End of training
Browse files- README.md +3 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Dec04_07-12-00_kali/events.out.tfevents.1733315930.kali.273677.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +773 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: microsoft/resnet-50
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
@@ -16,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# resnet-50-cocoa
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.8971
|
| 22 |
- Accuracy: 0.8628
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: microsoft/resnet-50
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
|
|
|
| 18 |
|
| 19 |
# resnet-50-cocoa
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the SemilleroCV/Cocoa-dataset dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.8971
|
| 24 |
- Accuracy: 0.8628
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.8628158844765343,
|
| 4 |
+
"eval_loss": 0.897123396396637,
|
| 5 |
+
"eval_runtime": 16.5935,
|
| 6 |
+
"eval_samples_per_second": 16.693,
|
| 7 |
+
"eval_steps_per_second": 2.109,
|
| 8 |
+
"total_flos": 1.6633116935737344e+17,
|
| 9 |
+
"train_loss": 1.1215976812401596,
|
| 10 |
+
"train_runtime": 1562.8364,
|
| 11 |
+
"train_samples_per_second": 5.01,
|
| 12 |
+
"train_steps_per_second": 0.627
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.8628158844765343,
|
| 4 |
+
"eval_loss": 0.897123396396637,
|
| 5 |
+
"eval_runtime": 16.5935,
|
| 6 |
+
"eval_samples_per_second": 16.693,
|
| 7 |
+
"eval_steps_per_second": 2.109
|
| 8 |
+
}
|
runs/Dec04_07-12-00_kali/events.out.tfevents.1733315930.kali.273677.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0dc9ea5cc2ae29268e39e651699066a0c8368c1ec7fde72dded53c4c762e4ed
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 1.6633116935737344e+17,
|
| 4 |
+
"train_loss": 1.1215976812401596,
|
| 5 |
+
"train_runtime": 1562.8364,
|
| 6 |
+
"train_samples_per_second": 5.01,
|
| 7 |
+
"train_steps_per_second": 0.627
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,773 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.897123396396637,
|
| 3 |
+
"best_model_checkpoint": "./cocoa_outputs_resnet/checkpoint-980",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 980,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05102040816326531,
|
| 13 |
+
"grad_norm": 9.393156051635742,
|
| 14 |
+
"learning_rate": 1.979591836734694e-05,
|
| 15 |
+
"loss": 1.8572,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10204081632653061,
|
| 20 |
+
"grad_norm": 6.8461503982543945,
|
| 21 |
+
"learning_rate": 1.9591836734693877e-05,
|
| 22 |
+
"loss": 1.8224,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15306122448979592,
|
| 27 |
+
"grad_norm": 8.049448013305664,
|
| 28 |
+
"learning_rate": 1.9387755102040817e-05,
|
| 29 |
+
"loss": 1.7955,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.20408163265306123,
|
| 34 |
+
"grad_norm": 6.181807041168213,
|
| 35 |
+
"learning_rate": 1.9183673469387756e-05,
|
| 36 |
+
"loss": 1.7641,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25510204081632654,
|
| 41 |
+
"grad_norm": 6.991772651672363,
|
| 42 |
+
"learning_rate": 1.8979591836734696e-05,
|
| 43 |
+
"loss": 1.7421,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.30612244897959184,
|
| 48 |
+
"grad_norm": 6.233796119689941,
|
| 49 |
+
"learning_rate": 1.8775510204081636e-05,
|
| 50 |
+
"loss": 1.7018,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35714285714285715,
|
| 55 |
+
"grad_norm": 7.064742088317871,
|
| 56 |
+
"learning_rate": 1.8571428571428575e-05,
|
| 57 |
+
