iko-01 commited on
Commit
75c5113
·
verified ·
1 Parent(s): ac2df07

رفع النموذج النهائي مع جميع الملفات للتجربة أو إعادة التدريب

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "transformers_version": "4.56.0",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.56.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fea69efbfc0669949f442b160ad3050c174c51ecb0ab08389804d4812fdd073
3
+ size 652163920
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c96035012d2e0e2f3f1b4f04907f26c424ee0cebfdbf5d10409362d9a0d68b5
3
+ size 995638603
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0cf9ea7ecca080470627e12e718a6c0a95a6db5a8db9104e652778805f4ca8
3
+ size 14455
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fd2c1f704e6c5005d86c25a72019cd7889a76930908905af4beff382485d58
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,349 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.072,
6
+ "eval_steps": 500,
7
+ "global_step": 4500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0016,
14
+ "grad_norm": 5.90625,
15
+ "learning_rate": 3.96e-06,
16
+ "loss": 3.1,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.0032,
21
+ "grad_norm": 6.625,
22
+ "learning_rate": 7.960000000000002e-06,
23
+ "loss": 3.1,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.0048,
28
+ "grad_norm": 4.125,
29
+ "learning_rate": 1.196e-05,
30
+ "loss": 2.98,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.0064,
35
+ "grad_norm": 3.78125,
36
+ "learning_rate": 1.5960000000000003e-05,
37
+ "loss": 2.72,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.008,
42
+ "grad_norm": 3.71875,
43
+ "learning_rate": 1.9960000000000002e-05,
44
+ "loss": 2.58,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.0096,
49
+ "grad_norm": 3.234375,
50
+ "learning_rate": 1.9968064516129034e-05,
51
+ "loss": 2.47,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.0112,
56
+ "grad_norm": 3.625,
57
+ "learning_rate": 1.9935806451612905e-05,
58
+ "loss": 2.44,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.0128,
63
+ "grad_norm": 3.328125,
64
+ "learning_rate": 1.9903548387096776e-05,
65
+ "loss": 2.45,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.0144,
70
+ "grad_norm": 3.234375,
71
+ "learning_rate": 1.9871290322580646e-05,
72
+ "loss": 2.41,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.016,
77
+ "grad_norm": 2.984375,
78
+ "learning_rate": 1.9839032258064517e-05,
79
+ "loss": 2.38,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.0176,
84
+ "grad_norm": 2.921875,
85
+ "learning_rate": 1.9806774193548387e-05,
86
+ "loss": 2.36,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.0192,
91
+ "grad_norm": 3.234375,
92
+ "learning_rate": 1.9774516129032258e-05,
93
+ "loss": 2.42,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.0208,
98
+ "grad_norm": 3.125,
99
+ "learning_rate": 1.9742258064516132e-05,
100
+ "loss": 2.44,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.0224,
105
+ "grad_norm": 3.03125,
106
+ "learning_rate": 1.9710000000000003e-05,
107
+ "loss": 2.4,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.024,
112
+ "grad_norm": 3.28125,
113
+ "learning_rate": 1.9677741935483873e-05,
114
+ "loss": 2.37,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.0256,
119
+ "grad_norm": 3.09375,
120
+ "learning_rate": 1.9645483870967744e-05,
121
+ "loss": 2.42,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.0272,
126
+ "grad_norm": 3.078125,
127
+ "learning_rate": 1.9613225806451615e-05,
128
+ "loss": 2.38,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.0288,
133
+ "grad_norm": 3.140625,
134
+ "learning_rate": 1.9580967741935485e-05,
135
+ "loss": 2.39,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.0304,
140
+ "grad_norm": 3.296875,
141
+ "learning_rate": 1.9548709677419356e-05,
142
+ "loss": 2.39,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.032,
147
+ "grad_norm": 3.515625,
148
+ "learning_rate": 1.9516451612903226e-05,
149
+ "loss": 2.33,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.0336,
154
+ "grad_norm": 3.375,
155
+ "learning_rate": 1.9484193548387097e-05,
156
+ "loss": 2.38,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.0352,
161
+ "grad_norm": 3.328125,
162
+ "learning_rate": 1.945193548387097e-05,
163
