Training in progress, step 600
Browse files- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- merges.txt +0 -0
- runs/Jul11_08-27-13_dohub-thlong-ai-codehub-67647dd758-c55gp/events.out.tfevents.1720686440.dohub-thlong-ai-codehub-67647dd758-c55gp.159722.0 +3 -0
- runs/Jul11_08-36-43_dohub-thlong-ai-codehub-67647dd758-c55gp/events.out.tfevents.1720687007.dohub-thlong-ai-codehub-67647dd758-c55gp.162176.0 +3 -0
- runs/Jul11_08-45-12_dohub-thlong-ai-codehub-67647dd758-c55gp/events.out.tfevents.1720687514.dohub-thlong-ai-codehub-67647dd758-c55gp.164936.0 +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +50 -0
- training_args.bin +3 -0
- vocab.json +0 -0
adapter_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-1.5B",
|
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": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"lm_head",
|
25 |
+
"k_proj",
|
26 |
+
"up_proj",
|
27 |
+
"v_proj",
|
28 |
+
"o_proj",
|
29 |
+
"down_proj",
|
30 |
+
"q_proj"
|
31 |
+
],
|
32 |
+
"task_type": "CAUSAL_LM",
|
33 |
+
"use_dora": false,
|
34 |
+
"use_rslora": false
|
35 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7691bc65892bac706d7ad70a079ee4b36cc7268e19a8377519db90cf6d73dc21
|
3 |
+
size 1017229528
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jul11_08-27-13_dohub-thlong-ai-codehub-67647dd758-c55gp/events.out.tfevents.1720686440.dohub-thlong-ai-codehub-67647dd758-c55gp.159722.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acae27c2528d785a38f8a9090ad704c25a589d28710beac7dfd0bfe537f8bc72
|
3 |
+
size 16945
|
runs/Jul11_08-36-43_dohub-thlong-ai-codehub-67647dd758-c55gp/events.out.tfevents.1720687007.dohub-thlong-ai-codehub-67647dd758-c55gp.162176.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fb77ed1c554c35225ae00e59ea62c25c72e9e0e7f16275e5f857962fb00878b
|
3 |
+
size 16945
|
runs/Jul11_08-45-12_dohub-thlong-ai-codehub-67647dd758-c55gp/events.out.tfevents.1720687514.dohub-thlong-ai-codehub-67647dd758-c55gp.164936.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c52215fc84eb6187b5099b1822fc6b73503857f955cedd77221e7f60b692dee7
|
3 |
+
size 17909
|
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 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 512,
|
39 |
+
"model_max_length": 32768,
|
40 |
+
"pad_to_multiple_of": null,
|
41 |
+
"pad_token": "<|endoftext|>",
|
42 |
+
"pad_token_type_id": 0,
|
43 |
+
"padding_side": "right",
|
44 |
+
"split_special_tokens": false,
|
45 |
+
"stride": 0,
|
46 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
47 |
+
"truncation_side": "right",
|
48 |
+
"truncation_strategy": "longest_first",
|
49 |
+
"unk_token": null
|
50 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f203c239c4cec4ae0f20b8df027141ae6e9dc293c497c04f5b902ecf835d5f65
|
3 |
+
size 5432
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|