Upload folder using huggingface_hub
Browse files- README.md +19 -28
- all_results.json +11 -11
- config.json +1 -1
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +58 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,36 +1,27 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
datasets:
|
4 |
-
- Open-Orca/OpenOrca
|
5 |
-
- ehartford/wizard_vicuna_70k_unfiltered
|
6 |
tags:
|
7 |
-
-
|
8 |
-
|
9 |
-
-
|
10 |
-
|
11 |
-
-
|
12 |
-
|
13 |
-
|
14 |
---
|
15 |
|
16 |
-
|
|
|
|
|
|
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
-
|
26 |
-
[RESPONSE] {model response}
|
27 |
-
|
28 |
-
or
|
29 |
-
|
30 |
-
[RESPONSE] {response}
|
31 |
-
[REVERSED-PROMPT] {model prompt reversed}
|
32 |
-
|
33 |
-
|
34 |
|
35 |
## Intended uses & limitations
|
36 |
|
@@ -38,9 +29,9 @@ More information needed
|
|
38 |
|
39 |
## Training and evaluation data
|
40 |
|
41 |
-
|
42 |
-
|
43 |
|
|
|
44 |
|
45 |
### Training hyperparameters
|
46 |
|
@@ -54,7 +45,7 @@ The following hyperparameters were used during training:
|
|
54 |
- num_epochs: 1.0
|
55 |
|
56 |
### Training results
|
57 |
-
|
58 |
|
59 |
|
60 |
### Framework versions
|
@@ -62,4 +53,4 @@ The following hyperparameters were used during training:
|
|
62 |
- Transformers 4.33.0.dev0
|
63 |
- Pytorch 2.1.0.dev20230605+cu121
|
64 |
- Datasets 2.14.4
|
65 |
-
- Tokenizers 0.13.3
|
|
|
1 |
---
|
2 |
+
base_model: ss5
|
|
|
|
|
|
|
3 |
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: ss6
|
9 |
+
results: []
|
|
|
10 |
---
|
11 |
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# ss6
|
16 |
|
17 |
+
This model is a fine-tuned version of [ss5](https://huggingface.co/ss5) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.2950
|
20 |
+
- Accuracy: 0.7084
|
21 |
|
22 |
## Model description
|
23 |
|
24 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
## Intended uses & limitations
|
27 |
|
|
|
29 |
|
30 |
## Training and evaluation data
|
31 |
|
32 |
+
More information needed
|
|
|
33 |
|
34 |
+
## Training procedure
|
35 |
|
36 |
### Training hyperparameters
|
37 |
|
|
|
45 |
- num_epochs: 1.0
|
46 |
|
47 |
### Training results
|
48 |
+
|
49 |
|
50 |
|
51 |
### Framework versions
|
|
|
53 |
- Transformers 4.33.0.dev0
|
54 |
- Pytorch 2.1.0.dev20230605+cu121
|
55 |
- Datasets 2.14.4
|
56 |
+
- Tokenizers 0.13.3
|
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 1.
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 232,
|
7 |
-
"eval_samples_per_second": 4.
|
8 |
-
"eval_steps_per_second": 0.
|
9 |
-
"perplexity":
|
10 |
-
"train_loss": 1.
|
11 |
-
"train_runtime":
|
12 |
-
"train_samples":
|
13 |
-
"train_samples_per_second": 3.
|
14 |
-
"train_steps_per_second": 0.
|
15 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.7083881079987865,
|
4 |
+
"eval_loss": 1.294954776763916,
|
5 |
+
"eval_runtime": 53.4048,
|
6 |
"eval_samples": 232,
|
7 |
+
"eval_samples_per_second": 4.344,
|
8 |
+
"eval_steps_per_second": 0.543,
|
9 |
+
"perplexity": 3.6508308680217363,
|
10 |
+
"train_loss": 1.2382940134009472,
|
11 |
+
"train_runtime": 11022.1698,
|
12 |
+
"train_samples": 38349,
|
13 |
+
"train_samples_per_second": 3.479,
|
14 |
+
"train_steps_per_second": 0.435
|
15 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"_remove_final_layer_norm": false,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "ss5",
|
3 |
"_remove_final_layer_norm": false,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 1.
