Upload folder using huggingface_hub
Browse files- README.md +18 -17
- all_results.json +19 -19
- config.json +1 -1
- eval_results.json +14 -14
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- train_results.json +6 -6
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
---
|
|
|
2 |
license: llama3
|
3 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
4 |
tags:
|
5 |
- alignment-handbook
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
-
- simonycl/
|
9 |
model-index:
|
10 |
- name: llama-3-8b-instruct-single-judge
|
11 |
results: []
|
@@ -16,17 +17,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# llama-3-8b-instruct-single-judge
|
18 |
|
19 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the simonycl/
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: -
|
23 |
-
- Rewards/rejected: -1.
|
24 |
-
- Rewards/accuracies: 0.
|
25 |
-
- Rewards/margins: 0.
|
26 |
-
- Logps/rejected: -
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected: -1.
|
29 |
-
- Logits/chosen: -1.
|
30 |
|
31 |
## Model description
|
32 |
|
@@ -46,14 +47,14 @@ More information needed
|
|
46 |
|
47 |
The following hyperparameters were used during training:
|
48 |
- learning_rate: 5e-07
|
49 |
-
- train_batch_size:
|
50 |
-
- eval_batch_size:
|
51 |
- seed: 42
|
52 |
- distributed_type: multi-GPU
|
53 |
- num_devices: 4
|
54 |
-
- gradient_accumulation_steps:
|
55 |
- total_train_batch_size: 128
|
56 |
-
- total_eval_batch_size:
|
57 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
- lr_scheduler_type: cosine
|
59 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -63,12 +64,12 @@ The following hyperparameters were used during training:
|
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
65 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
66 |
-
| 0.
|
67 |
|
68 |
|
69 |
### Framework versions
|
70 |
|
71 |
-
- Transformers 4.44.
|
72 |
- Pytorch 2.4.0+cu121
|
73 |
- Datasets 2.21.0
|
74 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
license: llama3
|
4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
5 |
tags:
|
6 |
- alignment-handbook
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback_single_judge
|
10 |
model-index:
|
11 |
- name: llama-3-8b-instruct-single-judge
|
12 |
results: []
|
|
|
17 |
|
18 |
# llama-3-8b-instruct-single-judge
|
19 |
|
20 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback_single_judge dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.6593
|
23 |
+
- Rewards/chosen: -1.3185
|
24 |
+
- Rewards/rejected: -1.5107
|
25 |
+
- Rewards/accuracies: 0.5935
|
26 |
+
- Rewards/margins: 0.1922
|
27 |
+
- Logps/rejected: -301.4192
|
28 |
+
- Logps/chosen: -283.3882
|
29 |
+
- Logits/rejected: -1.3226
|
30 |
+
- Logits/chosen: -1.3593
|
31 |
|
32 |
## Model description
|
33 |
|
|
|
47 |
|
48 |
The following hyperparameters were used during training:
|
49 |
- learning_rate: 5e-07
|
50 |
+
- train_batch_size: 1
|
51 |
+
- eval_batch_size: 2
|
52 |
- seed: 42
|
53 |
- distributed_type: multi-GPU
|
54 |
- num_devices: 4
|
55 |
+
- gradient_accumulation_steps: 32
|
56 |
- total_train_batch_size: 128
|
57 |
+
- total_eval_batch_size: 8
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: cosine
|
60 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
66 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
67 |
+
| 0.5714 | 0.8528 | 400 | 0.6593 | -1.3185 | -1.5107 | 0.5935 | 0.1922 | -301.4192 | -283.3882 | -1.3226 | -1.3593 |
|
68 |
|
69 |
|
70 |
### Framework versions
|
71 |
|
72 |
+
- Transformers 4.44.2
|
73 |
- Pytorch 2.4.0+cu121
|
74 |
- Datasets 2.21.0
|
75 |
- Tokenizers 0.19.1
|
all_results.json
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"eval_logits/chosen": -1.
|
4 |
-
"eval_logits/rejected": -1.
|
5 |
-
"eval_logps/chosen": -
|
6 |
-
"eval_logps/rejected": -
|
7 |
-
"eval_loss": 0.
|
8 |
-
"eval_rewards/accuracies": 0.
|
9 |
-
"eval_rewards/chosen": -
|
10 |
-
"eval_rewards/margins": 0.
|
11 |
-
"eval_rewards/rejected": -1.
|
12 |
-
"eval_runtime":
|
13 |
-
"eval_samples":
|
14 |
-
"eval_samples_per_second":
|
15 |
-
"eval_steps_per_second": 0.
