Hugging Face's logo

aixk
/
miniai

Transformers
Safetensors
Model card Files
xet
 Community
aixk commited on
Commit
6025d2f
·
verified ·
1 Parent(s): 4c3bee5

Upload checkpoint-2000

Browse files
Files changed (11) hide show
  1. checkpoint-2000/chat_template.jinja +4 -0
  2. checkpoint-2000/config.json +63 -0
  3. checkpoint-2000/generation_config.json +7 -0
  4. checkpoint-2000/model.safetensors +3 -0
  5. checkpoint-2000/optimizer.pt +3 -0
  6. checkpoint-2000/rng_state.pth +3 -0
  7. checkpoint-2000/scheduler.pt +3 -0
  8. checkpoint-2000/tokenizer.json +3 -0
  9. checkpoint-2000/tokenizer_config.json +18 -0
  10. checkpoint-2000/trainer_state.json +314 -0
  11. checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{ '<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ ' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-2000/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 640,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 2048,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen2",
48
+ "num_attention_heads": 10,
49
+ "num_hidden_layers": 30,
50
+ "num_key_value_heads": 2,
51
+ "pad_token_id": null,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 100000.0,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.0.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151665
63
+ }
checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.0.0",
6
+ "use_cache": true
7
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72af3b0a5b1a15641905d809f2c4f43ae8aed76dc1866190e930b27d23412c7
3
+ size 860425256
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fac24959d3d53f28098cd72f6d162402a69596c1461b28fe57ee931ee4b9f2
3
+ size 1721079713
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54bec29bca41a245bccb8b1c25c07e869bf8cf35a5b9a5006fa24c49f6cdf63f
3
+ size 1465
checkpoint-2000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>"
11
+ ],
12
+ "is_local": false,
13
+ "model_max_length": 131072,
14
+ "pad_token": "<|endoftext|>",
15
+ "split_special_tokens": false,
16
+ "tokenizer_class": "Qwen2Tokenizer",
17
+ "unk_token": null
18
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0031430624802515,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 7.85765620062875e-05,
14
+ "grad_norm": 3.4856550693511963,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 11.309625244140625,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.000157153124012575,
21
+ "grad_norm": 3.3093955516815186,
22
+ "learning_rate": 1.9800000000000004e-05,
23
+ "loss": 9.846463012695313,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.0002357296860188625,
28
+ "grad_norm": 3.2158353328704834,
29
+ "learning_rate": 2.98e-05,
30
+ "loss": 8.753692626953125,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.00031430624802515,
35
+ "grad_norm": 1.8870658874511719,
36
+ "learning_rate": 3.9800000000000005e-05,
37
+ "loss": 7.157894287109375,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.0003928828100314375,
42
+ "grad_norm": 1.709052562713623,
43
+ "learning_rate": 4.9800000000000004e-05,
44
+ "loss": 5.5407257080078125,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.000471459372037725,
49
+ "grad_norm": 2.6122117042541504,
50
+ "learning_rate": 5.9800000000000003e-05,
51
+ "loss": 4.60130126953125,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.0005500359340440125,
56
+ "grad_norm": 2.101297378540039,
57
+ "learning_rate": 6.98e-05,
58
+ "loss": 4.0536062622070315,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.0006286124960503,
63
+ "grad_norm": 3.6969990730285645,
64
+ "learning_rate": 7.98e-05,
65
+ "loss": 3.595623779296875,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.0007071890580565875,
70
+ "grad_norm": 1.2866711616516113,
71
+ "learning_rate": 8.98e-05,
72
+ "loss": 3.5386227416992186,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.000785765620062875,
77
+ "grad_norm": 1.563516616821289,
78
+ "learning_rate": 9.98e-05,
79
+ "loss": 3.341569519042969,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.0008643421820691625,
84
+ "grad_norm": 1.6755658388137817,
85
+ "learning_rate": 0.00010980000000000001,
86
+ "loss": 3.142231140136719,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.00094291874407545,
91
+ "grad_norm": 1.294084072113037,
92
+ "learning_rate": 0.0001198,
93
+ "loss": 3.1897616577148438,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.0010214953060817375,
98
+ "grad_norm": 1.468405842781067,
99
+ "learning_rate": 0.0001298,
100
+ "loss": 3.0959951782226565,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.001100071868088025,
105
+ "grad_norm": 1.301240086555481,
106
+ "learning_rate": 0.0001398,
107
+ "loss": 2.91419921875,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.0011786484300943124,
112
+ "grad_norm": 1.40414297580719,
113
+ "learning_rate": 0.0001498,
114
+ "loss": 2.933033447265625,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.0012572249921006,
119
+ "grad_norm": 1.468867540359497,
120
+ "learning_rate": 0.0001598,
121
+ "loss": 2.8924459838867187,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.0013358015541068875,
126
+ "grad_norm": 1.293474555015564,
