EXCO123 commited on
Commit
6e3dca1
·
verified ·
1 Parent(s): 25e01f6

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32001,
3
+ "<|im_start|>": 32000
4
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "arnir0/Tiny-LLM",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32000,
9
+ "eos_token_id": 32001,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 192,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1024,
15
+ "max_position_embeddings": 1024,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 2,
19
+ "num_hidden_layers": 1,
20
+ "num_key_value_heads": 1,
21
+ "pad_token_id": 32001,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.47.0",
29
+ "use_cache": true,
30
+ "vocab_size": 32002
31
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32000,
4
+ "eos_token_id": 32001,
5
+ "pad_token_id": 32001,
6
+ "transformers_version": "4.47.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff4e0cf6e8aa32c5f4ac83d97f0b0cb89640389b13620cd8ed682a337c4842d
3
+ size 51960328
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa5d3af43029aab2e3fc90f3b96d670933fe30a31dcc43fea80bd72f069fab8
3
+ size 26404146
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c917636c7a58af68a29056522a757e9f9b99005b776641aa157c536967817d
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7ab81f6f167a77d305fd2072c3f0653a829da163e38e23511eabde99bbdc11
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [
48
+ "<|im_start|>",
49
+ "<|im_end|>"
50
+ ],
51
+ "bos_token": "<|im_start|>",
52
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
53
+ "clean_up_tokenization_spaces": false,
54
+ "eos_token": "<|im_end|>",
55
+ "extra_special_tokens": {},
56
+ "legacy": true,
57
+ "model_max_length": 2048,
58
+ "pad_token": "<|im_end|>",
59
+ "sp_model_kwargs": {},
60
+ "spaces_between_special_tokens": false,
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": "<unk>",
63
+ "use_default_system_prompt": false
64
+ }
trainer_state.json ADDED
@@ -0,0 +1,433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8,
5
+ "eval_steps": 500,
6
+ "global_step": 50000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016,
13
+ "grad_norm": 35.146240234375,
14
+ "learning_rate": 4.9004900490049e-05,
15
+ "loss": 10.1867,
16
+ "mean_token_accuracy": 0.544253178048879,
17
+ "step": 1000
18
+ },
19
+ {
20
+ "epoch": 0.032,
21
+ "grad_norm": 32.855838775634766,
22
+ "learning_rate": 4.8004800480048006e-05,
23
+ "loss": 10.2308,
24
+ "mean_token_accuracy": 0.5428702699318528,
25
+ "step": 2000
26
+ },
27
+ {
28
+ "epoch": 0.048,
29
+ "grad_norm": 36.6450309753418,
30
+ "learning_rate": 4.700470047004701e-05,
31
+ "loss": 10.2215,
32
+ "mean_token_accuracy": 0.5424384255111218,
33
+ "step": 3000
34
+ },
35
+ {
36
+ "epoch": 0.064,
37
+ "grad_norm": 33.15324783325195,
38
+ "learning_rate": 4.6004600460046006e-05,
39
+ "loss": 10.2813,
40
+ "mean_token_accuracy": 0.5411355452165008,
41
+ "step": 4000
42
+ },
43
+ {
44
+ "epoch": 0.08,
45
+ "grad_norm": 31.203840255737305,
46
+ "learning_rate": 4.500450045004501e-05,
47
+ "loss": 10.2447,
48
+ "mean_token_accuracy": 0.5425998609103262,
49
+ "step": 5000
50
+ },
51
+ {
52
+ "epoch": 0.096,
53
+ "grad_norm": 29.603290557861328,
54
+ "learning_rate": 4.4004400440044006e-05,
55
+ "loss": 10.131,
56
+ "mean_token_accuracy": 0.5463594534434378,
57
+ "step": 6000
58
+ },
59
