Training in progress, step 160
Browse files- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- runs/May14_03-38-19_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715657942.ip-172-31-69-60.ec2.internal.11813.0 +3 -0
- runs/May14_03-42-15_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715658154.ip-172-31-69-60.ec2.internal.17129.0 +3 -0
- runs/May14_03-43-29_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715658226.ip-172-31-69-60.ec2.internal.19160.0 +3 -0
- runs/May14_03-44-45_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715658302.ip-172-31-69-60.ec2.internal.21202.0 +3 -0
- runs/May14_04-12-42_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715659979.ip-172-31-69-60.ec2.internal.12033.0 +3 -0
- runs/May14_04-18-17_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715660313.ip-172-31-69-60.ec2.internal.20085.0 +3 -0
- runs/May14_04-19-25_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715660382.ip-172-31-69-60.ec2.internal.21964.0 +3 -0
- runs/May14_05-10-08_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715663425.ip-172-31-69-60.ec2.internal.48805.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": 8,
|
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": 6,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"gate_proj",
|
23 |
+
"up_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj",
|
26 |
+
"down_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f2322ae4cfbeef77094de2270bb403a4b46e262f22203b5beeb0dbb61905e39
|
3 |
+
size 31516744
|
runs/May14_03-38-19_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715657942.ip-172-31-69-60.ec2.internal.11813.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e89c127e4fd62ff450646c3fc0d88a5eee55cb058d14c8b0a7d5a9ad58d989
|
3 |
+
size 4682
|
runs/May14_03-42-15_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715658154.ip-172-31-69-60.ec2.internal.17129.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e465020b9bf8fc7acfb39cefd986cdadbb42bd7827336909d3679c1bd7640140
|
3 |
+
size 4682
|
runs/May14_03-43-29_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715658226.ip-172-31-69-60.ec2.internal.19160.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d42c86635b406759e525ac7d41e78e3444c609ff463e51bac27a7e29fea5ebc0
|
3 |
+
size 4889
|
runs/May14_03-44-45_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715658302.ip-172-31-69-60.ec2.internal.21202.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7083fc21fde727d35d2a24d1ee1a1a66ae70d54508a0d82206f7b2f4e678c897
|
3 |
+
size 7373
|
runs/May14_04-12-42_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715659979.ip-172-31-69-60.ec2.internal.12033.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dcf8d0dbd82f07cbca8a1d9ea0e04615d477996cd3db326e53b804fbdf1e3fa
|
3 |
+
size 4889
|
runs/May14_04-18-17_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715660313.ip-172-31-69-60.ec2.internal.20085.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9da8c0a927dbd42df96c2d40ffd95c24893def4b9c8374754f0c61c1e27c891
|
3 |
+
size 4681
|
runs/May14_04-19-25_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715660382.ip-172-31-69-60.ec2.internal.21964.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8dc3c047f91795215c6257ac5adeba0e2e12e23a14fe41ac5dfe4e4225c73dd
|
3 |
+
size 7372
|
runs/May14_05-10-08_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715663425.ip-172-31-69-60.ec2.internal.48805.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c6931de8b8b882ed126e0bd1fe5874c78fcdf14bc00b0c0811b728b8a9d395
|
3 |
+
size 9677
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a925774678852e0977560a67fd69a20001a407d91d0a08c8f775a475480c8b8
|
3 |
+
size 6072
|