Commit
•
1fb7dff
1
Parent(s):
6e77e59
End of training
Browse files- README.md +4 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Oct11_08-53-50_ed9849b3ed7e/events.out.tfevents.1728637083.ed9849b3ed7e.2902.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +717 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: timm/resnet18.a1_in1k
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
@@ -16,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# test-timm
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [timm/resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
- Accuracy: 0.6811
|
| 23 |
|
| 24 |
## Model description
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: timm/resnet18.a1_in1k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
|
|
|
| 18 |
|
| 19 |
# test-timm
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [timm/resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k) on the davanstrien/zenodo-presentations-open-labels dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.5247
|
| 24 |
- Accuracy: 0.6811
|
| 25 |
|
| 26 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.6811023622047244,
|
| 4 |
+
"eval_loss": 0.5247489213943481,
|
| 5 |
+
"eval_runtime": 5.1879,
|
| 6 |
+
"eval_samples_per_second": 48.96,
|
| 7 |
+
"eval_steps_per_second": 6.168,
|
| 8 |
+
"total_flos": 7.24330215447552e+16,
|
| 9 |
+
"train_loss": 0.5726550849278768,
|
| 10 |
+
"train_runtime": 239.6067,
|
| 11 |
+
"train_samples_per_second": 29.945,
|
| 12 |
+
"train_steps_per_second": 3.756
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.6811023622047244,
|
| 4 |
+
"eval_loss": 0.5247489213943481,
|
| 5 |
+
"eval_runtime": 5.1879,
|
| 6 |
+
"eval_samples_per_second": 48.96,
|
| 7 |
+
"eval_steps_per_second": 6.168
|
| 8 |
+
}
|
runs/Oct11_08-53-50_ed9849b3ed7e/events.out.tfevents.1728637083.ed9849b3ed7e.2902.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdbcd2d160c0477145debee67124f71445cd93528a81d34781e6e288bb1c306a
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 7.24330215447552e+16,
|
| 4 |
+
"train_loss": 0.5726550849278768,
|
| 5 |
+
"train_runtime": 239.6067,
|
| 6 |
+
"train_samples_per_second": 29.945,
|
| 7 |
+
"train_steps_per_second": 3.756
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,717 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5247489213943481,
|
| 3 |
+
"best_model_checkpoint": "./beans_outputs/checkpoint-720",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05555555555555555,
|
| 13 |
+
"grad_norm": 3.8575210571289062,
|
| 14 |
+
"learning_rate": 1.977777777777778e-05,
|
| 15 |
+
"loss": 0.6949,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1111111111111111,
|
| 20 |
+
"grad_norm": 3.2087113857269287,
|
| 21 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 22 |
+
"loss": 0.6848,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16666666666666666,
|
| 27 |
+
"grad_norm": 2.9537899494171143,
|
| 28 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 29 |
+
"loss": 0.6871,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2222222222222222,
|
| 34 |
+
"grad_norm": 2.586965560913086,
|
| 35 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 36 |
+
"loss": 0.6731,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2777777777777778,
|
| 41 |
+
"grad_norm": 3.3346517086029053,
|
| 42 |
+
"learning_rate": 1.888888888888889e-05,
|
| 43 |
+
"loss": 0.6728,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3333333333333333,
|
| 48 |
+
"grad_norm": 2.4391684532165527,
|
| 49 |
+
"learning_rate": 1.866666666666667e-05,
|
| 50 |
+
"loss": 0.6617,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3888888888888889,
|
| 55 |
+
"grad_norm": 1.6900883913040161,
|
| 56 |
+
"learning_rate": 1.8444444444444448e-05,
|
| 57 |
+
"loss": 0.6671,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4444444444444444,
|
| 62 |
+
"grad_norm": 2.3360586166381836,
