End of training
Browse files- README.md +8 -8
- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
- tokenizer.json +1 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
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.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,11 +38,11 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- gradient_accumulation_steps: 4
|
45 |
-
- total_train_batch_size:
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.05
|
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch
|
55 |
-
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
18 |
|
19 |
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.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5874
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 2
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 8
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.05
|
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| 0.5743 | 0.9996 | 1178 | 0.3069 |
|
57 |
+
| 0.3457 | 2.0 | 2357 | 0.3704 |
|
58 |
+
| 0.9745 | 2.9987 | 3534 | 0.5874 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -10,20 +10,20 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"o_proj",
|
24 |
-
"k_proj",
|
25 |
"v_proj",
|
26 |
-
"q_proj"
|
|
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"k_proj",
|
26 |
+
"o_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
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:e96718103d173e42490b1ceb7c86fce5bf932d3fb6d2e2ecc0462d4eefade8e4
|
3 |
+
size 33588528
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88c7be8d34d851b21daef72d562e9cd1c59b7dcae7a4bd60cb8344dfdf1c7a41
|
3 |
size 5112
|