+ {
60
+ "epoch": 0.112,
61
+ "grad_norm": 31.61845588684082,
62
+ "learning_rate": 4.3004300430043e-05,
63
+ "loss": 10.0479,
64
+ "mean_token_accuracy": 0.5483995637446641,
65
+ "step": 7000
66
+ },
67
+ {
68
+ "epoch": 0.128,
69
+ "grad_norm": 31.28079605102539,
70
+ "learning_rate": 4.2004200420042006e-05,
71
+ "loss": 9.9802,
72
+ "mean_token_accuracy": 0.5492958616241813,
73
+ "step": 8000
74
+ },
75
+ {
76
+ "epoch": 0.144,
77
+ "grad_norm": 28.147220611572266,
78
+ "learning_rate": 4.100410041004101e-05,
79
+ "loss": 9.8445,
80
+ "mean_token_accuracy": 0.5530450477898121,
81
+ "step": 9000
82
+ },
83
+ {
84
+ "epoch": 0.16,
85
+ "grad_norm": 26.830713272094727,
86
+ "learning_rate": 4.0004000400040005e-05,
87
+ "loss": 9.8066,
88
+ "mean_token_accuracy": 0.5538738285191357,
89
+ "step": 10000
90
+ },
91
+ {
92
+ "epoch": 0.176,
93
+ "grad_norm": 28.744468688964844,
94
+ "learning_rate": 3.900390039003901e-05,
95
+ "loss": 9.7206,
96
+ "mean_token_accuracy": 0.5572981600053608,
97
+ "step": 11000
98
+ },
99
+ {
100
+ "epoch": 0.192,
101
+ "grad_norm": 25.372802734375,
102
+ "learning_rate": 3.8003800380038005e-05,
103
+ "loss": 9.6634,
104
+ "mean_token_accuracy": 0.5570068260915577,
105
+ "step": 12000
106
+ },
107
+ {
108
+ "epoch": 0.208,
109
+ "grad_norm": 31.25323486328125,
110
+ "learning_rate": 3.7003700370037e-05,
111
+ "loss": 9.5426,
112
+ "mean_token_accuracy": 0.5603208757042885,
113
+ "step": 13000
114
+ },
115
+ {
116
+ "epoch": 0.224,
117
+ "grad_norm": 33.54015350341797,
118
+ "learning_rate": 3.6003600360036005e-05,
119
+ "loss": 9.532,
120
+ "mean_token_accuracy": 0.561353420805186,
121
+ "step": 14000
122
+ },
123
+ {
124
+ "epoch": 0.24,
125
+ "grad_norm": 30.744821548461914,
126
+ "learning_rate": 3.500350035003501e-05,
127
+ "loss": 9.4778,
128
+ "mean_token_accuracy": 0.5629392731450498,
129
+ "step": 15000
130
+ },
131
+ {
132
+ "epoch": 0.256,
133
+ "grad_norm": 24.013673782348633,
134
+ "learning_rate": 3.4003400340034005e-05,
135
+ "loss": 9.477,
136
+ "mean_token_accuracy": 0.5625265723504126,
137
+ "step": 16000
138
+ },
139
+ {
140
+ "epoch": 0.272,
141
+ "grad_norm": 27.767776489257812,
142
+ "learning_rate": 3.300330033003301e-05,
143
+ "loss": 9.3889,
144
+ "mean_token_accuracy": 0.5659195666387677,
145
+ "step": 17000
146
+ },
147
+ {
148
+ "epoch": 0.288,
149
+ "grad_norm": 29.1698055267334,
150
+ "learning_rate": 3.2003200320032004e-05,
151
+ "loss": 9.3476,
152
+ "mean_token_accuracy": 0.5666751223653554,
153
+ "step": 18000
154
+ },
155
+ {
156
+ "epoch": 0.304,
157
+ "grad_norm": 29.41615867614746,
158
+ "learning_rate": 3.1003100310031e-05,
159
+ "loss": 9.3244,
160
+ "mean_token_accuracy": 0.5674368364065886,
161
+ "step": 19000
162
+ },
163
+ {
164
+ "epoch": 0.32,
165
+ "grad_norm": 23.839937210083008,
166
+ "learning_rate": 3.0003000300030004e-05,
167
+ "loss": 9.2717,
168
+ "mean_token_accuracy": 0.5696731022559106,
169
+ "step": 20000
170
+ },
171
+ {
172
+ "epoch": 0.336,
173
+ "grad_norm": 28.645061492919922,
174
+ "learning_rate": 2.9002900290029007e-05,
175
+ "loss": 9.2327,
176
+ "mean_token_accuracy": 0.5706070831567049,
177
+ "step": 21000
178
+ },
179
+ {
180
+ "epoch": 0.352,
181
+ "grad_norm": 26.104412078857422,
182
+ "learning_rate": 2.8002800280028004e-05,
183
+ "loss": 9.223,
184
+ "mean_token_accuracy": 0.5696454518660903,
185