+ "loss": 2.36,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.0368,
168
+ "grad_norm": 3.375,
169
+ "learning_rate": 1.9419677419354842e-05,
170
+ "loss": 2.39,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.0384,
175
+ "grad_norm": 3.109375,
176
+ "learning_rate": 1.938741935483871e-05,
177
+ "loss": 2.4,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.04,
182
+ "grad_norm": 3.3125,
183
+ "learning_rate": 1.9355161290322583e-05,
184
+ "loss": 2.4,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.0416,
189
+ "grad_norm": 3.15625,
190
+ "learning_rate": 1.9322903225806454e-05,
191
+ "loss": 2.39,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 0.0432,
196
+ "grad_norm": 3.171875,
197
+ "learning_rate": 1.9290645161290324e-05,
198
+ "loss": 2.39,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 0.0448,
203
+ "grad_norm": 3.15625,
204
+ "learning_rate": 1.9258387096774195e-05,
205
+ "loss": 2.39,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 0.0464,
210
+ "grad_norm": 3.78125,
211
+ "learning_rate": 1.9226129032258065e-05,
212
+ "loss": 2.39,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 0.048,
217
+ "grad_norm": 2.75,
218
+ "learning_rate": 1.9193870967741936e-05,
219
+ "loss": 2.37,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 0.0496,
224
+ "grad_norm": 3.109375,
225
+ "learning_rate": 1.9161612903225807e-05,
226
+ "loss": 2.38,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 0.0512,
231
+ "grad_norm": 3.203125,
232
+ "learning_rate": 1.912935483870968e-05,
233
+ "loss": 2.44,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 0.0528,
238
+ "grad_norm": 3.515625,
239
+ "learning_rate": 1.909709677419355e-05,
240
+ "loss": 2.36,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 0.0544,
245
+ "grad_norm": 3.765625,
246
+ "learning_rate": 1.906483870967742e-05,
247
+ "loss": 2.38,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 0.056,
252
+ "grad_norm": 3.09375,
253
+ "learning_rate": 1.9032580645161293e-05,
254
+ "loss": 2.44,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 0.0576,
259
+ "grad_norm": 3.578125,
260
+ "learning_rate": 1.9000322580645163e-05,
261
+ "loss": 2.39,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 0.0592,
266
+ "grad_norm": 3.578125,
267
+ "learning_rate": 1.8968064516129034e-05,
268
+ "loss": 2.44,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 0.0608,
273
+ "grad_norm": 3.28125,
274
+ "learning_rate": 1.8935806451612904e-05,
275
+ "loss": 2.37,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 0.0624,
280
+ "grad_norm": 3.1875,
281
+ "learning_rate": 1.8903548387096775e-05,
282
+ "loss": 2.36,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 0.064,
287
+ "grad_norm": 3.03125,
288
+ "learning_rate": 1.8871290322580646e-05,
289
+ "loss": 2.36,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 0.0656,
294
+ "grad_norm": 3.15625,
295
+ "learning_rate": 1.883903225806452e-05,
296
+ "loss": 2.39,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 0.0672,
301
+ "grad_norm": 3.390625,
302
+ "learning_rate": 1.880677419354839e-05,
303
+ "loss": 2.3,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 0.0688,
308
+ "grad_norm": 3.375,
309
+ "learning_rate": 1.8774516129032257e-05,
310
+ "loss": 2.4,
311
+ "step": 4300
312
+ },
313
+ {
314
+ "epoch": 0.0704,
315
+ "grad_norm": 3.359375,
316
+ "learning_rate": 1.874225806451613e-05,
317
+ "loss": 2.4,
318
+ "step": 4400
319
+ },
320
+ {
321
+ "epoch": 0.072,
322
+ "grad_norm": 3.0625,
323
+ "learning_rate": 1.8710000000000002e-05,
324
+ "loss": 2.32,
325
+ "step": 4500
326
+ }
327
+ ],
328
+ "logging_steps": 100,
329
+ "max_steps": 62500,
330
+ "num_input_tokens_seen": 0,
331
+ "num_train_epochs": 1,
332
+ "save_steps": 500,
333
+ "stateful_callbacks": {
334
+ "TrainerControl": {
335
+ "args": {
336
+ "should_epoch_stop": false,
337
+ "should_evaluate": false,
338
+ "should_log": false,
339
+ "should_save": true,
340
+ "should_training_stop": false
341
+ },
342
+ "attributes": {}
343
+ }
344
+ },
345
+ "total_flos": 1.8813026304e+16,
346
+ "train_batch_size": 8,
347
+ "trial_name": null,
348
+ "trial_params": null
349
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1c2c6de63c3466633f115406bfbfff03d10a07a25ca33d02a9cd1ed4e68cc0
3
+ size 5777