CreatorPhan
commited on
Commit
•
43cdb1d
1
Parent(s):
880d674
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +0 -13
- adapter_model.bin +1 -1
- checkpoint-1000/README.md +34 -0
- checkpoint-1000/adapter_config.json +23 -0
- checkpoint-1000/adapter_model.bin +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +6 -0
- checkpoint-1000/tokenizer.json +3 -0
- checkpoint-1000/tokenizer_config.json +10 -0
- checkpoint-1000/trainer_state.json +0 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1100/README.md +34 -0
- checkpoint-1100/adapter_config.json +23 -0
- checkpoint-1100/adapter_model.bin +3 -0
- checkpoint-1100/optimizer.pt +3 -0
- checkpoint-1100/rng_state.pth +3 -0
- checkpoint-1100/scheduler.pt +3 -0
- checkpoint-1100/special_tokens_map.json +6 -0
- checkpoint-1100/tokenizer.json +3 -0
- checkpoint-1100/tokenizer_config.json +10 -0
- checkpoint-1100/trainer_state.json +0 -0
- checkpoint-1100/training_args.bin +3 -0
- checkpoint-1200/README.md +34 -0
- checkpoint-1200/adapter_config.json +23 -0
- checkpoint-1200/adapter_model.bin +3 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/special_tokens_map.json +6 -0
- checkpoint-1200/tokenizer.json +3 -0
- checkpoint-1200/tokenizer_config.json +10 -0
- checkpoint-1200/trainer_state.json +0 -0
- checkpoint-1200/training_args.bin +3 -0
- checkpoint-1300/README.md +34 -0
- checkpoint-1300/adapter_config.json +23 -0
- checkpoint-1300/adapter_model.bin +3 -0
- checkpoint-1300/optimizer.pt +3 -0
- checkpoint-1300/rng_state.pth +3 -0
- checkpoint-1300/scheduler.pt +3 -0
- checkpoint-1300/special_tokens_map.json +6 -0
- checkpoint-1300/tokenizer.json +3 -0
- checkpoint-1300/tokenizer_config.json +10 -0
- checkpoint-1300/trainer_state.json +0 -0
- checkpoint-1300/training_args.bin +3 -0
- checkpoint-1400/README.md +34 -0
- checkpoint-1400/adapter_config.json +23 -0
- checkpoint-1400/adapter_model.bin +3 -0
- checkpoint-1400/optimizer.pt +3 -0
README.md
CHANGED
@@ -4,18 +4,6 @@ library_name: peft
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
7 |
-
The following `bitsandbytes` quantization config was used during training:
|
8 |
-
- quant_method: bitsandbytes
|
9 |
-
- load_in_8bit: True
|
10 |
-
- load_in_4bit: False
|
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: fp4
|
16 |
-
- bnb_4bit_use_double_quant: False
|
17 |
-
- bnb_4bit_compute_dtype: float32
|
18 |
-
|
19 |
The following `bitsandbytes` quantization config was used during training:
|
20 |
- quant_method: bitsandbytes
|
21 |
- load_in_8bit: True
|
@@ -29,6 +17,5 @@ The following `bitsandbytes` quantization config was used during training:
|
|
29 |
- bnb_4bit_compute_dtype: float32
|
30 |
### Framework versions
|
31 |
|
32 |
-
- PEFT 0.6.0.dev0
|
33 |
|
34 |
- PEFT 0.6.0.dev0
|
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
The following `bitsandbytes` quantization config was used during training:
|
8 |
- quant_method: bitsandbytes
|
9 |
- load_in_8bit: True
|
|
|
17 |
- bnb_4bit_compute_dtype: float32
|
18 |
### Framework versions
|
19 |
|
|
|
20 |
|
21 |
- PEFT 0.6.0.dev0
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39409357
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc8aa748553051f477f8856a04dab6c16386e77b50764d21abc20a51512c7c1e
|
3 |
size 39409357
|
checkpoint-1000/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: True
|
10 |
+
- load_in_4bit: False
|
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: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: True
|
22 |
+
- load_in_4bit: False
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: fp4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float32
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-1000/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
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,
|
11 |
+
"lora_dropout": 0.0,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"dense_4h_to_h",
|
18 |
+
"dense",
|
19 |
+
"dense_h_to_4h",
|
20 |
+
"query_key_value"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-1000/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f453889b7b5f1f21797413708a1c82782ca563c8173a223b50fb5e004837c160
|
3 |
+
size 39409357
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:980ce4082f86e8643d829ecc076ea00335d9e2d80d18c421ae802d241b9e3197
|
3 |
+
size 78844421
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5432f961e7c82cbe7b6ec30d027cf3db4d17372f65774be8cf037a208cbc1ac
|
3 |
+
size 14575
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203097d159784262bd5c95fedbda5673a26bd26ba8483bc4d9972c3ce0a53781
|
3 |
+
size 627
|
checkpoint-1000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
|
3 |
+
size 14500471
|
checkpoint-1000/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"tokenizer_class": "BloomTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
|
3 |
+
size 4155
|
checkpoint-1100/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: True
|
10 |
+
- load_in_4bit: False
|
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: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: True
|
22 |
+
- load_in_4bit: False
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: fp4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float32
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-1100/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
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,
|
11 |
+
"lora_dropout": 0.0,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"dense_4h_to_h",
|
18 |
+
"dense",
|
19 |
+
"dense_h_to_4h",
|
20 |
+
