End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Dec03_15-39-19_279d23e2c555/events.out.tfevents.1733241302.279d23e2c555.1261.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +701 -0
README.md
CHANGED
|
@@ -23,7 +23,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss:
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.7391304347826086
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.9394
|
| 37 |
+
- Accuracy: 0.7391
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26086956521739,
|
| 3 |
+
"eval_accuracy": 0.7391304347826086,
|
| 4 |
+
"eval_loss": 0.939383327960968,
|
| 5 |
+
"eval_runtime": 0.9725,
|
| 6 |
+
"eval_samples_per_second": 47.302,
|
| 7 |
+
"eval_steps_per_second": 3.085,
|
| 8 |
+
"total_flos": 8.989085534729011e+17,
|
| 9 |
+
"train_loss": 0.4470971633087505,
|
| 10 |
+
"train_runtime": 894.3938,
|
| 11 |
+
"train_samples_per_second": 32.29,
|
| 12 |
+
"train_steps_per_second": 0.492
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26086956521739,
|
| 3 |
+
"eval_accuracy": 0.7391304347826086,
|
| 4 |
+
"eval_loss": 0.939383327960968,
|
| 5 |
+
"eval_runtime": 0.9725,
|
| 6 |
+
"eval_samples_per_second": 47.302,
|
| 7 |
+
"eval_steps_per_second": 3.085
|
| 8 |
+
}
|
runs/Dec03_15-39-19_279d23e2c555/events.out.tfevents.1733241302.279d23e2c555.1261.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40a01f0c38679df1fad1218040fb55535b58b80256b0007b2b87be4583d0f500
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26086956521739,
|
| 3 |
+
"total_flos": 8.989085534729011e+17,
|
| 4 |
+
"train_loss": 0.4470971633087505,
|
| 5 |
+
"train_runtime": 894.3938,
|
| 6 |
+
"train_samples_per_second": 32.29,
|
| 7 |
+
"train_steps_per_second": 0.492
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,701 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7391304347826086,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-DMAE-da-colab/checkpoint-138",
|
| 4 |
+
"epoch": 38.26086956521739,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 440,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8695652173913043,
|
| 13 |
+
"grad_norm": 16.909873962402344,
|
| 14 |
+
"learning_rate": 9.090909090909091e-06,
|
| 15 |
+
"loss": 1.3823,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9565217391304348,
|
| 20 |
+
"eval_accuracy": 0.1956521739130435,
|
| 21 |
+
"eval_loss": 1.4058117866516113,
|
| 22 |
+
"eval_runtime": 0.9924,
|
| 23 |
+
"eval_samples_per_second": 46.35,
|
| 24 |
+
"eval_steps_per_second": 3.023,
|
| 25 |
+
"step": 11
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.7391304347826086,
|
| 29 |
+
"grad_norm": 19.725204467773438,
|
| 30 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 31 |
+
"loss": 1.3366,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.1956521739130435,
|
| 37 |
+
"eval_loss": 1.4482489824295044,
|
| 38 |
+
"eval_runtime": 0.7643,
|
| 39 |
+
"eval_samples_per_second": 60.185,
|
| 40 |
+
"eval_steps_per_second": 3.925,
|
| 41 |
+
"step": 23
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.608695652173913,
|
| 45 |
+
"grad_norm": 25.69033432006836,
|
| 46 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 47 |
+
"loss": 1.2352,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.9565217391304346,
|
| 52 |
+
"eval_accuracy": 0.45652173913043476,
|
| 53 |
+
"eval_loss": 1.230912685394287,
|
| 54 |
+
"eval_runtime": 0.8016,
|
| 55 |
+
"eval_samples_per_second": 57.387,
|
| 56 |
+
"eval_steps_per_second": 3.743,
|
| 57 |
+
"step": 34
