Model save
Browse files- .gitattributes +1 -0
- README.md +77 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +9 -0
- runs/Jun05_13-30-51_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717561870.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.933266.0 +3 -0
- special_tokens_map.json +34 -0
- tokenizer.json +3 -0
- tokenizer_config.json +70 -0
- train_results.json +9 -0
- trainer_state.json +151 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: gemma
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: google/gemma-2b
|
9 |
+
datasets:
|
10 |
+
- generator
|
11 |
+
model-index:
|
12 |
+
- name: gemma2b-summarize-claude3sonnet-1k
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# gemma2b-summarize-claude3sonnet-1k
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.6123
|
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: 0.0002
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- num_devices: 3
|
48 |
+
- gradient_accumulation_steps: 2
|
49 |
+
- total_train_batch_size: 48
|
50 |
+
- total_eval_batch_size: 24
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: cosine
|
53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
54 |
+
- num_epochs: 10
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
60 |
+
| 2.755 | 0.8571 | 3 | 3.1059 |
|
61 |
+
| 2.6986 | 2.0 | 7 | 2.8356 |
|
62 |
+
| 2.2478 | 2.8571 | 10 | 2.7310 |
|
63 |
+
| 2.2478 | 4.0 | 14 | 2.6773 |
|
64 |
+
| 1.9892 | 4.8571 | 17 | 2.6487 |
|
65 |
+
| 1.8401 | 6.0 | 21 | 2.6184 |
|
66 |
+
| 1.8401 | 6.8571 | 24 | 2.6133 |
|
67 |
+
| 1.7508 | 8.0 | 28 | 2.6098 |
|
68 |
+
| 1.7163 | 8.5714 | 30 | 2.6123 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- PEFT 0.10.0
|
74 |
+
- Transformers 4.40.0
|
75 |
+
- Pytorch 2.2.2+cu121
|
76 |
+
- Datasets 2.19.1
|
77 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"k_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:235bfa79bd64297f6d055553685ebe9e5f106a9e6c8b63b43b3d2eb8a5d789ec
|
3 |
+
size 19644912
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.571428571428571,
|
3 |
+
"total_flos": 1.762120022622208e+16,
|
4 |
+
"train_loss": 2.042347224553426,
|
5 |
+
"train_runtime": 106.802,
|
6 |
+
"train_samples": 992,
|
7 |
+
"train_samples_per_second": 14.232,
|
8 |
+
"train_steps_per_second": 0.281
|
9 |
+
}
|
runs/Jun05_13-30-51_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717561870.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.933266.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:063536afaed0ef614c80c80e58e2c9fcde2bf362f26e3c63068c6f81b9da8fb2
|
3 |
+
size 9663
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
|
3 |
+
size 17477501
|
tokenizer_config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<|im_start|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<|im_end|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<|im_start|>",
|
56 |
+
"<|im_end|>"
|
57 |
+
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "<eos>",
|
62 |
+
"legacy": null,
|
63 |
+
"model_max_length": 2048,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"sp_model_kwargs": {},
|
66 |
+
"spaces_between_special_tokens": false,
|
67 |
+
"tokenizer_class": "GemmaTokenizer",
|
68 |
+
"unk_token": "<unk>",
|
69 |
+
"use_default_system_prompt": false
|
70 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.571428571428571,
|
3 |
+
"total_flos": 1.762120022622208e+16,
|
4 |
+
"train_loss": 2.042347224553426,
|
5 |
+
"train_runtime": 106.802,
|
6 |
+
"train_samples": 992,
|
7 |
+
"train_samples_per_second": 14.232,
|
8 |
+
"train_steps_per_second": 0.281
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.571428571428571,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 30,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2857142857142857,
|
13 |
+
"grad_norm": 1.5,
|
14 |
+
"learning_rate": 6.666666666666667e-05,
|
15 |
+
"loss": 2.755,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.8571428571428571,
|
20 |
+
"eval_loss": 3.1059346199035645,