"loss": 1.6763,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.40816326530612246,
|
| 62 |
+
"grad_norm": 7.047808647155762,
|
| 63 |
+
"learning_rate": 1.836734693877551e-05,
|
| 64 |
+
"loss": 1.654,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45918367346938777,
|
| 69 |
+
"grad_norm": 8.950271606445312,
|
| 70 |
+
"learning_rate": 1.816326530612245e-05,
|
| 71 |
+
"loss": 1.6461,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5102040816326531,
|
| 76 |
+
"grad_norm": 7.686429023742676,
|
| 77 |
+
"learning_rate": 1.795918367346939e-05,
|
| 78 |
+
"loss": 1.6049,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5612244897959183,
|
| 83 |
+
"grad_norm": 6.434399127960205,
|
| 84 |
+
"learning_rate": 1.7755102040816327e-05,
|
| 85 |
+
"loss": 1.5926,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6122448979591837,
|
| 90 |
+
"grad_norm": 6.048853397369385,
|
| 91 |
+
"learning_rate": 1.7551020408163266e-05,
|
| 92 |
+
"loss": 1.5614,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6632653061224489,
|
| 97 |
+
"grad_norm": 12.146856307983398,
|
| 98 |
+
"learning_rate": 1.7346938775510206e-05,
|
| 99 |
+
"loss": 1.5344,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7142857142857143,
|
| 104 |
+
"grad_norm": 8.939432144165039,
|
| 105 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 106 |
+
"loss": 1.4892,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7653061224489796,
|
| 111 |
+
"grad_norm": 16.924053192138672,
|
| 112 |
+
"learning_rate": 1.6938775510204085e-05,
|
| 113 |
+
"loss": 1.4829,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8163265306122449,
|
| 118 |
+
"grad_norm": 10.929306983947754,
|
| 119 |
+
"learning_rate": 1.673469387755102e-05,
|
| 120 |
+
"loss": 1.5136,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8673469387755102,
|
| 125 |
+
"grad_norm": 12.943446159362793,
|
| 126 |
+
"learning_rate": 1.653061224489796e-05,
|
| 127 |
+
"loss": 1.4316,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9183673469387755,
|
| 132 |
+
"grad_norm": 6.890258312225342,
|
| 133 |
+
"learning_rate": 1.63265306122449e-05,
|
| 134 |
+
"loss": 1.4373,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9693877551020408,
|
| 139 |
+
"grad_norm": 9.790729522705078,
|
| 140 |
+
"learning_rate": 1.612244897959184e-05,
|
| 141 |
+
"loss": 1.4094,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"eval_accuracy": 0.8592057761732852,
|
| 147 |
+
"eval_loss": 1.4767718315124512,
|
| 148 |
+
"eval_runtime": 14.5787,
|
| 149 |
+
"eval_samples_per_second": 19.0,
|
| 150 |
+
"eval_steps_per_second": 2.401,
|
| 151 |
+
"step": 196
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.0204081632653061,
|
| 155 |
+
"grad_norm": 20.24932861328125,
|
| 156 |
+
"learning_rate": 1.5918367346938776e-05,
|
| 157 |
+
"loss": 1.4063,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.0714285714285714,
|
| 162 |
+
"grad_norm": 14.811591148376465,
|
| 163 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 164 |
+
"loss": 1.3551,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.1224489795918366,
|
| 169 |
+
"grad_norm": 18.894763946533203,
|
| 170 |
+
"learning_rate": 1.5510204081632655e-05,
|
| 171 |
+
"loss": 1.3314,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.1734693877551021,
|
| 176 |
+
"grad_norm": 13.06529426574707,
|
| 177 |
+
"learning_rate": 1.530612244897959e-05,
|
| 178 |
+
"loss": 1.3112,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.2244897959183674,
|
| 183 |
+
"grad_norm": 16.423351287841797,
|
| 184 |
+
"learning_rate": 1.510204081632653e-05,
|
| 185 |