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.4782608695652173,
|
| 61 |
+
"grad_norm": 22.049612045288086,
|
| 62 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 63 |
+
"loss": 1.1374,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.6086956521739131,
|
| 69 |
+
"eval_loss": 1.1031465530395508,
|
| 70 |
+
"eval_runtime": 0.9885,
|
| 71 |
+
"eval_samples_per_second": 46.536,
|
| 72 |
+
"eval_steps_per_second": 3.035,
|
| 73 |
+
"step": 46
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.3478260869565215,
|
| 77 |
+
"grad_norm": 29.715892791748047,
|
| 78 |
+
"learning_rate": 3.93939393939394e-05,
|
| 79 |
+
"loss": 1.0344,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.956521739130435,
|
| 84 |
+
"eval_accuracy": 0.5869565217391305,
|
| 85 |
+
"eval_loss": 1.0230214595794678,
|
| 86 |
+
"eval_runtime": 0.7523,
|
| 87 |
+
"eval_samples_per_second": 61.145,
|
| 88 |
+
"eval_steps_per_second": 3.988,
|
| 89 |
+
"step": 57
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.217391304347826,
|
| 93 |
+
"grad_norm": 42.69334030151367,
|
| 94 |
+
"learning_rate": 3.838383838383839e-05,
|
| 95 |
+
"loss": 0.8772,
|
| 96 |
+
"step": 60
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.6521739130434783,
|
| 101 |
+
"eval_loss": 0.9114828705787659,
|
| 102 |
+
"eval_runtime": 0.772,
|
| 103 |
+
"eval_samples_per_second": 59.587,
|
| 104 |
+
"eval_steps_per_second": 3.886,
|
| 105 |
+
"step": 69
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.086956521739131,
|
| 109 |
+
"grad_norm": 43.39430618286133,
|
| 110 |
+
"learning_rate": 3.7373737373737376e-05,
|
| 111 |
+
"loss": 0.8105,
|
| 112 |
+
"step": 70
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.956521739130435,
|
| 116 |
+
"grad_norm": 46.86561584472656,
|
| 117 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 118 |
+
"loss": 0.7321,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.956521739130435,
|
| 123 |
+
"eval_accuracy": 0.6521739130434783,
|
| 124 |
+
"eval_loss": 0.8857656717300415,
|
| 125 |
+
"eval_runtime": 1.0277,
|
| 126 |
+
"eval_samples_per_second": 44.76,
|
| 127 |
+
"eval_steps_per_second": 2.919,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.826086956521739,
|
| 132 |
+
"grad_norm": 42.23720169067383,
|
| 133 |
+
"learning_rate": 3.535353535353536e-05,
|
| 134 |
+
"loss": 0.6319,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"eval_accuracy": 0.6521739130434783,
|
| 140 |
+
"eval_loss": 0.866457998752594,
|
| 141 |
+
"eval_runtime": 0.7747,
|
| 142 |
+
"eval_samples_per_second": 59.38,
|
| 143 |
+
"eval_steps_per_second": 3.873,
|
| 144 |
+
"step": 92
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.695652173913043,
|
| 148 |
+
"grad_norm": 42.64775466918945,
|
| 149 |
+
"learning_rate": 3.434343434343435e-05,
|
| 150 |
+
"loss": 0.6438,
|
| 151 |
+
"step": 100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.956521739130435,
|
| 155 |
+
"eval_accuracy": 0.717391304347826,
|
| 156 |
+
"eval_loss": 0.7737635970115662,
|
| 157 |
+
"eval_runtime": 0.7744,
|
| 158 |
+
"eval_samples_per_second": 59.4,
|
| 159 |
+
"eval_steps_per_second": 3.874,
|
| 160 |
+
"step": 103
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.565217391304348,
|
| 164 |
+
"grad_norm": 60.89689636230469,
|
| 165 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 166 |
+
"loss": 0.4714,
|
| 167 |
+
"step": 110
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 10.0,
|
| 171 |
+
"eval_accuracy": 0.6304347826086957,
