End of training
Browse files- README.md +3 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Feb12_00-29-37_3621747748f3/events.out.tfevents.1707700961.3621747748f3.6471.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +1000 -55
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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) 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: 0.9383116883116883
|
| 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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2469
|
| 36 |
+
- Accuracy: 0.9383
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
-
"total_flos": 4.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 29.66,
|
| 3 |
+
"eval_accuracy": 0.9383116883116883,
|
| 4 |
+
"eval_loss": 0.24687811732292175,
|
| 5 |
+
"eval_runtime": 6.2481,
|
| 6 |
+
"eval_samples_per_second": 98.59,
|
| 7 |
+
"eval_steps_per_second": 3.201,
|
| 8 |
+
"total_flos": 4.0838875031628657e+18,
|
| 9 |
+
"train_loss": 0.17642173106356185,
|
| 10 |
+
"train_runtime": 3123.2223,
|
| 11 |
+
"train_samples_per_second": 53.205,
|
| 12 |
+
"train_steps_per_second": 0.413
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 29.66,
|
| 3 |
+
"eval_accuracy": 0.9383116883116883,
|
| 4 |
+
"eval_loss": 0.24687811732292175,
|
| 5 |
+
"eval_runtime": 6.2481,
|
| 6 |
+
"eval_samples_per_second": 98.59,
|
| 7 |
+
"eval_steps_per_second": 3.201
|
| 8 |
}
|
runs/Feb12_00-29-37_3621747748f3/events.out.tfevents.1707700961.3621747748f3.6471.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf7ed0f950111aebdac487a1f12d1bf8cff2ddc554a179540a10efe6e7c527d
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 4.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 29.66,
|
| 3 |
+
"total_flos": 4.0838875031628657e+18,
|
| 4 |
+
"train_loss": 0.17642173106356185,
|
| 5 |
+
"train_runtime": 3123.2223,
|
| 6 |
+
"train_samples_per_second": 53.205,
|
| 7 |
+
"train_steps_per_second": 0.413
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,128 +1,1073 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.23,
|
| 13 |
-
"learning_rate": 3.
|
| 14 |
-
"loss":
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.46,
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss":
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.69,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.92,
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.99,
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 0.
|
| 39 |
-
"eval_runtime": 6.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second": 3.
|
| 42 |
"step": 43
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 1.15,
|
| 46 |
-
"learning_rate":
|
| 47 |
-
"loss": 0.
|
| 48 |
"step": 50
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 1.38,
|
| 52 |
-
"learning_rate": 2.
|
| 53 |
-
"loss": 0.
|
| 54 |
"step": 60
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 1.61,
|
| 58 |
-
"learning_rate": 2.
|
| 59 |
-
"loss": 0.
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 1.84,
|
| 64 |
-
"learning_rate":
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 2.0,
|
| 70 |
-
"eval_accuracy": 0.
|
| 71 |
-
"eval_loss": 0.
|
| 72 |
-
"eval_runtime":
|
| 73 |
-
"eval_samples_per_second":
|
| 74 |
-
"eval_steps_per_second": 3.
|
| 75 |
"step": 87
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 2.07,
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 90
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 2.3,
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 2.53,
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 110
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 2.76,
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 120
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 2.
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"eval_samples_per_second": 96.442,
|
| 107 |
-
"eval_steps_per_second": 3.131,
|
| 108 |
-
"step": 129
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 2.
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
}
|
| 119 |
],
|
| 120 |
"logging_steps": 10,
|
| 121 |
-
"max_steps":
|
| 122 |
"num_input_tokens_seen": 0,
|
| 123 |
-
"num_train_epochs":
|
| 124 |
"save_steps": 500,
|
| 125 |
-
"total_flos": 4.
