Model save
Browse files- README.md +15 -9
- adapter_config.json +4 -8
- runs/May20_14-41-33_04bac4264f87/events.out.tfevents.1716216487.04bac4264f87.3853.0 +3 -0
- step_0/README.md +4 -2
- step_0/adapter_config.json +4 -8
- step_0/tokenizer.json +1 -0
- step_0/tokenizer_config.json +0 -1
- step_0/training_args.bin +2 -2
- tokenizer.json +1 -0
- tokenizer_config.json +0 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -5,9 +5,9 @@ tags:
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
|
|
8 |
datasets:
|
9 |
- generator
|
10 |
-
base_model: meta-llama/Llama-2-7b-chat-hf
|
11 |
model-index:
|
12 |
- name: llama2-7b-sft-lora
|
13 |
results: []
|
@@ -42,18 +42,24 @@ The following hyperparameters were used during training:
|
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 4
|
44 |
- distributed_type: multi-GPU
|
45 |
-
- num_devices:
|
46 |
- gradient_accumulation_steps: 4
|
47 |
-
- total_train_batch_size:
|
48 |
-
- total_eval_batch_size:
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
51 |
- num_epochs: 1
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
-
-
|
56 |
-
-
|
57 |
-
-
|
58 |
-
-
|
59 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
+
base_model: meta-llama/Llama-2-7b-chat-hf
|
9 |
datasets:
|
10 |
- generator
|
|
|
11 |
model-index:
|
12 |
- name: llama2-7b-sft-lora
|
13 |
results: []
|
|
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 4
|
44 |
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 2
|
46 |
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- total_eval_batch_size: 16
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
51 |
- num_epochs: 1
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
+
- Transformers 4.41.0
|
56 |
+
- Pytorch 2.1.0+cu121
|
57 |
+
- Datasets 2.14.6
|
58 |
+
- Tokenizers 0.19.1
|
59 |
+
## Training procedure
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
|
65 |
+
- PEFT 0.6.1
|
adapter_config.json
CHANGED
@@ -8,24 +8,20 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
-
"loftq_config": {},
|
12 |
"lora_alpha": 16,
|
13 |
"lora_dropout": 0.1,
|
14 |
-
"megatron_config": null,
|
15 |
-
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"v_proj",
|
23 |
"q_proj",
|
24 |
-
"k_proj",
|
25 |
-
"o_proj",
|
26 |
"up_proj",
|
27 |
-
"
|
28 |
],
|
29 |
-
"task_type": "CAUSAL_LM"
|
30 |
-
"use_rslora": false
|
31 |
}
|
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
|
|
11 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.1,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 64,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
+
"down_proj",
|
21 |
"v_proj",
|
22 |
"q_proj",
|
|
|
|
|
23 |
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
+
"task_type": "CAUSAL_LM"
|
|
|
27 |
}
|
runs/May20_14-41-33_04bac4264f87/events.out.tfevents.1716216487.04bac4264f87.3853.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36b1bd1bf287b0eaf3ea6ed62a68c8ce7b745fe4d536f214ea02b53c594e7735
|
3 |
+
size 4955
|
step_0/README.md
CHANGED
@@ -81,7 +81,7 @@ Use the code below to get started with the model.
|
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
84 |
-
### Training Procedure
|
85 |
|
86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
@@ -197,8 +197,10 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
197 |
## Model Card Contact
|
198 |
|
199 |
[More Information Needed]
|
|
|
200 |
|
201 |
|
202 |
### Framework versions
|
203 |
|
204 |
-
|
|
|
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
84 |
+
### Training Procedure
|
85 |
|
86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
|
|
197 |
## Model Card Contact
|
198 |
|
199 |
[More Information Needed]
|
200 |
+
## Training procedure
|
201 |
|
202 |
|
203 |
### Framework versions
|
204 |
|
205 |
+
|
206 |
+
- PEFT 0.6.1
|
step_0/adapter_config.json
CHANGED
@@ -8,24 +8,20 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
-
"loftq_config": {},
|
12 |
"lora_alpha": 16,
|
13 |
"lora_dropout": 0.1,
|
14 |
-
"megatron_config": null,
|
15 |
-
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"v_proj",
|
23 |
"q_proj",
|
24 |
-
"k_proj",
|
25 |
-
"o_proj",
|
26 |
"up_proj",
|
27 |
-
"
|
28 |
],
|
29 |
-
"task_type": "CAUSAL_LM"
|
30 |
-
"use_rslora": false
|
31 |
}
|
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
|
|
11 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.1,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 64,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
+
"down_proj",
|
21 |
"v_proj",
|
22 |
"q_proj",
|
|
|
|
|
23 |
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
+
"task_type": "CAUSAL_LM"
|
|
|
27 |
}
|
step_0/tokenizer.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
+
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
step_0/tokenizer_config.json
CHANGED
@@ -31,7 +31,6 @@
|
|
31 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
-
"legacy": false,
|
35 |
"model_max_length": 2048,
|
36 |
"pad_token": "</s>",
|
37 |
"padding_side": "right",
|
|
|
31 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
|
|
34 |
"model_max_length": 2048,
|
35 |
"pad_token": "</s>",
|
36 |
"padding_side": "right",
|
step_0/training_args.bin
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 sha256:5e053cf93f1736083927827130a127d281aa30f3d7b5c8bd7f0ef7a5ad298352
|
3 |
+
size 6136
|
tokenizer.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
+
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -31,7 +31,6 @@
|
|
31 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
-
"legacy": false,
|
35 |
"model_max_length": 2048,
|
36 |
"pad_token": "</s>",
|
37 |
"padding_side": "right",
|
|
|
31 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
|
|
34 |
"model_max_length": 2048,
|
35 |
"pad_token": "</s>",
|
36 |
"padding_side": "right",
|
training_args.bin
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 sha256:5e053cf93f1736083927827130a127d281aa30f3d7b5c8bd7f0ef7a5ad298352
|
3 |
+
size 6136
|