|
| 172 |
+
"eval_loss": 0.8491604924201965,
|
| 173 |
+
"eval_runtime": 1.0319,
|
| 174 |
+
"eval_samples_per_second": 44.578,
|
| 175 |
+
"eval_steps_per_second": 2.907,
|
| 176 |
+
"step": 115
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.434782608695652,
|
| 180 |
+
"grad_norm": 47.14131546020508,
|
| 181 |
+
"learning_rate": 3.232323232323232e-05,
|
| 182 |
+
"loss": 0.433,
|
| 183 |
+
"step": 120
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 10.956521739130435,
|
| 187 |
+
"eval_accuracy": 0.6956521739130435,
|
| 188 |
+
"eval_loss": 0.8385751247406006,
|
| 189 |
+
"eval_runtime": 0.7991,
|
| 190 |
+
"eval_samples_per_second": 57.561,
|
| 191 |
+
"eval_steps_per_second": 3.754,
|
| 192 |
+
"step": 126
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 11.304347826086957,
|
| 196 |
+
"grad_norm": 40.993927001953125,
|
| 197 |
+
"learning_rate": 3.131313131313132e-05,
|
| 198 |
+
"loss": 0.4793,
|
| 199 |
+
"step": 130
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 12.0,
|
| 203 |
+
"eval_accuracy": 0.7391304347826086,
|
| 204 |
+
"eval_loss": 0.939383327960968,
|
| 205 |
+
"eval_runtime": 0.7851,
|
| 206 |
+
"eval_samples_per_second": 58.594,
|
| 207 |
+
"eval_steps_per_second": 3.821,
|
| 208 |
+
"step": 138
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 12.173913043478262,
|
| 212 |
+
"grad_norm": 48.550899505615234,
|
| 213 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 214 |
+
"loss": 0.4769,
|
| 215 |
+
"step": 140
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 12.956521739130435,
|
| 219 |
+
"eval_accuracy": 0.6521739130434783,
|
| 220 |
+
"eval_loss": 0.9470547437667847,
|
| 221 |
+
"eval_runtime": 1.0593,
|
| 222 |
+
"eval_samples_per_second": 43.423,
|
| 223 |
+
"eval_steps_per_second": 2.832,
|
| 224 |
+
"step": 149
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.043478260869565,
|
| 228 |
+
"grad_norm": 84.14537811279297,
|
| 229 |
+
"learning_rate": 2.9292929292929297e-05,
|
| 230 |
+
"loss": 0.4308,
|
| 231 |
+
"step": 150
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 13.91304347826087,
|
| 235 |
+
"grad_norm": 54.65965270996094,
|
| 236 |
+
"learning_rate": 2.8282828282828285e-05,
|
| 237 |
+
"loss": 0.3872,
|
| 238 |
+
"step": 160
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 14.0,
|
| 242 |
+
"eval_accuracy": 0.6086956521739131,
|
| 243 |
+
"eval_loss": 1.1526373624801636,
|
| 244 |
+
"eval_runtime": 0.7735,
|
| 245 |
+
"eval_samples_per_second": 59.47,
|
| 246 |
+
"eval_steps_per_second": 3.878,
|
| 247 |
+
"step": 161
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 14.782608695652174,
|
| 251 |
+
"grad_norm": 63.24810791015625,
|
| 252 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 253 |
+
"loss": 0.3906,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 14.956521739130435,
|
| 258 |
+
"eval_accuracy": 0.6521739130434783,
|
| 259 |
+
"eval_loss": 1.057466983795166,
|
| 260 |
+
"eval_runtime": 0.7776,
|
| 261 |
+
"eval_samples_per_second": 59.156,
|
| 262 |
+
"eval_steps_per_second": 3.858,
|
| 263 |
+
"step": 172
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 15.652173913043478,
|
| 267 |
+
"grad_norm": 76.85520935058594,
|
| 268 |
+
"learning_rate": 2.6262626262626265e-05,
|
| 269 |
+
"loss": 0.3798,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 16.0,
|
| 274 |
+
"eval_accuracy": 0.6956521739130435,
|
| 275 |
+
"eval_loss": 1.0592772960662842,
|
| 276 |
+
"eval_runtime": 0.8046,
|
| 277 |
+