|
| 126 |
"train_batch_size": 32,
|
| 127 |
"trial_name": null,
|
| 128 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9383116883116883,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1218",
|
| 4 |
+
"epoch": 29.655172413793103,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1290,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.23,
|
| 13 |
+
"learning_rate": 3.875968992248062e-06,
|
| 14 |
+
"loss": 2.033,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.46,
|
| 19 |
+
"learning_rate": 7.751937984496124e-06,
|
| 20 |
+
"loss": 1.819,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.69,
|
| 25 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 26 |
+
"loss": 1.3652,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.92,
|
| 31 |
+
"learning_rate": 1.5503875968992248e-05,
|
| 32 |
+
"loss": 0.9843,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.99,
|
| 37 |
+
"eval_accuracy": 0.6948051948051948,
|
| 38 |
+
"eval_loss": 0.850001335144043,
|
| 39 |
+
"eval_runtime": 6.318,
|
| 40 |
+
"eval_samples_per_second": 97.499,
|
| 41 |
+
"eval_steps_per_second": 3.166,
|
| 42 |
"step": 43
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 1.15,
|
| 46 |
+
"learning_rate": 1.937984496124031e-05,
|
| 47 |
+
"loss": 0.816,
|
| 48 |
"step": 50
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 1.38,
|
| 52 |
+
"learning_rate": 2.3255813953488374e-05,
|
| 53 |
+
"loss": 0.7631,
|
| 54 |
"step": 60
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 1.61,
|
| 58 |
+
"learning_rate": 2.7131782945736434e-05,
|
| 59 |
+
"loss": 0.6499,
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 1.84,
|
| 64 |
+
"learning_rate": 3.1007751937984497e-05,
|
| 65 |
+
"loss": 0.5335,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 2.0,
|
| 70 |
+
"eval_accuracy": 0.7824675324675324,
|
| 71 |
+
"eval_loss": 0.5584108233451843,
|
| 72 |
+
"eval_runtime": 6.0937,
|
| 73 |
+
"eval_samples_per_second": 101.088,
|
| 74 |
+
"eval_steps_per_second": 3.282,
|
| 75 |
"step": 87
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 2.07,
|
| 79 |
+
"learning_rate": 3.488372093023256e-05,
|
| 80 |
+
"loss": 0.5594,
|
| 81 |
"step": 90
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 2.3,
|
| 85 |
+
"learning_rate": 3.875968992248062e-05,
|
| 86 |
+
"loss": 0.4565,
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 2.53,
|
| 91 |
+
"learning_rate": 4.263565891472868e-05,
|
| 92 |
+
"loss": 0.4759,
|
| 93 |
"step": 110
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 2.76,
|
| 97 |
+
"learning_rate": 4.651162790697675e-05,
|
| 98 |
+
"loss": 0.4542,
|
| 99 |
"step": 120
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 2.99,
|
| 103 |
+
"learning_rate": 4.995693367786391e-05,
|
| 104 |
+
"loss": 0.4263,
|
| 105 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 2.99,
|
| 109 |
+
"eval_accuracy": 0.8116883116883117,
|
| 110 |
+
"eval_loss": 0.4790755808353424,
|
| 111 |
+
"eval_runtime": 6.348,
|
| 112 |
+
"eval_samples_per_second": 97.038,
|
| 113 |
+
"eval_steps_per_second": 3.151,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.22,
|
| 118 |
+
"learning_rate": 4.952627045650302e-05,
|
| 119 |
+
"loss": 0.3769,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.45,
|
| 124 |
+
"learning_rate": 4.9095607235142123e-05,
|
| 125 |
+
"loss": 0.3852,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.68,
|
| 130 |
+
"learning_rate": 4.866494401378123e-05,
|
| 131 |
+
"loss": 0.3409,
|
| 132 |
+
"step": 160
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.91,
|
| 136 |
+
"learning_rate": 4.823428079242033e-05,
|
| 137 |
+
"loss": 0.3308,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.0,
|
| 142 |
+
"eval_accuracy": 0.8344155844155844,
|
| 143 |
+
"eval_loss": 0.4268946349620819,
|
| 144 |
+
"eval_runtime": 6.5538,
|
| 145 |
+
"eval_samples_per_second": 93.991,
|
| 146 |
+
"eval_steps_per_second": 3.052,
|
| 147 |
+
"step": 174
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.14,
|
| 151 |
+
"learning_rate": 4.780361757105943e-05,
|
| 152 |
+
"loss": 0.3093,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.37,
|
| 157 |
+
"learning_rate": 4.737295434969854e-05,
|
| 158 |
+
"loss": 0.3429,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.6,
|
| 163 |
+
"learning_rate": 4.694229112833764e-05,
|
| 164 |
+
"loss": 0.2697,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.83,
