Adapter
Browse files- README.md +57 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +90 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
base_model: meta-llama/Llama-2-7b-hf
|
6 |
+
model-index:
|
7 |
+
- name: Adapter
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# Adapter
|
15 |
+
|
16 |
+
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.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0002
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 4
|
40 |
+
- total_train_batch_size: 4
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 2
|
44 |
+
- training_steps: 10
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- PEFT 0.8.2
|
54 |
+
- Transformers 4.37.2
|
55 |
+
- Pytorch 2.2.0+cu121
|
56 |
+
- Datasets 2.17.0
|
57 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-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 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 64,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"base_layer"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2436678237584e664f8fa19926c6bc740291eb07999bece5d55bc63099d04c60
|
3 |
+
size 959884168
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.0,
|
3 |
+
"total_flos": 333801262080000.0,
|
4 |
+
"train_loss": 1.2641676783561706,
|
5 |
+
"train_runtime": 52.6099,
|
6 |
+
"train_samples_per_second": 0.76,
|
7 |
+
"train_steps_per_second": 0.19
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.0,
|
3 |
+
"total_flos": 333801262080000.0,
|
4 |
+
"train_loss": 1.2641676783561706,
|
5 |
+
"train_runtime": 52.6099,
|
6 |
+
"train_samples_per_second": 0.76,
|
7 |
+
"train_steps_per_second": 0.19
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0007727975270479134,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10,
|
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 |
+
"learning_rate": 0.0001,
|
14 |
+
"loss": 2.0357,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.8357,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.0,
|
25 |
+
"learning_rate": 0.000175,
|
26 |
+
"loss": 1.4764,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.0,
|
31 |
+
"learning_rate": 0.00015000000000000001,
|
32 |
+
"loss": 0.9966,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.0,
|
37 |
+
"learning_rate": 0.000125,
|
38 |
+
"loss": 1.339,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0,
|
43 |
+
"learning_rate": 0.0001,
|
44 |
+
"loss": 1.0031,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0,
|
49 |
+
"learning_rate": 7.500000000000001e-05,
|
50 |
+
"loss": 0.9943,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0,
|
55 |
+
"learning_rate": 5e-05,
|
56 |
+
"loss": 1.1203,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.0,
|
61 |
+
"learning_rate": 2.5e-05,
|
62 |
+
"loss": 0.9072,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.0,
|
67 |
+
"learning_rate": 0.0,
|
68 |
+
"loss": 0.9334,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.0,
|
73 |
+
"step": 10,
|
74 |
+
"total_flos": 333801262080000.0,
|
75 |
+
"train_loss": 1.2641676783561706,
|
76 |
+
"train_runtime": 52.6099,
|
77 |
+
"train_samples_per_second": 0.76,
|
78 |
+
"train_steps_per_second": 0.19
|
79 |
+
}
|
80 |
+
],
|
81 |
+
"logging_steps": 1,
|
82 |
+
"max_steps": 10,
|
83 |
+
"num_input_tokens_seen": 0,
|
84 |
+
"num_train_epochs": 1,
|
85 |
+
"save_steps": 500,
|
86 |
+
"total_flos": 333801262080000.0,
|
87 |
+
"train_batch_size": 1,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": null
|
90 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f1c62c602a1ddff417feb535d1e72776f88b3b26d149c83aa329759e46e44d9
|
3 |
+
size 4664
|