+
"loss": 1.2519,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.2755102040816326,
|
| 190 |
+
"grad_norm": 11.016277313232422,
|
| 191 |
+
"learning_rate": 1.4897959183673472e-05,
|
| 192 |
+
"loss": 1.3565,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.3265306122448979,
|
| 197 |
+
"grad_norm": 7.271716594696045,
|
| 198 |
+
"learning_rate": 1.469387755102041e-05,
|
| 199 |
+
"loss": 1.2681,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.3775510204081631,
|
| 204 |
+
"grad_norm": 8.437969207763672,
|
| 205 |
+
"learning_rate": 1.448979591836735e-05,
|
| 206 |
+
"loss": 1.2675,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.4285714285714286,
|
| 211 |
+
"grad_norm": 6.352739334106445,
|
| 212 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 213 |
+
"loss": 1.1948,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.4795918367346939,
|
| 218 |
+
"grad_norm": 17.921051025390625,
|
| 219 |
+
"learning_rate": 1.4081632653061225e-05,
|
| 220 |
+
"loss": 1.3366,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.5306122448979593,
|
| 225 |
+
"grad_norm": 22.707721710205078,
|
| 226 |
+
"learning_rate": 1.3877551020408165e-05,
|
| 227 |
+
"loss": 1.2684,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.5816326530612246,
|
| 232 |
+
"grad_norm": 8.037663459777832,
|
| 233 |
+
"learning_rate": 1.3673469387755102e-05,
|
| 234 |
+
"loss": 1.2322,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.6326530612244898,
|
| 239 |
+
"grad_norm": 9.421684265136719,
|
| 240 |
+
"learning_rate": 1.3469387755102042e-05,
|
| 241 |
+
"loss": 1.1945,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.683673469387755,
|
| 246 |
+
"grad_norm": 27.85601043701172,
|
| 247 |
+
"learning_rate": 1.326530612244898e-05,
|
| 248 |
+
"loss": 1.2519,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.7346938775510203,
|
| 253 |
+
"grad_norm": 15.291147232055664,
|
| 254 |
+
"learning_rate": 1.3061224489795918e-05,
|
| 255 |
+
"loss": 1.1934,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.7857142857142856,
|
| 260 |
+
"grad_norm": 10.985498428344727,
|
| 261 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 262 |
+
"loss": 1.123,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.836734693877551,
|
| 267 |
+
"grad_norm": 9.827385902404785,
|
| 268 |
+
"learning_rate": 1.2653061224489798e-05,
|
| 269 |
+
"loss": 1.1677,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.8877551020408163,
|
| 274 |
+
"grad_norm": 16.994632720947266,
|
| 275 |
+
"learning_rate": 1.2448979591836736e-05,
|
| 276 |
+
"loss": 1.171,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.9387755102040818,
|
| 281 |
+
"grad_norm": 16.16167449951172,
|
| 282 |
+
"learning_rate": 1.2244897959183674e-05,
|
| 283 |
+
"loss": 1.1488,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.989795918367347,
|
| 288 |
+
"grad_norm": 12.466065406799316,
|
| 289 |
+
"learning_rate": 1.2040816326530614e-05,
|
| 290 |
+
"loss": 1.0664,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.0,
|
| 295 |
+
"eval_accuracy": 0.8628158844765343,
|
| 296 |
+
"eval_loss": 1.2089825868606567,
|
| 297 |
+
"eval_runtime": 17.1021,
|
| 298 |
+
"eval_samples_per_second": 16.197,
|
| 299 |
+
"eval_steps_per_second": 2.047,
|
| 300 |
+
"step": 392
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.0408163265306123,
|
| 304 |
+
"grad_norm": 14.415572166442871,
|
| 305 |
+
"learning_rate": 1.1836734693877552e-05,
|
| 306 |
+
"loss": 1.1081,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.0918367346938775,
|
| 311 |
+
"grad_norm": 16.120677947998047,
|
| 312 |
