diaenra commited on
Commit
5b86e82
·
verified ·
1 Parent(s): fa138f0

Training in progress, step 239

Browse files
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "EleutherAI/gpt-neo-125m",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "embed_tokens",
19
+ "lm_head"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "c_fc",
27
+ "o_proj",
28
+ "up_proj",
29
+ "v_proj",
30
+ "c_proj",
31
+ "out_proj",
32
+ "k_proj",
33
+ "down_proj",
34
+ "gate_proj",
35
+ "q_proj"
36
+ ],
37
+ "task_type": "CAUSAL_LM",
38
+ "use_dora": 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:ffd92c22b7e97408b11053cb3e1cf2e65314e42d2fa15add5e740aee77599537
3
+ size 98447936
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "EleutherAI/gpt-neo-125m",
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPTNeoForCausalLM"
7
+ ],
8
+ "attention_dropout": 0,
9
+ "attention_layers": [
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local",
20
+ "global",
21
+ "local"
22
+ ],
23
+ "attention_types": [
24
+ [
25
+ [
26
+ "global",
27
+ "local"
28
+ ],
29
+ 6
30
+ ]
31
+ ],
32
+ "bos_token_id": 50256,
33
+ "classifier_dropout": 0.1,
34
+ "embed_dropout": 0,
35
+ "eos_token_id": 50256,
36
+ "gradient_checkpointing": false,
37
+ "hidden_size": 768,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": null,
40
+ "layer_norm_epsilon": 1e-05,
41
+ "max_position_embeddings": 2048,
42
+ "model_type": "gpt_neo",
43
+ "num_heads": 12,
44
+ "num_layers": 12,
45
+ "resid_dropout": 0,
46
+ "summary_activation": null,
47
+ "summary_first_dropout": 0.1,
48
+ "summary_proj_to_labels": true,
49
+ "summary_type": "cls_index",
50
+ "summary_use_proj": true,
51
+ "transformers_version": "4.46.0",
52
+ "use_cache": false,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
16
+ "clean_up_tokenization_spaces": true,
17
+ "eos_token": "<|endoftext|>",
18
+ "errors": "replace",
19
+ "model_max_length": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea73325cfaba42a7080e4cecc3eb6c2d4df9a17c4ab3a21f566fec7670a2fd9
3
+ size 6840
vocab.json ADDED
The diff for this file is too large to render. See raw diff