prateeky2806
commited on
Commit
·
caa2f34
1
Parent(s):
49448e2
Training in progress, step 3200
Browse files- adapter_model.bin +1 -1
- checkpoint-2800/adapter_model/adapter_model/README.md +12 -0
- checkpoint-2800/adapter_model/adapter_model/adapter_model.bin +1 -1
- checkpoint-3200/README.md +20 -0
- checkpoint-3200/adapter_config.json +26 -0
- checkpoint-3200/adapter_model.bin +3 -0
- checkpoint-3200/added_tokens.json +3 -0
- checkpoint-3200/optimizer.pt +3 -0
- checkpoint-3200/rng_state.pth +3 -0
- checkpoint-3200/scheduler.pt +3 -0
- checkpoint-3200/special_tokens_map.json +6 -0
- checkpoint-3200/tokenizer.model +3 -0
- checkpoint-3200/tokenizer_config.json +35 -0
- checkpoint-3200/trainer_state.json +0 -0
- checkpoint-3200/training_args.bin +3 -0
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319977229
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b31ff1fa7512b97c86022fd6817ddd126b6e34652f8f60daea2706ad8422fa3a
|
3 |
size 319977229
|
checkpoint-2800/adapter_model/adapter_model/README.md
CHANGED
@@ -4,6 +4,17 @@ library_name: peft
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
The following `bitsandbytes` quantization config was used during training:
|
8 |
- load_in_8bit: False
|
9 |
- load_in_4bit: True
|
@@ -16,5 +27,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
16 |
- bnb_4bit_compute_dtype: bfloat16
|
17 |
### Framework versions
|
18 |
|
|
|
19 |
|
20 |
- PEFT 0.4.0
|
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: False
|
9 |
+
- load_in_4bit: True
|
10 |
+
- llm_int8_threshold: 6.0
|
11 |
+
- llm_int8_skip_modules: None
|
12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
13 |
+
- llm_int8_has_fp16_weight: False
|
14 |
+
- bnb_4bit_quant_type: nf4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
|
18 |
The following `bitsandbytes` quantization config was used during training:
|
19 |
- load_in_8bit: False
|
20 |
- load_in_4bit: True
|
|
|
27 |
- bnb_4bit_compute_dtype: bfloat16
|
28 |
### Framework versions
|
29 |
|
30 |
+
- PEFT 0.4.0
|
31 |
|
32 |
- PEFT 0.4.0
|
checkpoint-2800/adapter_model/adapter_model/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319977229
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:491401ca3f291de401e624be90eec8b82f47608e4a5b92375841a78f20ef31a2
|
3 |
size 319977229
|
checkpoint-3200/README.md
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: False
|
9 |
+
- load_in_4bit: True
|
10 |
+
- llm_int8_threshold: 6.0
|
11 |
+
- llm_int8_skip_modules: None
|
12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
13 |
+
- llm_int8_has_fp16_weight: False
|
14 |
+
- bnb_4bit_quant_type: nf4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
### Framework versions
|
18 |
+
|
19 |
+
|
20 |
+
- PEFT 0.4.0
|
checkpoint-3200/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
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 |
+
"up_proj",
|
18 |
+
"down_proj",
|
19 |
+
"gate_proj",
|
20 |
+
"v_proj",
|
21 |
+
"o_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-3200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b31ff1fa7512b97c86022fd6817ddd126b6e34652f8f60daea2706ad8422fa3a
|
3 |
+
size 319977229
|
checkpoint-3200/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
checkpoint-3200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b6523ebee19a3851ecd02d668d4c697f0012fd2ec145c27e2a77c1a419d9b1e
|
3 |
+
size 1279539973
|
checkpoint-3200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6ca7252308ca0c1e30c28172b0cd6f8ed67827371a16beb65b45afd58b5dd8b
|
3 |
+
size 14511
|
checkpoint-3200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
|
3 |
+
size 627
|
checkpoint-3200/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<unk>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-3200/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-3200/tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-3200/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc844453681a251fdf8c3fc912cbe0e758ca7584bc5f76e223f598c3f259462e
|
3 |
+
size 6011
|