"eval_samples_per_second": 57.172,
|
| 278 |
+
"eval_steps_per_second": 3.729,
|
| 279 |
+
"step": 184
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 16.52173913043478,
|
| 283 |
+
"grad_norm": 43.57295608520508,
|
| 284 |
+
"learning_rate": 2.5252525252525253e-05,
|
| 285 |
+
"loss": 0.3377,
|
| 286 |
+
"step": 190
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 16.956521739130434,
|
| 290 |
+
"eval_accuracy": 0.6086956521739131,
|
| 291 |
+
"eval_loss": 1.0782535076141357,
|
| 292 |
+
"eval_runtime": 0.7945,
|
| 293 |
+
"eval_samples_per_second": 57.9,
|
| 294 |
+
"eval_steps_per_second": 3.776,
|
| 295 |
+
"step": 195
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 17.391304347826086,
|
| 299 |
+
"grad_norm": 55.173805236816406,
|
| 300 |
+
"learning_rate": 2.4242424242424244e-05,
|
| 301 |
+
"loss": 0.3919,
|
| 302 |
+
"step": 200
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 18.0,
|
| 306 |
+
"eval_accuracy": 0.6521739130434783,
|
| 307 |
+
"eval_loss": 1.1066713333129883,
|
| 308 |
+
"eval_runtime": 0.7682,
|
| 309 |
+
"eval_samples_per_second": 59.879,
|
| 310 |
+
"eval_steps_per_second": 3.905,
|
| 311 |
+
"step": 207
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 18.26086956521739,
|
| 315 |
+
"grad_norm": 44.900856018066406,
|
| 316 |
+
"learning_rate": 2.3232323232323232e-05,
|
| 317 |
+
"loss": 0.3631,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 18.956521739130434,
|
| 322 |
+
"eval_accuracy": 0.6739130434782609,
|
| 323 |
+
"eval_loss": 1.1017966270446777,
|
| 324 |
+
"eval_runtime": 0.7687,
|
| 325 |
+
"eval_samples_per_second": 59.84,
|
| 326 |
+
"eval_steps_per_second": 3.903,
|
| 327 |
+
"step": 218
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 19.130434782608695,
|
| 331 |
+
"grad_norm": 45.883216857910156,
|
| 332 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 333 |
+
"loss": 0.3433,
|
| 334 |
+
"step": 220
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 20.0,
|
| 338 |
+
"grad_norm": 29.03622055053711,
|
| 339 |
+
"learning_rate": 2.121212121212121e-05,
|
| 340 |
+
"loss": 0.2762,
|
| 341 |
+
"step": 230
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 20.0,
|
| 345 |
+
"eval_accuracy": 0.6521739130434783,
|
| 346 |
+
"eval_loss": 1.147935152053833,
|
| 347 |
+
"eval_runtime": 1.0114,
|
| 348 |
+
"eval_samples_per_second": 45.482,
|
| 349 |
+
"eval_steps_per_second": 2.966,
|
| 350 |
+
"step": 230
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 20.869565217391305,
|
| 354 |
+
"grad_norm": 49.36585235595703,
|
| 355 |
+
"learning_rate": 2.0202020202020206e-05,
|
| 356 |
+
"loss": 0.2935,
|
| 357 |
+
"step": 240
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 20.956521739130434,
|
| 361 |
+
"eval_accuracy": 0.6956521739130435,
|
| 362 |
+
"eval_loss": 1.1054612398147583,
|
| 363 |
+
"eval_runtime": 0.7595,
|
| 364 |
+
"eval_samples_per_second": 60.565,
|
| 365 |
+
"eval_steps_per_second": 3.95,
|
| 366 |
+
"step": 241
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 21.73913043478261,
|
| 370 |
+
"grad_norm": 34.57924270629883,
|
| 371 |
+
"learning_rate": 1.9191919191919194e-05,
|
| 372 |
+
"loss": 0.3029,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 22.0,
|
| 377 |
+
"eval_accuracy": 0.6739130434782609,
|
| 378 |
+
"eval_loss": 1.120306372642517,
|
| 379 |
+
"eval_runtime": 0.7563,
|
| 380 |
+
"eval_samples_per_second": 60.82,
|
| 381 |
+
"eval_steps_per_second": 3.967,
|
| 382 |
+
"step": 253
