NobleMathews
commited on
Commit
β’
3d1c8ad
1
Parent(s):
05e4dfa
Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
- added_tokens.json +6 -0
- checkpoint-12/README.md +34 -0
- checkpoint-12/adapter_config.json +23 -0
- checkpoint-12/adapter_model.bin +3 -0
- checkpoint-12/added_tokens.json +6 -0
- checkpoint-12/optimizer.pt +3 -0
- checkpoint-12/rng_state_0.pth +3 -0
- checkpoint-12/rng_state_1.pth +3 -0
- checkpoint-12/rng_state_2.pth +3 -0
- checkpoint-12/rng_state_3.pth +3 -0
- checkpoint-12/rng_state_4.pth +3 -0
- checkpoint-12/scheduler.pt +3 -0
- checkpoint-12/special_tokens_map.json +30 -0
- checkpoint-12/tokenizer.json +0 -0
- checkpoint-12/tokenizer.model +3 -0
- checkpoint-12/tokenizer_config.json +44 -0
- checkpoint-12/trainer_state.json +79 -0
- checkpoint-12/training_args.bin +3 -0
- runs/Sep27_02-45-57_watgpu308/events.out.tfevents.1695782758.watgpu308.134136.0 +3 -0
- runs/Sep27_03-35-54_watgpu308/events.out.tfevents.1695785756.watgpu308.135013.0 +3 -0
- runs/Sep27_03-42-19_watgpu308/events.out.tfevents.1695786141.watgpu308.135308.0 +3 -0
- runs/Sep27_03-45-34_watgpu308/events.out.tfevents.1695786335.watgpu308.135599.0 +3 -0
- runs/Sep27_04-12-32_watgpu308/events.out.tfevents.1695787953.watgpu308.135921.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- training_args.bin +3 -0
- training_params.json +1 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
widget:
|
6 |
+
- text: "I love AutoTrain because "
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Trained Using AutoTrain
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-Python-hf",
|
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 |
+
"lora_alpha": 64,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 32,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad08a13448968a1c90fe5b9c031048f4eea166d4d2d71c31e7b6763541ced6f6
|
3 |
+
size 67154893
|
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"β<EOT>": 32003,
|
3 |
+
"β<MID>": 32001,
|
4 |
+
"β<PRE>": 32000,
|
5 |
+
"β<SUF>": 32002
|
6 |
+
}
|
checkpoint-12/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: 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: False
|
17 |
+
- bnb_4bit_compute_dtype: float16
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: False
|
22 |
+
- load_in_4bit: True
|
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: nf4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float16
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-12/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-Python-hf",
|
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 |
+
"lora_alpha": 64,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 32,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-12/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad08a13448968a1c90fe5b9c031048f4eea166d4d2d71c31e7b6763541ced6f6
|
3 |
+
size 67154893
|
checkpoint-12/added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"β<EOT>": 32003,
|
3 |
+
"β<MID>": 32001,
|
4 |
+
"β<PRE>": 32000,
|
5 |
+
"β<SUF>": 32002
|
6 |
+
}
|
checkpoint-12/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74a4ea92f22fc96a0d4074f4f8aa0b738d3830f9b17bd5709f8dee66071641e6
|
3 |
+
size 134325445
|
checkpoint-12/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d721a336286dc83d73a4f5dea214e2a10a0504b44cc0df4658691c76ca84b18b
|
3 |
+
size 18615
|
checkpoint-12/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c2413ae53fc1ef17a4cd89e1a13b34e3414058f2ac68662bf808e647a540e6c
|
3 |
+
size 18679
|
checkpoint-12/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a743cd664f30abe5e3c0bca0955ec7b0b17a7ca5e447a2629efb5df37a80c915
|
3 |
+
size 18679
|
checkpoint-12/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2456791adb431abc17aef99ba1e664360f2ee95d451aea411082812e87cf3cdc
|
3 |
+
size 18679
|
checkpoint-12/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c582bdf9a62052f5c7714ea0ad98e66325cda0c6c58759c0be919e992608b43
|
3 |
+
size 18679
|
checkpoint-12/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:261697186a97391ee0bf89f29f8cf2242833166e1803758175a2f9c4c4ef9454
|
3 |
+
size 627
|
checkpoint-12/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"content": "<s>",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": true,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": "</s>",
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-12/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-12/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-12/tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"__type": "AddedToken",
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"clean_up_tokenization_spaces": false,
|
17 |
+
"eos_token": {
|
18 |
+
"__type": "AddedToken",
|
19 |
+
"content": "</s>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": true,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"eot_token": "β<EOT>",
|
26 |
+
"fill_token": "<FILL_ME>",
|
27 |
+
"legacy": null,
|
28 |
+
"middle_token": "β<MID>",
|
29 |
+
"model_max_length": 4096,
|
30 |
+
"pad_token": null,
|
31 |
+
"prefix_token": "β<PRE>",
|
32 |
+
"sp_model_kwargs": {},
|
33 |
+
"suffix_token": "β<SUF>",
|
34 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
35 |
+
"unk_token": {
|
36 |
+
"__type": "AddedToken",
|
37 |
+
"content": "<unk>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false
|
42 |
+
},