|
16 |
"total_flos": 0.0,
|
17 |
-
"train_loss": 0.
|
18 |
-
"train_runtime":
|
19 |
-
"train_samples":
|
20 |
-
"train_samples_per_second":
|
21 |
-
"train_steps_per_second": 0.
|
22 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9999333733093477,
|
3 |
+
"eval_logits/chosen": -1.3400534391403198,
|
4 |
+
"eval_logits/rejected": -1.3050051927566528,
|
5 |
+
"eval_logps/chosen": -281.1357727050781,
|
6 |
+
"eval_logps/rejected": -299.5000915527344,
|
7 |
+
"eval_loss": 0.6583243012428284,
|
8 |
+
"eval_rewards/accuracies": 0.5955284833908081,
|
9 |
+
"eval_rewards/chosen": -1.2959448099136353,
|
10 |
+
"eval_rewards/margins": 0.1955154538154602,
|
11 |
+
"eval_rewards/rejected": -1.4914603233337402,
|
12 |
+
"eval_runtime": 246.7004,
|
13 |
+
"eval_samples": 1962,
|
14 |
+
"eval_samples_per_second": 7.953,
|
15 |
+
"eval_steps_per_second": 0.997,
|
16 |
"total_flos": 0.0,
|
17 |
+
"train_loss": 0.6122812041595801,
|
18 |
+
"train_runtime": 25569.0191,
|
19 |
+
"train_samples": 60035,
|
20 |
+
"train_samples_per_second": 2.348,
|
21 |
+
"train_steps_per_second": 0.018
|
22 |
}
|
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
-
"transformers_version": "4.44.
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 128256
|
29 |
}
|
|
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.44.2",
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 128256
|
29 |
}
|
eval_results.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"eval_logits/chosen": -1.
|
4 |
-
"eval_logits/rejected": -1.
|
5 |
-
"eval_logps/chosen": -
|
6 |
-
"eval_logps/rejected": -
|
7 |
-
"eval_loss": 0.
|
8 |
-
"eval_rewards/accuracies": 0.
|
9 |
-
"eval_rewards/chosen": -
|
10 |
-
"eval_rewards/margins": 0.
|
11 |
-
"eval_rewards/rejected": -1.
|
12 |
-
"eval_runtime":
|
13 |
-
"eval_samples":
|
14 |
-
"eval_samples_per_second":
|
15 |
-
"eval_steps_per_second": 0.
|
16 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9999333733093477,
|
3 |
+
"eval_logits/chosen": -1.3400534391403198,
|
4 |
+
"eval_logits/rejected": -1.3050051927566528,
|
5 |
+
"eval_logps/chosen": -281.1357727050781,
|
6 |
+
"eval_logps/rejected": -299.5000915527344,
|
7 |
+
"eval_loss": 0.6583243012428284,
|
8 |
+
"eval_rewards/accuracies": 0.5955284833908081,
|
9 |
+
"eval_rewards/chosen": -1.2959448099136353,
|
10 |
+
"eval_rewards/margins": 0.1955154538154602,
|
11 |
+
"eval_rewards/rejected": -1.4914603233337402,
|
12 |
+
"eval_runtime": 246.7004,
|
13 |
+
"eval_samples": 1962,
|
14 |
+
"eval_samples_per_second": 7.953,
|
15 |
+
"eval_steps_per_second": 0.997
|
16 |
}
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
"max_length": 4096,
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
-
"transformers_version": "4.44.
|
12 |
}
|
|
|
8 |
"max_length": 4096,
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.44.2"
|
12 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6e4d90ca23309ff8eac136cabb590b316716750495a0c31e5350acb9d4ef75d
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c74e3dd2d01e552f3bc27d13dd658c744b28ef135ddf094fda73eca9df516d24
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:977482c84531661824fc55aeca30e8ec58c3d023d938872cecf3151167625922
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268bf2e3e02a5198884981188188fe3c144ba230d27dab75e41140618193b2e8
|
3 |
size 1168138808
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples":
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9999333733093477,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6122812041595801,
|
5 |
+
"train_runtime": 25569.0191,
|
6 |
+
"train_samples": 60035,
|
7 |
+
"train_samples_per_second": 2.348,
|
8 |
+
"train_steps_per_second": 0.018
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:789be51aeff227264050e7503678d5a40962ef4754d2aa42eefdb72c95b40441
|
3 |
size 7544
|