|
| 63 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 64 |
+
"loss": 0.6341,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5,
|
| 69 |
+
"grad_norm": 2.310093641281128,
|
| 70 |
+
"learning_rate": 1.8e-05,
|
| 71 |
+
"loss": 0.6446,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5555555555555556,
|
| 76 |
+
"grad_norm": 2.071892499923706,
|
| 77 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 78 |
+
"loss": 0.6478,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6111111111111112,
|
| 83 |
+
"grad_norm": 1.9108268022537231,
|
| 84 |
+
"learning_rate": 1.7555555555555556e-05,
|
| 85 |
+
"loss": 0.6333,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6666666666666666,
|
| 90 |
+
"grad_norm": 1.8000233173370361,
|
| 91 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 92 |
+
"loss": 0.6368,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7222222222222222,
|
| 97 |
+
"grad_norm": 2.010941982269287,
|
| 98 |
+
"learning_rate": 1.7111111111111112e-05,
|
| 99 |
+
"loss": 0.6417,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7777777777777778,
|
| 104 |
+
"grad_norm": 2.502824068069458,
|
| 105 |
+
"learning_rate": 1.688888888888889e-05,
|
| 106 |
+
"loss": 0.6175,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8333333333333334,
|
| 111 |
+
"grad_norm": 2.920900821685791,
|
| 112 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 113 |
+
"loss": 0.5894,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8888888888888888,
|
| 118 |
+
"grad_norm": 2.418879985809326,
|
| 119 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 120 |
+
"loss": 0.6012,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9444444444444444,
|
| 125 |
+
"grad_norm": 2.625758171081543,
|
| 126 |
+
"learning_rate": 1.6222222222222223e-05,
|
| 127 |
+
"loss": 0.5761,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"grad_norm": 3.7166590690612793,
|
| 133 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 134 |
+
"loss": 0.6138,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_accuracy": 0.6811023622047244,
|
| 140 |
+
"eval_loss": 0.6001904010772705,
|
| 141 |
+
"eval_runtime": 5.9005,
|
| 142 |
+
"eval_samples_per_second": 43.047,
|
| 143 |
+
"eval_steps_per_second": 5.423,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.0555555555555556,
|
| 148 |
+
"grad_norm": 3.4292004108428955,
|
| 149 |
+
"learning_rate": 1.577777777777778e-05,
|
| 150 |
+
"loss": 0.6237,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.1111111111111112,
|
| 155 |
+
"grad_norm": 2.9556570053100586,
|
| 156 |
+
"learning_rate": 1.555555555555556e-05,
|
| 157 |
+
"loss": 0.6242,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.1666666666666667,
|
| 162 |
+
"grad_norm": 2.3123323917388916,
|
| 163 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 164 |
+
"loss": 0.6179,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.2222222222222223,
|
| 169 |
+
"grad_norm": 1.728090763092041,
|
| 170 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 171 |
+
"loss": 0.6208,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.2777777777777777,
|
| 176 |
+
"grad_norm": 2.110353946685791,
|
| 177 |
+
"learning_rate": 1.488888888888889e-05,
|
| 178 |
+
"loss": 0.5744,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.3333333333333333,
|
| 183 |
+
"grad_norm": 2.0783276557922363,
|
| 184 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 185 |
+
"loss": 0.5388,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.3888888888888888,
|
| 190 |
+
"grad_norm": 2.3175930976867676,
|
| 191 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 192 |
+
"loss": 0.5846,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.4444444444444444,
|
| 197 |
+
"grad_norm": 3.0923080444335938,
|
| 198 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 199 |
+
"loss": 0.5831,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.5,
