IshaanMan123 commited on
Commit
724cee0
·
verified ·
1 Parent(s): 593f2e6

upload fresh checkpoint

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "capacity_factor_eval": 2.0,
9
+ "capacity_factor_train": 1.25,
10
+ "drop_tks": true,
11
+ "dropout_rate": 0.0,
12
+ "dtype": "float32",
13
+ "eos_token_id": 2,
14
+ "expert_parallel": null,
15
+ "gated": true,
16
+ "head_dim": 64,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 768,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 2048,
21
+ "layer_norm_epsilon": 1e-06,
22
+ "max_position_embeddings": 2048,
23
+ "min_capacity": 4,
24
+ "mlp_bias": false,
25
+ "model_type": "llama",
26
+ "moe_layer_interval": 4,
27
+ "noisy_policy": null,
28
+ "num_attention_heads": 12,
29
+ "num_experts": 16,
30
+ "num_hidden_layers": 12,
31
+ "num_key_value_heads": 12,
32
+ "pad_token_id": 0,
33
+ "pretraining_tp": 1,
34
+ "rms_norm_eps": 1e-06,
35
+ "rope_parameters": {
36
+ "rope_theta": 10000.0,
37
+ "rope_type": "default"
38
+ },
39
+ "tie_word_embeddings": false,
40
+ "topk": 2,
41
+ "transformers_version": "5.2.0",
42
+ "use_cache": true,
43
+ "vocab_size": 256384
44
+ }
checkpoint/dataset_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"processed_items": 0}
checkpoint/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "5.2.0"
7
+ }
checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a4313faf7c7809692f60bd195633188307ffc10f2f40c8f5c4f656da9c93899
3
+ size 1915051264
checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1007b88bc64d1e50a3594117716e55a0e1238a467c38e18db57d251cb699a11
3
+ size 16853279
checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "</s>",
6
+ "extra_ids": 300,
7
+ "extra_special_tokens": [
8
+ "<extra_id_0>",
9
+ "<extra_id_1>",
10
+ "<extra_id_2>",
11
+ "<extra_id_3>",
12
+ "<extra_id_4>",
13
+ "<extra_id_5>",
14
+ "<extra_id_6>",
15
+ "<extra_id_7>",
16
+ "<extra_id_8>",
17
+ "<extra_id_9>",
18
+ "<extra_id_10>",
19
+ "<extra_id_11>",
20
+ "<extra_id_12>",
21
+ "<extra_id_13>",
22
+ "<extra_id_14>",
23
+ "<extra_id_15>",
24
+ "<extra_id_16>",
25
+ "<extra_id_17>",
26
+ "<extra_id_18>",
27
+ "<extra_id_19>",
28
+ "<extra_id_20>",
29
+ "<extra_id_21>",
30
+ "<extra_id_22>",
31
+ "<extra_id_23>",
32
+ "<extra_id_24>",
33
+ "<extra_id_25>",
34
+ "<extra_id_26>",
35
+ "<extra_id_27>",
36
+ "<extra_id_28>",
37
+ "<extra_id_29>",
38
+ "<extra_id_30>",
39
+ "<extra_id_31>",
40
+ "<extra_id_32>",
41
+ "<extra_id_33>",
42
+ "<extra_id_34>",
43
+ "<extra_id_35>",
44
+ "<extra_id_36>",
45
+ "<extra_id_37>",
46
+ "<extra_id_38>",
47
+ "<extra_id_39>",
48
+ "<extra_id_40>",
49
+ "<extra_id_41>",
50
+ "<extra_id_42>",
51
+ "<extra_id_43>",
52
+ "<extra_id_44>",
53
+ "<extra_id_45>",
54
+ "<extra_id_46>",
55
+ "<extra_id_47>",
56
+ "<extra_id_48>",
57
+ "<extra_id_49>",
58
+ "<extra_id_50>",
59
+ "<extra_id_51>",
60
+ "<extra_id_52>",
61
+ "<extra_id_53>",
62
+ "<extra_id_54>",
63
+ "<extra_id_55>",
64
+ "<extra_id_56>",
65
+ "<extra_id_57>",
66
+ "<extra_id_58>",
67
+ "<extra_id_59>",
68
+ "<extra_id_60>",
69
