Training in progress, step 11400, checkpoint
Browse files- checkpoint-11400/README.md +21 -0
- checkpoint-11400/adapter_config.json +26 -0
- checkpoint-11400/adapter_model.bin +3 -0
- checkpoint-11400/added_tokens.json +8 -0
- checkpoint-11400/optimizer.pt +3 -0
- checkpoint-11400/rng_state.pth +3 -0
- checkpoint-11400/scheduler.pt +3 -0
- checkpoint-11400/special_tokens_map.json +11 -0
- checkpoint-11400/tokenizer.model +3 -0
- checkpoint-11400/tokenizer_config.json +74 -0
- checkpoint-11400/trainer_state.json +0 -0
- checkpoint-11400/training_args.bin +3 -0
checkpoint-11400/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.4.0
|
checkpoint-11400/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "SkunkworksAI/Mistralic-7B-1",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"o_proj",
|
18 |
+
"up_proj",
|
19 |
+
"q_proj",
|
20 |
+
"gate_proj",
|
21 |
+
"k_proj",
|
22 |
+
"v_proj",
|
23 |
+
"down_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-11400/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:985777fa90d240f66ba4e01ab74335b554a22bebf91b8d26ea7462f6e91ed3c1
|
3 |
+
size 335706314
|
checkpoint-11400/added_tokens.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0,
|
5 |
+
"<|im_end|>": 32000,
|
6 |
+
"<|im_start|>": 32001,
|
7 |
+
"[PAD]": 32002
|
8 |
+
}
|
checkpoint-11400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9e3715ff330af0314d07359f72c44592c52d9d353a24acce5ee6a1841f5c35a
|
3 |
+
size 1342453434
|
checkpoint-11400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b88ad0d6508afb1eceb7ad48f9a2efdb094acab5b84b6cdbbf013deb8390d15e
|
3 |
+
size 14180
|
checkpoint-11400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a84682ccab9034dd09cdca368957f2316132abef40cf21a4a5de34fc2e36d6c4
|
3 |
+
size 1064
|
checkpoint-11400/special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
checkpoint-11400/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-11400/tokenizer_config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": true,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": true,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": true,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": true,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|im_end|>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": true,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|im_start|>",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "[PAD]",
|
47 |
+
"lstrip": true,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<unk>",
|
56 |
+
"<s>",
|
57 |
+
"</s>"
|
58 |
+
],
|
59 |
+
"bos_token": "<s>",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "</s>",
|
62 |
+
"legacy": true,
|
63 |
+
"model_max_length": 1000000000000000019884624838656,
|
64 |
+
"pad_token": "[PAD]",
|
65 |
+
"padding_side": "right",
|
66 |
+
"sp_model_kwargs": {},
|
67 |
+
"spaces_between_special_tokens": false,
|
68 |
+
"tokenizer_class": "LlamaTokenizer",
|
69 |
+
"tokenizer_file": null,
|
70 |
+
"trust_remote_code": false,
|
71 |
+
"unk_token": "<unk>",
|
72 |
+
"use_default_system_prompt": true,
|
73 |
+
"use_fast": true
|
74 |
+
}
|
checkpoint-11400/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-11400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82011218927c454a3c72e42fcb2e27f36999c5f454001eb2a7f9b2c6d4f761a
|
3 |
+
size 6392
|