
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 52.57142857142857,
|
| 544 |
+
"eval_accuracy": 0.6388888888888888,
|
| 545 |
+
"eval_loss": 0.8728136420249939,
|
| 546 |
+
"eval_runtime": 0.5023,
|
| 547 |
+
"eval_samples_per_second": 71.671,
|
| 548 |
+
"eval_steps_per_second": 3.982,
|
| 549 |
+
"step": 92
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 53.714285714285715,
|
| 553 |
+
"eval_accuracy": 0.6666666666666666,
|
| 554 |
+
"eval_loss": 0.9075747728347778,
|
| 555 |
+
"eval_runtime": 0.4997,
|
| 556 |
+
"eval_samples_per_second": 72.043,
|
| 557 |
+
"eval_steps_per_second": 4.002,
|
| 558 |
+
"step": 94
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 54.857142857142854,
|
| 562 |
+
"eval_accuracy": 0.6388888888888888,
|
| 563 |
+
"eval_loss": 0.9174892902374268,
|
| 564 |
+
"eval_runtime": 0.5088,
|
| 565 |
+
"eval_samples_per_second": 70.753,
|
| 566 |
+
"eval_steps_per_second": 3.931,
|
| 567 |
+
"step": 96
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 56.0,
|
| 571 |
+
"eval_accuracy": 0.5833333333333334,
|
| 572 |
+
"eval_loss": 0.9145221710205078,
|
| 573 |
+
"eval_runtime": 0.5129,
|
| 574 |
+
"eval_samples_per_second": 70.19,
|
| 575 |
+
"eval_steps_per_second": 3.899,
|
| 576 |
+
"step": 98
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 56.57142857142857,
|
| 580 |
+
"eval_accuracy": 0.5833333333333334,
|
| 581 |
+
"eval_loss": 0.9118825197219849,
|
| 582 |
+
"eval_runtime": 0.4996,
|
| 583 |
+
"eval_samples_per_second": 72.056,
|
| 584 |
+
"eval_steps_per_second": 4.003,
|
| 585 |
+
"step": 99
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 57.142857142857146,
|
| 589 |
+
"grad_norm": 6.797101020812988,
|
| 590 |
+
"learning_rate": 0.0,
|
| 591 |
+
"loss": 0.3259,
|
| 592 |
+
"step": 100
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 57.142857142857146,
|
| 596 |
+
"eval_accuracy": 0.5833333333333334,
|
| 597 |
+
"eval_loss": 0.9102092385292053,
|
| 598 |
+
"eval_runtime": 0.5165,
|
| 599 |
+
"eval_samples_per_second": 69.7,
|
| 600 |
+
"eval_steps_per_second": 3.872,
|
| 601 |
+
"step": 100
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 57.142857142857146,
|
| 605 |
+
"step": 100,
|
| 606 |
+
"total_flos": 8.899329213047992e+17,
|
| 607 |
+
"train_loss": 0.6362448835372925,
|
| 608 |
+
"train_runtime": 561.1572,
|
| 609 |
+
"train_samples_per_second": 35.819,
|
| 610 |
+
"train_steps_per_second": 0.178
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 57.142857142857146,
|
| 614 |
+
"eval_accuracy": 0.6944444444444444,
|
| 615 |
+
"eval_loss": 0.8281329870223999,
|
| 616 |
+
"eval_runtime": 0.5522,
|
| 617 |
+
"eval_samples_per_second": 65.19,
|
| 618 |
+
"eval_steps_per_second": 3.622,
|
| 619 |
+
"step": 100
|
| 620 |
+
}
|
| 621 |
+
],
|
| 622 |
+
"logging_steps": 10,
|
| 623 |
+
"max_steps": 100,
|
| 624 |
+
"num_input_tokens_seen": 0,
|
| 625 |
+
"num_train_epochs": 100,
|
| 626 |
+
"save_steps": 500,
|
| 627 |
+
"stateful_callbacks": {
|
| 628 |
+
"TrainerControl": {
|
| 629 |
+
"args": {
|
| 630 |
+
"should_epoch_stop": false,
|
| 631 |
+
"should_evaluate": false,
|
| 632 |
+
"should_log": false,
|
| 633 |
+
"should_save": true,
|
| 634 |
+
"should_training_stop": true
|
| 635 |
+
},
|
| 636 |
+
"attributes": {}
|
| 637 |
+
}
|
| 638 |
+
},
|
| 639 |
+
"total_flos": 8.899329213047992e+17,
|
| 640 |
+
"train_batch_size": 32,
|
| 641 |
+
"trial_name": null,
|
| 642 |
+
"trial_params": null
|
| 643 |
+
}
|