|
| 169 |
+
"learning_rate": 4.651162790697675e-05,
|
| 170 |
+
"loss": 0.2882,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.99,
|
| 175 |
+
"eval_accuracy": 0.8636363636363636,
|
| 176 |
+
"eval_loss": 0.35674524307250977,
|
| 177 |
+
"eval_runtime": 6.3226,
|
| 178 |
+
"eval_samples_per_second": 97.428,
|
| 179 |
+
"eval_steps_per_second": 3.163,
|
| 180 |
+
"step": 217
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.06,
|
| 184 |
+
"learning_rate": 4.6080964685615853e-05,
|
| 185 |
+
"loss": 0.2729,
|
| 186 |
+
"step": 220
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 5.29,
|
| 190 |
+
"learning_rate": 4.565030146425496e-05,
|
| 191 |
+
"loss": 0.2543,
|
| 192 |
+
"step": 230
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 5.52,
|
| 196 |
+
"learning_rate": 4.521963824289406e-05,
|
| 197 |
+
"loss": 0.2526,
|
| 198 |
+
"step": 240
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.75,
|
| 202 |
+
"learning_rate": 4.478897502153316e-05,
|
| 203 |
+
"loss": 0.255,
|
| 204 |
+
"step": 250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.98,
|
| 208 |
+
"learning_rate": 4.435831180017227e-05,
|
| 209 |
+
"loss": 0.2517,
|
| 210 |
+
"step": 260
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 6.0,
|
| 214 |
+
"eval_accuracy": 0.8701298701298701,
|
| 215 |
+
"eval_loss": 0.33171918988227844,
|
| 216 |
+
"eval_runtime": 5.9688,
|
| 217 |
+
"eval_samples_per_second": 103.204,
|
| 218 |
+
"eval_steps_per_second": 3.351,
|
| 219 |
+
"step": 261
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.21,
|
| 223 |
+
"learning_rate": 4.392764857881137e-05,
|
| 224 |
+
"loss": 0.2317,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 6.44,
|
| 229 |
+
"learning_rate": 4.349698535745048e-05,
|
| 230 |
+
"loss": 0.1944,
|
| 231 |
+
"step": 280
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.67,
|
| 235 |
+
"learning_rate": 4.306632213608958e-05,
|
| 236 |
+
"loss": 0.248,
|
| 237 |
+
"step": 290
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 6.9,
|
| 241 |
+
"learning_rate": 4.263565891472868e-05,
|
| 242 |
+
"loss": 0.1908,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.99,
|
| 247 |
+
"eval_accuracy": 0.8814935064935064,
|
| 248 |
+
"eval_loss": 0.3081734776496887,
|
| 249 |
+
"eval_runtime": 6.4591,
|
| 250 |
+
"eval_samples_per_second": 95.369,
|
| 251 |
+
"eval_steps_per_second": 3.096,
|
| 252 |
+
"step": 304
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 7.13,
|
| 256 |
+
"learning_rate": 4.220499569336779e-05,
|
| 257 |
+
"loss": 0.1726,
|
| 258 |
+
"step": 310
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 7.36,
|
| 262 |
+
"learning_rate": 4.177433247200689e-05,
|
| 263 |
+
"loss": 0.1663,
|
| 264 |
+
"step": 320
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 7.59,
|
| 268 |
+
"learning_rate": 4.1343669250646e-05,
|
| 269 |
+
"loss": 0.1602,
|
| 270 |
+
"step": 330
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 7.82,
|
| 274 |
+
"learning_rate": 4.09130060292851e-05,
|
| 275 |
+
"loss": 0.187,
|
| 276 |
+
"step": 340
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 8.0,
|
| 280 |
+
"eval_accuracy": 0.8798701298701299,
|
| 281 |
+
"eval_loss": 0.3230064809322357,
|
| 282 |
+
"eval_runtime": 6.0202,
|
| 283 |
+
"eval_samples_per_second": 102.322,
|
| 284 |
+
"eval_steps_per_second": 3.322,
|
| 285 |
+
"step": 348
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 8.05,
|
| 289 |
+
"learning_rate": 4.048234280792421e-05,
|
| 290 |
+
"loss": 0.1676,
|
| 291 |
+
"step": 350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 8.28,
|
| 295 |
+
"learning_rate": 4.005167958656331e-05,
|
| 296 |
+
"loss": 0.1681,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 8.51,
|
| 301 |
+
"learning_rate": 3.962101636520241e-05,
|
| 302 |
+
"loss": 0.1818,
|
| 303 |
+
"step": 370
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.74,
|
| 307 |
+
"learning_rate": 3.919035314384152e-05,
|
| 308 |
+
"loss": 0.1299,
|
| 309 |
+
"step": 380
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 8.97,
|
| 313 |
+
"learning_rate": 3.875968992248062e-05,
|
| 314 |
+
"loss": 0.1434,
|
| 315 |
+
"step": 390
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.99,
|
| 319 |
+
"eval_accuracy": 0.900974025974026,
|
| 320 |
+
"eval_loss": 0.3322867453098297,
|
| 321 |
+
"eval_runtime": 6.3218,
|
| 322 |
+
"eval_samples_per_second": 97.44,
|
| 323 |
+
