Training in progress, step 30
Browse files
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
base_model: meta-llama/Llama-3.2-1B-Instruct
|
3 |
-
datasets: shoubing35/ones_digit_sft_dataset
|
4 |
library_name: transformers
|
5 |
model_name: llama-1B-sft
|
6 |
tags:
|
@@ -12,7 +11,7 @@ licence: license
|
|
12 |
|
13 |
# Model Card for llama-1B-sft
|
14 |
|
15 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
|
16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
17 |
|
18 |
## Quick start
|
|
|
1 |
---
|
2 |
base_model: meta-llama/Llama-3.2-1B-Instruct
|
|
|
3 |
library_name: transformers
|
4 |
model_name: llama-1B-sft
|
5 |
tags:
|
|
|
11 |
|
12 |
# Model Card for llama-1B-sft
|
13 |
|
14 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
|
15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
|
17 |
## Quick start
|
adapter_config.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
"loftq_config": {},
|
15 |
"lora_alpha": 32,
|
16 |
"lora_bias": false,
|
17 |
-
"lora_dropout": 0.
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": [
|
@@ -25,7 +25,12 @@
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
|
|
|
|
28 |
"q_proj",
|
|
|
|
|
|
|
29 |
"v_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
14 |
"loftq_config": {},
|
15 |
"lora_alpha": 32,
|
16 |
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.0,
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": [
|
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
+
"gate_proj",
|
29 |
+
"up_proj",
|
30 |
"q_proj",
|
31 |
+
"down_proj",
|
32 |
+
"o_proj",
|
33 |
+
"k_proj",
|
34 |
"v_proj"
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
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 sha256:2d56b190a3917505f5e82b811ceafa1ead1c177e29d5c3d7d38224d31ea572c2
|
3 |
+
size 1095792688
|
runs/Apr13_22-23-48_239d878514d9/events.out.tfevents.1744583038.239d878514d9.15324.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e774765fa96acba51f8d3b74eb29220191afdeca5ab36f845b49ecc9dd0b8a3
|
3 |
+
size 9772
|
runs/Apr13_22-25-22_239d878514d9/events.out.tfevents.1744583132.239d878514d9.15791.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09563963d1748518e08b9bcd9a75340897731e877f360260849be8a59d009902
|
3 |
+
size 9772
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ca4866cf342be84ada3a4bb2c3fcbc06949be107896fed2d818e410b2f7820
|
3 |
size 5688
|