theoldmandthesea
commited on
Commit
•
f9e53cb
1
Parent(s):
fef8c7f
Updated model
Browse files- README.md +54 -0
- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +28 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Llama-2-7b-hf
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: BizConsultant
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# BizConsultant
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
16 |
+
|
17 |
+
## Model description
|
18 |
+
|
19 |
+
More information needed
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Training and evaluation data
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training procedure
|
30 |
+
|
31 |
+
### Training hyperparameters
|
32 |
+
|
33 |
+
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 0.0002
|
35 |
+
- train_batch_size: 1
|
36 |
+
- eval_batch_size: 8
|
37 |
+
- seed: 42
|
38 |
+
- gradient_accumulation_steps: 4
|
39 |
+
- total_train_batch_size: 4
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- lr_scheduler_warmup_steps: 2
|
43 |
+
- training_steps: 6
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.32.0.dev0
|
52 |
+
- Pytorch 2.0.0
|
53 |
+
- Datasets 2.14.4
|
54 |
+
- Tokenizers 0.13.3
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": null,
|
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": 64,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"gate_proj",
|
18 |
+
"o_proj",
|
19 |
+
"down_proj",
|
20 |
+
"k_proj",
|
21 |
+
"q_proj",
|
22 |
+
"v_proj",
|
23 |
+
"up_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a2fc323a0408cee7d756cfb402c31c80a8dcd3e782dc114de20c42a63ed16a2
|
3 |
+
size 160077005
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.0,
|
3 |
+
"total_flos": 42650566778880.0,
|
4 |
+
"train_loss": 2.389628251393636,
|
5 |
+
"train_runtime": 39.2629,
|
6 |
+
"train_samples_per_second": 0.611,
|
7 |
+
"train_steps_per_second": 0.153
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.0,
|
3 |
+
"total_flos": 42650566778880.0,
|
4 |
+
"train_loss": 2.389628251393636,
|
5 |
+
"train_runtime": 39.2629,
|
6 |
+
"train_samples_per_second": 0.611,
|
7 |
+
"train_steps_per_second": 0.153
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0013729977116704805,
|
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 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"step": 6,
|
14 |
+
"total_flos": 42650566778880.0,
|
15 |
+
"train_loss": 2.389628251393636,
|
16 |
+
"train_runtime": 39.2629,
|
17 |
+
"train_samples_per_second": 0.611,
|
18 |
+
"train_steps_per_second": 0.153
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 10,
|
22 |
+
"max_steps": 6,
|
23 |
+
"num_train_epochs": 1,
|
24 |
+
"save_steps": 500,
|
25 |
+
"total_flos": 42650566778880.0,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": null
|
28 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ac0db2deb2139cb448a023a3dc53a82c952d78c89d126c7a619268f1a86d61
|
3 |
+
size 4091
|