|
43 |
+
"use_default_system_prompt": false
|
44 |
+
}
|
checkpoint-12/trainer_state.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7733290791511536,
|
3 |
+
"best_model_checkpoint": "ctllama7b/checkpoint-12",
|
4 |
+
"epoch": 5.086956521739131,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 12,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09,
|
13 |
+
"eval_loss": 0.9089534878730774,
|
14 |
+
"eval_runtime": 8.5765,
|
15 |
+
"eval_samples_per_second": 10.027,
|
16 |
+
"eval_steps_per_second": 0.7,
|
17 |
+
"step": 2
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.09,
|
21 |
+
"eval_loss": 0.9039565920829773,
|
22 |
+
"eval_runtime": 8.6271,
|
23 |
+
"eval_samples_per_second": 9.969,
|
24 |
+
"eval_steps_per_second": 0.695,
|
25 |
+
"step": 4
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.04,
|
29 |
+
"learning_rate": 7.1428571428571436e-06,
|
30 |
+
"loss": 0.8946,
|
31 |
+
"step": 5
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.09,
|
35 |
+
"eval_loss": 0.8744738101959229,
|
36 |
+
"eval_runtime": 8.6363,
|
37 |
+
"eval_samples_per_second": 9.958,
|
38 |
+
"eval_steps_per_second": 0.695,
|
39 |
+
"step": 6
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.09,
|
43 |
+
"eval_loss": 0.8518250584602356,
|
44 |
+
"eval_runtime": 8.6389,
|
45 |
+
"eval_samples_per_second": 9.955,
|
46 |
+
"eval_steps_per_second": 0.695,
|
47 |
+
"step": 8
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 4.09,
|
51 |
+
"learning_rate": 1.4285714285714287e-05,
|
52 |
+
"loss": 0.844,
|
53 |
+
"step": 10
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.09,
|
57 |
+
"eval_loss": 0.7924608588218689,
|
58 |
+
"eval_runtime": 8.6417,
|
59 |
+
"eval_samples_per_second": 9.952,
|
60 |
+
"eval_steps_per_second": 0.694,
|
61 |
+
"step": 10
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 5.09,
|
65 |
+
"eval_loss": 0.7733290791511536,
|
66 |
+
"eval_runtime": 8.6368,
|
67 |
+
"eval_samples_per_second": 9.957,
|
68 |
+
"eval_steps_per_second": 0.695,
|
69 |
+
"step": 12
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 5,
|
73 |
+
"max_steps": 138,
|
74 |
+
"num_train_epochs": 6,
|
75 |
+
"save_steps": 500,
|
76 |
+
"total_flos": 1.2482646458236928e+16,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": null
|
79 |
+
}
|
checkpoint-12/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a28d331e80dabfad199c64be770675c6c306ca4fdc0aa80d4b3ae144a4ca1259
|
3 |
+
size 4027
|
runs/Sep27_02-45-57_watgpu308/events.out.tfevents.1695782758.watgpu308.134136.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25122db6efaec7fac9d5a50302758427a662d1c2bcece98b25682cc8ea2cffed
|
3 |
+
size 6704
|
runs/Sep27_03-35-54_watgpu308/events.out.tfevents.1695785756.watgpu308.135013.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa07ab269a73f2fca2fae691f88ae1e93be047fe41430087da8fdde474fc2701
|
3 |
+
size 4452
|
runs/Sep27_03-42-19_watgpu308/events.out.tfevents.1695786141.watgpu308.135308.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24b11c29557594ed135a1d5316cad13c7447b26e675677980faf28bb9e99ca16
|
3 |
+
size 4452
|
runs/Sep27_03-45-34_watgpu308/events.out.tfevents.1695786335.watgpu308.135599.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34c28b9bbe72f26d623eb75535cecfcaccf38810c7ef3637bcee058ea7f19cd3
|
3 |
+
size 6704
|
runs/Sep27_04-12-32_watgpu308/events.out.tfevents.1695787953.watgpu308.135921.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:654c12fcfc131f46f66932b2b7411624f5ecb4389432c2c11dd16b27a8a3e99e
|
3 |
+
size 6704
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"content": "<s>",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": true,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": "</s>",
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"__type": "AddedToken",
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"clean_up_tokenization_spaces": false,
|
17 |
+
"eos_token": {
|
18 |
+
"__type": "AddedToken",
|
19 |
+
"content": "</s>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": true,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"eot_token": "β<EOT>",
|
26 |
+
"fill_token": "<FILL_ME>",
|
27 |
+
"legacy": null,
|
28 |
+
"middle_token": "β<MID>",
|
29 |
+
"model_max_length": 4096,
|
30 |
+
"pad_token": null,
|
31 |
+
"prefix_token": "β<PRE>",
|
32 |
+
"sp_model_kwargs": {},
|
33 |
+
"suffix_token": "β<SUF>",
|
34 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
35 |
+
"unk_token": {
|
36 |
+
"__type": "AddedToken",
|
37 |
+
"content": "<unk>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false
|
42 |
+
},
|
43 |
+
"use_default_system_prompt": false
|
44 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a28d331e80dabfad199c64be770675c6c306ca4fdc0aa80d4b3ae144a4ca1259
|
3 |
+
size 4027
|
training_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "codellama/CodeLlama-7b-Python-hf", "data_path": "/u3/ns3mathe/tdg/2_code_llama_finetuning/dataset_processing/data", "project_name": "ctllama7b", "train_split": "train", "valid_split": "validation", "text_column": "text", "lr": 2e-05, "epochs": 6, "batch_size": 3, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 4096, "use_peft": true, "lora_r": 32, "lora_alpha": 64, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 4096, "repo_id": "NobleMathews/ctllama7b", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}
|