End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec03_20-45-15_DESKTOP-SKBE9FB/events.out.tfevents.1733282194.DESKTOP-SKBE9FB.16984.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +717 -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: 0.9032258064516129
|
| 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: 0.3226
|
| 36 |
+
- Accuracy: 0.9032
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.62,
|
| 3 |
+
"eval_accuracy": 0.9032258064516129,
|
| 4 |
+
"eval_loss": 0.3226192891597748,
|
| 5 |
+
"eval_runtime": 2.5527,
|
| 6 |
+
"eval_samples_per_second": 24.288,
|
| 7 |
+
"eval_steps_per_second": 1.567,
|
| 8 |
+
"train_loss": 0.24997490516730717,
|
| 9 |
+
"train_runtime": 1716.8626,
|
| 10 |
+
"train_samples_per_second": 21.621,
|
| 11 |
+
"train_steps_per_second": 0.326
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.62,
|
| 3 |
+
"eval_accuracy": 0.9032258064516129,
|
| 4 |
+
"eval_loss": 0.3226192891597748,
|
| 5 |
+
"eval_runtime": 2.5527,
|
| 6 |
+
"eval_samples_per_second": 24.288,
|
| 7 |
+
"eval_steps_per_second": 1.567
|
| 8 |
+
}
|
runs/Dec03_20-45-15_DESKTOP-SKBE9FB/events.out.tfevents.1733282194.DESKTOP-SKBE9FB.16984.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa897d6e96fdb2e6e50db98d1abf7abe8e7511e774f19390fa45be7f35b2c7c0
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.62,
|
| 3 |
+
"train_loss": 0.24997490516730717,
|
| 4 |
+
"train_runtime": 1716.8626,
|
| 5 |
+
"train_samples_per_second": 21.621,
|
| 6 |
+
"train_steps_per_second": 0.326
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,717 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9032258064516129,
|
| 3 |
+
"best_model_checkpoint": "BEiT-TO-DA\\checkpoint-116",
|
| 4 |
+
"epoch": 38.62068965517241,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 560,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.69,
|
| 13 |
+
"learning_rate": 4.910714285714286e-05,
|
| 14 |
+
"loss": 1.5028,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.97,
|
| 19 |
+
"eval_accuracy": 0.14516129032258066,
|
| 20 |
+
"eval_loss": 1.3862112760543823,
|
| 21 |
+
"eval_runtime": 2.2297,
|
| 22 |
+
"eval_samples_per_second": 27.806,
|
| 23 |
+
"eval_steps_per_second": 1.794,
|
| 24 |
+
"step": 14
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.38,
|
| 28 |
+
"learning_rate": 4.8214285714285716e-05,
|
| 29 |
+
"loss": 1.3358,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.8064516129032258,
|
| 35 |
+
"eval_loss": 1.0830727815628052,
|
| 36 |
+
"eval_runtime": 2.045,
|
| 37 |
+
"eval_samples_per_second": 30.318,
|
| 38 |
+
"eval_steps_per_second": 1.956,
|
| 39 |
+
"step": 29
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.07,
|
| 43 |
+
"learning_rate": 4.732142857142857e-05,
|
| 44 |
+
"loss": 1.1346,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.76,
|
| 49 |
+
"learning_rate": 4.642857142857143e-05,
|
| 50 |
+
"loss": 0.8919,
|
| 51 |
+
"step": 40
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.97,
|
| 55 |
+
"eval_accuracy": 0.8225806451612904,
|
| 56 |
+
"eval_loss": 0.8097184300422668,
|
| 57 |
+
"eval_runtime": 1.9686,
|
| 58 |
+
"eval_samples_per_second": 31.495,
|
| 59 |
+
"eval_steps_per_second": 2.032,
|
| 60 |
+
"step": 43
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.45,
|
