alicegoesdown commited on
Commit
872d055
·
verified ·
1 Parent(s): 70ab92c

Training in progress, step 150

Browse files
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-560m",
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": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "word_embeddings",
24
+ "dense_h_to_4h",
25
+ "lm_head",
26
+ "query_key_value",
27
+ "dense",
28
+ "dense_4h_to_h"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f1ab3ea2d2af98e9c3ce0d09b8bb2a1b6a713b947a97e0a40767fe4e4846a2
3
+ size 2170056600
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:592c59c98adf2e8f3e83b6394c6b1788941e44d546133031b57e9181a2e64999
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc2f539879909cd58bb7a4f29889350cf66180874338528a13567610a0f8806
3
  size 5496