+
"learning_rate": 1.1632653061224491e-05,
|
| 313 |
+
"loss": 1.1347,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.142857142857143,
|
| 318 |
+
"grad_norm": 9.960640907287598,
|
| 319 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 320 |
+
"loss": 1.0755,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.193877551020408,
|
| 325 |
+
"grad_norm": 14.734106063842773,
|
| 326 |
+
"learning_rate": 1.1224489795918367e-05,
|
| 327 |
+
"loss": 1.0976,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.2448979591836733,
|
| 332 |
+
"grad_norm": 12.98324203491211,
|
| 333 |
+
"learning_rate": 1.1020408163265306e-05,
|
| 334 |
+
"loss": 0.9844,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.295918367346939,
|
| 339 |
+
"grad_norm": 8.834336280822754,
|
| 340 |
+
"learning_rate": 1.0816326530612246e-05,
|
| 341 |
+
"loss": 1.0923,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.3469387755102042,
|
| 346 |
+
"grad_norm": 10.948126792907715,
|
| 347 |
+
"learning_rate": 1.0612244897959186e-05,
|
| 348 |
+
"loss": 0.9711,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.3979591836734695,
|
| 353 |
+
"grad_norm": 13.707374572753906,
|
| 354 |
+
"learning_rate": 1.0408163265306123e-05,
|
| 355 |
+
"loss": 1.0786,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.4489795918367347,
|
| 360 |
+
"grad_norm": 18.081064224243164,
|
| 361 |
+
"learning_rate": 1.0204081632653063e-05,
|
| 362 |
+
"loss": 1.0399,
|
| 363 |
+
"step": 480
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.5,
|
| 367 |
+
"grad_norm": 12.470099449157715,
|
| 368 |
+
"learning_rate": 1e-05,
|
| 369 |
+
"loss": 0.9344,
|
| 370 |
+
"step": 490
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.5510204081632653,
|
| 374 |
+
"grad_norm": 10.96716022491455,
|
| 375 |
+
"learning_rate": 9.795918367346939e-06,
|
| 376 |
+
"loss": 1.043,
|
| 377 |
+
"step": 500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.6020408163265305,
|
| 381 |
+
"grad_norm": 7.244050025939941,
|
| 382 |
+
"learning_rate": 9.591836734693878e-06,
|
| 383 |
+
"loss": 0.9058,
|
| 384 |
+
"step": 510
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.6530612244897958,
|
| 388 |
+
"grad_norm": 10.213088035583496,
|
| 389 |
+
"learning_rate": 9.387755102040818e-06,
|
| 390 |
+
"loss": 0.9683,
|
| 391 |
+
"step": 520
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.704081632653061,
|
| 395 |
+
"grad_norm": 30.410015106201172,
|
| 396 |
+
"learning_rate": 9.183673469387756e-06,
|
| 397 |
+
"loss": 1.0396,
|
| 398 |
+
"step": 530
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.7551020408163263,
|
| 402 |
+
"grad_norm": 10.457310676574707,
|
| 403 |
+
"learning_rate": 8.979591836734695e-06,
|
| 404 |
+
"loss": 1.0215,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.806122448979592,
|
| 409 |
+
"grad_norm": 12.294684410095215,
|
| 410 |
+
"learning_rate": 8.775510204081633e-06,
|
| 411 |
+
"loss": 0.9301,
|
| 412 |
+
"step": 550
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.857142857142857,
|
| 416 |
+
"grad_norm": 10.194703102111816,
|
| 417 |
+
"learning_rate": 8.571428571428571e-06,
|
| 418 |
+
"loss": 0.9541,
|
| 419 |
+
"step": 560
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.9081632653061225,
|
| 423 |
+
"grad_norm": 17.80396842956543,
|
| 424 |
+
"learning_rate": 8.36734693877551e-06,
|
| 425 |
+
"loss": 0.964,
|
| 426 |
+
"step": 570
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.9591836734693877,
|
| 430 |
+
"grad_norm": 12.601577758789062,
|
| 431 |
+
"learning_rate": 8.16326530612245e-06,
|
| 432 |
+
"loss": 1.0295,