+ "step": 22000
186
+ },
187
+ {
188
+ "epoch": 0.368,
189
+ "grad_norm": 28.753164291381836,
190
+ "learning_rate": 2.7002700270027004e-05,
191
+ "loss": 9.145,
192
+ "mean_token_accuracy": 0.5734736853465437,
193
+ "step": 23000
194
+ },
195
+ {
196
+ "epoch": 0.384,
197
+ "grad_norm": 21.9370174407959,
198
+ "learning_rate": 2.6002600260026007e-05,
199
+ "loss": 9.1538,
200
+ "mean_token_accuracy": 0.5731835125163197,
201
+ "step": 24000
202
+ },
203
+ {
204
+ "epoch": 0.4,
205
+ "grad_norm": 31.202007293701172,
206
+ "learning_rate": 2.5002500250025003e-05,
207
+ "loss": 9.1016,
208
+ "mean_token_accuracy": 0.5749420530423522,
209
+ "step": 25000
210
+ },
211
+ {
212
+ "epoch": 0.416,
213
+ "grad_norm": 24.899829864501953,
214
+ "learning_rate": 2.4002400240024003e-05,
215
+ "loss": 9.1086,
216
+ "mean_token_accuracy": 0.5731981860995292,
217
+ "step": 26000
218
+ },
219
+ {
220
+ "epoch": 0.432,
221
+ "grad_norm": 26.59105682373047,
222
+ "learning_rate": 2.3002300230023003e-05,
223
+ "loss": 9.0585,
224
+ "mean_token_accuracy": 0.575087952144444,
225
+ "step": 27000
226
+ },
227
+ {
228
+ "epoch": 0.448,
229
+ "grad_norm": 27.35274314880371,
230
+ "learning_rate": 2.2002200220022003e-05,
231
+ "loss": 9.0378,
232
+ "mean_token_accuracy": 0.5757604394182563,
233
+ "step": 28000
234
+ },
235
+ {
236
+ "epoch": 0.464,
237
+ "grad_norm": 23.581249237060547,
238
+ "learning_rate": 2.1002100210021003e-05,
239
+ "loss": 9.087,
240
+ "mean_token_accuracy": 0.5731492869332433,
241
+ "step": 29000
242
+ },
243
+ {
244
+ "epoch": 0.48,
245
+ "grad_norm": 26.905712127685547,
246
+ "learning_rate": 2.0002000200020003e-05,
247
+ "loss": 9.0834,
248
+ "mean_token_accuracy": 0.5751373803690076,
249
+ "step": 30000
250
+ },
251
+ {
252
+ "epoch": 0.496,
253
+ "grad_norm": 24.928512573242188,
254
+ "learning_rate": 1.9001900190019003e-05,
255
+ "loss": 9.0077,
256
+ "mean_token_accuracy": 0.5775581553503871,
257
+ "step": 31000
258
+ },
259
+ {
260
+ "epoch": 0.512,
261
+ "grad_norm": 28.373720169067383,
262
+ "learning_rate": 1.8001800180018002e-05,
263
+ "loss": 9.0328,
264
+ "mean_token_accuracy": 0.575654436133802,
265
+ "step": 32000
266
+ },
267
+ {
268
+ "epoch": 0.528,
269
+ "grad_norm": 26.213802337646484,
270
+ "learning_rate": 1.7001700170017002e-05,
271
+ "loss": 8.9223,
272
+ "mean_token_accuracy": 0.5791815776266158,
273
+ "step": 33000
274
+ },
275
+ {
276
+ "epoch": 0.544,
277
+ "grad_norm": 27.070953369140625,
278
+ "learning_rate": 1.6001600160016002e-05,
279
+ "loss": 8.9483,
280
+ "mean_token_accuracy": 0.5792850709185005,
281
+ "step": 34000
282
+ },
283
+ {
284
+ "epoch": 0.56,
285
+ "grad_norm": 22.90890884399414,
286
+ "learning_rate": 1.5001500150015002e-05,
287
+ "loss": 9.0419,
288
+ "mean_token_accuracy": 0.5748572928607464,
289
+ "step": 35000
290
+ },
291
+ {
292
+ "epoch": 0.576,
293
+ "grad_norm": 28.693235397338867,
294
+ "learning_rate": 1.4001400140014002e-05,
295
+ "loss": 8.951,
296
+ "mean_token_accuracy": 0.5788668767511844,
297
+ "step": 36000
298
+ },
299
+ {
300
+ "epoch": 0.592,
301
+ "grad_norm": 27.749176025390625,
302
+ "learning_rate": 1.3001300130013003e-05,
303
+ "loss": 8.9335,
304
+ "mean_token_accuracy": 0.5779373695105314,
305
+ "step": 37000
306
+ },
307
+ {
308
+ "epoch": 0.608,
309
+ "grad_norm": 25.057411193847656,
310
+ "learning_rate": 1.2001200120012002e-05,