"eval_steps_per_second": 3.164,
|
| 324 |
+
"step": 391
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.2,
|
| 328 |
+
"learning_rate": 3.832902670111973e-05,
|
| 329 |
+
"loss": 0.1432,
|
| 330 |
+
"step": 400
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 9.43,
|
| 334 |
+
"learning_rate": 3.789836347975883e-05,
|
| 335 |
+
"loss": 0.1313,
|
| 336 |
+
"step": 410
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 9.66,
|
| 340 |
+
"learning_rate": 3.746770025839794e-05,
|
| 341 |
+
"loss": 0.1546,
|
| 342 |
+
"step": 420
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 9.89,
|
| 346 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 347 |
+
"loss": 0.1277,
|
| 348 |
+
"step": 430
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 10.0,
|
| 352 |
+
"eval_accuracy": 0.9074675324675324,
|
| 353 |
+
"eval_loss": 0.2488991618156433,
|
| 354 |
+
"eval_runtime": 6.4317,
|
| 355 |
+
"eval_samples_per_second": 95.776,
|
| 356 |
+
"eval_steps_per_second": 3.11,
|
| 357 |
+
"step": 435
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 10.11,
|
| 361 |
+
"learning_rate": 3.660637381567614e-05,
|
| 362 |
+
"loss": 0.1349,
|
| 363 |
+
"step": 440
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 10.34,
|
| 367 |
+
"learning_rate": 3.617571059431525e-05,
|
| 368 |
+
"loss": 0.1074,
|
| 369 |
+
"step": 450
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 10.57,
|
| 373 |
+
"learning_rate": 3.5745047372954346e-05,
|
| 374 |
+
"loss": 0.1218,
|
| 375 |
+
"step": 460
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 10.8,
|
| 379 |
+
"learning_rate": 3.531438415159346e-05,
|
| 380 |
+
"loss": 0.156,
|
| 381 |
+
"step": 470
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 10.99,
|
| 385 |
+
"eval_accuracy": 0.887987012987013,
|
| 386 |
+
"eval_loss": 0.3245611786842346,
|
| 387 |
+
"eval_runtime": 6.5235,
|
| 388 |
+
"eval_samples_per_second": 94.429,
|
| 389 |
+
"eval_steps_per_second": 3.066,
|
| 390 |
+
"step": 478
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 11.03,
|
| 394 |
+
"learning_rate": 3.488372093023256e-05,
|
| 395 |
+
"loss": 0.1113,
|
| 396 |
+
"step": 480
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 11.26,
|
| 400 |
+
"learning_rate": 3.445305770887167e-05,
|
| 401 |
+
"loss": 0.0888,
|
| 402 |
+
"step": 490
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 11.49,
|
| 406 |
+
"learning_rate": 3.4022394487510767e-05,
|
| 407 |
+
"loss": 0.1083,
|
| 408 |
+
"step": 500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 11.72,
|
| 412 |
+
"learning_rate": 3.359173126614987e-05,
|
| 413 |
+
"loss": 0.1126,
|
| 414 |
+
"step": 510
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 11.95,
|
| 418 |
+
"learning_rate": 3.316106804478898e-05,
|
| 419 |
+
"loss": 0.0781,
|
| 420 |
+
"step": 520
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 12.0,
|
| 424 |
+
"eval_accuracy": 0.900974025974026,
|
| 425 |
+
"eval_loss": 0.31213870644569397,
|
| 426 |
+
"eval_runtime": 5.9923,
|
| 427 |
+
"eval_samples_per_second": 102.799,
|
| 428 |
+
"eval_steps_per_second": 3.338,
|
| 429 |
+
"step": 522
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 12.18,
|
| 433 |
+
"learning_rate": 3.273040482342808e-05,
|
| 434 |
+
"loss": 0.0906,
|
| 435 |
+
"step": 530
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 12.41,
|
| 439 |
+
"learning_rate": 3.229974160206719e-05,
|
| 440 |
+
"loss": 0.0864,
|
| 441 |
+
"step": 540
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 12.64,
|
| 445 |
+
"learning_rate": 3.186907838070629e-05,
|
| 446 |
+
"loss": 0.0854,
|
| 447 |
+
"step": 550
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 12.87,
|
| 451 |
+
"learning_rate": 3.143841515934539e-05,
|
| 452 |
+
"loss": 0.1001,
|
| 453 |
+
"step": 560
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 12.99,
|
| 457 |
+
"eval_accuracy": 0.9058441558441559,
|
| 458 |
+
"eval_loss": 0.27083244919776917,
|
| 459 |
+
"eval_runtime": 6.2499,
|
| 460 |
+
"eval_samples_per_second": 98.561,
|
| 461 |
+
"eval_steps_per_second": 3.2,
|
| 462 |
+
"step": 565
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 13.1,
|
| 466 |
+
"learning_rate": 3.1007751937984497e-05,
|
| 467 |
+
"loss": 0.0923,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 13.33,
|
| 472 |
+
"learning_rate": 3.05770887166236e-05,
|
| 473 |
+
"loss": 0.0771,
|
| 474 |
+
"step": 580
