jssky commited on
Commit
e1ac836
1 Parent(s): cf6b917

Training in progress, step 25

Browse files
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "migtissera/Tess-v2.5-Phi-3-medium-128k-14B",
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": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "qkv_proj",
24
+ "down_proj",
25
+ "o_proj",
26
+ "gate_up_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7bbded54307be40990ea487c5eac800e3087a2245a2b1700185ef0bd5e0f73b
3
+ size 445688440
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|end_of_text|>": 32012,
4
+ "<|endoftext|>": 32000,
5
+ "<|end|>": 32007,
6
+ "<|im_end|>": 32011,
7
+ "<|im_start|>": 32013,
8
+ "<|placeholder1|>": 32002,
9
+ "<|placeholder2|>": 32003,
10
+ "<|placeholder3|>": 32004,
11
+ "<|placeholder4|>": 32005,
12
+ "<|placeholder5|>": 32008,
13
+ "<|placeholder6|>": 32009,
14
+ "<|system|>": 32006,
15
+ "<|user|>": 32010
16
+ }
config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "migtissera/Tess-v2.5-Phi-3-medium-128k-14B",
4
+ "architectures": [
5
+ "Phi3ForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
11
+ "AutoModelForCausalLM": "microsoft/Phi-3-medium-128k-instruct--modeling_phi3.Phi3ForCausalLM"
12
+ },
13
+ "bos_token_id": 1,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 32011,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 5120,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 17920,
20
+ "max_position_embeddings": 131072,
21
+ "model_type": "phi3",
22
+ "num_attention_heads": 40,
23
+ "num_hidden_layers": 40,
24
+ "num_key_value_heads": 10,
25
+ "original_max_position_embeddings": 4096,
26
+ "pad_token_id": null,
27
+ "resid_pdrop": 0.0,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": {
30
+ "long_factor": [
31
+ 1.0,
32
+ 1.0,
33
+ 1.0,
34
+ 1.0,
35
+ 1.0,
36
+ 1.0,
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.0,
43
+ 1.0,
44
+ 1.25,
45
+ 1.25,
46
+ 1.5,
47
+ 2.0,
48
+ 2.75,
49
+ 5.75,
50
+ 5.75,
51
+ 6.5,
52
+ 9.25,
53
+ 11.0,
54
+ 13.25,
55
+ 19.25,
56
+ 19.75,
57
+ 19.75,
58
+ 21.25,
59
+ 21.5,
60
+ 26.5,
61
+ 30.0,
62
+ 33.75,
63
+ 35.25,
64
+ 38.5,
65
+ 42.0,
66
+ 42.25,
67
+ 46.0,
68
+ 47.0,
69
+ 50.0,
70
+ 50.5,
71
+ 51.0,
72
+ 52.0,
73
+ 52.75,
74
+ 53.75,
75
+ 54.75,
76
+ 57.0,
77
+ 57.25,
78
+ 58.5,
79
+ 59.25,
80
+ 59.5,
81
+ 62.0,
82
+ 62.5,
83
+ 62.75,
84
+ 63.25,
85
+ 63.25,
86
+ 63.25,
87
+ 63.75,
88
+ 64.0,
89
+ 64.0,
90
+ 64.25,
91
+ 64.5,
92
+ 64.5,
93
+ 65.0,
94
+ 65.0
95
+ ],
96
+ "short_factor": [
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.01,
104
+ 1.02,
105
+ 1.02,
106
+ 1.04,
107
+ 1.04,
108
+ 1.07,
109
+ 1.07,
110
+ 1.1,
111
+ 1.3000000000000003,
112
+ 1.3000000000000003,
113
+ 1.5000000000000004,
114
+ 1.5700000000000005,
115
+ 1.9000000000000008,
116
+ 2.3100000000000014,
117
+ 2.759999999999992,
118
+ 3.3899999999999784,
119
+ 3.9399999999999666,
120
+ 4.009999999999965,
121
+ 4.289999999999959,
122
+ 4.349999999999958,
123
+ 5.349999999999937,
124
+ 6.659999999999909,
125
+ 7.029999999999901,
126
+ 7.51999999999989,
127
+ 8.00999999999988,
128
+ 8.249999999999876,
129
+ 8.279999999999875,
130
+ 9.629999999999846,
131
+ 9.89999999999984,
132
+ 10.589999999999826,
133
+ 11.049999999999816,
134
+ 11.7899999999998,
135
+ 12.189999999999792,
136
+ 12.889999999999777,
137
+ 13.129999999999772,
138
+ 13.16999999999977,
139
+ 13.20999999999977,
140
+ 13.479999999999764,
141
+ 13.539999999999763,
142
+ 13.779999999999758,
143
+ 13.929999999999755,
144
+ 14.429999999999744,
145
+ 14.759999999999737,
146
+ 15.149999999999729,
147
+ 15.419999999999723,
148
+ 15.53999999999972,
149
+ 15.659999999999718,
150
+ 15.749999999999716,
151
+ 15.759999999999716,
152
+ 15.799999999999715,
153
+ 16.05999999999971,
154
+ 16.079999999999714,
155
+ 16.11999999999972,
156
+ 16.11999999999972,
157
+ 16.18999999999973,
158
+ 16.31999999999975,
159
+ 16.539999999999786,
160
+ 16.799999999999827
161
+ ],
162
+ "type": "su"
163
+ },
164
+ "rope_theta": 10000.0,
165
+ "sliding_window": 131072,
166
+ "tie_word_embeddings": false,
167
+ "torch_dtype": "bfloat16",
168
+ "transformers_version": "4.46.0",
169
+ "use_cache": false,
170
+ "vocab_size": 32064
171
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|im_end|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|end_of_text|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|im_start|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ }
142
+ },
143
+ "bos_token": "<s>",
144
+ "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 %}",
145
+ "clean_up_tokenization_spaces": false,
146
+ "eos_token": "<|im_end|>",
147
+ "legacy": false,
148
+ "model_max_length": 131072,
149
+ "pad_token": "<|end_of_text|>",
150
+ "padding_side": "left",
151
+ "sp_model_kwargs": {},
152
+ "spaces_between_special_tokens": false,
153
+ "tokenizer_class": "LlamaTokenizer",
154
+ "unk_token": "<unk>",
155
+ "use_default_system_prompt": false
156
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892af885f005a01eef4e187d1ad4000ad0fde4defdcb7fc09c0c5753fcb4600a
3
+ size 6776