aixk commited on
Commit
6fcf022
·
verified ·
1 Parent(s): 2ea85ce

Upload folder using huggingface_hub

Browse files
checkpoint-300/config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastHyperNet125mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 768,
7
+ "hyperbolic_dim": 16,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 2048,
10
+ "max_position_embeddings": 512,
11
+ "model_type": "fasthypernet_125m_16k",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 16,
14
+ "transformers_version": "5.13.1",
15
+ "use_cache": false,
16
+ "vocab_size": 16384
17
+ }
checkpoint-300/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.13.1"
6
+ }
checkpoint-300/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be314a40a37eb766f57a46c7e4f66aba59fcac1c9174b654c9f9f6527b416a1
3
+ size 543870712
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa48a26942e0f33e1e00330cae109823168c3e760b342c63707c6e20974ccdc1
3
+ size 276872907
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e045814b258ef8456ddc9ba59bbeeecdaab20d9b6083f4a4b1f6929fea7a4003
3
+ size 14645
checkpoint-300/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fa2753f3b07b658b59f7f79b4e27e41efe35b832dc10b7fa38277d4854d4e4
3
+ size 1383
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9caf4175b2cbb80ccda4b391553912cbcf59bb272ca11583f5c5d1380f05f8af
3
+ size 1465
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleLinguisticTokenizer",
3
+ "vocab_size": 16384,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0008786876507040851,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.9289588356802836e-05,
14
+ "grad_norm": 43.412994384765625,
15
+ "learning_rate": 4.8e-07,
16
+ "loss": 9.4322,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 5.857917671360567e-05,
21
+ "grad_norm": 24.38200569152832,
22
+ "learning_rate": 1.0799999999999998e-06,
23
+ "loss": 9.4165,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 8.786876507040851e-05,
28
+ "grad_norm": 25.624269485473633,
29
+ "learning_rate": 1.6799999999999998e-06,
30
+ "loss": 9.3983,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.00011715835342721134,
35
+ "grad_norm": 25.8831729888916,
36
+ "learning_rate": 2.2799999999999998e-06,
37
+ "loss": 9.4015,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.00014644794178401418,
42
+ "grad_norm": 18.858943939208984,
43
+ "learning_rate": 2.8799999999999995e-06,
44
+ "loss": 9.369,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.00017573753014081702,
49
+ "grad_norm": 32.19478225708008,
50
+ "learning_rate": 3.4799999999999993e-06,
51
+ "loss": 9.3743,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.00020502711849761985,
56
+ "grad_norm": 29.089111328125,
57
+ "learning_rate": 4.079999999999999e-06,
58
+ "loss": 9.3628,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0002343167068544227,
63
+ "grad_norm": 45.67530822753906,
64
+ "learning_rate": 4.679999999999999e-06,
65
+ "loss": 9.359,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0002636062952112255,
70
+ "grad_norm": 33.06043243408203,
71
+ "learning_rate": 5.28e-06,
72
+ "loss": 9.3381,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.00029289588356802836,
77
+ "grad_norm": 32.19873809814453,
78
+ "learning_rate": 5.88e-06,
79
+ "loss": 9.3304,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.0003221854719248312,
84
+ "grad_norm": 39.30705261230469,
85
+ "learning_rate": 6.48e-06,
86
+ "loss": 9.3144,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.00035147506028163403,
91
+ "grad_norm": 42.05266189575195,
92
+ "learning_rate": 7.079999999999999e-06,
93
+ "loss": 9.3104,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00038076464863843687,
98
+ "grad_norm": 33.91127014160156,
99
+ "learning_rate": 7.68e-06,
100
+ "loss": 9.3218,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0004100542369952397,
105
+ "grad_norm": 31.721614837646484,
106
+ "learning_rate": 8.279999999999999e-06,
107
+ "loss": 9.3045,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.00043934382535204254,
112
+ "grad_norm": 59.37827682495117,
113
+ "learning_rate": 8.88e-06,
114
+ "loss": 9.3054,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0004686334137088454,
119
+ "grad_norm": 74.16336059570312,
120
+ "learning_rate": 9.48e-06,
121
+ "loss": 9.2952,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.0004979230020656483,
126
+ "grad_norm": 33.57463836669922,
127
+ "learning_rate": 1.0079999999999998e-05,
128
+ "loss": 9.2887,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.000527212590422451,
133
+ "grad_norm": 37.42033386230469,
134
+ "learning_rate": 1.068e-05,
135
+ "loss": 9.2839,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.0005565021787792539,
140
+ "grad_norm": 33.58783721923828,
141
+ "learning_rate": 1.1279999999999999e-05,
142
+ "loss": 9.2869,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.0005857917671360567,
147
+ "grad_norm": 33.92068862915039,
148
+ "learning_rate": 1.188e-05,
149
+ "loss": 9.2636,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0006150813554928596,
154
+ "grad_norm": 36.4366455078125,
155
+ "learning_rate": 1.2479999999999999e-05,
156
+ "loss": 9.2653,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0006443709438496624,
161
+ "grad_norm": 27.894250869750977,
162
+ "learning_rate": 1.3079999999999998e-05,
163
+ "loss": 9.2699,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0006736605322064653,
168
+ "grad_norm": 39.57080078125,
169
+ "learning_rate": 1.3559999999999997e-05,
170
+ "loss": 9.2491,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0007029501205632681,
175
+ "grad_norm": 18.53085708618164,
176
+ "learning_rate": 1.4159999999999998e-05,
177
+ "loss": 9.2552,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.000732239708920071,
182
+ "grad_norm": 41.72337341308594,
183
+ "learning_rate": 1.476e-05,
184
+ "loss": 9.2611,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0007615292972768737,
189
+ "grad_norm": 21.73541831970215,
190
+ "learning_rate": 1.536e-05,
191
+ "loss": 9.2928,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0007908188856336766,
196
+ "grad_norm": 59.771385192871094,
197
+ "learning_rate": 1.5959999999999996e-05,
198
+ "loss": 9.2558,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0008201084739904794,
203
+ "grad_norm": 75.89784240722656,
204
+ "learning_rate": 1.6559999999999997e-05,
205
+ "loss": 9.2438,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.0008493980623472823,
210
+ "grad_norm": 33.123294830322266,
211
+ "learning_rate": 1.716e-05,
212
+ "loss": 9.278,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.0008786876507040851,
217
+ "grad_norm": 39.20044708251953,
218
+ "learning_rate": 1.776e-05,
219
+ "loss": 9.2508,
220
+ "step": 300
221
+ }
222
+ ],
223
+ "logging_steps": 10,
224
+ "max_steps": 1000000,
225
+ "num_input_tokens_seen": 0,
226
+ "num_train_epochs": 3,
227
+ "save_steps": 100,
228
+ "stateful_callbacks": {
229
+ "TrainerControl": {
230
+ "args": {
231
+ "should_epoch_stop": false,
232
+ "should_evaluate": false,
233
+ "should_log": false,
234
+ "should_save": true,
235
+ "should_training_stop": false
236
+ },
237
+ "attributes": {}
238
+ }
239
+ },
240
+ "total_flos": 780676104192000.0,
241
+ "train_batch_size": 4,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52216374f0eeee8b1d9f89469c7170b070f292bc69dacbc00514897d8019d442
3
+ size 5201