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 13.56,
|
| 478 |
+
"learning_rate": 3.0146425495262704e-05,
|
| 479 |
+
"loss": 0.0873,
|
| 480 |
+
"step": 590
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 13.79,
|
| 484 |
+
"learning_rate": 2.971576227390181e-05,
|
| 485 |
+
"loss": 0.0892,
|
| 486 |
+
"step": 600
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 14.0,
|
| 490 |
+
"eval_accuracy": 0.913961038961039,
|
| 491 |
+
"eval_loss": 0.2581653296947479,
|
| 492 |
+
"eval_runtime": 6.4729,
|
| 493 |
+
"eval_samples_per_second": 95.166,
|
| 494 |
+
"eval_steps_per_second": 3.09,
|
| 495 |
+
"step": 609
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 14.02,
|
| 499 |
+
"learning_rate": 2.9285099052540914e-05,
|
| 500 |
+
"loss": 0.0802,
|
| 501 |
+
"step": 610
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 14.25,
|
| 505 |
+
"learning_rate": 2.8854435831180023e-05,
|
| 506 |
+
"loss": 0.073,
|
| 507 |
+
"step": 620
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 14.48,
|
| 511 |
+
"learning_rate": 2.842377260981912e-05,
|
| 512 |
+
"loss": 0.0584,
|
| 513 |
+
"step": 630
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 14.71,
|
| 517 |
+
"learning_rate": 2.7993109388458226e-05,
|
| 518 |
+
"loss": 0.0552,
|
| 519 |
+
"step": 640
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 14.94,
|
| 523 |
+
"learning_rate": 2.7562446167097332e-05,
|
| 524 |
+
"loss": 0.0644,
|
| 525 |
+
"step": 650
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 14.99,
|
| 529 |
+
"eval_accuracy": 0.922077922077922,
|
| 530 |
+
"eval_loss": 0.24860848486423492,
|
| 531 |
+
"eval_runtime": 6.4617,
|
| 532 |
+
"eval_samples_per_second": 95.332,
|
| 533 |
+
"eval_steps_per_second": 3.095,
|
| 534 |
+
"step": 652
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 15.17,
|
| 538 |
+
"learning_rate": 2.7131782945736434e-05,
|
| 539 |
+
"loss": 0.0906,
|
| 540 |
+
"step": 660
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 15.4,
|
| 544 |
+
"learning_rate": 2.670111972437554e-05,
|
| 545 |
+
"loss": 0.0507,
|
| 546 |
+
"step": 670
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 15.63,
|
| 550 |
+
"learning_rate": 2.6270456503014644e-05,
|
| 551 |
+
"loss": 0.0597,
|
| 552 |
+
"step": 680
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 15.86,
|
| 556 |
+
"learning_rate": 2.5839793281653746e-05,
|
| 557 |
+
"loss": 0.0689,
|
| 558 |
+
"step": 690
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 16.0,
|
| 562 |
+
"eval_accuracy": 0.9237012987012987,
|
| 563 |
+
"eval_loss": 0.246454119682312,
|
| 564 |
+
"eval_runtime": 6.0878,
|
| 565 |
+
"eval_samples_per_second": 101.186,
|
| 566 |
+
"eval_steps_per_second": 3.285,
|
| 567 |
+
"step": 696
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 16.09,
|
| 571 |
+
"learning_rate": 2.540913006029285e-05,
|
| 572 |
+
"loss": 0.0696,
|
| 573 |
+
"step": 700
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 16.32,
|
| 577 |
+
"learning_rate": 2.4978466838931956e-05,
|
| 578 |
+
"loss": 0.0563,
|
| 579 |
+
"step": 710
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 16.55,
|
| 583 |
+
"learning_rate": 2.4547803617571062e-05,
|
| 584 |
+
"loss": 0.058,
|
| 585 |
+
"step": 720
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 16.78,
|
| 589 |
+
"learning_rate": 2.4117140396210164e-05,
|
| 590 |
+
"loss": 0.0547,
|
| 591 |
+
"step": 730
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 16.99,
|
| 595 |
+
"eval_accuracy": 0.9334415584415584,
|
| 596 |
+
"eval_loss": 0.24022094905376434,
|
| 597 |
+
"eval_runtime": 6.0529,
|
| 598 |
+
"eval_samples_per_second": 101.769,
|
| 599 |
+
"eval_steps_per_second": 3.304,
|
| 600 |
+
"step": 739
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 17.01,
|
| 604 |
+
"learning_rate": 2.368647717484927e-05,
|
| 605 |
+
"loss": 0.068,
|
| 606 |
+
"step": 740
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 17.24,
|
| 610 |
+
"learning_rate": 2.3255813953488374e-05,
|
| 611 |
+
"loss": 0.0556,
|
| 612 |
+
"step": 750
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 17.47,
|
| 616 |
+
"learning_rate": 2.282515073212748e-05,
|
| 617 |
+
"loss": 0.0541,
|
| 618 |
+
"step": 760
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 17.7,
|
| 622 |
+
"learning_rate": 2.239448751076658e-05,
|
| 623 |
+
"loss": 0.0444,
|
| 624 |
+
"step": 770
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 17.93,
|
| 628 |
