Training in progress, epoch 1
Browse files- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +4 -0
- merges.txt +0 -0
- runs/Apr01_01-33-39_c13/events.out.tfevents.1711949623.c13.1310215.0 +3 -0
- runs/Apr01_01-37-36_c13/events.out.tfevents.1711949859.c13.1310846.0 +3 -0
- runs/Apr01_01-38-24_c14/events.out.tfevents.1711949907.c14.956199.0 +3 -0
- runs/Apr01_01-43-30_c14/events.out.tfevents.1711950213.c14.956992.0 +3 -0
- runs/Apr01_01-44-48_c14/events.out.tfevents.1711950291.c14.957195.0 +3 -0
- runs/Feb25_09-56-01_octopod/events.out.tfevents.1708872962.octopod.386795.0 +3 -0
- runs/Mar31_22-52-27_c20/events.out.tfevents.1711939949.c20.1118889.0 +3 -0
- runs/Mar31_22-56-25_c13/events.out.tfevents.1711940188.c13.1284726.0 +3 -0
- runs/Mar31_23-00-42_c13/events.out.tfevents.1711940444.c13.1285511.0 +3 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer_config.json +51 -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": "facebook/opt-350m",
|
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": 128,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 256,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"project_out",
|
23 |
+
"fc1",
|
24 |
+
"out_proj",
|
25 |
+
"fc2",
|
26 |
+
"k_proj",
|
27 |
+
"v_proj",
|
28 |
+
"q_proj",
|
29 |
+
"project_in"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b091bee9c600c6fb0c1a5503133c101c1ad6f042cceafb7a8819c37a1b07d10
|
3 |
+
size 662065760
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 50265,
|
3 |
+
"<|im_start|>": 50266
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr01_01-33-39_c13/events.out.tfevents.1711949623.c13.1310215.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9822757c8bf04d79f8dafde1ffb710b0ab535ae117c8c8675623b72a1dd525b
|
3 |
+
size 4921
|
runs/Apr01_01-37-36_c13/events.out.tfevents.1711949859.c13.1310846.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:575ae5326f3e225ff1a124e52d94cc382d4f29b992587813d007814f431c483b
|
3 |
+
size 4921
|
runs/Apr01_01-38-24_c14/events.out.tfevents.1711949907.c14.956199.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c47809f270359fb615da1d1716271feabbc23d9d061c302865db3abeb0f30b6
|
3 |
+
size 4921
|
runs/Apr01_01-43-30_c14/events.out.tfevents.1711950213.c14.956992.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b9d384526569fe07efe5b0d51ecbc13444bc64752af89f44395a690d9408c91
|
3 |
+
size 4921
|
runs/Apr01_01-44-48_c14/events.out.tfevents.1711950291.c14.957195.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5478915d05e2d5ec327fcb18926ac0f4e7c1e5c833250811930b7cd9068630ee
|
3 |
+
size 5691
|
runs/Feb25_09-56-01_octopod/events.out.tfevents.1708872962.octopod.386795.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98e5514af1879729945bf667ecb72b9a5ca9ec99f00e3a54b5d746f4521e1683
|
3 |
+
size 4966
|
runs/Mar31_22-52-27_c20/events.out.tfevents.1711939949.c20.1118889.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c126e9e46f1677052fe34b375d7d843f60561e47a8c863ab48a4b6ff59abef2e
|
3 |
+
size 4923
|
runs/Mar31_22-56-25_c13/events.out.tfevents.1711940188.c13.1284726.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c68d1ed3026e10419f072cd516dcc137988e307daf0304f92b225114442ce6b3
|
3 |
+
size 4923
|
runs/Mar31_23-00-42_c13/events.out.tfevents.1711940444.c13.1285511.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:310de318537afa15055ca78414a558998a5c21a3c94edd338358f1593751bf94
|
3 |
+
size 4923
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|im_end|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|im_start|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<|im_start|>",
|
19 |
+
"eos_token": "<|im_end|>",
|
20 |
+
"pad_token": "<|im_end|>",
|
21 |
+
"unk_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"1": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"2": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50265": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"50266": {
|
30 |
+
"content": "<|im_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [
|
39 |
+
"<|im_end|>",
|
40 |
+
"<|im_start|>"
|
41 |
+
],
|
42 |
+
"bos_token": "<|im_start|>",
|
43 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"eos_token": "<|im_end|>",
|
46 |
+
"errors": "replace",
|
47 |
+
"model_max_length": 1000000000000000019884624838656,
|
48 |
+
"pad_token": "<|im_end|>",
|
49 |
+
"tokenizer_class": "GPT2Tokenizer",
|
50 |
+
"unk_token": "</s>"
|
51 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d44371b8199990b773f4cf21d190faa1ea32b40e4acb003244c16be5ccfe5b8
|
3 |
+
size 4792
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|