|
| 433 |
+
"step": 580
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.0,
|
| 437 |
+
"eval_accuracy": 0.8628158844765343,
|
| 438 |
+
"eval_loss": 0.9923866987228394,
|
| 439 |
+
"eval_runtime": 14.8495,
|
| 440 |
+
"eval_samples_per_second": 18.654,
|
| 441 |
+
"eval_steps_per_second": 2.357,
|
| 442 |
+
"step": 588
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.010204081632653,
|
| 446 |
+
"grad_norm": 12.689225196838379,
|
| 447 |
+
"learning_rate": 7.959183673469388e-06,
|
| 448 |
+
"loss": 0.9564,
|
| 449 |
+
"step": 590
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.061224489795918,
|
| 453 |
+
"grad_norm": 13.568258285522461,
|
| 454 |
+
"learning_rate": 7.755102040816327e-06,
|
| 455 |
+
"loss": 1.0031,
|
| 456 |
+
"step": 600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.1122448979591835,
|
| 460 |
+
"grad_norm": 15.86646842956543,
|
| 461 |
+
"learning_rate": 7.551020408163265e-06,
|
| 462 |
+
"loss": 0.9434,
|
| 463 |
+
"step": 610
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.163265306122449,
|
| 467 |
+
"grad_norm": 16.88734245300293,
|
| 468 |
+
"learning_rate": 7.346938775510205e-06,
|
| 469 |
+
"loss": 0.9468,
|
| 470 |
+
"step": 620
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.2142857142857144,
|
| 474 |
+
"grad_norm": 14.894389152526855,
|
| 475 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 476 |
+
"loss": 0.9284,
|
| 477 |
+
"step": 630
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.2653061224489797,
|
| 481 |
+
"grad_norm": 13.203142166137695,
|
| 482 |
+
"learning_rate": 6.938775510204082e-06,
|
| 483 |
+
"loss": 0.9288,
|
| 484 |
+
"step": 640
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.316326530612245,
|
| 488 |
+
"grad_norm": 13.70313835144043,
|
| 489 |
+
"learning_rate": 6.734693877551021e-06,
|
| 490 |
+
"loss": 0.8879,
|
| 491 |
+
"step": 650
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.36734693877551,
|
| 495 |
+
"grad_norm": 22.619674682617188,
|
| 496 |
+
"learning_rate": 6.530612244897959e-06,
|
| 497 |
+
"loss": 0.9367,
|
| 498 |
+
"step": 660
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.4183673469387754,
|
| 502 |
+
"grad_norm": 17.59436798095703,
|
| 503 |
+
"learning_rate": 6.326530612244899e-06,
|
| 504 |
+
"loss": 0.9176,
|
| 505 |
+
"step": 670
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.4693877551020407,
|
| 509 |
+
"grad_norm": 12.488346099853516,
|
| 510 |
+
"learning_rate": 6.122448979591837e-06,
|
| 511 |
+
"loss": 0.9448,
|
| 512 |
+
"step": 680
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.520408163265306,
|
| 516 |
+
"grad_norm": 7.665136337280273,
|
| 517 |
+
"learning_rate": 5.918367346938776e-06,
|
| 518 |
+
"loss": 0.8446,
|
| 519 |
+
"step": 690
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.571428571428571,
|
| 523 |
+
"grad_norm": 7.547515392303467,
|
| 524 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 525 |
+
"loss": 0.8465,
|
| 526 |
+
"step": 700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.622448979591837,
|
| 530 |
+
"grad_norm": 5.4680304527282715,
|
| 531 |
+
"learning_rate": 5.510204081632653e-06,
|
| 532 |
+
"loss": 0.8302,
|
| 533 |
+
"step": 710
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 3.673469387755102,
|
| 537 |
+
"grad_norm": 22.36733055114746,
|
| 538 |
+
"learning_rate": 5.306122448979593e-06,
|
| 539 |
+
"loss": 0.9601,
|
| 540 |
+
"step": 720
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.7244897959183674,
|
| 544 |
+
"grad_norm": 12.001816749572754,
|
| 545 |
+
"learning_rate": 5.1020408163265315e-06,
