Hugging Face's logo

tyzhu
/
olmo-1b-finecode-5ksteps

Safetensors
Model card Files
xet
Community
tyzhu commited on
Commit
3cb3b28
·
verified ·
1 Parent(s): da757e6

olmo-1b-finecode-5ksteps to hf at time 2025-11-09 04:17:36

Browse files
Files changed (6) hide show
  1. final/config.json +27 -0
  2. final/generation_config.json +6 -0
  3. final/hyperparameters.yaml +57 -0
  4. final/model_config.yaml +44 -0
  5. final/tokenizer.json +0 -0
  6. final/tokenizer_config.json +238 -0
final/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "clip_qkv": null,
8
+ "eos_token_id": 50279,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8192,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "olmo",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 16,
17
+ "num_key_value_heads": 16,
18
+ "pad_token_id": 1,
19
+ "pretraining_tp": 1,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.40.0",
25
+ "use_cache": true,
26
+ "vocab_size": 50304
27
+ }
final/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
final/hyperparameters.yaml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model_name: OLMo-1B-hf
2
+ out_dir: /home/aiops/zhuty/litgpt_out/pretrain/olmo-1b-finecode-5ksteps
3
+ precision: bf16-mixed
4
+ initial_checkpoint_dir: checkpoints/allenai/OLMo-1B-hf
5
+ resume: auto
6
+ data:
7
+ class_path: litgpt.data.TextFiles
8
+ init_args:
9
+ train_data_path: /home/aiops/zhuty/cont_data/finecode/train
10
+ val_data_path: /home/aiops/zhuty/cont_data/finecode/test
11
+ seed: 42
12
+ num_workers: 8
13
+ add_eos: true
14
+ train:
15
+ save_interval: 1000
16
+ save_optimizer_state: true
17
+ max_optimizer_state: 1
18
+ log_interval: 1
19
+ global_batch_size: 1024
20
+ micro_batch_size: 8
21
+ lr_warmup_fraction: 0.01
22
+ max_steps: 5000
23
+ max_seq_length: 1024
24
+ max_norm: 1.0
25
+ min_lr: 5.0e-06
26
+ eval:
27
+ interval: 1000
28
+ max_iters: 100
29
+ initial_validation: true
30
+ final_validation: true
31
+ evaluate_example: first
32
+ num_generation_examples: 1
33
+ calculate_exact_match: false
34
+ log:
35
+ project: mathcont
36
+ optimizer:
37
+ class_path: torch.optim.AdamW
38
+ init_args:
39
+ lr: 5.0e-05
40
+ weight_decay: 0.1
41
+ betas:
42
+ - 0.9
43
+ - 0.95
44
+ devices: auto
45
+ num_nodes: 1
46
+ tokenizer_dir: checkpoints/allenai/OLMo-1B-hf
47
+ logger_name: wandb
48
+ seed: 42
49
+ compiler: torch
50
+ executors:
51
+ - sdpa
52
+ - torchcompile
53
+ - torch
54
+ strategy: fsdp
55
+ diffusion: false
56
+ mask_token_id: 811
57
+ sampling_eps: 0.001
final/model_config.yaml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ attention_logit_softcapping: null
2
+ attention_scores_scalar: null
3
+ attn_bias: false
4
+ bias: false
5
+ block_size: 2048
6
+ final_logit_softcapping: null
7
+ gelu_approximate: none
8
+ head_size: 128
9
+ hf_config:
10
+ name: OLMo-1B-hf
11
+ org: allenai
12
+ intermediate_size: 8192
13
+ lm_head_bias: false
14
+ mlp_class_name: LLaMAMLP
15
+ moe_intermediate_size: null
16
+ n_embd: 2048
17
+ n_expert: 0
18
+ n_expert_per_token: 0
19
+ n_head: 16
20
+ n_layer: 16
21
+ n_query_groups: 16
22
+ name: OLMo-1B-hf
23
+ norm_1: true
24
+ norm_2: true
25
+ norm_class_name: LayerNorm
26
+ norm_eps: 1.0e-05
27
+ norm_qk: false
28
+ norm_qk_type: default
29
+ padded_vocab_size: 50304
30
+ padding_multiple: 512
31
+ parallel_residual: false
32
+ post_attention_norm: false
33
+ post_mlp_norm: false
34
+ rope_adjustments: null
35
+ rope_base: 10000
36
+ rope_condense_ratio: 1
37
+ rope_indices: null
38
+ rope_local_base_freq: null
39
+ rotary_percentage: 1.0
40
+ scale_embeddings: false
41
+ shared_attention_norm: false
42
+ sliding_window_indices: null
43
+ sliding_window_size: null
44
+ vocab_size: 50280
final/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final/tokenizer_config.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
232
+ "clean_up_tokenization_spaces": true,
233
+ "eos_token": "<|endoftext|>",
234
+ "model_max_length": 1000000000000000019884624838656,
235
+ "pad_token": "<|padding|>",
236
+ "tokenizer_class": "GPTNeoXTokenizer",
237
+ "unk_token": null
238
+ }