madhan2301
commited on
Commit
·
193eed5
1
Parent(s):
3570823
Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- checkpoint-6/README.md +34 -0
- checkpoint-6/adapter_config.json +20 -0
- checkpoint-6/adapter_model.bin +3 -0
- checkpoint-6/optimizer.pt +3 -0
- checkpoint-6/rng_state.pth +3 -0
- checkpoint-6/scheduler.pt +3 -0
- checkpoint-6/special_tokens_map.json +4 -0
- checkpoint-6/tokenizer.json +0 -0
- checkpoint-6/tokenizer_config.json +6 -0
- checkpoint-6/trainer_state.json +18 -0
- checkpoint-6/training_args.bin +3 -0
- runs/Aug22_15-30-55_10dc72f89191/events.out.tfevents.1692718255.10dc72f89191.2514.0 +3 -0
- special_tokens_map.json +4 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "stabilityai/stablecode-instruct-alpha-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": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"query_key_value"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49d8d1fbf84cc67d435741eeb42c7e946b77c00aa1394564af757ebb14f313f
|
3 |
+
size 20995057
|
checkpoint-6/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 0.5.0
|
33 |
+
|
34 |
+
- PEFT 0.5.0
|
checkpoint-6/adapter_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "stabilityai/stablecode-instruct-alpha-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": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"query_key_value"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
checkpoint-6/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49d8d1fbf84cc67d435741eeb42c7e946b77c00aa1394564af757ebb14f313f
|
3 |
+
size 20995057
|
checkpoint-6/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b303fcd79d501ce97fd27111fb998ebc243e2fcffa631a1189f4eefef2f8b38
|
3 |
+
size 41996805
|
checkpoint-6/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a789f231409e7671b5bc08dfe3e723ee0840c6fbca6a399dc7f91c5faed4aeb
|
3 |
+
size 14575
|
checkpoint-6/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41ecd2fbe1b8f6aa58297dfb7c99825739c34a2e6aa391842acd5a91d681ceb7
|
3 |
+
size 627
|
checkpoint-6/special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<|endoftext|>",
|
3 |
+
"pad_token": "<|endoftext|>"
|
4 |
+
}
|
checkpoint-6/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6/tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 2048,
|
4 |
+
"padding_side": "right",
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
+
}
|
checkpoint-6/trainer_state.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [],
|
11 |
+
"logging_steps": 12,
|
12 |
+
"max_steps": 60,
|
13 |
+
"num_train_epochs": 1,
|
14 |
+
"save_steps": 500,
|
15 |
+
"total_flos": 93971042795520.0,
|
16 |
+
"trial_name": null,
|
17 |
+
"trial_params": null
|
18 |
+
}
|
checkpoint-6/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b28def0eb50ff7518cf64bc069313eadc8bfd53fded24ffbc6a61ab412349e2
|
3 |
+
size 4027
|
runs/Aug22_15-30-55_10dc72f89191/events.out.tfevents.1692718255.10dc72f89191.2514.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ed53891c30652f0cfb06cad34f6951826f221e375e17e24934371a50b14fa98
|
3 |
+
size 4897
|
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<|endoftext|>",
|
3 |
+
"pad_token": "<|endoftext|>"
|
4 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 2048,
|
4 |
+
"padding_side": "right",
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b28def0eb50ff7518cf64bc069313eadc8bfd53fded24ffbc6a61ab412349e2
|
3 |
+
size 4027
|
training_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "stabilityai/stablecode-instruct-alpha-3b", "data_path": "aboonaji/alpaca_micro_demo", "project_name": "TuneLLM", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 1, "batch_size": 2, "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": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "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": 1024, "repo_id": "madhan2301/Stable-code-FineTuned-version", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}
|