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 22.608695652173914,
|
| 386 |
+
"grad_norm": 50.57252502441406,
|
| 387 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 388 |
+
"loss": 0.2857,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 22.956521739130434,
|
| 393 |
+
"eval_accuracy": 0.6304347826086957,
|
| 394 |
+
"eval_loss": 1.2819756269454956,
|
| 395 |
+
"eval_runtime": 0.7606,
|
| 396 |
+
"eval_samples_per_second": 60.476,
|
| 397 |
+
"eval_steps_per_second": 3.944,
|
| 398 |
+
"step": 264
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 23.47826086956522,
|
| 402 |
+
"grad_norm": 32.393211364746094,
|
| 403 |
+
"learning_rate": 1.7171717171717173e-05,
|
| 404 |
+
"loss": 0.2603,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 24.0,
|
| 409 |
+
"eval_accuracy": 0.6304347826086957,
|
| 410 |
+
"eval_loss": 1.2550427913665771,
|
| 411 |
+
"eval_runtime": 0.7542,
|
| 412 |
+
"eval_samples_per_second": 60.991,
|
| 413 |
+
"eval_steps_per_second": 3.978,
|
| 414 |
+
"step": 276
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 24.347826086956523,
|
| 418 |
+
"grad_norm": 53.81830596923828,
|
| 419 |
+
"learning_rate": 1.616161616161616e-05,
|
| 420 |
+
"loss": 0.2162,
|
| 421 |
+
"step": 280
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 24.956521739130434,
|
| 425 |
+
"eval_accuracy": 0.6739130434782609,
|
| 426 |
+
"eval_loss": 1.1655433177947998,
|
| 427 |
+
"eval_runtime": 0.7904,
|
| 428 |
+
"eval_samples_per_second": 58.201,
|
| 429 |
+
"eval_steps_per_second": 3.796,
|
| 430 |
+
"step": 287
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 25.217391304347824,
|
| 434 |
+
"grad_norm": 61.60272216796875,
|
| 435 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 436 |
+
"loss": 0.2465,
|
| 437 |
+
"step": 290
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 26.0,
|
| 441 |
+
"eval_accuracy": 0.6739130434782609,
|
| 442 |
+
"eval_loss": 1.2510898113250732,
|
| 443 |
+
"eval_runtime": 0.796,
|
| 444 |
+
"eval_samples_per_second": 57.789,
|
| 445 |
+
"eval_steps_per_second": 3.769,
|
| 446 |
+
"step": 299
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 26.08695652173913,
|
| 450 |
+
"grad_norm": 50.68645477294922,
|
| 451 |
+
"learning_rate": 1.4141414141414143e-05,
|
| 452 |
+
"loss": 0.2503,
|
| 453 |
+
"step": 300
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 26.956521739130434,
|
| 457 |
+
"grad_norm": 62.43329620361328,
|
| 458 |
+
"learning_rate": 1.3131313131313132e-05,
|
| 459 |
+
"loss": 0.2238,
|
| 460 |
+
"step": 310
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 26.956521739130434,
|
| 464 |
+
"eval_accuracy": 0.6304347826086957,
|
| 465 |
+
"eval_loss": 1.3460850715637207,
|
| 466 |
+
"eval_runtime": 1.0048,
|
| 467 |
+
"eval_samples_per_second": 45.782,
|
| 468 |
+
"eval_steps_per_second": 2.986,
|
| 469 |
+
"step": 310
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 27.82608695652174,
|
| 473 |
+
"grad_norm": 56.05590057373047,
|
| 474 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 475 |
+
"loss": 0.2271,
|
| 476 |
+
"step": 320
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 28.0,
|
| 480 |
+
"eval_accuracy": 0.6304347826086957,
|
| 481 |
+
"eval_loss": 1.3471860885620117,
|
| 482 |
+
"eval_runtime": 0.7754,
|
| 483 |
+
"eval_samples_per_second": 59.324,
|
| 484 |
+
"eval_steps_per_second": 3.869,
|
| 485 |
+
"step": 322
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 28.695652173913043,
|
| 489 |
+
"grad_norm": 36.40557098388672,
|
