error577 commited on
Commit
46658b4
·
verified ·
1 Parent(s): 6a06971

Training in progress, step 100

Browse files
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "berkeley-nest/Starling-LM-7B-alpha",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 256,
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
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "up_proj",
29
+ "gate_proj",
30
+ "q_proj",
31
+ "down_proj",
32
+ "o_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": true
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8483f94645b8bf12d586ae196203b4ec6d46a3cfd8932dc27ae57563bb1993
3
+ size 1195486552
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<sep>": 32002,
3
+ "<|end_of_turn|>": 32000,
4
+ "<|pad_0|>": 32001
5
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.51.0",
25
+ "use_cache": false,
26
+ "vocab_size": 32003
27
+ }
runs/Apr18_21-22-13_0b8955eb08fd/events.out.tfevents.1745011362.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6830226d621ed022600d56bfee76a07d431f7562d28788d411ead8b2614b9793
3
+ size 9306
runs/Apr18_21-28-16_0b8955eb08fd/events.out.tfevents.1745011725.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526ab58d94d95a54784bcc70924e5662a8148270f9e248b20fdaa867027b71ca
3
+ size 9981
runs/Apr18_21-32-39_0b8955eb08fd/events.out.tfevents.1745011990.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2176c3ee5de17e56185957ff0382184e9451c745d20a721624b20163b7b3a3
3
+ size 7259
runs/Apr18_21-34-08_0b8955eb08fd/events.out.tfevents.1745012077.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6241c428678f23ac19f1d0e472d0349ee564d0e380082796657e5054712f5fd8
3
+ size 7260
runs/Apr18_21-36-20_0b8955eb08fd/events.out.tfevents.1745012190.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431b3835692746221d8a130faa3fe3c70bcca3c4bb2f3e0ed6d88d0d647d0c20
3
+ size 7257
runs/Apr18_21-38-14_0b8955eb08fd/events.out.tfevents.1745012304.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17cf8bb9d80119a14ebd3873dda4b981bd0787b36949113a5c1307a5c4e2ef1
3
+ size 9285
runs/Apr18_21-40-39_0b8955eb08fd/events.out.tfevents.1745012448.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a092c0673591bd5e7dbf7d68caeb547356324148e62757fba09bbc112776f870
3
+ size 7289
runs/Apr18_21-42-27_0b8955eb08fd/events.out.tfevents.1745012557.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aee815c30214b085aaf83655c6de94776c993c9f16a87da991ee34448103296
3
+ size 14720
runs/Apr18_21-46-24_0b8955eb08fd/events.out.tfevents.1745012813.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd81381fd65d2fac5fbf90d65c85dfc9eb91731db1fd4f943f368948c1afd8b2
3
+ size 16751
runs/Apr18_21-53-27_0b8955eb08fd/events.out.tfevents.1745013236.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c756bacbf214362d581e939db0490782ad9b593ea4459261be3f47bd29b71aa4
3
+ size 54608
runs/Apr18_21-59-40_0b8955eb08fd/events.out.tfevents.1745013610.0b8955eb08fd.101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f446d027f086d8d12c4614a0fb6c6a749057621017d74a4df83357dfc8fc576
3
+ size 74887
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|end_of_turn|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "sep_token": "<sep>",
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|end_of_turn|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|pad_0|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<sep>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "additional_special_tokens": [
56
+ "<|end_of_turn|>",
57
+ "<|pad_0|>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "<|end_of_turn|>",
63
+ "extra_special_tokens": {},
64
+ "legacy": true,
65
+ "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "<|end_of_turn|>",
67
+ "sep_token": "<sep>",
68
+ "sp_model_kwargs": {},
69
+ "spaces_between_special_tokens": false,
70
+ "tokenizer_class": "LlamaTokenizer",
71
+ "unk_token": "<unk>",
72
+ "use_default_system_prompt": true
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d12d09b60268c013ceb752eb2c7528dc1800ca12cde2a72a3b95b45ac07d37
3
+ size 8081