brandolorian
commited on
Commit
•
a4df772
1
Parent(s):
97d632c
End of training
Browse files- README.md +56 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
- runs/Feb19_03-47-35_020d1a1e0686/events.out.tfevents.1708314456.020d1a1e0686.980.0 +2 -2
- tmp-checkpoint-9213/config.json +28 -0
- tmp-checkpoint-9213/generation_config.json +6 -0
- tmp-checkpoint-9213/model.safetensors +3 -0
- tmp-checkpoint-9213/optimizer.pt +3 -0
- tmp-checkpoint-9213/training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: Qwen/Qwen1.5-0.5B
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: answer-Qwen-stioning
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# answer-Qwen-stioning
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- eval_loss: 2.6400
|
19 |
+
- eval_runtime: 68.7183
|
20 |
+
- eval_samples_per_second: 178.744
|
21 |
+
- eval_steps_per_second: 22.352
|
22 |
+
- epoch: 3.0
|
23 |
+
- step: 9213
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 9
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.38.0.dev0
|
54 |
+
- Pytorch 2.1.0+cu121
|
55 |
+
- Datasets 2.17.0
|
56 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151643,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"transformers_version": "4.38.0.dev0"
|
6 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1855983640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5cf8b0666cc281fcbe36f06b6430412c56e5e6a8b2ea63b46394377c403a32
|
3 |
size 1855983640
|
runs/Feb19_03-47-35_020d1a1e0686/events.out.tfevents.1708314456.020d1a1e0686.980.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1699038897dc7559ca27b4b5bf75eb11de3d33dfc1efdefd95b09b0417824f15
|
3 |
+
size 8273
|
tmp-checkpoint-9213/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen1.5-0.5B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 2816,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 21,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": 32768,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.38.0.dev0",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 151936
|
28 |
+
}
|
tmp-checkpoint-9213/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151643,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"transformers_version": "4.38.0.dev0"
|
6 |
+
}
|
tmp-checkpoint-9213/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5cf8b0666cc281fcbe36f06b6430412c56e5e6a8b2ea63b46394377c403a32
|
3 |
+
size 1855983640
|
tmp-checkpoint-9213/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ed2e00af91fc86d02179e2909420d6530265d4053af9d0fa48986cf80185c23
|
3 |
+
size 622406692
|
tmp-checkpoint-9213/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:156ef38c462ff12e8551beb130fa94f60ec351a654b354c44c750fc1b4965b67
|
3 |
+
size 4920
|