Training in progress, step 252
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Jun30_05-29-20_989637c6c04b/events.out.tfevents.1719725381.989637c6c04b.8801.0 +3 -0
- runs/Jun30_05-29-20_989637c6c04b/events.out.tfevents.1719725500.989637c6c04b.8801.1 +3 -0
- runs/Jun30_05-29-20_989637c6c04b/events.out.tfevents.1719725761.989637c6c04b.8801.2 +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/paligemma-3b-pt-224",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.0,
|
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 |
+
"gate_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj",
|
27 |
+
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3caadf39572007499e2f703ac295090b26ba0b490c8e1b3f8c82ee0f7607a46c
|
3 |
+
size 45258384
|
runs/Jun30_05-29-20_989637c6c04b/events.out.tfevents.1719725381.989637c6c04b.8801.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b30b400533f094716d1178d3a9801dedc580c8768e7a8c0683918db8943b46d
|
3 |
+
size 5738
|
runs/Jun30_05-29-20_989637c6c04b/events.out.tfevents.1719725500.989637c6c04b.8801.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d4fea296ffc82ec2d3f0e3e2eef8e2cd0dd1de97e41e5f86973b31f4b7d1aab
|
3 |
+
size 5738
|
runs/Jun30_05-29-20_989637c6c04b/events.out.tfevents.1719725761.989637c6c04b.8801.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5651ff729561011767e00086ff3928883660f6f3f9e7b06319bbc6278de1b521
|
3 |
+
size 6510
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23836e1f973a7e6f1367ca6f699177f12e3631815ae2268c3877dae247a909d1
|
3 |
+
size 5176
|