xammi commited on
Commit
56c1a15
1 Parent(s): 35e43b8

Training in progress, step 500

Browse files
adapter_config.json CHANGED
@@ -10,8 +10,8 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 32,
14
- "lora_dropout": 0,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": [
@@ -19,17 +19,17 @@
19
  "embed_tokens"
20
  ],
21
  "peft_type": "LORA",
22
- "r": 128,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
 
26
  "k_proj",
27
- "gate_proj",
28
  "down_proj",
29
- "up_proj",
30
- "q_proj",
31
- "o_proj",
32
- "v_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": [
 
19
  "embed_tokens"
20
  ],
21
  "peft_type": "LORA",
22
+ "r": 64,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "v_proj",
27
+ "q_proj",
28
+ "up_proj",
29
  "k_proj",
 
30
  "down_proj",
31
+ "gate_proj",
32
+ "o_proj"
 
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc9c7876d7156408690c7ccc761aafcbb838cfe1b2b664bcbf07c3f99a0e5965
3
- size 928031856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3596e2378a263bb9c76017ad1de3fdb5fc2252ab7b8b772315811250ffcfa5e0
3
+ size 726180672
runs/Sep30_17-48-15_sammie/events.out.tfevents.1727740850.sammie.31562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c804c0f96a64899849acb6d539ed3e21b4c1b68271a5f0b19520bd84fe082c0
3
+ size 16281
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4096,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -33,9 +33,9 @@
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": false,
36
- "model_max_length": 2048,
37
  "pad_token": "<unk>",
38
- "padding_side": "left",
39
  "sp_model_kwargs": {},
40
  "tokenizer_class": "LlamaTokenizer",
41
  "unk_token": "<unk>",
 
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": false,
36
+ "model_max_length": 4096,
37
  "pad_token": "<unk>",
38
+ "padding_side": "right",
39
  "sp_model_kwargs": {},
40
  "tokenizer_class": "LlamaTokenizer",
41
  "unk_token": "<unk>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6129c47eb3d79d123e565041755fd270ca35bbb347ebac7e635faa2854c724d
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdb3f501f1aa60bff535898f0e98623e86d31015f48e9ec78edeb142fada39c0
3
  size 5496