311
+ "loss": 8.8612,
312
+ "mean_token_accuracy": 0.5811370112374425,
313
+ "step": 38000
314
+ },
315
+ {
316
+ "epoch": 0.624,
317
+ "grad_norm": 26.132497787475586,
318
+ "learning_rate": 1.1001100110011001e-05,
319
+ "loss": 8.8688,
320
+ "mean_token_accuracy": 0.5816743801310659,
321
+ "step": 39000
322
+ },
323
+ {
324
+ "epoch": 0.64,
325
+ "grad_norm": 26.350906372070312,
326
+ "learning_rate": 1.0001000100010001e-05,
327
+ "loss": 8.8358,
328
+ "mean_token_accuracy": 0.5821756240203977,
329
+ "step": 40000
330
+ },
331
+ {
332
+ "epoch": 0.656,
333
+ "grad_norm": 24.874052047729492,
334
+ "learning_rate": 9.000900090009001e-06,
335
+ "loss": 8.8207,
336
+ "mean_token_accuracy": 0.5826298766359687,
337
+ "step": 41000
338
+ },
339
+ {
340
+ "epoch": 0.672,
341
+ "grad_norm": 26.102046966552734,
342
+ "learning_rate": 8.000800080008001e-06,
343
+ "loss": 8.8275,
344
+ "mean_token_accuracy": 0.5821652906313538,
345
+ "step": 42000
346
+ },
347
+ {
348
+ "epoch": 0.688,
349
+ "grad_norm": 29.679323196411133,
350
+ "learning_rate": 7.000700070007001e-06,
351
+ "loss": 8.85,
352
+ "mean_token_accuracy": 0.5809146241471171,
353
+ "step": 43000
354
+ },
355
+ {
356
+ "epoch": 0.704,
357
+ "grad_norm": 26.106046676635742,
358
+ "learning_rate": 6.000600060006001e-06,
359
+ "loss": 8.8531,
360
+ "mean_token_accuracy": 0.5821815392710269,
361
+ "step": 44000
362
+ },
363
+ {
364
+ "epoch": 0.72,
365
+ "grad_norm": 22.304044723510742,
366
+ "learning_rate": 5.000500050005001e-06,
367
+ "loss": 8.8142,
368
+ "mean_token_accuracy": 0.5825774453170598,
369
+ "step": 45000
370
+ },
371
+ {
372
+ "epoch": 0.736,
373
+ "grad_norm": 28.982166290283203,
374
+ "learning_rate": 4.0004000400040005e-06,
375
+ "loss": 8.8434,
376
+ "mean_token_accuracy": 0.5813510757684708,
377
+ "step": 46000
378
+ },
379
+ {
380
+ "epoch": 0.752,
381
+ "grad_norm": 27.076814651489258,
382
+ "learning_rate": 3.0003000300030004e-06,
383
+ "loss": 8.7994,
384
+ "mean_token_accuracy": 0.5838636282868683,
385
+ "step": 47000
386
+ },
387
+ {
388
+ "epoch": 0.768,
389
+ "grad_norm": 26.112808227539062,
390
+ "learning_rate": 2.0002000200020003e-06,
391
+ "loss": 8.8055,
392
+ "mean_token_accuracy": 0.5828906665407121,
393
+ "step": 48000
394
+ },
395
+ {
396
+ "epoch": 0.784,
397
+ "grad_norm": 24.94652557373047,
398
+ "learning_rate": 1.0001000100010001e-06,
399
+ "loss": 8.8295,
400
+ "mean_token_accuracy": 0.5821196795813739,
401
+ "step": 49000
402
+ },
403
+ {
404
+ "epoch": 0.8,
405
+ "grad_norm": 28.15529441833496,
406
+ "learning_rate": 0.0,
407
+ "loss": 8.7714,
408
+ "mean_token_accuracy": 0.5843258857652545,
409
+ "step": 50000
410
+ }
411
+ ],
412
+ "logging_steps": 1000,
413
+ "max_steps": 50000,
414
+ "num_input_tokens_seen": 0,
415
+ "num_train_epochs": 1,
416
+ "save_steps": 500,
417
+ "stateful_callbacks": {
418
+ "TrainerControl": {
419
+ "args": {
420
+ "should_epoch_stop": false,
421
+ "should_evaluate": false,
422
+ "should_log": false,
423
+ "should_save": true,
424
+ "should_training_stop": true
425
+ },
426
+ "attributes": {}
427
+ }
428
+ },
429
+ "total_flos": 1.68231960576e+16,
430
+ "train_batch_size": 4,
431
+ "trial_name": null,
432
+ "trial_params": null
433
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c535604d9e4c89b200240de3a2f02689fd12d98f9d3f6c3313f1e2aa469bbe
3
+ size 5496