"query_key_value"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-1100/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:475f2b2ac94b5181337d2afa8e4c9ca58b6bb0a30162d0174dc0d849d31a30b0
|
3 |
+
size 39409357
|
checkpoint-1100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2866f6f91b96afb3514ac044018e0555e8cbf2349cf0707fcab04ed3fddf495
|
3 |
+
size 78844421
|
checkpoint-1100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a2ce2e2326ca04fc964861061399d5335411f688384a0f62f8f943f1fff584e
|
3 |
+
size 14575
|
checkpoint-1100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4088610c769d87bd694b880357ee2736f8d9456a674ba2deac6ae25ba56fffaa
|
3 |
+
size 627
|
checkpoint-1100/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-1100/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
|
3 |
+
size 14500471
|
checkpoint-1100/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"tokenizer_class": "BloomTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-1100/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
|
3 |
+
size 4155
|
checkpoint-1200/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: True
|
10 |
+
- load_in_4bit: False
|
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: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: True
|
22 |
+
- load_in_4bit: False
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: fp4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float32
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-1200/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
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,
|
11 |
+
"lora_dropout": 0.0,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"dense_4h_to_h",
|
18 |
+
"dense",
|
19 |
+
"dense_h_to_4h",
|
20 |
+
"query_key_value"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-1200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d13f1953081527a4a05ac5762a6e373fae509922a72baa18bfbc0ea2fdd0db77
|
3 |
+
size 39409357
|
checkpoint-1200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b4d37b67055d94cd6568b24b76e241acc964153f215407a64e94710d00d1e06
|
3 |
+
size 78844421
|
checkpoint-1200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b32bbef891dbdd3524f32551a03a56bb081b6c86879cea3d24ae28b3c8f4bc5f
|
3 |
+
size 14575
|
checkpoint-1200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13122a9f43d31f9abd38d193f16e53342905df794d9995e7f5483234c3e54c54
|
3 |
+
size 627
|
checkpoint-1200/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-1200/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
|
3 |
+
size 14500471
|
checkpoint-1200/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"tokenizer_class": "BloomTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-1200/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
|
3 |
+
size 4155
|
checkpoint-1300/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: True
|
10 |
+
- load_in_4bit: False
|
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: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: True
|
22 |
+
- load_in_4bit: False
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: fp4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float32
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-1300/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
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,
|
11 |
+
"lora_dropout": 0.0,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"dense_4h_to_h",
|
18 |
+
"dense",
|
19 |
+
"dense_h_to_4h",
|
20 |
+
"query_key_value"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-1300/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:557e20c98ce81a1b2174b31161d704a79e1057d7cba9a8a3a044698f748e1a96
|
3 |
+
size 39409357
|
checkpoint-1300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2311ed46f1164ff3772d9c69e8f7347964538333edd4438abef82e7683876dc
|
3 |
+
size 78844421
|
checkpoint-1300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2233b71d28d82b8331de6224e1abb884bd9108ce746c680fd1c4d641c935668
|
3 |
+
size 14575
|
checkpoint-1300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af8fb4309008de879e60055efbf110ed70c676d2270a50eb4a6b5b40910d4878
|
3 |
+
size 627
|
checkpoint-1300/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-1300/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
|
3 |
+
size 14500471
|
checkpoint-1300/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"tokenizer_class": "BloomTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-1300/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
|
3 |
+
size 4155
|
checkpoint-1400/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: True
|
10 |
+
- load_in_4bit: False
|
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: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: True
|
22 |
+
- load_in_4bit: False
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: fp4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float32
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-1400/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
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,
|
11 |
+
"lora_dropout": 0.0,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"dense_4h_to_h",
|
18 |
+
"dense",
|
19 |
+
"dense_h_to_4h",
|
20 |
+
"query_key_value"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-1400/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:019860e9604c2bce3e1eb82f3a576a7272afd222d602f5fba5c803b83043ee76
|
3 |
+
size 39409357
|
checkpoint-1400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dff811fb285c320d3235ecb226a73a05ba2c9fa3c8dcea292fb556c245eba3c7
|
3 |
+
size 78844421
|