Training in progress, step 100
Browse files- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- angle.config +27 -0
- merges.txt +0 -0
- runs/Apr24_09-53-03_beta-M12SWA-TF/events.out.tfevents.1713923586.beta-M12SWA-TF.1504211.0 +3 -0
- runs/Apr24_10-55-09_beta-M12SWA-TF/events.out.tfevents.1713927310.beta-M12SWA-TF.1506031.0 +3 -0
- runs/Apr24_10-56-07_beta-M12SWA-TF/events.out.tfevents.1713927371.beta-M12SWA-TF.1506519.0 +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
- vocab.json +0 -0
adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-0.5B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
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": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"v_proj",
|
24 |
+
"o_proj",
|
25 |
+
"down_proj",
|
26 |
+
"up_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_dora": false,
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93d0c39180108199a73a3a36aab0bb63210e11576be474629935deed05ebc6f6
|
3 |
+
size 60599872
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
angle.config
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_name_or_path": "Qwen/Qwen1.5-0.5B",
|
3 |
+
"max_length": 75,
|
4 |
+
"model_kwargs": {},
|
5 |
+
"pooling_strategy": "avg",
|
6 |
+
"lora_config_kwargs": {
|
7 |
+
"task_type": "CAUSAL_LM",
|
8 |
+
"r": 32,
|
9 |
+
"lora_alpha": 32,
|
10 |
+
"lora_dropout": 0.1,
|
11 |
+
"bias": "none",
|
12 |
+
"target_modules": [
|
13 |
+
"k_proj",
|
14 |
+
"v_proj",
|
15 |
+
"o_proj",
|
16 |
+
"up_proj",
|
17 |
+
"down_proj",
|
18 |
+
"q_proj",
|
19 |
+
"gate_proj"
|
20 |
+
]
|
21 |
+
},
|
22 |
+
"is_llm": 1,
|
23 |
+
"apply_billm": 1,
|
24 |
+
"billm_model_class": "Qwen2ForCausalLM",
|
25 |
+
"apply_lora": 1,
|
26 |
+
"tokenizer_padding_side": null
|
27 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr24_09-53-03_beta-M12SWA-TF/events.out.tfevents.1713923586.beta-M12SWA-TF.1504211.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fbb8eb5c5a1648101330ab6ba51183c0340c8cbcd133df510fc9b17ab952348
|
3 |
+
size 13335
|
runs/Apr24_10-55-09_beta-M12SWA-TF/events.out.tfevents.1713927310.beta-M12SWA-TF.1506031.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c4bf30d3909ad1183ed7c00803e4244bb1b71417dcd757265fe16ceced1210e
|
3 |
+
size 4136
|
runs/Apr24_10-56-07_beta-M12SWA-TF/events.out.tfevents.1713927371.beta-M12SWA-TF.1506519.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3de427cde0881781bc04079f0b5aed3da9ad403d2c7ee5c2278a3d71a2b3c7d5
|
3 |
+
size 7248
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c126e947453c98ae2874e51c8a9e30cb4053abdc05af3a74df5c79a95bb7ec42
|
3 |
+
size 4539
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|