|
| 204 |
+
"grad_norm": 1.994885802268982,
|
| 205 |
+
"learning_rate": 1.4e-05,
|
| 206 |
+
"loss": 0.5929,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.5555555555555556,
|
| 211 |
+
"grad_norm": 3.28375244140625,
|
| 212 |
+
"learning_rate": 1.377777777777778e-05,
|
| 213 |
+
"loss": 0.5965,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.6111111111111112,
|
| 218 |
+
"grad_norm": 2.8813462257385254,
|
| 219 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 220 |
+
"loss": 0.5358,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.6666666666666665,
|
| 225 |
+
"grad_norm": 3.112164258956909,
|
| 226 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 227 |
+
"loss": 0.5877,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.7222222222222223,
|
| 232 |
+
"grad_norm": 1.542144775390625,
|
| 233 |
+
"learning_rate": 1.3111111111111113e-05,
|
| 234 |
+
"loss": 0.5485,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.7777777777777777,
|
| 239 |
+
"grad_norm": 2.144716262817383,
|
| 240 |
+
"learning_rate": 1.288888888888889e-05,
|
| 241 |
+
"loss": 0.6028,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.8333333333333335,
|
| 246 |
+
"grad_norm": 2.632028102874756,
|
| 247 |
+
"learning_rate": 1.2666666666666667e-05,
|
| 248 |
+
"loss": 0.5295,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.8888888888888888,
|
| 253 |
+
"grad_norm": 2.2505481243133545,
|
| 254 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 255 |
+
"loss": 0.6173,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.9444444444444444,
|
| 260 |
+
"grad_norm": 2.7676846981048584,
|
| 261 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 262 |
+
"loss": 0.5421,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.0,
|
| 267 |
+
"grad_norm": 2.5781171321868896,
|
| 268 |
+
"learning_rate": 1.2e-05,
|
| 269 |
+
"loss": 0.5028,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.0,
|
| 274 |
+
"eval_accuracy": 0.6811023622047244,
|
| 275 |
+
"eval_loss": 0.5528703927993774,
|
| 276 |
+
"eval_runtime": 4.4862,
|
| 277 |
+
"eval_samples_per_second": 56.618,
|
| 278 |
+
"eval_steps_per_second": 7.133,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.0555555555555554,
|
| 283 |
+
"grad_norm": 2.5306832790374756,
|
| 284 |
+
"learning_rate": 1.177777777777778e-05,
|
| 285 |
+
"loss": 0.5849,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.111111111111111,
|
| 290 |
+
"grad_norm": 2.1644484996795654,
|
| 291 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 292 |
+
"loss": 0.5268,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.1666666666666665,
|
| 297 |
+
"grad_norm": 1.9074407815933228,
|
| 298 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 299 |
+
"loss": 0.55,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.2222222222222223,
|
| 304 |
+
"grad_norm": 3.7348294258117676,
|
| 305 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 306 |
+
"loss": 0.6125,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.2777777777777777,
|
| 311 |
+
"grad_norm": 2.921757221221924,
|
| 312 |
+
"learning_rate": 1.088888888888889e-05,
|
| 313 |
+
"loss": 0.642,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.3333333333333335,
|
| 318 |
+
"grad_norm": 2.2528910636901855,
|
| 319 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 320 |
+
"loss": 0.5009,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.388888888888889,
|
| 325 |
+
"grad_norm": 1.6619905233383179,
|
| 326 |
+
"learning_rate": 1.0444444444444445e-05,
|
| 327 |
+
"loss": 0.5158,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.4444444444444446,
|
| 332 |
+
"grad_norm": 3.4696500301361084,
|
| 333 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 334 |
+
"loss": 0.6036,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.5,
|
| 339 |
+
"grad_norm": 2.936615467071533,
|
| 340 |
+
"learning_rate": 1e-05,
|
| 341 |