|
21 |
+
"eval_runtime": 0.5642,
|
22 |
+
"eval_samples_per_second": 17.725,
|
23 |
+
"eval_steps_per_second": 1.772,
|
24 |
+
"step": 3
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.4285714285714286,
|
28 |
+
"grad_norm": 1.34375,
|
29 |
+
"learning_rate": 0.00019730448705798239,
|
30 |
+
"loss": 2.6986,
|
31 |
+
"step": 5
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_loss": 2.8355600833892822,
|
36 |
+
"eval_runtime": 0.5011,
|
37 |
+
"eval_samples_per_second": 19.954,
|
38 |
+
"eval_steps_per_second": 1.995,
|
39 |
+
"step": 7
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.857142857142857,
|
43 |
+
"grad_norm": 2.375,
|
44 |
+
"learning_rate": 0.0001686241637868734,
|
45 |
+
"loss": 2.2478,
|
46 |
+
"step": 10
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.857142857142857,
|
50 |
+
"eval_loss": 2.730991840362549,
|
51 |
+
"eval_runtime": 0.6312,
|
52 |
+
"eval_samples_per_second": 15.842,
|
53 |
+
"eval_steps_per_second": 1.584,
|
54 |
+
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.0,
|
58 |
+
"eval_loss": 2.6772868633270264,
|
59 |
+
"eval_runtime": 0.5219,
|
60 |
+
"eval_samples_per_second": 19.162,
|
61 |
+
"eval_steps_per_second": 1.916,
|
62 |
+
"step": 14
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.285714285714286,
|
66 |
+
"grad_norm": 1.1875,
|
67 |
+
"learning_rate": 0.00011736481776669306,
|
68 |
+
"loss": 1.9892,
|
69 |
+
"step": 15
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.857142857142857,
|
73 |
+
"eval_loss": 2.648698091506958,
|
74 |
+
"eval_runtime": 0.6365,
|
75 |
+
"eval_samples_per_second": 15.712,
|
76 |
+
"eval_steps_per_second": 1.571,
|
77 |
+
"step": 17
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 5.714285714285714,
|
81 |
+
"grad_norm": 0.6015625,
|
82 |
+
"learning_rate": 6.039202339608432e-05,
|
83 |
+
"loss": 1.8401,
|
84 |
+
"step": 20
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 2.618410348892212,
|
89 |
+
"eval_runtime": 0.5361,
|
90 |
+
"eval_samples_per_second": 18.654,
|
91 |
+
"eval_steps_per_second": 1.865,
|
92 |
+
"step": 21
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.857142857142857,
|
96 |
+
"eval_loss": 2.6133430004119873,
|
97 |
+
"eval_runtime": 0.6782,
|
98 |
+
"eval_samples_per_second": 14.744,
|
99 |
+
"eval_steps_per_second": 1.474,
|
100 |
+
"step": 24
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 7.142857142857143,
|
104 |
+
"grad_norm": 0.859375,
|
105 |
+
"learning_rate": 1.6451218858706374e-05,
|
106 |
+
"loss": 1.7508,
|
107 |
+
"step": 25
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_loss": 2.6098170280456543,
|
112 |
+
"eval_runtime": 0.5541,
|
113 |
+
"eval_samples_per_second": 18.047,
|
114 |
+
"eval_steps_per_second": 1.805,
|
115 |
+
"step": 28
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 8.571428571428571,
|
119 |
+
"grad_norm": 0.52734375,
|
120 |
+
"learning_rate": 0.0,
|
121 |
+
"loss": 1.7163,
|
122 |
+
"step": 30
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.571428571428571,
|
126 |
+
"eval_loss": 2.6123337745666504,
|
127 |
+
"eval_runtime": 0.5428,
|
128 |
+
"eval_samples_per_second": 18.424,
|
129 |
+
"eval_steps_per_second": 1.842,
|
130 |
+
"step": 30
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 8.571428571428571,
|
134 |
+
"step": 30,
|
135 |
+
"total_flos": 1.762120022622208e+16,
|
136 |
+
"train_loss": 2.042347224553426,
|
137 |
+
"train_runtime": 106.802,
|
138 |
+
"train_samples_per_second": 14.232,
|
139 |
+
"train_steps_per_second": 0.281
|
140 |
+
}
|
141 |
+
],
|
142 |
+
"logging_steps": 5,
|
143 |
+
"max_steps": 30,
|
144 |
+
"num_input_tokens_seen": 0,
|
145 |
+
"num_train_epochs": 10,
|
146 |
+
"save_steps": 100,
|
147 |
+
"total_flos": 1.762120022622208e+16,
|
148 |
+
"train_batch_size": 8,
|
149 |
+
"trial_name": null,
|
150 |
+
"trial_params": null
|
151 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a72da4d8a3a9f22b931c17b97fd88c596325a038d5784d2760a0c024c98897a
|
3 |
+
size 5240
|