| 64 |
+
"learning_rate": 4.5535714285714286e-05,
|
| 65 |
+
"loss": 0.7328,
|
| 66 |
+
"step": 50
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"eval_accuracy": 0.7741935483870968,
|
| 71 |
+
"eval_loss": 0.6545600891113281,
|
| 72 |
+
"eval_runtime": 2.0425,
|
| 73 |
+
"eval_samples_per_second": 30.355,
|
| 74 |
+
"eval_steps_per_second": 1.958,
|
| 75 |
+
"step": 58
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.14,
|
| 79 |
+
"learning_rate": 4.464285714285715e-05,
|
| 80 |
+
"loss": 0.6079,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 4.83,
|
| 85 |
+
"learning_rate": 4.375e-05,
|
| 86 |
+
"loss": 0.4881,
|
| 87 |
+
"step": 70
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.97,
|
| 91 |
+
"eval_accuracy": 0.8225806451612904,
|
| 92 |
+
"eval_loss": 0.4860498309135437,
|
| 93 |
+
"eval_runtime": 1.9434,
|
| 94 |
+
"eval_samples_per_second": 31.902,
|
| 95 |
+
"eval_steps_per_second": 2.058,
|
| 96 |
+
"step": 72
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.52,
|
| 100 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 101 |
+
"loss": 0.4367,
|
| 102 |
+
"step": 80
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 6.0,
|
| 106 |
+
"eval_accuracy": 0.8548387096774194,
|
| 107 |
+
"eval_loss": 0.47702911496162415,
|
| 108 |
+
"eval_runtime": 2.1423,
|
| 109 |
+
"eval_samples_per_second": 28.94,
|
| 110 |
+
"eval_steps_per_second": 1.867,
|
| 111 |
+
"step": 87
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.21,
|
| 115 |
+
"learning_rate": 4.196428571428572e-05,
|
| 116 |
+
"loss": 0.3971,
|
| 117 |
+
"step": 90
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.9,
|
| 121 |
+
"learning_rate": 4.107142857142857e-05,
|
| 122 |
+
"loss": 0.3343,
|
| 123 |
+
"step": 100
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.97,
|
| 127 |
+
"eval_accuracy": 0.8548387096774194,
|
| 128 |
+
"eval_loss": 0.39124295115470886,
|
| 129 |
+
"eval_runtime": 2.085,
|
| 130 |
+
"eval_samples_per_second": 29.736,
|
| 131 |
+
"eval_steps_per_second": 1.918,
|
| 132 |
+
"step": 101
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 7.59,
|
| 136 |
+
"learning_rate": 4.017857142857143e-05,
|
| 137 |
+
"loss": 0.2794,
|
| 138 |
+
"step": 110
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 8.0,
|
| 142 |
+
"eval_accuracy": 0.9032258064516129,
|
| 143 |
+
"eval_loss": 0.3226192891597748,
|
| 144 |
+
"eval_runtime": 2.0791,
|
| 145 |
+
"eval_samples_per_second": 29.821,
|
| 146 |
+
"eval_steps_per_second": 1.924,
|
| 147 |
+
"step": 116
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.28,
|
| 151 |
+
"learning_rate": 3.928571428571429e-05,
|
| 152 |
+
"loss": 0.2586,
|
| 153 |
+
"step": 120
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 8.97,
|
| 157 |
+
"learning_rate": 3.839285714285715e-05,
|
| 158 |
+
"loss": 0.2424,
|
| 159 |
+
"step": 130
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.97,
|
| 163 |
+
"eval_accuracy": 0.7903225806451613,
|
| 164 |
+
"eval_loss": 0.6426439881324768,
|
| 165 |
+
"eval_runtime": 2.129,
|
| 166 |
+
"eval_samples_per_second": 29.122,
|
| 167 |
+
"eval_steps_per_second": 1.879,
|
| 168 |
+
"step": 130
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.66,
|
| 172 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 173 |
+
"loss": 0.2875,
