End of training
Browse files- README.md +57 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/Apr01_19-22-17_7b6d45b43bf4/events.out.tfevents.1711999361.7b6d45b43bf4.6185.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +72 -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-2-13b-chat-hf
|
6 |
+
model-index:
|
7 |
+
- name: llama2_13b_lora_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 |
+
# llama2_13b_lora_adapter
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-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: 2e-05
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 16
|
40 |
+
- total_train_batch_size: 16
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: cosine
|
43 |
+
- lr_scheduler_warmup_ratio: 0.1
|
44 |
+
- num_epochs: 1
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- PEFT 0.10.0
|
54 |
+
- Transformers 4.38.2
|
55 |
+
- Pytorch 2.2.1+cu121
|
56 |
+
- Datasets 2.18.0
|
57 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:200a737144cfcf9452cc740c811c7a9f74627fdeb58ac6f017cea08da846f3b7
|
3 |
size 250422888
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 4.878623526912e+16,
|
4 |
+
"train_loss": 0.9400251382752393,
|
5 |
+
"train_runtime": 7654.5047,
|
6 |
+
"train_samples_per_second": 1.377,
|
7 |
+
"train_steps_per_second": 0.086
|
8 |
+
}
|
runs/Apr01_19-22-17_7b6d45b43bf4/events.out.tfevents.1711999361.7b6d45b43bf4.6185.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96927db4ba8b91b32293d00aed897df4917b1fb2525b3e63d7052dd9f0e0dad8
|
3 |
+
size 6686
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 4.878623526912e+16,
|
4 |
+
"train_loss": 0.9400251382752393,
|
5 |
+
"train_runtime": 7654.5047,
|
6 |
+
"train_samples_per_second": 1.377,
|
7 |
+
"train_steps_per_second": 0.086
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9985772550507446,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 658,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15,
|
13 |
+
"grad_norm": 1.3818485736846924,
|
14 |
+
"learning_rate": 1.984705192213004e-05,
|
15 |
+
"loss": 1.5534,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3,
|
20 |
+
"grad_norm": 1.1903014183044434,
|
21 |
+
"learning_rate": 1.761094828138534e-05,
|
22 |
+
"loss": 0.8705,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.46,
|
27 |
+
"grad_norm": 1.446919322013855,
|
28 |
+
"learning_rate": 1.3281315178199537e-05,
|
29 |
+
"loss": 0.8352,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.61,
|
34 |
+
"grad_norm": 1.4014055728912354,
|
35 |
+
"learning_rate": 8.04909677983872e-06,
|
36 |
+
"loss": 0.8368,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.76,
|
41 |
+
"grad_norm": 1.499550461769104,
|
42 |
+
"learning_rate": 3.3535097208036584e-06,
|
43 |
+
"loss": 0.8154,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.91,
|
48 |
+
"grad_norm": 1.5235815048217773,
|
49 |
+
"learning_rate": 4.861604459298697e-07,
|
50 |
+
"loss": 0.8083,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0,
|
55 |
+
"step": 658,
|
56 |
+
"total_flos": 4.878623526912e+16,
|
57 |
+
"train_loss": 0.9400251382752393,
|
58 |
+
"train_runtime": 7654.5047,
|
59 |
+
"train_samples_per_second": 1.377,
|
60 |
+
"train_steps_per_second": 0.086
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"logging_steps": 100,
|
64 |
+
"max_steps": 658,
|
65 |
+
"num_input_tokens_seen": 0,
|
66 |
+
"num_train_epochs": 1,
|
67 |
+
"save_steps": 500,
|
68 |
+
"total_flos": 4.878623526912e+16,
|
69 |
+
"train_batch_size": 1,
|
70 |
+
"trial_name": null,
|
71 |
+
"trial_params": null
|
72 |
+
}
|