+
"loss": 0.5424,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.5555555555555554,
|
| 346 |
+
"grad_norm": 4.1920952796936035,
|
| 347 |
+
"learning_rate": 9.777777777777779e-06,
|
| 348 |
+
"loss": 0.5532,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.611111111111111,
|
| 353 |
+
"grad_norm": 2.4296085834503174,
|
| 354 |
+
"learning_rate": 9.555555555555556e-06,
|
| 355 |
+
"loss": 0.5436,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.6666666666666665,
|
| 360 |
+
"grad_norm": 2.5725982189178467,
|
| 361 |
+
"learning_rate": 9.333333333333334e-06,
|
| 362 |
+
"loss": 0.5015,
|
| 363 |
+
"step": 480
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.7222222222222223,
|
| 367 |
+
"grad_norm": 4.97006368637085,
|
| 368 |
+
"learning_rate": 9.111111111111112e-06,
|
| 369 |
+
"loss": 0.5775,
|
| 370 |
+
"step": 490
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.7777777777777777,
|
| 374 |
+
"grad_norm": 3.6014504432678223,
|
| 375 |
+
"learning_rate": 8.888888888888888e-06,
|
| 376 |
+
"loss": 0.5689,
|
| 377 |
+
"step": 500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.8333333333333335,
|
| 381 |
+
"grad_norm": 1.8251533508300781,
|
| 382 |
+
"learning_rate": 8.666666666666668e-06,
|
| 383 |
+
"loss": 0.5137,
|
| 384 |
+
"step": 510
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.888888888888889,
|
| 388 |
+
"grad_norm": 3.503689765930176,
|
| 389 |
+
"learning_rate": 8.444444444444446e-06,
|
| 390 |
+
"loss": 0.5827,
|
| 391 |
+
"step": 520
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.9444444444444446,
|
| 395 |
+
"grad_norm": 2.4786183834075928,
|
| 396 |
+
"learning_rate": 8.222222222222222e-06,
|
| 397 |
+
"loss": 0.5202,
|
| 398 |
+
"step": 530
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.0,
|
| 402 |
+
"grad_norm": 2.0592217445373535,
|
| 403 |
+
"learning_rate": 8.000000000000001e-06,
|
| 404 |
+
"loss": 0.5103,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.0,
|
| 409 |
+
"eval_accuracy": 0.6811023622047244,
|
| 410 |
+
"eval_loss": 0.5325487852096558,
|
| 411 |
+
"eval_runtime": 5.1901,
|
| 412 |
+
"eval_samples_per_second": 48.94,
|
| 413 |
+
"eval_steps_per_second": 6.166,
|
| 414 |
+
"step": 540
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.0555555555555554,
|
| 418 |
+
"grad_norm": 1.9031552076339722,
|
| 419 |
+
"learning_rate": 7.77777777777778e-06,
|
| 420 |
+
"loss": 0.5273,
|
| 421 |
+
"step": 550
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.111111111111111,
|
| 425 |
+
"grad_norm": 2.656759262084961,
|
| 426 |
+
"learning_rate": 7.555555555555556e-06,
|
| 427 |
+
"loss": 0.5824,
|
| 428 |
+
"step": 560
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.1666666666666665,
|
| 432 |
+
"grad_norm": 1.8883424997329712,
|
| 433 |
+
"learning_rate": 7.333333333333333e-06,
|
| 434 |
+
"loss": 0.5653,
|
| 435 |
+
"step": 570
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.2222222222222223,
|
| 439 |
+
"grad_norm": 2.118739128112793,
|
| 440 |
+
"learning_rate": 7.111111111111112e-06,
|
| 441 |
+
"loss": 0.5057,
|
| 442 |
+
"step": 580
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.2777777777777777,
|
| 446 |
+
"grad_norm": 1.90389883518219,
|
| 447 |
+
"learning_rate": 6.88888888888889e-06,
|
| 448 |
+
"loss": 0.6118,
|
| 449 |
+
"step": 590
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.3333333333333335,
|
| 453 |
+
"grad_norm": 1.8850902318954468,
|
| 454 |
+
"learning_rate": 6.666666666666667e-06,
|
| 455 |
+
"loss": 0.5682,
|
| 456 |
+
"step": 600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.388888888888889,
|
| 460 |
+
"grad_norm": 5.424034118652344,
|
| 461 |
+
"learning_rate": 6.444444444444445e-06,
|
| 462 |
+
"loss": 0.5501,
|
| 463 |
+
"step": 610
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.4444444444444446,
|
| 467 |
+
"grad_norm": 6.140316963195801,
|
| 468 |
+
