mazesmazes commited on
Commit
61b63e7
·
verified ·
1 Parent(s): 0a4eab5

Training in progress - step 500

Browse files
adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 256,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "q_proj",
33
+ "v_proj"
34
+ ],
35
+ "target_parameters": null,
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_qalora": false,
40
+ "use_rslora": false
41
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dcb26ac7804610a5bc77c191526f97f242b4bcb5af81518c467ea578c20692b
3
+ size 36715216
config.json CHANGED
@@ -161,17 +161,12 @@
161
  "label_smoothing": 0.0,
162
  "length_penalty": 1.0,
163
  "llm_dim": 1024,
164
- "lora_alpha": 512,
165
  "lora_dropout": 0.05,
166
- "lora_rank": 128,
167
  "lora_target_modules": [
168
  "q_proj",
169
- "k_proj",
170
- "v_proj",
171
- "o_proj",
172
- "gate_proj",
173
- "up_proj",
174
- "down_proj"
175
  ],
176
  "mask_feature_length": 10,
177
  "mask_feature_min_masks": 0,
@@ -269,7 +264,7 @@
269
  "transformers_version": "5.0.0.dev0",
270
  "use_cache": false,
271
  "use_lora": true,
272
- "use_specaugment": false,
273
  "user_prompt": "Please transcribe this English audio into text: <audio>",
274
  "vocab_size": 151670
275
  }
 
161
  "label_smoothing": 0.0,
162
  "length_penalty": 1.0,
163
  "llm_dim": 1024,
164
+ "lora_alpha": 256,
165
  "lora_dropout": 0.05,
166
+ "lora_rank": 64,
167
  "lora_target_modules": [
168
  "q_proj",
169
+ "v_proj"
 
 
 
 
 
170
  ],
171
  "mask_feature_length": 10,
172
  "mask_feature_min_masks": 0,
 
264
  "transformers_version": "5.0.0.dev0",
265
  "use_cache": false,
266
  "use_lora": true,
267
+ "use_specaugment": true,
268
  "user_prompt": "Please transcribe this English audio into text: <audio>",
269
  "vocab_size": 151670
270
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e47c1dad96a0b9e1a85a0a0545ce0fda86d3a8a26bccf2306db9e3de0d48abcc
3
  size 25172384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cffe0014c706fa3ee367300697c9f0e58853f9ae247077fadad9e32b8b30b717
3
  size 25172384