+
"learning_rate": 2.1963824289405686e-05,
|
| 629 |
+
"loss": 0.0597,
|
| 630 |
+
"step": 780
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 18.0,
|
| 634 |
+
"eval_accuracy": 0.9237012987012987,
|
| 635 |
+
"eval_loss": 0.2533910572528839,
|
| 636 |
+
"eval_runtime": 6.1928,
|
| 637 |
+
"eval_samples_per_second": 99.47,
|
| 638 |
+
"eval_steps_per_second": 3.23,
|
| 639 |
+
"step": 783
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 18.16,
|
| 643 |
+
"learning_rate": 2.153316106804479e-05,
|
| 644 |
+
"loss": 0.0461,
|
| 645 |
+
"step": 790
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 18.39,
|
| 649 |
+
"learning_rate": 2.1102497846683894e-05,
|
| 650 |
+
"loss": 0.044,
|
| 651 |
+
"step": 800
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 18.62,
|
| 655 |
+
"learning_rate": 2.0671834625323e-05,
|
| 656 |
+
"loss": 0.0474,
|
| 657 |
+
"step": 810
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 18.85,
|
| 661 |
+
"learning_rate": 2.0241171403962104e-05,
|
| 662 |
+
"loss": 0.0512,
|
| 663 |
+
"step": 820
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 18.99,
|
| 667 |
+
"eval_accuracy": 0.9318181818181818,
|
| 668 |
+
"eval_loss": 0.24004700779914856,
|
| 669 |
+
"eval_runtime": 6.4994,
|
| 670 |
+
"eval_samples_per_second": 94.777,
|
| 671 |
+
"eval_steps_per_second": 3.077,
|
| 672 |
+
"step": 826
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 19.08,
|
| 676 |
+
"learning_rate": 1.9810508182601206e-05,
|
| 677 |
+
"loss": 0.056,
|
| 678 |
+
"step": 830
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 19.31,
|
| 682 |
+
"learning_rate": 1.937984496124031e-05,
|
| 683 |
+
"loss": 0.0527,
|
| 684 |
+
"step": 840
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 19.54,
|
| 688 |
+
"learning_rate": 1.8949181739879416e-05,
|
| 689 |
+
"loss": 0.0282,
|
| 690 |
+
"step": 850
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 19.77,
|
| 694 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 695 |
+
"loss": 0.0486,
|
| 696 |
+
"step": 860
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 20.0,
|
| 700 |
+
"learning_rate": 1.8087855297157624e-05,
|
| 701 |
+
"loss": 0.041,
|
| 702 |
+
"step": 870
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 20.0,
|
| 706 |
+
"eval_accuracy": 0.9285714285714286,
|
| 707 |
+
"eval_loss": 0.23969942331314087,
|
| 708 |
+
"eval_runtime": 6.4042,
|
| 709 |
+
"eval_samples_per_second": 96.187,
|
| 710 |
+
"eval_steps_per_second": 3.123,
|
| 711 |
+
"step": 870
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 20.23,
|
| 715 |
+
"learning_rate": 1.765719207579673e-05,
|
| 716 |
+
"loss": 0.0347,
|
| 717 |
+
"step": 880
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 20.46,
|
| 721 |
+
"learning_rate": 1.7226528854435834e-05,
|
| 722 |
+
"loss": 0.0523,
|
| 723 |
+
"step": 890
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 20.69,
|
| 727 |
+
"learning_rate": 1.6795865633074936e-05,
|
| 728 |
+
"loss": 0.0334,
|
| 729 |
+
"step": 900
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 20.92,
|
| 733 |
+
"learning_rate": 1.636520241171404e-05,
|
| 734 |
+
"loss": 0.0376,
|
| 735 |
+
"step": 910
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 20.99,
|
| 739 |
+
"eval_accuracy": 0.926948051948052,
|
| 740 |
+
"eval_loss": 0.26630115509033203,
|
| 741 |
+
"eval_runtime": 6.6399,
|
| 742 |
+
"eval_samples_per_second": 92.772,
|
| 743 |
+
"eval_steps_per_second": 3.012,
|
| 744 |
+
"step": 913
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 21.15,
|
| 748 |
+
"learning_rate": 1.5934539190353146e-05,
|
| 749 |
+
"loss": 0.0334,
|
| 750 |
+
"step": 920
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 21.38,
|
| 754 |
+
"learning_rate": 1.5503875968992248e-05,
|
| 755 |
+
"loss": 0.042,
|
| 756 |
+
"step": 930
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 21.61,
|
| 760 |
+
"learning_rate": 1.5073212747631352e-05,
|
| 761 |
+
"loss": 0.0444,
|
| 762 |
+
"step": 940
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 21.84,
|
| 766 |
+
"learning_rate": 1.4642549526270457e-05,
|
| 767 |
+
"loss": 0.0412,
|
| 768 |
+
"step": 950
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 22.0,
|
| 772 |
+
"eval_accuracy": 0.922077922077922,
|
| 773 |
+
"eval_loss": 0.3025703430175781,
|
| 774 |
+
"eval_runtime": 6.5146,
|
| 775 |
+
"eval_samples_per_second": 94.556,
|
| 776 |
+
"eval_steps_per_second": 3.07,