127
+ "learning_rate": 0.0001698,
128
+ "loss": 2.845906982421875,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.001414378116113175,
133
+ "grad_norm": 1.3119351863861084,
134
+ "learning_rate": 0.0001798,
135
+ "loss": 2.829622497558594,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.0014929546781194626,
140
+ "grad_norm": 1.3707680702209473,
141
+ "learning_rate": 0.0001898,
142
+ "loss": 2.864462890625,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.00157153124012575,
147
+ "grad_norm": 1.312740683555603,
148
+ "learning_rate": 0.0001998,
149
+ "loss": 2.6262371826171873,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.0016501078021320375,
154
+ "grad_norm": 1.2023130655288696,
155
+ "learning_rate": 0.0001999999992672945,
156
+ "loss": 2.7077838134765626,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.001728684364138325,
161
+ "grad_norm": 1.2671232223510742,
162
+ "learning_rate": 0.00019999999700906016,
163
+ "loss": 2.6466583251953124,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.0018072609261446126,
168
+ "grad_norm": 1.2444766759872437,
169
+ "learning_rate": 0.00019999999322499186,
170
+ "loss": 2.659414978027344,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.0018858374881509,
175
+ "grad_norm": 1.2258152961730957,
176
+ "learning_rate": 0.0001999999879150896,
177
+ "loss": 2.7120596313476564,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.0019644140501571877,
182
+ "grad_norm": 1.3060775995254517,
183
+ "learning_rate": 0.00019999998107935355,
184
+ "loss": 2.641546325683594,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.002042990612163475,
189
+ "grad_norm": 0.9617738127708435,
190
+ "learning_rate": 0.00019999997271778373,
191
+ "loss": 2.64413330078125,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.0021215671741697624,
196
+ "grad_norm": 1.1611496210098267,
197
+ "learning_rate": 0.0001999999628303803,
198
+ "loss": 2.4549749755859374,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.00220014373617605,
203
+ "grad_norm": 1.0154592990875244,
204
+ "learning_rate": 0.00019999995141714344,
205
+ "loss": 2.620474548339844,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.0022787202981823375,
210
+ "grad_norm": 0.8560603857040405,
211
+ "learning_rate": 0.00019999993847807327,
212
+ "loss": 2.5877325439453127,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.002357296860188625,
217
+ "grad_norm": 1.0139614343643188,
218
+ "learning_rate": 0.00019999992401317004,
219
+ "loss": 2.427532196044922,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.0024358734221949126,
224
+ "grad_norm": 0.9686440825462341,
225
+ "learning_rate": 0.00019999990802243393,
226
+ "loss": 2.493535461425781,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.0025144499842012,
231
+ "grad_norm": 1.187860369682312,
232
+ "learning_rate": 0.00019999989050586522,
233
+ "loss": 2.452259063720703,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.0025930265462074877,
238
+ "grad_norm": 1.183596134185791,
239
+ "learning_rate": 0.00019999987146346416,
240
+ "loss": 2.3872813415527343,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.002671603108213775,
245
+ "grad_norm": 1.1113741397857666,
246
+ "learning_rate": 0.000199999850895231,
247
+ "loss": 2.4507025146484374,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.0027501796702200623,
252
+ "grad_norm": 0.9131802916526794,
253
+ "learning_rate": 0.00019999982880116612,
254
+ "loss": 2.323751220703125,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.00282875623222635,
259
+ "grad_norm": 1.0744889974594116,
260
+ "learning_rate": 0.00019999980518126985,
261
+ "loss": 2.3506312561035156,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.0029073327942326374,
266
+ "grad_norm": 1.0484017133712769,
267
+ "learning_rate": 0.00019999978003554247,
268
+ "loss": 2.464927520751953,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.002985909356238925,
273
+ "grad_norm": 1.0957303047180176,
274
+ "learning_rate": 0.0001999997533639845,
275
+ "loss": 2.3626954650878904,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.0030644859182452125,
280
+ "grad_norm": 1.1429017782211304,
281
+ "learning_rate": 0.0001999997251665962,
282
+ "loss": 2.3631982421875,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.0031430624802515,
287
+ "grad_norm": 1.168506383895874,
288
+ "learning_rate": 0.00019999969544337812,
289
+ "loss": 2.3775091552734375,
290
+ "step": 2000
291
+ }
292
+ ],
293
+ "logging_steps": 50,
294
+ "max_steps": 1272646,
295
+ "num_input_tokens_seen": 0,
296
+ "num_train_epochs": 2,
297
+ "save_steps": 1000,
298
+ "stateful_callbacks": {
299
+ "TrainerControl": {
300
+ "args": {
301
+ "should_epoch_stop": false,
302
+ "should_evaluate": false,
303
+ "should_log": false,
304
+ "should_save": true,
305
+ "should_training_stop": false
306
+ },
307
+ "attributes": {}
308
+ }
309
+ },
310
+ "total_flos": 2276798425113600.0,
311
+ "train_batch_size": 1,
312
+ "trial_name": null,
313
+ "trial_params": null
314
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d4e277d07a3e33729def2f305e71bde59755c9baac68812ca3cd169729e960
3
+ size 5137