NairaRahim
commited on
Training in progress, step 1000
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729072177.6fd9b007ca9b.263.0 +3 -0
- runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729073177.6fd9b007ca9b.263.1 +3 -0
- runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729073202.6fd9b007ca9b.263.2 +3 -0
- runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729074783.6fd9b007ca9b.263.3 +3 -0
- runs/Oct16_10-39-14_6fd9b007ca9b/events.out.tfevents.1729075207.6fd9b007ca9b.579.0 +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 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj",
|
26 |
+
"v_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"up_proj",
|
29 |
+
"down_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:b2708aff015569f25e1c9f2bfb508e37400eddadc924aa763ce131f156eba099
|
3 |
+
size 45258384
|
runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729072177.6fd9b007ca9b.263.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ebb6f6ca7c14ef103adc0af507d8577ea8155690afdbdde8acf4a5a7b2745e
|
3 |
+
size 5649
|
runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729073177.6fd9b007ca9b.263.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1d0cbc1e705e09cf6d481b3032dd60855970aa23648142fc149dc7e8a11154c
|
3 |
+
size 5649
|
runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729073202.6fd9b007ca9b.263.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa563d782cf5b79d46ee22fe9bb68eeb58df93bf959e2e6241feb341749723cf
|
3 |
+
size 5856
|
runs/Oct16_09-48-43_6fd9b007ca9b/events.out.tfevents.1729074783.6fd9b007ca9b.263.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac02ae477c5576ee787a94cf389482ebbbf157745b455f5146135c1a3516b3f7
|
3 |
+
size 16771
|
runs/Oct16_10-39-14_6fd9b007ca9b/events.out.tfevents.1729075207.6fd9b007ca9b.579.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:023834eb1d1eb5170ca20ee323282c7d5f0d8b768e3dca509cb51cbc552e9807
|
3 |
+
size 7755
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48622affbf01bc79734e6230026e8c16dff17932f0710e573e935ea2b0c896d4
|
3 |
+
size 5112
|