|
| 174 |
+
"step": 140
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.0,
|
| 178 |
+
"eval_accuracy": 0.8709677419354839,
|
| 179 |
+
"eval_loss": 0.4603542685508728,
|
| 180 |
+
"eval_runtime": 2.0375,
|
| 181 |
+
"eval_samples_per_second": 30.429,
|
| 182 |
+
"eval_steps_per_second": 1.963,
|
| 183 |
+
"step": 145
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 10.34,
|
| 187 |
+
"learning_rate": 3.6607142857142853e-05,
|
| 188 |
+
"loss": 0.226,
|
| 189 |
+
"step": 150
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.97,
|
| 193 |
+
"eval_accuracy": 0.8548387096774194,
|
| 194 |
+
"eval_loss": 0.3026295006275177,
|
| 195 |
+
"eval_runtime": 1.9845,
|
| 196 |
+
"eval_samples_per_second": 31.243,
|
| 197 |
+
"eval_steps_per_second": 2.016,
|
| 198 |
+
"step": 159
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 11.03,
|
| 202 |
+
"learning_rate": 3.571428571428572e-05,
|
| 203 |
+
"loss": 0.2307,
|
| 204 |
+
"step": 160
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 11.72,
|
| 208 |
+
"learning_rate": 3.4821428571428574e-05,
|
| 209 |
+
"loss": 0.1819,
|
| 210 |
+
"step": 170
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 12.0,
|
| 214 |
+
"eval_accuracy": 0.8709677419354839,
|
| 215 |
+
"eval_loss": 0.3874911963939667,
|
| 216 |
+
"eval_runtime": 2.167,
|
| 217 |
+
"eval_samples_per_second": 28.611,
|
| 218 |
+
"eval_steps_per_second": 1.846,
|
| 219 |
+
"step": 174
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.41,
|
| 223 |
+
"learning_rate": 3.392857142857143e-05,
|
| 224 |
+
"loss": 0.2354,
|
| 225 |
+
"step": 180
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.97,
|
| 229 |
+
"eval_accuracy": 0.9032258064516129,
|
| 230 |
+
"eval_loss": 0.3412918746471405,
|
| 231 |
+
"eval_runtime": 1.943,
|
| 232 |
+
"eval_samples_per_second": 31.91,
|
| 233 |
+
"eval_steps_per_second": 2.059,
|
| 234 |
+
"step": 188
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 13.1,
|
| 238 |
+
"learning_rate": 3.303571428571429e-05,
|
| 239 |
+
"loss": 0.1651,
|
| 240 |
+
"step": 190
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 13.79,
|
| 244 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 245 |
+
"loss": 0.2264,
|
| 246 |
+
"step": 200
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 14.0,
|
| 250 |
+
"eval_accuracy": 0.8870967741935484,
|
| 251 |
+
"eval_loss": 0.3948277235031128,
|
| 252 |
+
"eval_runtime": 2.0535,
|
| 253 |
+
"eval_samples_per_second": 30.193,
|
| 254 |
+
"eval_steps_per_second": 1.948,
|
| 255 |
+
"step": 203
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 14.48,
|
| 259 |
+
"learning_rate": 3.125e-05,
|
| 260 |
+
"loss": 0.1652,
|
| 261 |
+
"step": 210
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 14.97,
|
| 265 |
+
"eval_accuracy": 0.8709677419354839,
|
| 266 |
+
"eval_loss": 0.36500856280326843,
|
| 267 |
+
"eval_runtime": 1.978,
|
| 268 |
+
"eval_samples_per_second": 31.345,
|
| 269 |
+
"eval_steps_per_second": 2.022,
|
| 270 |
+
"step": 217
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 15.17,
|
| 274 |
+
"learning_rate": 3.0357142857142857e-05,
|
| 275 |
+
"loss": 0.1601,
|
| 276 |
+
"step": 220
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 15.86,
|
| 280 |
+
"learning_rate": 2.9464285714285718e-05,
|
| 281 |
+
"loss": 0.1449,