|
| 546 |
+
"loss": 0.8835,
|
| 547 |
+
"step": 730
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.7755102040816326,
|
| 551 |
+
"grad_norm": 23.104984283447266,
|
| 552 |
+
"learning_rate": 4.897959183673469e-06,
|
| 553 |
+
"loss": 0.8024,
|
| 554 |
+
"step": 740
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.826530612244898,
|
| 558 |
+
"grad_norm": 13.406716346740723,
|
| 559 |
+
"learning_rate": 4.693877551020409e-06,
|
| 560 |
+
"loss": 1.0554,
|
| 561 |
+
"step": 750
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.877551020408163,
|
| 565 |
+
"grad_norm": 9.763223648071289,
|
| 566 |
+
"learning_rate": 4.489795918367348e-06,
|
| 567 |
+
"loss": 0.79,
|
| 568 |
+
"step": 760
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.928571428571429,
|
| 572 |
+
"grad_norm": 10.93140983581543,
|
| 573 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 574 |
+
"loss": 0.8532,
|
| 575 |
+
"step": 770
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.979591836734694,
|
| 579 |
+
"grad_norm": 10.841426849365234,
|
| 580 |
+
"learning_rate": 4.081632653061225e-06,
|
| 581 |
+
"loss": 0.8401,
|
| 582 |
+
"step": 780
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.0,
|
| 586 |
+
"eval_accuracy": 0.8628158844765343,
|
| 587 |
+
"eval_loss": 0.9142875075340271,
|
| 588 |
+
"eval_runtime": 14.5094,
|
| 589 |
+
"eval_samples_per_second": 19.091,
|
| 590 |
+
"eval_steps_per_second": 2.412,
|
| 591 |
+
"step": 784
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.030612244897959,
|
| 595 |
+
"grad_norm": 11.179267883300781,
|
| 596 |
+
"learning_rate": 3.877551020408164e-06,
|
| 597 |
+
"loss": 0.8061,
|
| 598 |
+
"step": 790
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 4.081632653061225,
|
| 602 |
+
"grad_norm": 6.5305585861206055,
|
| 603 |
+
"learning_rate": 3.6734693877551024e-06,
|
| 604 |
+
"loss": 0.8525,
|
| 605 |
+
"step": 800
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.13265306122449,
|
| 609 |
+
"grad_norm": 7.101966857910156,
|
| 610 |
+
"learning_rate": 3.469387755102041e-06,
|
| 611 |
+
"loss": 0.7967,
|
| 612 |
+
"step": 810
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.183673469387755,
|
| 616 |
+
"grad_norm": 9.439040184020996,
|
| 617 |
+
"learning_rate": 3.2653061224489794e-06,
|
| 618 |
+
"loss": 0.8487,
|
| 619 |
+
"step": 820
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 4.23469387755102,
|
| 623 |
+
"grad_norm": 16.658971786499023,
|
| 624 |
+
"learning_rate": 3.0612244897959185e-06,
|
| 625 |
+
"loss": 0.8698,
|
| 626 |
+
"step": 830
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.285714285714286,
|
| 630 |
+
"grad_norm": 14.88980484008789,
|
| 631 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 632 |
+
"loss": 0.7877,
|
| 633 |
+
"step": 840
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.336734693877551,
|
| 637 |
+
"grad_norm": 10.878366470336914,
|
| 638 |
+
"learning_rate": 2.6530612244897964e-06,
|
| 639 |
+
"loss": 0.7731,
|
| 640 |
+
"step": 850
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.387755102040816,
|
| 644 |
+
"grad_norm": 11.978877067565918,
|
| 645 |
+
"learning_rate": 2.4489795918367347e-06,
|
| 646 |
+
"loss": 0.8627,
|
| 647 |
+
"step": 860
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 4.438775510204081,
|
| 651 |
+
"grad_norm": 20.543222427368164,
|
| 652 |
+
"learning_rate": 2.244897959183674e-06,
|
| 653 |
+
"loss": 0.8106,
|
| 654 |
+
"step": 870
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.489795918367347,
|
| 658 |
+
"grad_norm": 5.99076509475708,
|
| 659 |
+