|
| 777 |
+
"step": 957
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 22.07,
|
| 781 |
+
"learning_rate": 1.421188630490956e-05,
|
| 782 |
+
"loss": 0.0321,
|
| 783 |
+
"step": 960
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 22.3,
|
| 787 |
+
"learning_rate": 1.3781223083548666e-05,
|
| 788 |
+
"loss": 0.0383,
|
| 789 |
+
"step": 970
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 22.53,
|
| 793 |
+
"learning_rate": 1.335055986218777e-05,
|
| 794 |
+
"loss": 0.027,
|
| 795 |
+
"step": 980
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 22.76,
|
| 799 |
+
"learning_rate": 1.2919896640826873e-05,
|
| 800 |
+
"loss": 0.0446,
|
| 801 |
+
"step": 990
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 22.99,
|
| 805 |
+
"learning_rate": 1.2489233419465978e-05,
|
| 806 |
+
"loss": 0.0423,
|
| 807 |
+
"step": 1000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 22.99,
|
| 811 |
+
"eval_accuracy": 0.9301948051948052,
|
| 812 |
+
"eval_loss": 0.26784056425094604,
|
| 813 |
+
"eval_runtime": 6.0495,
|
| 814 |
+
"eval_samples_per_second": 101.827,
|
| 815 |
+
"eval_steps_per_second": 3.306,
|
| 816 |
+
"step": 1000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 23.22,
|
| 820 |
+
"learning_rate": 1.2058570198105082e-05,
|
| 821 |
+
"loss": 0.0327,
|
| 822 |
+
"step": 1010
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 23.45,
|
| 826 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 827 |
+
"loss": 0.0463,
|
| 828 |
+
"step": 1020
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 23.68,
|
| 832 |
+
"learning_rate": 1.119724375538329e-05,
|
| 833 |
+
"loss": 0.0314,
|
| 834 |
+
"step": 1030
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 23.91,
|
| 838 |
+
"learning_rate": 1.0766580534022396e-05,
|
| 839 |
+
"loss": 0.0266,
|
| 840 |
+
"step": 1040
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 24.0,
|
| 844 |
+
"eval_accuracy": 0.9318181818181818,
|
| 845 |
+
"eval_loss": 0.25100043416023254,
|
| 846 |
+
"eval_runtime": 6.0247,
|
| 847 |
+
"eval_samples_per_second": 102.246,
|
| 848 |
+
"eval_steps_per_second": 3.32,
|
| 849 |
+
"step": 1044
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 24.14,
|
| 853 |
+
"learning_rate": 1.03359173126615e-05,
|
| 854 |
+
"loss": 0.0257,
|
| 855 |
+
"step": 1050
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 24.37,
|
| 859 |
+
"learning_rate": 9.905254091300603e-06,
|
| 860 |
+
"loss": 0.0292,
|
| 861 |
+
"step": 1060
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 24.6,
|
| 865 |
+
"learning_rate": 9.474590869939708e-06,
|
| 866 |
+
"loss": 0.0329,
|
| 867 |
+
"step": 1070
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 24.83,
|
| 871 |
+
"learning_rate": 9.043927648578812e-06,
|
| 872 |
+
"loss": 0.0313,
|
| 873 |
+
"step": 1080
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 24.99,
|
| 877 |
+
"eval_accuracy": 0.9334415584415584,
|
| 878 |
+
"eval_loss": 0.2541840672492981,
|
| 879 |
+
"eval_runtime": 6.4751,
|
| 880 |
+
"eval_samples_per_second": 95.134,
|
| 881 |
+
"eval_steps_per_second": 3.089,
|
| 882 |
+
"step": 1087
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 25.06,
|
| 886 |
+
"learning_rate": 8.613264427217917e-06,
|
| 887 |
+
"loss": 0.0178,
|
| 888 |
+
"step": 1090
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 25.29,
|
| 892 |
+
"learning_rate": 8.18260120585702e-06,
|
| 893 |
+
"loss": 0.0189,
|
| 894 |
+
"step": 1100
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 25.52,
|
| 898 |
+
"learning_rate": 7.751937984496124e-06,
|
| 899 |
+
"loss": 0.0399,
|
| 900 |
+
"step": 1110
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 25.75,
|
| 904 |
+
"learning_rate": 7.3212747631352285e-06,
|
| 905 |
+
"loss": 0.0269,
|
| 906 |
+
"step": 1120
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 25.98,
|
| 910 |
+
"learning_rate": 6.890611541774333e-06,
|
| 911 |
+
"loss": 0.0207,
|
| 912 |
+
"step": 1130
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 26.0,
|
| 916 |
+
"eval_accuracy": 0.9334415584415584,
|
| 917 |
+
"eval_loss": 0.2742658257484436,
|
| 918 |
+
"eval_runtime": 6.484,
|
| 919 |
+
"eval_samples_per_second": 95.003,
|
| 920 |
+
"eval_steps_per_second": 3.084,
|
| 921 |
+
"step": 1131
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 26.21,
|
| 925 |
+
"learning_rate": 6.4599483204134365e-06,
|
| 926 |
+
"loss": 0.0412,
|
| 927 |
+
