Training in progress, step 990
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Jun25_23-08-13_5e1ce99cc592/events.out.tfevents.1719356894.5e1ce99cc592.2359.0 +3 -0
- runs/Jun25_23-19-51_5e1ce99cc592/events.out.tfevents.1719357592.5e1ce99cc592.2359.1 +3 -0
- runs/Jun25_23-20-07_5e1ce99cc592/events.out.tfevents.1719357607.5e1ce99cc592.2359.2 +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 |
+
"o_proj",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj",
|
26 |
+
"up_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj",
|
29 |
+
"k_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 sha256:0b9c267484f101cfa929999daa8641b3e81aa760716a21f93f063d5a78c9c5f6
|
3 |
+
size 45258384
|
runs/Jun25_23-08-13_5e1ce99cc592/events.out.tfevents.1719356894.5e1ce99cc592.2359.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a60073a9bb758a5c41ab58ab2a406770e4caa9f27a2fd2057d671fb931178c
|
3 |
+
size 5704
|
runs/Jun25_23-19-51_5e1ce99cc592/events.out.tfevents.1719357592.5e1ce99cc592.2359.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bb177d5a42c30cf0212867788186d94a00c3ba4c2eeba0d306da5c6376bbefd
|
3 |
+
size 5704
|
runs/Jun25_23-20-07_5e1ce99cc592/events.out.tfevents.1719357607.5e1ce99cc592.2359.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aad1a165a14a633955b2d8de1273d71c089be42c922747eed47e9cef7d69d891
|
3 |
+
size 16373
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a675ba98030da7ef8142585a8a147476d8be2640fcf9bad092d4d9e3195de471
|
3 |
+
size 5112
|