Cikola/Llama2_OneShot-Learning
Browse files- README.md +15 -14
- adapter_config.json +5 -8
- adapter_model.safetensors +2 -2
- runs/Jul20_17-47-41_jupyter-s0569591/events.out.tfevents.1721497662.jupyter-s0569591.69.0 +3 -0
- runs/Jul20_17-49-51_jupyter-s0569591/events.out.tfevents.1721497791.jupyter-s0569591.69.1 +3 -0
- runs/Jul20_17-53-02_jupyter-s0569591/events.out.tfevents.1721497983.jupyter-s0569591.69.2 +3 -0
- runs/Jul20_18-00-12_jupyter-s0569591/events.out.tfevents.1721498413.jupyter-s0569591.69.3 +3 -0
- runs/Jul20_18-07-01_jupyter-s0569591/events.out.tfevents.1721498822.jupyter-s0569591.69.4 +3 -0
- tokenizer_config.json +0 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,9 +1,7 @@
|
|
1 |
---
|
2 |
-
base_model: meta-llama/Llama-2-7b-
|
3 |
library_name: peft
|
4 |
license: llama2
|
5 |
-
metrics:
|
6 |
-
- accuracy
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
@@ -16,10 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# results
|
18 |
|
19 |
-
This model is a fine-tuned version of [meta-llama/Llama-2-7b-
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Accuracy: 1.0
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -52,14 +49,18 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
-
|
57 |
-
| No log | 0
|
58 |
-
| No log | 2.0 |
|
59 |
-
| No log |
|
60 |
-
| No log | 4.0 |
|
61 |
-
| No log |
|
62 |
-
| No log | 6.0 |
|
|
|
|
|
|
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: meta-llama/Llama-2-7b-hf
|
3 |
library_name: peft
|
4 |
license: llama2
|
|
|
|
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
|
|
14 |
|
15 |
# results
|
16 |
|
17 |
+
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.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.1270
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| No log | 1.0 | 1 | 7.8752 |
|
55 |
+
| No log | 2.0 | 2 | 7.1592 |
|
56 |
+
| No log | 3.0 | 3 | 5.8948 |
|
57 |
+
| No log | 4.0 | 4 | 3.9066 |
|
58 |
+
| No log | 5.0 | 5 | 2.6638 |
|
59 |
+
| No log | 6.0 | 6 | 2.2232 |
|
60 |
+
| No log | 7.0 | 7 | 2.1572 |
|
61 |
+
| No log | 8.0 | 8 | 2.1381 |
|
62 |
+
| No log | 9.0 | 9 | 2.1296 |
|
63 |
+
| No log | 10.0 | 10 | 2.1270 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "meta-llama/Llama-2-7b-
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -14,19 +14,16 @@
|
|
14 |
"lora_dropout": 0.1,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
-
"modules_to_save":
|
18 |
-
"classifier",
|
19 |
-
"score"
|
20 |
-
],
|
21 |
"peft_type": "LORA",
|
22 |
"r": 64,
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
-
"task_type": "
|
30 |
"use_dora": false,
|
31 |
"use_rslora": false
|
32 |
}
|
|
|
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,
|
|
|
14 |
"lora_dropout": 0.1,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
|
|
|
|
|
|
18 |
"peft_type": "LORA",
|
19 |
"r": 64,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
28 |
"use_rslora": false
|
29 |
}
|
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:e2d76d97c2f36176a51a8562fc74efd5a2891b743676b585335732e38c3e25c0
|
3 |
+
size 134235048
|
runs/Jul20_17-47-41_jupyter-s0569591/events.out.tfevents.1721497662.jupyter-s0569591.69.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67ce00939b08e5cf559923ae093d087be397b7efd5cbed3a02be1f464ad064ea
|
3 |
+
size 5333
|
runs/Jul20_17-49-51_jupyter-s0569591/events.out.tfevents.1721497791.jupyter-s0569591.69.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b967bb8c1933d0968b2b26c0f593ffddac57c4543e3dfbb2c73ddd714fd4b41
|
3 |
+
size 5333
|
runs/Jul20_17-53-02_jupyter-s0569591/events.out.tfevents.1721497983.jupyter-s0569591.69.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d83dbe46d813a352eb9ff6dd733ec5c2681fdaa545ac9b5a5d7aa0d2fb67bc1
|
3 |
+
size 5333
|
runs/Jul20_18-00-12_jupyter-s0569591/events.out.tfevents.1721498413.jupyter-s0569591.69.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47a3774582aa1b5b24ab222be12d1249509b7e11d512c5e38495c39a21a26cf0
|
3 |
+
size 5339
|
runs/Jul20_18-07-01_jupyter-s0569591/events.out.tfevents.1721498822.jupyter-s0569591.69.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5dd63b996d75c989a4ed8d3c7da61e2ef7599391e0efe77e9b6fb30a255bc2e
|
3 |
+
size 8347
|
tokenizer_config.json
CHANGED
@@ -29,7 +29,6 @@
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|
32 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": false,
|
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
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 sha256:97e75a2aeafd58517718ad752fa80e2e16cf3a82e3c388c251b0b2cfecd35db6
|
3 |
size 5112
|