|
| 282 |
+
"step": 230
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 16.0,
|
| 286 |
+
"eval_accuracy": 0.8870967741935484,
|
| 287 |
+
"eval_loss": 0.3610541820526123,
|
| 288 |
+
"eval_runtime": 2.1646,
|
| 289 |
+
"eval_samples_per_second": 28.643,
|
| 290 |
+
"eval_steps_per_second": 1.848,
|
| 291 |
+
"step": 232
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 16.55,
|
| 295 |
+
"learning_rate": 2.857142857142857e-05,
|
| 296 |
+
"loss": 0.0993,
|
| 297 |
+
"step": 240
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 16.97,
|
| 301 |
+
"eval_accuracy": 0.8709677419354839,
|
| 302 |
+
"eval_loss": 0.4573518931865692,
|
| 303 |
+
"eval_runtime": 1.9815,
|
| 304 |
+
"eval_samples_per_second": 31.29,
|
| 305 |
+
"eval_steps_per_second": 2.019,
|
| 306 |
+
"step": 246
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 17.24,
|
| 310 |
+
"learning_rate": 2.767857142857143e-05,
|
| 311 |
+
"loss": 0.1642,
|
| 312 |
+
"step": 250
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 17.93,
|
| 316 |
+
"learning_rate": 2.6785714285714288e-05,
|
| 317 |
+
"loss": 0.1566,
|
| 318 |
+
"step": 260
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 18.0,
|
| 322 |
+
"eval_accuracy": 0.8870967741935484,
|
| 323 |
+
"eval_loss": 0.3923678696155548,
|
| 324 |
+
"eval_runtime": 2.043,
|
| 325 |
+
"eval_samples_per_second": 30.348,
|
| 326 |
+
"eval_steps_per_second": 1.958,
|
| 327 |
+
"step": 261
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 18.62,
|
| 331 |
+
"learning_rate": 2.5892857142857148e-05,
|
| 332 |
+
"loss": 0.1399,
|
| 333 |
+
"step": 270
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 18.97,
|
| 337 |
+
"eval_accuracy": 0.8548387096774194,
|
| 338 |
+
"eval_loss": 0.48281946778297424,
|
| 339 |
+
"eval_runtime": 2.0105,
|
| 340 |
+
"eval_samples_per_second": 30.838,
|
| 341 |
+
"eval_steps_per_second": 1.99,
|
| 342 |
+
"step": 275
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 19.31,
|
| 346 |
+
"learning_rate": 2.5e-05,
|
| 347 |
+
"loss": 0.1659,
|
| 348 |
+
"step": 280
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 20.0,
|
| 352 |
+
"learning_rate": 2.4107142857142858e-05,
|
| 353 |
+
"loss": 0.1025,
|
| 354 |
+
"step": 290
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 20.0,
|
| 358 |
+
"eval_accuracy": 0.8709677419354839,
|
| 359 |
+
"eval_loss": 0.5376753807067871,
|
| 360 |
+
"eval_runtime": 2.1678,
|
| 361 |
+
"eval_samples_per_second": 28.601,
|
| 362 |
+
"eval_steps_per_second": 1.845,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 20.69,
|
| 367 |
+
"learning_rate": 2.3214285714285715e-05,
|
| 368 |
+
"loss": 0.0855,
|
| 369 |
+
"step": 300
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 20.97,
|
| 373 |
+
"eval_accuracy": 0.8548387096774194,
|
| 374 |
+
"eval_loss": 0.4958372414112091,
|
| 375 |
+
"eval_runtime": 2.035,
|
| 376 |
+
"eval_samples_per_second": 30.467,
|
| 377 |
+
"eval_steps_per_second": 1.966,
|
| 378 |
+
"step": 304
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 21.38,
|
| 382 |
+
"learning_rate": 2.2321428571428575e-05,
|
| 383 |
+
"loss": 0.1419,
|
| 384 |
+
"step": 310
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 22.0,
|
| 388 |
+
"eval_accuracy": 0.8387096774193549,
|
| 389 |
+
"eval_loss": 0.6155916452407837,
