Chanyut73 commited on
Commit
0cc24b6
·
verified ·
1 Parent(s): f11be00

Training in progress, step 500

Browse files
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "OpensourceThai/Wilai",
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": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
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": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "v_proj",
29
+ "q_proj"
30
+ ],
31
+ "target_parameters": null,
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_qalora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8fefe3cfe33c69dbe2c00787a1bbaa42bdb2e39e5aa139547181d35f8f3020
3
+ size 1182520
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50256,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.56.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5657ab69cd65d99b5dbde2041563c2a55f4475ca6a2bc8712ee0249057fceaf
3
+ size 497774208
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781547.2d91f6c9d2f7.203.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432bba1dd0f08e8a5781921021009c173d19861dbe6b496ce895f5b8f98285aa
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781588.2d91f6c9d2f7.203.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ff94a229112040220ee6753d9827f2a6b1d6c8d8abef78dad2e5b83a9e10ff
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781607.2d91f6c9d2f7.203.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ec8658198468390336b303a5a0b1396908315fc5f4e1836a3df60b33a582f0
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781626.2d91f6c9d2f7.203.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f1ad4eb7c423ff266e8c39e2a80d43ae2136ac10347943d279d12fccb5d3f29
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781636.2d91f6c9d2f7.203.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc96431b2da4c9530476e752c4cf91e3819967da43d650c9d0663d02ef2e96a5
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781651.2d91f6c9d2f7.203.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2f93b119e38e77b92b220b9b40aa18a1771109c2ff6bb8e301312587c8d34e
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781685.2d91f6c9d2f7.203.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd9a04f811445e8c9ee85233784fa7361d68d59f0cfbdce15b1e61bcc532dc9
3
+ size 5485
runs/Sep25_06-25-46_2d91f6c9d2f7/events.out.tfevents.1758781711.2d91f6c9d2f7.203.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6050f3039a54e97aec349ee722046d852167e6846e3a4de6c956c412b43145
3
+ size 5485
runs/Sep25_06-28-57_2d91f6c9d2f7/events.out.tfevents.1758781738.2d91f6c9d2f7.203.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804b3ddfe8ab1879fb17411188b6a020fc06e1e909f3aee2ef98ddb172064f83
3
+ size 174168
runs/Sep25_08-21-37_2d91f6c9d2f7/events.out.tfevents.1758788515.2d91f6c9d2f7.28743.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc44922537429afe870641210bf44dcae3cdb38240cd50d1d0064de58be4bda2
3
+ size 5244
runs/Sep25_08-23-54_2d91f6c9d2f7/events.out.tfevents.1758788671.2d91f6c9d2f7.28743.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f2bb62d41ac11fad57461a30c0a415b05113a0d251a151f6bdd6fec72291e0
3
+ size 5455
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73cb18ac6d9be827b1d9387b85ad7b14c0068a4b45e3007f3dfe99723382b17
3
+ size 5777
vocab.json ADDED
The diff for this file is too large to render. See raw diff