+ "<extra_id_61>",
70
+ "<extra_id_62>",
71
+ "<extra_id_63>",
72
+ "<extra_id_64>",
73
+ "<extra_id_65>",
74
+ "<extra_id_66>",
75
+ "<extra_id_67>",
76
+ "<extra_id_68>",
77
+ "<extra_id_69>",
78
+ "<extra_id_70>",
79
+ "<extra_id_71>",
80
+ "<extra_id_72>",
81
+ "<extra_id_73>",
82
+ "<extra_id_74>",
83
+ "<extra_id_75>",
84
+ "<extra_id_76>",
85
+ "<extra_id_77>",
86
+ "<extra_id_78>",
87
+ "<extra_id_79>",
88
+ "<extra_id_80>",
89
+ "<extra_id_81>",
90
+ "<extra_id_82>",
91
+ "<extra_id_83>",
92
+ "<extra_id_84>",
93
+ "<extra_id_85>",
94
+ "<extra_id_86>",
95
+ "<extra_id_87>",
96
+ "<extra_id_88>",
97
+ "<extra_id_89>",
98
+ "<extra_id_90>",
99
+ "<extra_id_91>",
100
+ "<extra_id_92>",
101
+ "<extra_id_93>",
102
+ "<extra_id_94>",
103
+ "<extra_id_95>",
104
+ "<extra_id_96>",
105
+ "<extra_id_97>",
106
+ "<extra_id_98>",
107
+ "<extra_id_99>",
108
+ "<extra_id_100>",
109
+ "<extra_id_101>",
110
+ "<extra_id_102>",
111
+ "<extra_id_103>",
112
+ "<extra_id_104>",
113
+ "<extra_id_105>",
114
+ "<extra_id_106>",
115
+ "<extra_id_107>",
116
+ "<extra_id_108>",
117
+ "<extra_id_109>",
118
+ "<extra_id_110>",
119
+ "<extra_id_111>",
120
+ "<extra_id_112>",
121
+ "<extra_id_113>",
122
+ "<extra_id_114>",
123
+ "<extra_id_115>",
124
+ "<extra_id_116>",
125
+ "<extra_id_117>",
126
+ "<extra_id_118>",
127
+ "<extra_id_119>",
128
+ "<extra_id_120>",
129
+ "<extra_id_121>",
130
+ "<extra_id_122>",
131
+ "<extra_id_123>",
132
+ "<extra_id_124>",
133
+ "<extra_id_125>",
134
+ "<extra_id_126>",
135
+ "<extra_id_127>",
136
+ "<extra_id_128>",
137
+ "<extra_id_129>",
138
+ "<extra_id_130>",
139
+ "<extra_id_131>",
140
+ "<extra_id_132>",
141
+ "<extra_id_133>",
142
+ "<extra_id_134>",
143
+ "<extra_id_135>",
144
+ "<extra_id_136>",
145
+ "<extra_id_137>",
146
+ "<extra_id_138>",
147
+ "<extra_id_139>",
148
+ "<extra_id_140>",
149
+ "<extra_id_141>",
150
+ "<extra_id_142>",
151
+ "<extra_id_143>",
152
+ "<extra_id_144>",
153
+ "<extra_id_145>",
154
+ "<extra_id_146>",
155
+ "<extra_id_147>",
156
+ "<extra_id_148>",
157
+ "<extra_id_149>",
158
+ "<extra_id_150>",
159
+ "<extra_id_151>",
160
+ "<extra_id_152>",
161
+ "<extra_id_153>",
162
+ "<extra_id_154>",
163
+ "<extra_id_155>",
164
+ "<extra_id_156>",
165
+ "<extra_id_157>",
166
+ "<extra_id_158>",
167
+ "<extra_id_159>",
168
+ "<extra_id_160>",
169
+ "<extra_id_161>",
170
+ "<extra_id_162>",
171
+ "<extra_id_163>",
172
+ "<extra_id_164>",
173
+ "<extra_id_165>",
174
+ "<extra_id_166>",
175
+ "<extra_id_167>",
176
+ "<extra_id_168>",
177
+ "<extra_id_169>",
178
+ "<extra_id_170>",
179
+ "<extra_id_171>",
180
+ "<extra_id_172>",
181
+ "<extra_id_173>",
182
+ "<extra_id_174>",
183
+ "<extra_id_175>",
184
+ "<extra_id_176>",
185
+ "<extra_id_177>",
186
+ "<extra_id_178>",
187
+ "<extra_id_179>",
188
+ "<extra_id_180>",
189
+ "<extra_id_181>",
190
+ "<extra_id_182>",
191
+ "<extra_id_183>",
192
+ "<extra_id_184>",
193
+ "<extra_id_185>",
194
+ "<extra_id_186>",
195
+ "<extra_id_187>",
196
+ "<extra_id_188>",
197
+ "<extra_id_189>",
198
+ "<extra_id_190>",