"learning_rate": 2.0408163265306125e-06,
|
| 660 |
+
"loss": 0.8779,
|
| 661 |
+
"step": 880
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.540816326530612,
|
| 665 |
+
"grad_norm": 13.510481834411621,
|
| 666 |
+
"learning_rate": 1.8367346938775512e-06,
|
| 667 |
+
"loss": 0.8535,
|
| 668 |
+
"step": 890
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.591836734693878,
|
| 672 |
+
"grad_norm": 14.781784057617188,
|
| 673 |
+
"learning_rate": 1.6326530612244897e-06,
|
| 674 |
+
"loss": 0.8972,
|
| 675 |
+
"step": 900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.642857142857143,
|
| 679 |
+
"grad_norm": 14.63200855255127,
|
| 680 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 681 |
+
"loss": 0.9312,
|
| 682 |
+
"step": 910
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.6938775510204085,
|
| 686 |
+
"grad_norm": 19.910818099975586,
|
| 687 |
+
"learning_rate": 1.2244897959183673e-06,
|
| 688 |
+
"loss": 0.8134,
|
| 689 |
+
"step": 920
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.744897959183674,
|
| 693 |
+
"grad_norm": 16.637697219848633,
|
| 694 |
+
"learning_rate": 1.0204081632653063e-06,
|
| 695 |
+
"loss": 0.8341,
|
| 696 |
+
"step": 930
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 4.795918367346939,
|
| 700 |
+
"grad_norm": 5.32245397567749,
|
| 701 |
+
"learning_rate": 8.163265306122449e-07,
|
| 702 |
+
"loss": 0.7553,
|
| 703 |
+
"step": 940
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 4.846938775510204,
|
| 707 |
+
"grad_norm": 13.930354118347168,
|
| 708 |
+
"learning_rate": 6.122448979591837e-07,
|
| 709 |
+
"loss": 0.8303,
|
| 710 |
+
"step": 950
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.8979591836734695,
|
| 714 |
+
"grad_norm": 18.44146728515625,
|
| 715 |
+
"learning_rate": 4.0816326530612243e-07,
|
| 716 |
+
"loss": 0.8247,
|
| 717 |
+
"step": 960
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 4.948979591836735,
|
| 721 |
+
"grad_norm": 15.450093269348145,
|
| 722 |
+
"learning_rate": 2.0408163265306121e-07,
|
| 723 |
+
"loss": 0.9838,
|
| 724 |
+
"step": 970
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 5.0,
|
| 728 |
+
"grad_norm": 38.064430236816406,
|
| 729 |
+
"learning_rate": 0.0,
|
| 730 |
+
"loss": 0.8213,
|
| 731 |
+
"step": 980
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 5.0,
|
| 735 |
+
"eval_accuracy": 0.8628158844765343,
|
| 736 |
+
"eval_loss": 0.897123396396637,
|
| 737 |
+
"eval_runtime": 14.3653,
|
| 738 |
+
"eval_samples_per_second": 19.283,
|
| 739 |
+
"eval_steps_per_second": 2.436,
|
| 740 |
+
"step": 980
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 5.0,
|
| 744 |
+
"step": 980,
|
| 745 |
+
"total_flos": 1.6633116935737344e+17,
|
| 746 |
+
"train_loss": 1.1215976812401596,
|
| 747 |
+
"train_runtime": 1562.8364,
|
| 748 |
+
"train_samples_per_second": 5.01,
|
| 749 |
+
"train_steps_per_second": 0.627
|
| 750 |
+
}
|
| 751 |
+
],
|
| 752 |
+
"logging_steps": 10,
|
| 753 |
+
"max_steps": 980,
|
| 754 |
+
"num_input_tokens_seen": 0,
|
| 755 |
+
"num_train_epochs": 5,
|
| 756 |
+
"save_steps": 500,
|
| 757 |
+
"stateful_callbacks": {
|
| 758 |
+
"TrainerControl": {
|
| 759 |
+
"args": {
|
| 760 |
+
"should_epoch_stop": false,
|
| 761 |
+
"should_evaluate": false,
|
| 762 |
+
"should_log": false,
|
| 763 |
+
"should_save": true,
|
| 764 |
+
"should_training_stop": true
|
| 765 |
+
},
|
| 766 |
+
"attributes": {}
|
| 767 |
+
}
|
| 768 |
+
},
|
| 769 |
+
"total_flos": 1.6633116935737344e+17,
|
| 770 |
+
"train_batch_size": 8,
|
| 771 |
+
"trial_name": null,
|
| 772 |
+
"trial_params": null
|
| 773 |
+
}
|