Abhaykoul commited on
Commit
885d170
1 Parent(s): 44cb957

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - OEvortex/vortex-mini
5
+ language:
6
+ - en
7
+ - hi
8
+ library_name: transformers
9
+ base_model: OEvortex/HelpingAI-Lite
10
+ tags:
11
+ - HelpingAI
12
+ pipeline_tag: text-generation
13
+ widget:
14
+ - text: |
15
+ <|system|>
16
+ You are a chatbot who can be a teacher!</s>
17
+ <|user|>
18
+ Give three tips for staying healthy.</s>
19
+ <|assistant|>
20
+ ---
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "OEvortex/HelpingAI-Lite",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.38.0.dev0",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 2048,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.38.0.dev0"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d385dfcd73c639f4d03a0b8e304425b94d59a72270fe7aac6668e443c115b3
3
+ size 2200119664
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41212e1b85000977fdb3aa9d9f030cb2c5b893b05690b97ebe411fe27adaeff9
3
+ size 2200164273
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
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.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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "trust_remote_code": false,
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false,
44
+ "use_fast": true
45
+ }
trainer_state.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.00012304421224634436,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.3413,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.5983,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 6e-05,
26
+ "loss": 1.5431,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.7992,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.2091,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "learning_rate": 0.00012,
44
+ "loss": 2.7719,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.0,
49
+ "learning_rate": 0.00012,
50
+ "loss": 3.317,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "learning_rate": 0.00014,
56
+ "loss": 1.1447,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.0,
61
+ "learning_rate": 0.00016,
62
+ "loss": 1.4177,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.0,
67
+ "learning_rate": 0.00018,
68
+ "loss": 1.851,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.0,
73
+ "learning_rate": 0.0002,
74
+ "loss": 1.9526,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.0,
79
+ "learning_rate": 0.00019781476007338058,
80
+ "loss": 1.7479,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.0,
85
+ "learning_rate": 0.0001913545457642601,
86
+ "loss": 1.3683,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.0,
91
+ "learning_rate": 0.00018090169943749476,
92
+ "loss": 0.527,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "learning_rate": 0.00016691306063588583,
98
+ "loss": 2.01,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.0,
103
+ "learning_rate": 0.00015000000000000001,
104
+ "loss": 1.2848,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.0,
109
+ "learning_rate": 0.00013090169943749476,
110
+ "loss": 1.2189,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.0,
115
+ "learning_rate": 0.00011045284632676536,
116
+ "loss": 1.4882,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.0,
121
+ "learning_rate": 8.954715367323468e-05,
122
+ "loss": 0.5045,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.0,
127
+ "learning_rate": 6.909830056250527e-05,
128
+ "loss": 1.454,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.0,
133
+ "learning_rate": 5.000000000000002e-05,
134
+ "loss": 1.2887,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "learning_rate": 3.308693936411421e-05,
140
+ "loss": 0.8272,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.0,
145
+ "learning_rate": 1.9098300562505266e-05,
146
+ "loss": 1.6697,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.0,
151
+ "learning_rate": 8.645454235739903e-06,
152
+ "loss": 1.6019,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.0,
157
+ "learning_rate": 2.1852399266194314e-06,
158
+ "loss": 1.0745,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.0,
163
+ "eval_loss": NaN,
164
+ "eval_runtime": 4150.2492,
165
+ "eval_samples_per_second": 11.575,
166
+ "eval_steps_per_second": 11.575,
167
+ "step": 25
168
+ }
169
+ ],
170
+ "logging_steps": 1,
171
+ "max_steps": 25,
172
+ "num_input_tokens_seen": 0,
173
+ "num_train_epochs": 1,
174
+ "save_steps": 500,
175
+ "total_flos": 183123718963200.0,
176
+ "train_batch_size": 1,
177
+ "trial_name": null,
178
+ "trial_params": null
179
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35287ef26a7dfcc015e0237824a0fa49982706609ab72610ad14222df433fe99
3
+ size 4859