|
| 390 |
+
"eval_runtime": 2.099,
|
| 391 |
+
"eval_samples_per_second": 29.538,
|
| 392 |
+
"eval_steps_per_second": 1.906,
|
| 393 |
+
"step": 319
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 22.07,
|
| 397 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 398 |
+
"loss": 0.1266,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 22.76,
|
| 403 |
+
"learning_rate": 2.0535714285714285e-05,
|
| 404 |
+
"loss": 0.117,
|
| 405 |
+
"step": 330
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 22.97,
|
| 409 |
+
"eval_accuracy": 0.8709677419354839,
|
| 410 |
+
"eval_loss": 0.4914974272251129,
|
| 411 |
+
"eval_runtime": 2.0475,
|
| 412 |
+
"eval_samples_per_second": 30.281,
|
| 413 |
+
"eval_steps_per_second": 1.954,
|
| 414 |
+
"step": 333
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 23.45,
|
| 418 |
+
"learning_rate": 1.9642857142857145e-05,
|
| 419 |
+
"loss": 0.0905,
|
| 420 |
+
"step": 340
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 24.0,
|
| 424 |
+
"eval_accuracy": 0.8709677419354839,
|
| 425 |
+
"eval_loss": 0.5896703600883484,
|
| 426 |
+
"eval_runtime": 2.111,
|
| 427 |
+
"eval_samples_per_second": 29.37,
|
| 428 |
+
"eval_steps_per_second": 1.895,
|
| 429 |
+
"step": 348
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 24.14,
|
| 433 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 434 |
+
"loss": 0.1049,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 24.83,
|
| 439 |
+
"learning_rate": 1.785714285714286e-05,
|
| 440 |
+
"loss": 0.1199,
|
| 441 |
+
"step": 360
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 24.97,
|
| 445 |
+
"eval_accuracy": 0.8709677419354839,
|
| 446 |
+
"eval_loss": 0.4870842695236206,
|
| 447 |
+
"eval_runtime": 2.0015,
|
| 448 |
+
"eval_samples_per_second": 30.977,
|
| 449 |
+
"eval_steps_per_second": 1.999,
|
| 450 |
+
"step": 362
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 25.52,
|
| 454 |
+
"learning_rate": 1.6964285714285715e-05,
|
| 455 |
+
"loss": 0.1246,
|
| 456 |
+
"step": 370
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 26.0,
|
| 460 |
+
"eval_accuracy": 0.8548387096774194,
|
| 461 |
+
"eval_loss": 0.4824499189853668,
|
| 462 |
+
"eval_runtime": 2.0932,
|
| 463 |
+
"eval_samples_per_second": 29.619,
|
| 464 |
+
"eval_steps_per_second": 1.911,
|
| 465 |
+
"step": 377
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 26.21,
|
| 469 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 470 |
+
"loss": 0.1051,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 26.9,
|
| 475 |
+
"learning_rate": 1.5178571428571429e-05,
|
| 476 |
+
"loss": 0.0967,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 26.97,
|
| 481 |
+
"eval_accuracy": 0.8064516129032258,
|
| 482 |
+
"eval_loss": 0.7483570575714111,
|
| 483 |
+
"eval_runtime": 2.0485,
|
| 484 |
+
"eval_samples_per_second": 30.266,
|
| 485 |
+
"eval_steps_per_second": 1.953,
|
| 486 |
+
"step": 391
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 27.59,
|
| 490 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 491 |
+
"loss": 0.1025,
|
| 492 |
+
"step": 400
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 28.0,
|
| 496 |
+
"eval_accuracy": 0.8387096774193549,
|
| 497 |
+
"eval_loss": 0.6973522901535034,
|
| 498 |
+
"eval_runtime": 2.0675,
|
| 499 |
+