"learning_rate": 6.222222222222223e-06,
|
| 469 |
+
"loss": 0.6259,
|
| 470 |
+
"step": 620
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.5,
|
| 474 |
+
"grad_norm": 2.766357183456421,
|
| 475 |
+
"learning_rate": 6e-06,
|
| 476 |
+
"loss": 0.5077,
|
| 477 |
+
"step": 630
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.5555555555555554,
|
| 481 |
+
"grad_norm": 2.0831124782562256,
|
| 482 |
+
"learning_rate": 5.777777777777778e-06,
|
| 483 |
+
"loss": 0.5609,
|
| 484 |
+
"step": 640
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.611111111111111,
|
| 488 |
+
"grad_norm": 1.9845359325408936,
|
| 489 |
+
"learning_rate": 5.555555555555557e-06,
|
| 490 |
+
"loss": 0.4875,
|
| 491 |
+
"step": 650
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.6666666666666665,
|
| 495 |
+
"grad_norm": 1.5764096975326538,
|
| 496 |
+
"learning_rate": 5.333333333333334e-06,
|
| 497 |
+
"loss": 0.4979,
|
| 498 |
+
"step": 660
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.7222222222222223,
|
| 502 |
+
"grad_norm": 3.984339952468872,
|
| 503 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 504 |
+
"loss": 0.5522,
|
| 505 |
+
"step": 670
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.7777777777777777,
|
| 509 |
+
"grad_norm": 2.4655332565307617,
|
| 510 |
+
"learning_rate": 4.888888888888889e-06,
|
| 511 |
+
"loss": 0.5476,
|
| 512 |
+
"step": 680
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.8333333333333335,
|
| 516 |
+
"grad_norm": 2.9143753051757812,
|
| 517 |
+
"learning_rate": 4.666666666666667e-06,
|
| 518 |
+
"loss": 0.5901,
|
| 519 |
+
"step": 690
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.888888888888889,
|
| 523 |
+
"grad_norm": 2.023881435394287,
|
| 524 |
+
"learning_rate": 4.444444444444444e-06,
|
| 525 |
+
"loss": 0.5842,
|
| 526 |
+
"step": 700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.9444444444444446,
|
| 530 |
+
"grad_norm": 2.730069398880005,
|
| 531 |
+
"learning_rate": 4.222222222222223e-06,
|
| 532 |
+
"loss": 0.5443,
|
| 533 |
+
"step": 710
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.0,
|
| 537 |
+
"grad_norm": 2.496239185333252,
|
| 538 |
+
"learning_rate": 4.000000000000001e-06,
|
| 539 |
+
"loss": 0.4892,
|
| 540 |
+
"step": 720
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 4.0,
|
| 544 |
+
"eval_accuracy": 0.6811023622047244,
|
| 545 |
+
"eval_loss": 0.5247489213943481,
|
| 546 |
+
"eval_runtime": 4.9059,
|
| 547 |
+
"eval_samples_per_second": 51.774,
|
| 548 |
+
"eval_steps_per_second": 6.523,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.055555555555555,
|
| 553 |
+
"grad_norm": 1.9344916343688965,
|
| 554 |
+
"learning_rate": 3.777777777777778e-06,
|
| 555 |
+
"loss": 0.5017,
|
| 556 |
+
"step": 730
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 4.111111111111111,
|
| 560 |
+
"grad_norm": 3.2695019245147705,
|
| 561 |
+
"learning_rate": 3.555555555555556e-06,
|
| 562 |
+
"loss": 0.5974,
|
| 563 |
+
"step": 740
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 4.166666666666667,
|
| 567 |
+
"grad_norm": 4.992809772491455,
|
| 568 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 569 |
+
"loss": 0.5307,
|
| 570 |
+
"step": 750
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.222222222222222,
|
| 574 |
+
"grad_norm": 3.5359721183776855,
|
| 575 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 576 |
+
"loss": 0.5372,
|
| 577 |
+
"step": 760
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 4.277777777777778,
|
| 581 |
+
"grad_norm": 2.123009204864502,
|
| 582 |
+
"learning_rate": 2.888888888888889e-06,
|
| 583 |
+
"loss": 0.49,
|
| 584 |
+
"step": 770
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.333333333333333,
|
| 588 |
+
"grad_norm": 2.8134477138519287,
|
| 589 |
+
"learning_rate": 2.666666666666667e-06,
|
| 590 |
+
"loss": 0.4749,
|
| 591 |
+
"step": 780
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.388888888888889,
