stealthwriter
commited on
Commit
•
018adf1
1
Parent(s):
18c44f7
End of training
Browse files- README.md +5 -0
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +46 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ license: mit
|
|
3 |
base_model: roberta-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: llamaHorAI2
|
8 |
results: []
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# llamaHorAI2
|
15 |
|
16 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: roberta-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: llamaHorAI2
|
10 |
results: []
|
|
|
16 |
# llamaHorAI2
|
17 |
|
18 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.9503
|
21 |
+
- Accuracy: 0.7318
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.7318286151491966,
|
4 |
+
"eval_loss": 0.9503203630447388,
|
5 |
+
"eval_runtime": 3.1972,
|
6 |
+
"eval_samples": 2614,
|
7 |
+
"eval_samples_per_second": 817.584,
|
8 |
+
"eval_steps_per_second": 102.276,
|
9 |
+
"train_loss": 0.3296431981824589,
|
10 |
+
"train_runtime": 167.8728,
|
11 |
+
"train_samples": 10456,
|
12 |
+
"train_samples_per_second": 311.426,
|
13 |
+
"train_steps_per_second": 9.74
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.7318286151491966,
|
4 |
+
"eval_loss": 0.9503203630447388,
|
5 |
+
"eval_runtime": 3.1972,
|
6 |
+
"eval_samples": 2614,
|
7 |
+
"eval_samples_per_second": 817.584,
|
8 |
+
"eval_steps_per_second": 102.276
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.3296431981824589,
|
4 |
+
"train_runtime": 167.8728,
|
5 |
+
"train_samples": 10456,
|
6 |
+
"train_samples_per_second": 311.426,
|
7 |
+
"train_steps_per_second": 9.74
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1635,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.53,
|
13 |
+
"learning_rate": 1.3883792048929665e-05,
|
14 |
+
"loss": 0.4996,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 3.06,
|
19 |
+
"learning_rate": 7.767584097859327e-06,
|
20 |
+
"loss": 0.3259,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 4.59,
|
25 |
+
"learning_rate": 1.6513761467889911e-06,
|
26 |
+
"loss": 0.2073,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 5.0,
|
31 |
+
"step": 1635,
|
32 |
+
"total_flos": 1719430746777600.0,
|
33 |
+
"train_loss": 0.3296431981824589,
|
34 |
+
"train_runtime": 167.8728,
|
35 |
+
"train_samples_per_second": 311.426,
|
36 |
+
"train_steps_per_second": 9.74
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 1635,
|
41 |
+
"num_train_epochs": 5,
|
42 |
+
"save_steps": 500,
|
43 |
+
"total_flos": 1719430746777600.0,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|