"eval_samples_per_second": 29.988,
|
| 500 |
+
"eval_steps_per_second": 1.935,
|
| 501 |
+
"step": 406
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 28.28,
|
| 505 |
+
"learning_rate": 1.3392857142857144e-05,
|
| 506 |
+
"loss": 0.0955,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 28.97,
|
| 511 |
+
"learning_rate": 1.25e-05,
|
| 512 |
+
"loss": 0.1112,
|
| 513 |
+
"step": 420
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 28.97,
|
| 517 |
+
"eval_accuracy": 0.8225806451612904,
|
| 518 |
+
"eval_loss": 0.6391315460205078,
|
| 519 |
+
"eval_runtime": 2.0205,
|
| 520 |
+
"eval_samples_per_second": 30.686,
|
| 521 |
+
"eval_steps_per_second": 1.98,
|
| 522 |
+
"step": 420
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 29.66,
|
| 526 |
+
"learning_rate": 1.1607142857142857e-05,
|
| 527 |
+
"loss": 0.0715,
|
| 528 |
+
"step": 430
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 30.0,
|
| 532 |
+
"eval_accuracy": 0.8225806451612904,
|
| 533 |
+
"eval_loss": 0.6585091948509216,
|
| 534 |
+
"eval_runtime": 2.0845,
|
| 535 |
+
"eval_samples_per_second": 29.744,
|
| 536 |
+
"eval_steps_per_second": 1.919,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 30.34,
|
| 541 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 542 |
+
"loss": 0.085,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 30.97,
|
| 547 |
+
"eval_accuracy": 0.8064516129032258,
|
| 548 |
+
"eval_loss": 0.7087302207946777,
|
| 549 |
+
"eval_runtime": 2.3831,
|
| 550 |
+
"eval_samples_per_second": 26.017,
|
| 551 |
+
"eval_steps_per_second": 1.678,
|
| 552 |
+
"step": 449
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 31.03,
|
| 556 |
+
"learning_rate": 9.821428571428573e-06,
|
| 557 |
+
"loss": 0.0707,
|
| 558 |
+
"step": 450
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 31.72,
|
| 562 |
+
"learning_rate": 8.92857142857143e-06,
|
| 563 |
+
"loss": 0.1032,
|
| 564 |
+
"step": 460
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 32.0,
|
| 568 |
+
"eval_accuracy": 0.8387096774193549,
|
| 569 |
+
"eval_loss": 0.6093763113021851,
|
| 570 |
+
"eval_runtime": 2.041,
|
| 571 |
+
"eval_samples_per_second": 30.377,
|
| 572 |
+
"eval_steps_per_second": 1.96,
|
| 573 |
+
"step": 464
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 32.41,
|
| 577 |
+
"learning_rate": 8.035714285714286e-06,
|
| 578 |
+
"loss": 0.0836,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 32.97,
|
| 583 |
+
"eval_accuracy": 0.8064516129032258,
|
| 584 |
+
"eval_loss": 0.5578293204307556,
|
| 585 |
+
"eval_runtime": 2.0097,
|
| 586 |
+
"eval_samples_per_second": 30.85,
|
| 587 |
+
"eval_steps_per_second": 1.99,
|
| 588 |
+
"step": 478
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 33.1,
|
| 592 |
+
"learning_rate": 7.142857142857143e-06,
|
| 593 |
+
"loss": 0.1029,
|
| 594 |
+
"step": 480
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 33.79,
|
| 598 |
+
"learning_rate": 6.25e-06,
|
| 599 |
+
"loss": 0.0716,
|
| 600 |
+
"step": 490
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 34.0,
|
| 604 |
+
"eval_accuracy": 0.8709677419354839,
|
| 605 |
+
"eval_loss": 0.5497013330459595,
|
| 606 |
+
"eval_runtime": 2.0935,
|
| 607 |
+
"eval_samples_per_second": 29.615,
|
| 608 |
+
"eval_steps_per_second": 1.911,
|
| 609 |
+
"step": 493
