hansa15100 commited on
Commit
4e968aa
1 Parent(s): 1f72b82

Training in progress, step 1

Browse files
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-mix-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": 16,
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": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "gate_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "o_proj",
28
+ "v_proj",
29
+ "up_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:c4e2eb20f34dbbada05ee47d60a50c1cdd727a8c23d65c7d0e6c0fa488e6945c
3
+ size 45259216
runs/Jun26_11-36-28_aid-iad-bm-gpu4-8-ad1-002/events.out.tfevents.1719401797.aid-iad-bm-gpu4-8-ad1-002.283036.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92efa645a6d785e78f595db524fbbe31da0adc22a06707b9ee77b1f0eede0726
3
+ size 5245
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d3bc9002a0a66ff8fb0b1b286d8dd82a0f3b433a68b151937519e0afd2379e
3
+ size 5176