"step": 1140
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 26.44,
|
| 931 |
+
"learning_rate": 6.029285099052541e-06,
|
| 932 |
+
"loss": 0.0271,
|
| 933 |
+
"step": 1150
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 26.67,
|
| 937 |
+
"learning_rate": 5.598621877691645e-06,
|
| 938 |
+
"loss": 0.0268,
|
| 939 |
+
"step": 1160
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 26.9,
|
| 943 |
+
"learning_rate": 5.16795865633075e-06,
|
| 944 |
+
"loss": 0.0292,
|
| 945 |
+
"step": 1170
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 26.99,
|
| 949 |
+
"eval_accuracy": 0.9318181818181818,
|
| 950 |
+
"eval_loss": 0.2614338994026184,
|
| 951 |
+
"eval_runtime": 6.1763,
|
| 952 |
+
"eval_samples_per_second": 99.736,
|
| 953 |
+
"eval_steps_per_second": 3.238,
|
| 954 |
+
"step": 1174
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 27.13,
|
| 958 |
+
"learning_rate": 4.737295434969854e-06,
|
| 959 |
+
"loss": 0.0248,
|
| 960 |
+
"step": 1180
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 27.36,
|
| 964 |
+
"learning_rate": 4.3066322136089585e-06,
|
| 965 |
+
"loss": 0.0329,
|
| 966 |
+
"step": 1190
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 27.59,
|
| 970 |
+
"learning_rate": 3.875968992248062e-06,
|
| 971 |
+
"loss": 0.0307,
|
| 972 |
+
"step": 1200
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 27.82,
|
| 976 |
+
"learning_rate": 3.4453057708871665e-06,
|
| 977 |
+
"loss": 0.0242,
|
| 978 |
+
"step": 1210
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 28.0,
|
| 982 |
+
"eval_accuracy": 0.9383116883116883,
|
| 983 |
+
"eval_loss": 0.24687811732292175,
|
| 984 |
+
"eval_runtime": 5.9381,
|
| 985 |
+
"eval_samples_per_second": 103.737,
|
| 986 |
+
"eval_steps_per_second": 3.368,
|
| 987 |
+
"step": 1218
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 28.05,
|
| 991 |
+
"learning_rate": 3.0146425495262704e-06,
|
| 992 |
+
"loss": 0.0295,
|
| 993 |
+
"step": 1220
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 28.28,
|
| 997 |
+
"learning_rate": 2.583979328165375e-06,
|
| 998 |
+
"loss": 0.0161,
|
| 999 |
+
"step": 1230
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 28.51,
|
| 1003 |
+
"learning_rate": 2.1533161068044793e-06,
|
| 1004 |
+
"loss": 0.034,
|
| 1005 |
+
"step": 1240
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 28.74,
|
| 1009 |
+
"learning_rate": 1.7226528854435832e-06,
|
| 1010 |
+
"loss": 0.0247,
|
| 1011 |
+
"step": 1250
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 28.97,
|
| 1015 |
+
"learning_rate": 1.2919896640826874e-06,
|
| 1016 |
+
"loss": 0.0201,
|
| 1017 |
+
"step": 1260
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 28.99,
|
| 1021 |
+
"eval_accuracy": 0.9366883116883117,
|
| 1022 |
+
"eval_loss": 0.2533850371837616,
|
| 1023 |
+
"eval_runtime": 6.3893,
|
| 1024 |
+
"eval_samples_per_second": 96.411,
|
| 1025 |
+
"eval_steps_per_second": 3.13,
|
| 1026 |
+
"step": 1261
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 29.2,
|
| 1030 |
+
"learning_rate": 8.613264427217916e-07,
|
| 1031 |
+
"loss": 0.0262,
|
| 1032 |
+
"step": 1270
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 29.43,
|
| 1036 |
+
"learning_rate": 4.306632213608958e-07,
|
| 1037 |
+
"loss": 0.0226,
|
| 1038 |
+
"step": 1280
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 29.66,
|
| 1042 |
+
"learning_rate": 0.0,
|
| 1043 |
+
"loss": 0.0354,
|
| 1044 |
+
"step": 1290
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 29.66,
|
| 1048 |
+
"eval_accuracy": 0.9366883116883117,
|
| 1049 |
+
"eval_loss": 0.2525167465209961,
|
| 1050 |
+
"eval_runtime": 6.455,
|
| 1051 |
+
"eval_samples_per_second": 95.43,
|
| 1052 |
+
"eval_steps_per_second": 3.098,
|
| 1053 |
+
"step": 1290
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 29.66,
|
| 1057 |
+
"step": 1290,
|
| 1058 |
+
"total_flos": 4.0838875031628657e+18,
|
| 1059 |
+
"train_loss": 0.17642173106356185,
|
| 1060 |
+
"train_runtime": 3123.2223,
|
| 1061 |
+
"train_samples_per_second": 53.205,
|
| 1062 |
+
"train_steps_per_second": 0.413
|
| 1063 |
}
|
| 1064 |
],
|
| 1065 |
"logging_steps": 10,
|
| 1066 |
+
"max_steps": 1290,
|
| 1067 |
"num_input_tokens_seen": 0,
|
| 1068 |
+
"num_train_epochs": 30,
|
| 1069 |
"save_steps": 500,
|
| 1070 |
+
"total_flos": 4.0838875031628657e+18,
|
| 1071 |
"train_batch_size": 32,
|
| 1072 |
"trial_name": null,
|
| 1073 |
"trial_params": null
|