nsnihal commited on
Commit
841cab8
·
verified ·
1 Parent(s): 52862aa

Model save

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/seamless-m4t-v2-large
5
+ tags:
6
+ - base_model:adapter:facebook/seamless-m4t-v2-large
7
+ - lora
8
+ - transformers
9
+ model-index:
10
+ - name: braj-speech-to-text
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # braj-speech-to-text
18
+
19
+ This model is a fine-tuned version of [facebook/seamless-m4t-v2-large](https://huggingface.co/facebook/seamless-m4t-v2-large) on the None dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 8
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 100
47
+ - num_epochs: 3
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Framework versions
51
+
52
+ - PEFT 0.16.0
53
+ - Transformers 4.53.2
54
+ - Pytorch 2.6.0+cu124
55
+ - Datasets 2.14.4
56
+ - Tokenizers 0.21.2
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "facebook/seamless-m4t-v2-large",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "fc1",
29
+ "k_proj",
30
+ "q_proj",
31
+ "v_proj",
32
+ "fc2",
33
+ "out_proj"
34
+ ],
35
+ "task_type": "SEQ_2_SEQ_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_qalora": false,
39
+ "use_rslora": false
40
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f208e2f58f6191605381186082ba71b2cf51cfdc47f66a9b373efffa9608390f
3
+ size 26806288
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead6b043f161c9c22b7672b900dbf8caff8f39644ce46415649d3650f6ede8e2
3
+ size 5368