pritamqu commited on
Commit
11aa5e5
·
verified ·
1 Parent(s): f1af559

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. adapter_config.json +34 -0
  2. config.json +66 -0
  3. model.pth +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/h/pritam/pritam_ssd004/.cache/huggingface/hub/Mistral-7B-Instruct-v0.2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": false,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 256,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "/h/pritam/pritam_ssd004/OUTPUTS/Video-LLM/Phase2/GenData/video_chat2_mistral/tp_random-random_erase-stage2/diverse_10.json",
3
+ "media_root": "",
4
+ "num_frames": 16,
5
+ "yes_count": 500,
6
+ "no_count": 750,
7
+ "num_workers": 6,
8
+ "batch_size": 2,
9
+ "gradient_accumulation_steps": 4,
10
+ "trainable_modules": [],
11
+ "subset_size": -1,
12
+ "init_lora_zero": false,
13
+ "model_name_or_path": "/h/pritam/pritam_ssd004/.cache/huggingface/hub/VideoChat2_stage3_Mistral_7B",
14
+ "model": {
15
+ "lora_r": 128,
16
+ "lora_alpha": 256,
17
+ "lora_dropout": 0.05,
18
+ "lora_bias": "none"
19
+ },
20
+ "loss_alpha": 0.01,
21
+ "loss_beta": 0.9,
22
+ "loss_fn": "phrase_dpo_tkld",
23
+ "optimizer": {
24
+ "opt": "adamW",
25
+ "lr": 2e-05,
26
+ "opt_betas": [
27
+ 0.9,
28
+ 0.999
29
+ ],
30
+ "weight_decay": 0.02,
31
+ "max_grad_norm": -1,
32
+ "different_lr": {
33
+ "enable": false,
34
+ "module_names": [],
35
+ "lr": 0.001
36
+ }
37
+ },
38
+ "scheduler": {
39
+ "sched": "cosine",
40
+ "epochs": 1,
41
+ "min_lr_multi": 0.01,
42
+ "warmup_epochs": 0.0
43
+ },
44
+ "fp16": true,
45
+ "gradient_checkpointing": true,
46
+ "wandb": {
47
+ "enable": true,
48
+ "entity": "pritamqu",
49
+ "project": "ViSA-VideoChat2"
50
+ },
51
+ "dist_url": "env://",
52
+ "device": "cuda",
53
+ "output_dir": "/h/pritam/pritam_ssd004/OUTPUTS/Video-LLM/Phase2/ViSA/videochat2_mistral_7b/202503070207031433_phrase_dpo_tkld_2e-5_0.01_0.9_500_750_1_diverse_10_tp_random-random_erase_lora_128_256_cosine_lr_gradfix_dynamic",
54
+ "resume": false,
55
+ "debug": false,
56
+ "log_freq": 1,
57
+ "seed": 42,
58
+ "save_latest": true,
59
+ "auto_resume": true,
60
+ "pretrained_path": "",
61
+ "rank": 0,
62
+ "world_size": 4,
63
+ "gpu": 0,
64
+ "distributed": true,
65
+ "dist_backend": "nccl"
66
+ }
model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b030c32b8e721743e87bdf595cab6d146c1cb28083d713036a67110835d43a
3
+ size 1342632441