|
| 595 |
+
"grad_norm": 2.195077896118164,
|
| 596 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 597 |
+
"loss": 0.5876,
|
| 598 |
+
"step": 790
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 4.444444444444445,
|
| 602 |
+
"grad_norm": 4.078568935394287,
|
| 603 |
+
"learning_rate": 2.222222222222222e-06,
|
| 604 |
+
"loss": 0.5609,
|
| 605 |
+
"step": 800
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.5,
|
| 609 |
+
"grad_norm": 2.6274867057800293,
|
| 610 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 611 |
+
"loss": 0.5392,
|
| 612 |
+
"step": 810
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.555555555555555,
|
| 616 |
+
"grad_norm": 1.7526293992996216,
|
| 617 |
+
"learning_rate": 1.777777777777778e-06,
|
| 618 |
+
"loss": 0.4965,
|
| 619 |
+
"step": 820
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 4.611111111111111,
|
| 623 |
+
"grad_norm": 2.3001506328582764,
|
| 624 |
+
"learning_rate": 1.5555555555555558e-06,
|
| 625 |
+
"loss": 0.5345,
|
| 626 |
+
"step": 830
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.666666666666667,
|
| 630 |
+
"grad_norm": 2.5624406337738037,
|
| 631 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 632 |
+
"loss": 0.5765,
|
| 633 |
+
"step": 840
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.722222222222222,
|
| 637 |
+
"grad_norm": 2.199018716812134,
|
| 638 |
+
"learning_rate": 1.111111111111111e-06,
|
| 639 |
+
"loss": 0.5547,
|
| 640 |
+
"step": 850
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.777777777777778,
|
| 644 |
+
"grad_norm": 3.756605625152588,
|
| 645 |
+
"learning_rate": 8.88888888888889e-07,
|
| 646 |
+
"loss": 0.5021,
|
| 647 |
+
"step": 860
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 4.833333333333333,
|
| 651 |
+
"grad_norm": 1.6385400295257568,
|
| 652 |
+
"learning_rate": 6.666666666666667e-07,
|
| 653 |
+
"loss": 0.5858,
|
| 654 |
+
"step": 870
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.888888888888889,
|
| 658 |
+
"grad_norm": 5.481604099273682,
|
| 659 |
+
"learning_rate": 4.444444444444445e-07,
|
| 660 |
+
"loss": 0.5062,
|
| 661 |
+
"step": 880
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.944444444444445,
|
| 665 |
+
"grad_norm": 2.554666042327881,
|
| 666 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 667 |
+
"loss": 0.5355,
|
| 668 |
+
"step": 890
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 5.0,
|
| 672 |
+
"grad_norm": 5.525686264038086,
|
| 673 |
+
"learning_rate": 0.0,
|
| 674 |
+
"loss": 0.5779,
|
| 675 |
+
"step": 900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 5.0,
|
| 679 |
+
"eval_accuracy": 0.6811023622047244,
|
| 680 |
+
"eval_loss": 0.530208170413971,
|
| 681 |
+
"eval_runtime": 5.531,
|
| 682 |
+
"eval_samples_per_second": 45.923,
|
| 683 |
+
"eval_steps_per_second": 5.786,
|
| 684 |
+
"step": 900
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 5.0,
|
| 688 |
+
"step": 900,
|
| 689 |
+
"total_flos": 7.24330215447552e+16,
|
| 690 |
+
"train_loss": 0.5726550849278768,
|
| 691 |
+
"train_runtime": 239.6067,
|
| 692 |
+
"train_samples_per_second": 29.945,
|
| 693 |
+
"train_steps_per_second": 3.756
|
| 694 |
+
}
|
| 695 |
+
],
|
| 696 |
+
"logging_steps": 10,
|
| 697 |
+
"max_steps": 900,
|
| 698 |
+
"num_input_tokens_seen": 0,
|
| 699 |
+
"num_train_epochs": 5,
|
| 700 |
+
"save_steps": 500,
|
| 701 |
+
"stateful_callbacks": {
|
| 702 |
+
"TrainerControl": {
|
| 703 |
+
"args": {
|
| 704 |
+
"should_epoch_stop": false,
|
| 705 |
+
"should_evaluate": false,
|
| 706 |
+
"should_log": false,
|
| 707 |
+
"should_save": true,
|
| 708 |
+
"should_training_stop": true
|
| 709 |
+
},
|
| 710 |
+
"attributes": {}
|
| 711 |
+
}
|
| 712 |
+
},
|
| 713 |
+
"total_flos": 7.24330215447552e+16,
|
| 714 |
+
"train_batch_size": 8,
|
| 715 |
+
"trial_name": null,
|
| 716 |
+
"trial_params": null
|
| 717 |
+
}
|