Hugging Face's logo

hamishivi
/
OLMo-1B-0724-SFT-hf

Text Generation
Transformers
PyTorch
TensorBoard
English
olmo
conversational
Inference Endpoints
Model card Files Metrics Community
hamishivi commited on
Commit
9423e8d
•
1 Parent(s): bf40f3f

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. config.json +27 -0
  2. generation_config.json +6 -0
  3. open_instruct_sft/1720955732.5983117/events.out.tfevents.1720955732.ebc48c9636f6.96.1 +3 -0
  4. open_instruct_sft/1720955732.5995874/hparams.yml +45 -0
  5. open_instruct_sft/1720992823.8925228/events.out.tfevents.1720992823.dc8db3e15b48.96.1 +3 -0
  6. open_instruct_sft/1720992823.893762/hparams.yml +45 -0
  7. open_instruct_sft/events.out.tfevents.1720955732.ebc48c9636f6.96.0 +3 -0
  8. open_instruct_sft/events.out.tfevents.1720992823.dc8db3e15b48.96.0 +3 -0
  9. pytorch_model.bin +3 -0
  10. special_tokens_map.json +17 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +239 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/OLMo-1B-0724-hf",
3
+ "architectures": [
4
+ "OlmoForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": 8.0,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "olmo",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 16,
19
+ "pad_token_id": 1,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.40.2",
25
+ "use_cache": true,
26
+ "vocab_size": 50304
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.40.2"
6
+ }
open_instruct_sft/1720955732.5983117/events.out.tfevents.1720955732.ebc48c9636f6.96.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c63a7a2e60bbd72fc304473cfff4e701b8f1a73acdfc21936e953b18bd195d5
3
+ size 2258
open_instruct_sft/1720955732.5995874/hparams.yml ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ add_bos: true
2
+ checkpointing_steps: null
3
+ clip_grad_norm: -1
4
+ config_name: null
5
+ dataset_config_name: null
6
+ dataset_name: allenai/tulu-v2-sft-mixture-olmo-4096
7
+ dpo_beta: 0.1
8
+ dpo_use_paged_optimizer: false
9
+ gradient_accumulation_steps: 16
10
+ gradient_checkpointing: false
11
+ learning_rate: 1.0e-05
12
+ logging_steps: 1
13
+ lora_alpha: 16
14
+ lora_dropout: 0.1
15
+ lora_rank: 64
16
+ low_cpu_mem_usage: false
17
+ lr_scheduler_type: linear
18
+ max_seq_length: 4096
19
+ max_train_samples: null
20
+ max_train_steps: 12740
21
+ model_name_or_path: allenai/OLMo-1B-0724-hf
22
+ model_revision: main
23
+ num_train_epochs: 5
24
+ output_dir: /output
25
+ overwrite_cache: false
26
+ per_device_train_batch_size: 1
27
+ preprocessing_num_workers: 16
28
+ reduce_loss: mean
29
+ report_to: tensorboard
30
+ resume_from_checkpoint: null
31
+ seed: 42
32
+ timeout: 1800
33
+ tokenizer_name: allenai/OLMo-1B-0724-hf
34
+ tokenizer_revision: main
35
+ train_file: null
36
+ trust_remote_code: false
37
+ use_8bit_optimizer: false
38
+ use_flash_attn: true
39
+ use_lora: false
40
+ use_qlora: false
41
+ use_slow_tokenizer: true
42
+ wandb_entity: null
43
+ warmup_ratio: 0.03
44
+ weight_decay: 0.0
45
+ with_tracking: true
open_instruct_sft/1720992823.8925228/events.out.tfevents.1720992823.dc8db3e15b48.96.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0974ace0baac37d6baf1fe2297634f4347377ae10d411403c03b06e09ed609
3
+ size 2258
open_instruct_sft/1720992823.893762/hparams.yml ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ add_bos: true
2
+ checkpointing_steps: null
3
+ clip_grad_norm: -1
4
+ config_name: null
5
+ dataset_config_name: null
6
+ dataset_name: allenai/tulu-v2-sft-mixture-olmo-4096
7
+ dpo_beta: 0.1
8
+ dpo_use_paged_optimizer: false
9
+ gradient_accumulation_steps: 16
10
+ gradient_checkpointing: false
11
+ learning_rate: 1.0e-05
12
+ logging_steps: 1
13
+ lora_alpha: 16
14
+ lora_dropout: 0.1
15
+ lora_rank: 64
16
+ low_cpu_mem_usage: false
17
+ lr_scheduler_type: linear
18
+ max_seq_length: 4096
19
+ max_train_samples: null
20
+ max_train_steps: 12740
21
+ model_name_or_path: allenai/OLMo-1B-0724-hf
22
+ model_revision: main
23
+ num_train_epochs: 5
24
+ output_dir: /output
25
+ overwrite_cache: false
26
+ per_device_train_batch_size: 1
27
+ preprocessing_num_workers: 16
28
+ reduce_loss: mean
29
+ report_to: tensorboard
30
+ resume_from_checkpoint: null
31
+ seed: 42
32
+ timeout: 1800
33
+ tokenizer_name: allenai/OLMo-1B-0724-hf
34
+ tokenizer_revision: main
35
+ train_file: null
36
+ trust_remote_code: false
37
+ use_8bit_optimizer: false
38
+ use_flash_attn: true
39
+ use_lora: false
40
+ use_qlora: false
41
+ use_slow_tokenizer: true
42
+ wandb_entity: null
43
+ warmup_ratio: 0.03
44
+ weight_decay: 0.0
45
+ with_tracking: true
open_instruct_sft/events.out.tfevents.1720955732.ebc48c9636f6.96.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8d4a6ee57ca12c81325cc52e6879e6262b8c41bc62a1de789cb16f232b196f
3
+ size 545436
open_instruct_sft/events.out.tfevents.1720992823.dc8db3e15b48.96.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ce367e37097bba51483b5d696c0299c210f8e87a4bd23397dfac9b4facf09d
3
+ size 1286574
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca1587d0f825a8b2cf9ce597e599de3733c6897983c5bf8798c0f212ba0e7c9
3
+ size 2559611026
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "pad_token": {
11
+ "content": "<|padding|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "|||IP_ADDRESS|||",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "|||EMAIL_ADDRESS|||",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
+ "content": "|||PHONE_NUMBER|||",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "50279": {
223
+ "content": "<|endoftext|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ }
230
+ },
231
+ "bos_token": "<|endoftext|>",
232
+ "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
233
+ "clean_up_tokenization_spaces": true,
234
+ "eos_token": "<|endoftext|>",
235
+ "model_max_length": 1000000000000000019884624838656,
236
+ "pad_token": "<|padding|>",
237
+ "tokenizer_class": "GPTNeoXTokenizer",
238
+ "unk_token": null
239
+ }