| 490 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 491 |
+
"loss": 0.2694,
|
| 492 |
+
"step": 330
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 28.956521739130434,
|
| 496 |
+
"eval_accuracy": 0.6304347826086957,
|
| 497 |
+
"eval_loss": 1.4501123428344727,
|
| 498 |
+
"eval_runtime": 0.746,
|
| 499 |
+
"eval_samples_per_second": 61.663,
|
| 500 |
+
"eval_steps_per_second": 4.022,
|
| 501 |
+
"step": 333
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 29.565217391304348,
|
| 505 |
+
"grad_norm": 46.565956115722656,
|
| 506 |
+
"learning_rate": 1.0101010101010103e-05,
|
| 507 |
+
"loss": 0.1903,
|
| 508 |
+
"step": 340
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 30.0,
|
| 512 |
+
"eval_accuracy": 0.6304347826086957,
|
| 513 |
+
"eval_loss": 1.462881326675415,
|
| 514 |
+
"eval_runtime": 1.0409,
|
| 515 |
+
"eval_samples_per_second": 44.193,
|
| 516 |
+
"eval_steps_per_second": 2.882,
|
| 517 |
+
"step": 345
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 30.434782608695652,
|
| 521 |
+
"grad_norm": 92.46195220947266,
|
| 522 |
+
"learning_rate": 9.090909090909091e-06,
|
| 523 |
+
"loss": 0.2054,
|
| 524 |
+
"step": 350
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 30.956521739130434,
|
| 528 |
+
"eval_accuracy": 0.6304347826086957,
|
| 529 |
+
"eval_loss": 1.4671651124954224,
|
| 530 |
+
"eval_runtime": 0.7747,
|
| 531 |
+
"eval_samples_per_second": 59.374,
|
| 532 |
+
"eval_steps_per_second": 3.872,
|
| 533 |
+
"step": 356
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 31.304347826086957,
|
| 537 |
+
"grad_norm": 44.79200744628906,
|
| 538 |
+
"learning_rate": 8.08080808080808e-06,
|
| 539 |
+
"loss": 0.199,
|
| 540 |
+
"step": 360
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 32.0,
|
| 544 |
+
"eval_accuracy": 0.6304347826086957,
|
| 545 |
+
"eval_loss": 1.472485899925232,
|
| 546 |
+
"eval_runtime": 0.7531,
|
| 547 |
+
"eval_samples_per_second": 61.078,
|
| 548 |
+
"eval_steps_per_second": 3.983,
|
| 549 |
+
"step": 368
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 32.17391304347826,
|
| 553 |
+
"grad_norm": 34.2342643737793,
|
| 554 |
+
"learning_rate": 7.070707070707071e-06,
|
| 555 |
+
"loss": 0.2034,
|
| 556 |
+
"step": 370
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 32.95652173913044,
|
| 560 |
+
"eval_accuracy": 0.6521739130434783,
|
| 561 |
+
"eval_loss": 1.4506837129592896,
|
| 562 |
+
"eval_runtime": 0.9808,
|
| 563 |
+
"eval_samples_per_second": 46.899,
|
| 564 |
+
"eval_steps_per_second": 3.059,
|
| 565 |
+
"step": 379
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 33.04347826086956,
|
| 569 |
+
"grad_norm": 28.347145080566406,
|
| 570 |
+
"learning_rate": 6.060606060606061e-06,
|
| 571 |
+
"loss": 0.1959,
|
| 572 |
+
"step": 380
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 33.91304347826087,
|
| 576 |
+
"grad_norm": 44.34228515625,
|
| 577 |
+
"learning_rate": 5.0505050505050515e-06,
|
| 578 |
+
"loss": 0.2048,
|
| 579 |
+
"step": 390
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 34.0,
|
| 583 |
+
"eval_accuracy": 0.6304347826086957,
|
| 584 |
+
"eval_loss": 1.4330270290374756,
|
| 585 |
+
"eval_runtime": 0.9488,
|
| 586 |
+
"eval_samples_per_second": 48.484,
|
| 587 |
+
"eval_steps_per_second": 3.162,
|
| 588 |
+
"step": 391
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 34.78260869565217,
|
| 592 |
+
"grad_norm": 38.90620803833008,
|
| 593 |
+
"learning_rate": 4.04040404040404e-06,
|
| 594 |
+
"loss": 0.1767,