199
+ "<extra_id_191>",
200
+ "<extra_id_192>",
201
+ "<extra_id_193>",
202
+ "<extra_id_194>",
203
+ "<extra_id_195>",
204
+ "<extra_id_196>",
205
+ "<extra_id_197>",
206
+ "<extra_id_198>",
207
+ "<extra_id_199>",
208
+ "<extra_id_200>",
209
+ "<extra_id_201>",
210
+ "<extra_id_202>",
211
+ "<extra_id_203>",
212
+ "<extra_id_204>",
213
+ "<extra_id_205>",
214
+ "<extra_id_206>",
215
+ "<extra_id_207>",
216
+ "<extra_id_208>",
217
+ "<extra_id_209>",
218
+ "<extra_id_210>",
219
+ "<extra_id_211>",
220
+ "<extra_id_212>",
221
+ "<extra_id_213>",
222
+ "<extra_id_214>",
223
+ "<extra_id_215>",
224
+ "<extra_id_216>",
225
+ "<extra_id_217>",
226
+ "<extra_id_218>",
227
+ "<extra_id_219>",
228
+ "<extra_id_220>",
229
+ "<extra_id_221>",
230
+ "<extra_id_222>",
231
+ "<extra_id_223>",
232
+ "<extra_id_224>",
233
+ "<extra_id_225>",
234
+ "<extra_id_226>",
235
+ "<extra_id_227>",
236
+ "<extra_id_228>",
237
+ "<extra_id_229>",
238
+ "<extra_id_230>",
239
+ "<extra_id_231>",
240
+ "<extra_id_232>",
241
+ "<extra_id_233>",
242
+ "<extra_id_234>",
243
+ "<extra_id_235>",
244
+ "<extra_id_236>",
245
+ "<extra_id_237>",
246
+ "<extra_id_238>",
247
+ "<extra_id_239>",
248
+ "<extra_id_240>",
249
+ "<extra_id_241>",
250
+ "<extra_id_242>",
251
+ "<extra_id_243>",
252
+ "<extra_id_244>",
253
+ "<extra_id_245>",
254
+ "<extra_id_246>",
255
+ "<extra_id_247>",
256
+ "<extra_id_248>",
257
+ "<extra_id_249>",
258
+ "<extra_id_250>",
259
+ "<extra_id_251>",
260
+ "<extra_id_252>",
261
+ "<extra_id_253>",
262
+ "<extra_id_254>",
263
+ "<extra_id_255>",
264
+ "<extra_id_256>",
265
+ "<extra_id_257>",
266
+ "<extra_id_258>",
267
+ "<extra_id_259>",
268
+ "<extra_id_260>",
269
+ "<extra_id_261>",
270
+ "<extra_id_262>",
271
+ "<extra_id_263>",
272
+ "<extra_id_264>",
273
+ "<extra_id_265>",
274
+ "<extra_id_266>",
275
+ "<extra_id_267>",
276
+ "<extra_id_268>",
277
+ "<extra_id_269>",
278
+ "<extra_id_270>",
279
+ "<extra_id_271>",
280
+ "<extra_id_272>",
281
+ "<extra_id_273>",
282
+ "<extra_id_274>",
283
+ "<extra_id_275>",
284
+ "<extra_id_276>",
285
+ "<extra_id_277>",
286
+ "<extra_id_278>",
287
+ "<extra_id_279>",
288
+ "<extra_id_280>",
289
+ "<extra_id_281>",
290
+ "<extra_id_282>",
291
+ "<extra_id_283>",
292
+ "<extra_id_284>",
293
+ "<extra_id_285>",
294
+ "<extra_id_286>",
295
+ "<extra_id_287>",
296
+ "<extra_id_288>",
297
+ "<extra_id_289>",
298
+ "<extra_id_290>",
299
+ "<extra_id_291>",
300
+ "<extra_id_292>",
301
+ "<extra_id_293>",
302
+ "<extra_id_294>",
303
+ "<extra_id_295>",
304
+ "<extra_id_296>",
305
+ "<extra_id_297>",
306
+ "<extra_id_298>",
307
+ "<extra_id_299>"
308
+ ],
309
+ "is_local": false,
310
+ "model_max_length": 1000000000000000019884624838656,
311
+ "pad_token": "<pad>",
312
+ "sp_model_kwargs": {},
313
+ "spaces_between_special_tokens": false,
314
+ "tokenizer_class": "T5Tokenizer",
315
+ "unk_token": "<unk>"
316
+ }
checkpoint/trainer_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cbb1c296d60508c05f67932dd0b0101643234d000a15c42b02d2c0a14192df
3
+ size 1361