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 232,
|
7 |
-
"eval_samples_per_second": 4.
|
8 |
-
"eval_steps_per_second": 0.
|
9 |
-
"perplexity":
|
10 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.7083881079987865,
|
4 |
+
"eval_loss": 1.294954776763916,
|
5 |
+
"eval_runtime": 53.4048,
|
6 |
"eval_samples": 232,
|
7 |
+
"eval_samples_per_second": 4.344,
|
8 |
+
"eval_steps_per_second": 0.543,
|
9 |
+
"perplexity": 3.6508308680217363
|
10 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2631648218
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8c1c4b4f568da599148a79e669bbd5590428dfaf7064385627c5948af153ced
|
3 |
size 2631648218
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second": 3.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 1.2382940134009472,
|
4 |
+
"train_runtime": 11022.1698,
|
5 |
+
"train_samples": 38349,
|
6 |
+
"train_samples_per_second": 3.479,
|
7 |
+
"train_steps_per_second": 0.435
|
8 |
}
|
trainer_state.json
CHANGED
@@ -3,38 +3,80 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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.
|
13 |
-
"learning_rate":
|
14 |
-
"loss": 1.
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate":
|
20 |
-
"loss": 1.
|
21 |
"step": 1000
|
22 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
{
|
24 |
"epoch": 1.0,
|
25 |
-
"step":
|
26 |
-
"total_flos":
|
27 |
-
"train_loss": 1.
|
28 |
-
"train_runtime":
|
29 |
-
"train_samples_per_second": 3.
|
30 |
-
"train_steps_per_second": 0.
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|
34 |
-
"max_steps":
|
35 |
"num_train_epochs": 1,
|
36 |
-
"save_steps": -
|
37 |
-
"total_flos":
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4794,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"learning_rate": 4.478514810179391e-05,
|
14 |
+
"loss": 1.3792,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.21,
|
19 |
+
"learning_rate": 3.9570296203587817e-05,
|
20 |
+
"loss": 1.3043,
|
21 |
"step": 1000
|
22 |
},
|
23 |
+
{
|
24 |
+
"epoch": 0.31,
|
25 |
+
"learning_rate": 3.435544430538173e-05,
|
26 |
+
"loss": 1.2641,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.42,
|
31 |
+
"learning_rate": 2.9140592407175638e-05,
|
32 |
+
"loss": 1.2319,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.52,
|
37 |
+
"learning_rate": 2.3925740508969545e-05,
|
38 |
+
"loss": 1.2035,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.63,
|
43 |
+
"learning_rate": 1.8710888610763455e-05,
|
44 |
+
"loss": 1.2072,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.73,
|
49 |
+
"learning_rate": 1.3496036712557364e-05,
|
50 |
+
"loss": 1.1955,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.83,
|
55 |
+
"learning_rate": 8.281184814351273e-06,
|
56 |
+
"loss": 1.1949,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.94,
|
61 |
+
"learning_rate": 3.0663329161451816e-06,
|
62 |
+
"loss": 1.194,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
{
|
66 |
"epoch": 1.0,
|
67 |
+
"step": 4794,
|
68 |
+
"total_flos": 2.8476642525865574e+17,
|
69 |
+
"train_loss": 1.2382940134009472,
|
70 |
+
"train_runtime": 11022.1698,
|
71 |
+
"train_samples_per_second": 3.479,
|
72 |
+
"train_steps_per_second": 0.435
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 500,
|
76 |
+
"max_steps": 4794,
|
77 |
"num_train_epochs": 1,
|
78 |
+
"save_steps": -4794,
|
79 |
+
"total_flos": 2.8476642525865574e+17,
|
80 |
"trial_name": null,
|
81 |
"trial_params": null
|
82 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13435d31ff4c3a7b19d246d3aedb0e34f659b86388d243bd7658841e425d0944
|
3 |
size 4472
|