|
| 595 |
+
"step": 400
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 34.95652173913044,
|
| 599 |
+
"eval_accuracy": 0.6304347826086957,
|
| 600 |
+
"eval_loss": 1.4638035297393799,
|
| 601 |
+
"eval_runtime": 0.7554,
|
| 602 |
+
"eval_samples_per_second": 60.894,
|
| 603 |
+
"eval_steps_per_second": 3.971,
|
| 604 |
+
"step": 402
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 35.65217391304348,
|
| 608 |
+
"grad_norm": 32.936920166015625,
|
| 609 |
+
"learning_rate": 3.0303030303030305e-06,
|
| 610 |
+
"loss": 0.1799,
|
| 611 |
+
"step": 410
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 36.0,
|
| 615 |
+
"eval_accuracy": 0.6304347826086957,
|
| 616 |
+
"eval_loss": 1.4231865406036377,
|
| 617 |
+
"eval_runtime": 0.7731,
|
| 618 |
+
"eval_samples_per_second": 59.501,
|
| 619 |
+
"eval_steps_per_second": 3.88,
|
| 620 |
+
"step": 414
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 36.52173913043478,
|
| 624 |
+
"grad_norm": 32.154483795166016,
|
| 625 |
+
"learning_rate": 2.02020202020202e-06,
|
| 626 |
+
"loss": 0.1903,
|
| 627 |
+
"step": 420
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 36.95652173913044,
|
| 631 |
+
"eval_accuracy": 0.6304347826086957,
|
| 632 |
+
"eval_loss": 1.450764536857605,
|
| 633 |
+
"eval_runtime": 1.0455,
|
| 634 |
+
"eval_samples_per_second": 43.997,
|
| 635 |
+
"eval_steps_per_second": 2.869,
|
| 636 |
+
"step": 425
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 37.391304347826086,
|
| 640 |
+
"grad_norm": 32.06462860107422,
|
| 641 |
+
"learning_rate": 1.01010101010101e-06,
|
| 642 |
+
"loss": 0.1864,
|
| 643 |
+
"step": 430
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 38.0,
|
| 647 |
+
"eval_accuracy": 0.6304347826086957,
|
| 648 |
+
"eval_loss": 1.4460225105285645,
|
| 649 |
+
"eval_runtime": 0.78,
|
| 650 |
+
"eval_samples_per_second": 58.972,
|
| 651 |
+
"eval_steps_per_second": 3.846,
|
| 652 |
+
"step": 437
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 38.26086956521739,
|
| 656 |
+
"grad_norm": 44.23124694824219,
|
| 657 |
+
"learning_rate": 0.0,
|
| 658 |
+
"loss": 0.1818,
|
| 659 |
+
"step": 440
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 38.26086956521739,
|
| 663 |
+
"eval_accuracy": 0.6304347826086957,
|
| 664 |
+
"eval_loss": 1.4456393718719482,
|
| 665 |
+
"eval_runtime": 0.9819,
|
| 666 |
+
"eval_samples_per_second": 46.85,
|
| 667 |
+
"eval_steps_per_second": 3.055,
|
| 668 |
+
"step": 440
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 38.26086956521739,
|
| 672 |
+
"step": 440,
|
| 673 |
+
"total_flos": 8.989085534729011e+17,
|
| 674 |
+
"train_loss": 0.4470971633087505,
|
| 675 |
+
"train_runtime": 894.3938,
|
| 676 |
+
"train_samples_per_second": 32.29,
|
| 677 |
+
"train_steps_per_second": 0.492
|
| 678 |
+
}
|
| 679 |
+
],
|
| 680 |
+
"logging_steps": 10,
|
| 681 |
+
"max_steps": 440,
|
| 682 |
+
"num_input_tokens_seen": 0,
|
| 683 |
+
"num_train_epochs": 40,
|
| 684 |
+
"save_steps": 500,
|
| 685 |
+
"stateful_callbacks": {
|
| 686 |
+
"TrainerControl": {
|
| 687 |
+
"args": {
|
| 688 |
+
"should_epoch_stop": false,
|
| 689 |
+
"should_evaluate": false,
|
| 690 |
+
"should_log": false,
|
| 691 |
+
"should_save": true,
|
| 692 |
+
"should_training_stop": true
|
| 693 |
+
},
|
| 694 |
+
"attributes": {}
|
| 695 |
+
}
|
| 696 |
+
},
|
| 697 |
+
"total_flos": 8.989085534729011e+17,
|
| 698 |
+
"train_batch_size": 16,
|
| 699 |
+
"trial_name": null,
|
| 700 |
+
"trial_params": null
|
| 701 |
+
}
|