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 34.48,
|
| 613 |
+
"learning_rate": 5.357142857142857e-06,
|
| 614 |
+
"loss": 0.069,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 34.97,
|
| 619 |
+
"eval_accuracy": 0.8709677419354839,
|
| 620 |
+
"eval_loss": 0.5093409419059753,
|
| 621 |
+
"eval_runtime": 2.0105,
|
| 622 |
+
"eval_samples_per_second": 30.839,
|
| 623 |
+
"eval_steps_per_second": 1.99,
|
| 624 |
+
"step": 507
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 35.17,
|
| 628 |
+
"learning_rate": 4.464285714285715e-06,
|
| 629 |
+
"loss": 0.0719,
|
| 630 |
+
"step": 510
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 35.86,
|
| 634 |
+
"learning_rate": 3.5714285714285714e-06,
|
| 635 |
+
"loss": 0.0577,
|
| 636 |
+
"step": 520
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 36.0,
|
| 640 |
+
"eval_accuracy": 0.8709677419354839,
|
| 641 |
+
"eval_loss": 0.5188572406768799,
|
| 642 |
+
"eval_runtime": 2.0901,
|
| 643 |
+
"eval_samples_per_second": 29.663,
|
| 644 |
+
"eval_steps_per_second": 1.914,
|
| 645 |
+
"step": 522
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 36.55,
|
| 649 |
+
"learning_rate": 2.6785714285714285e-06,
|
| 650 |
+
"loss": 0.0882,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 36.97,
|
| 655 |
+
"eval_accuracy": 0.8225806451612904,
|
| 656 |
+
"eval_loss": 0.6530526280403137,
|
| 657 |
+
"eval_runtime": 2.0785,
|
| 658 |
+
"eval_samples_per_second": 29.829,
|
| 659 |
+
"eval_steps_per_second": 1.924,
|
| 660 |
+
"step": 536
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 37.24,
|
| 664 |
+
"learning_rate": 1.7857142857142857e-06,
|
| 665 |
+
"loss": 0.0673,
|
| 666 |
+
"step": 540
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 37.93,
|
| 670 |
+
"learning_rate": 8.928571428571428e-07,
|
| 671 |
+
"loss": 0.0563,
|
| 672 |
+
"step": 550
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 38.0,
|
| 676 |
+
"eval_accuracy": 0.8225806451612904,
|
| 677 |
+
"eval_loss": 0.6660893559455872,
|
| 678 |
+
"eval_runtime": 2.139,
|
| 679 |
+
"eval_samples_per_second": 28.986,
|
| 680 |
+
"eval_steps_per_second": 1.87,
|
| 681 |
+
"step": 551
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 38.62,
|
| 685 |
+
"learning_rate": 0.0,
|
| 686 |
+
"loss": 0.0841,
|
| 687 |
+
"step": 560
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 38.62,
|
| 691 |
+
"eval_accuracy": 0.8225806451612904,
|
| 692 |
+
"eval_loss": 0.6615698933601379,
|
| 693 |
+
"eval_runtime": 1.969,
|
| 694 |
+
"eval_samples_per_second": 31.489,
|
| 695 |
+
"eval_steps_per_second": 2.032,
|
| 696 |
+
"step": 560
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 38.62,
|
| 700 |
+
"step": 560,
|
| 701 |
+
"total_flos": 2.776175636329267e+18,
|
| 702 |
+
"train_loss": 0.24997490516730717,
|
| 703 |
+
"train_runtime": 1716.8626,
|
| 704 |
+
"train_samples_per_second": 21.621,
|
| 705 |
+
"train_steps_per_second": 0.326
|
| 706 |
+
}
|
| 707 |
+
],
|
| 708 |
+
"logging_steps": 10,
|
| 709 |
+
"max_steps": 560,
|
| 710 |
+
"num_input_tokens_seen": 0,
|
| 711 |
+
"num_train_epochs": 40,
|
| 712 |
+
"save_steps": 500,
|
| 713 |
+
"total_flos": 2.776175636329267e+18,
|
| 714 |
+
"train_batch_size": 16,
|
| 715 |
+
"trial_name": null,
|
| 716 |
+
"trial_params": null
|
| 717 |
+
}
|