aixk commited on
Commit
0291442
·
1 Parent(s): bd7cf6a

System: Prune old checkpoint folder checkpoint-400 to save space

Browse files
checkpoint-400/config.json DELETED
@@ -1,19 +0,0 @@
1
- {
2
- "architectures": [
3
- "FastPlus40mForCausalLM"
4
- ],
5
- "dtype": "float32",
6
- "hidden_size": 512,
7
- "initializer_range": 0.02,
8
- "intermediate_size": 1536,
9
- "kd_alpha": 0.4,
10
- "kd_temperature": 2.5,
11
- "max_position_embeddings": 512,
12
- "model_type": "fastplus_40m",
13
- "num_attention_heads": 8,
14
- "num_hidden_layers": 11,
15
- "tie_word_embeddings": true,
16
- "transformers_version": "5.12.0",
17
- "use_cache": false,
18
- "vocab_size": 8160
19
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-400/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "output_attentions": false,
4
- "output_hidden_states": false,
5
- "transformers_version": "5.12.0"
6
- }
 
 
 
 
 
 
 
checkpoint-400/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-400/tokenizer_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<s>",
4
- "eos_token": "</s>",
5
- "extra_special_tokens": [
6
- "<|user|>",
7
- "<|assistant|>"
8
- ],
9
- "model_max_length": 1000000000000000019884624838656,
10
- "pad_token": "<pad>",
11
- "tokenizer_class": "TokenizersBackend",
12
- "unk_token": "<unk>"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-400/trainer_state.json DELETED
@@ -1,354 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.20743525751142514,
6
- "eval_steps": 500,
7
- "global_step": 400,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.005185881437785629,
14
- "grad_norm": 266.6409606933594,
15
- "learning_rate": 2.5499999999999996e-05,
16
- "loss": 144.2415283203125,
17
- "original_ce_loss": 9.0144,
18
- "step": 10
19
- },
20
- {
21
- "epoch": 0.010371762875571258,
22
- "grad_norm": 272.673095703125,
23
- "learning_rate": 6.8e-05,
24
- "loss": 143.50185546875,
25
- "original_ce_loss": 8.9682,
26
- "step": 20
27
- },
28
- {
29
- "epoch": 0.015557644313356886,
30
- "grad_norm": 437.08270263671875,
31
- "learning_rate": 0.00010625,
32
- "loss": 140.732373046875,
33
- "original_ce_loss": 8.7951,
34
- "step": 30
35
- },
36
- {
37
- "epoch": 0.020743525751142515,
38
- "grad_norm": 268.7778625488281,
39
- "learning_rate": 0.00014450000000000002,
40
- "loss": 128.16519775390626,
41
- "original_ce_loss": 8.0096,
42
- "step": 40
43
- },
44
- {
45
- "epoch": 0.025929407188928142,
46
- "grad_norm": 38.690486907958984,
47
- "learning_rate": 0.000187,
48
- "loss": 117.56219482421875,
49
- "original_ce_loss": 7.347,
50
- "step": 50
51
- },
52
- {
53
- "epoch": 0.031115288626713773,
54
- "grad_norm": 31.22739028930664,
55
- "learning_rate": 0.0002295,
56
- "loss": 111.48564453125,
57
- "original_ce_loss": 6.9672,
58
- "step": 60
59
- },
60
- {
61
- "epoch": 0.0363011700644994,
62
- "grad_norm": 17.76206398010254,
63
- "learning_rate": 0.000272,
64
- "loss": 104.34268798828126,
65
- "original_ce_loss": 6.5207,
66
- "step": 70
67
- },
68
- {
69
- "epoch": 0.04148705150228503,
70
- "grad_norm": 101.92194366455078,
71
- "learning_rate": 0.0003145,
72
- "loss": 100.91859130859375,
73
- "original_ce_loss": 6.3067,
74
- "step": 80
75
- },
76
- {
77
- "epoch": 0.04667293294007066,
78
- "grad_norm": 28.36432647705078,
79
- "learning_rate": 0.00035699999999999995,
80
- "loss": 100.308935546875,
81
- "original_ce_loss": 6.2686,
82
- "step": 90
83
- },
84
- {
85
- "epoch": 0.051858814377856284,
86
- "grad_norm": 17.224742889404297,
87
- "learning_rate": 0.00039949999999999995,
88
- "loss": 100.14071655273438,
89
- "original_ce_loss": 6.2581,
90
- "step": 100
91
- },
92
- {
93
- "epoch": 0.057044695815641915,
94
- "grad_norm": 52.153076171875,
95
- "learning_rate": 0.0004249971787418828,
96
- "loss": 99.686962890625,
97
- "original_ce_loss": 6.2298,
98
- "step": 110
99
- },
100
- {
101
- "epoch": 0.062230577253427545,
102
- "grad_norm": 16.022294998168945,
103
- "learning_rate": 0.00042494702512599277,
104
- "loss": 99.31576538085938,
105
- "original_ce_loss": 6.2066,
106
- "step": 120
107
- },
108
- {
109
- "epoch": 0.06741645869121317,
110
- "grad_norm": 20.817411422729492,
111
- "learning_rate": 0.00042483419391697364,
112
- "loss": 97.84152221679688,
113
- "original_ce_loss": 6.1144,
114
- "step": 130
115
- },
116
- {
117
- "epoch": 0.0726023401289988,
118
- "grad_norm": 13.969531059265137,
119
- "learning_rate": 0.00042465871840307033,
120
- "loss": 97.0799072265625,
121
- "original_ce_loss": 6.0668,
122
- "step": 140
123
- },
124
- {
125
- "epoch": 0.07778822156678443,
126
- "grad_norm": 12.968173027038574,
127
- "learning_rate": 0.00042442065035428465,
128
- "loss": 95.65609741210938,
129
- "original_ce_loss": 5.9779,
130
- "step": 150
131
- },
132
- {
133
- "epoch": 0.08297410300457006,
134
- "grad_norm": 16.16962242126465,
135
- "learning_rate": 0.00042412006000710166,
136
- "loss": 94.4610107421875,
137
- "original_ce_loss": 5.9032,
138
- "step": 160
139
- },
140
- {
141
- "epoch": 0.08815998444235569,
142
- "grad_norm": 15.63354206085205,
143
- "learning_rate": 0.0004237570360437679,
144
- "loss": 93.08035888671876,
145
- "original_ce_loss": 5.8169,
146
- "step": 170
147
- },
148
- {
149
- "epoch": 0.09334586588014132,
150
- "grad_norm": 19.45943260192871,
151
- "learning_rate": 0.00042333168556612805,
152
- "loss": 91.3424560546875,
153
- "original_ce_loss": 5.7083,
154
- "step": 180
155
- },
156
- {
157
- "epoch": 0.09853174731792694,
158
- "grad_norm": 12.314143180847168,
159
- "learning_rate": 0.0004228441340640267,
160
- "loss": 89.93196411132813,
161
- "original_ce_loss": 5.6201,
162
- "step": 190
163
- },
164
- {
165
- "epoch": 0.10371762875571257,
166
- "grad_norm": 10.550477981567383,
167
- "learning_rate": 0.00042229452537828567,
168
- "loss": 87.97509765625,
169
- "original_ce_loss": 5.4978,
170
- "step": 200
171
- },
172
- {
173
- "epoch": 0.1089035101934982,
174
- "grad_norm": 18.28213882446289,
175
- "learning_rate": 0.00042168302165826693,
176
- "loss": 86.10928344726562,
177
- "original_ce_loss": 5.3812,
178
- "step": 210
179
- },
180
- {
181
- "epoch": 0.11408939163128383,
182
- "grad_norm": 19.054182052612305,
183
- "learning_rate": 0.0004210098033140343,
184
- "loss": 84.20543212890625,
185
- "original_ce_loss": 5.2622,
186
- "step": 220
187
- },
188
- {
189
- "epoch": 0.11927527306906946,
190
- "grad_norm": 11.32401180267334,
191
- "learning_rate": 0.00042035130458263533,
192
- "loss": 82.33561401367187,
193
- "original_ce_loss": 5.1454,
194
- "step": 230
195
- },
196
- {
197
- "epoch": 0.12446115450685509,
198
- "grad_norm": 22.777610778808594,
199
- "learning_rate": 0.00041956139064506354,
200
- "loss": 82.01093139648438,
201
- "original_ce_loss": 5.1251,
202
- "step": 240
203
- },
204
- {
205
- "epoch": 0.12964703594464072,
206
- "grad_norm": 14.207376480102539,
207
- "learning_rate": 0.00041879823026024296,
208
- "loss": 86.503125,
209
- "original_ce_loss": 5.4058,
210
- "step": 250
211
- },
212
- {
213
- "epoch": 0.13483291738242634,
214
- "grad_norm": NaN,
215
- "learning_rate": 0.00041798577018333747,
216
- "loss": 89.17313232421876,
217
- "original_ce_loss": 5.5727,
218
- "step": 260
219
- },
220
- {
221
- "epoch": 0.14001879882021198,
222
- "grad_norm": 25.01464080810547,
223
- "learning_rate": 0.00041741683681028474,
224
- "loss": 89.0274169921875,
225
- "original_ce_loss": 5.5636,
226
- "step": 270
227
- },
228
- {
229
- "epoch": 0.1452046802579976,
230
- "grad_norm": 19.480703353881836,
231
- "learning_rate": 0.0004164202798601907,
232
- "loss": 88.31423950195312,
233
- "original_ce_loss": 5.519,
234
- "step": 280
235
- },
236
- {
237
- "epoch": 0.15039056169578324,
238
- "grad_norm": 12.254472732543945,
239
- "learning_rate": 0.0004155797029694326,
240
- "loss": 82.24807739257812,
241
- "original_ce_loss": 5.1399,
242
- "step": 290
243
- },
244
- {
245
- "epoch": 0.15557644313356886,
246
- "grad_norm": 25.232437133789062,
247
- "learning_rate": 0.0004144750780853972,
248
- "loss": 76.16737060546875,
249
- "original_ce_loss": 4.7599,
250
- "step": 300
251
- },
252
- {
253
- "epoch": 0.16076232457135448,
254
- "grad_norm": 19.2685546875,
255
- "learning_rate": 0.00041331086511459537,
256
- "loss": 73.167529296875,
257
- "original_ce_loss": 4.5724,
258
- "step": 310
259
- },
260
- {
261
- "epoch": 0.16594820600914012,
262
- "grad_norm": 18.996484756469727,
263
- "learning_rate": 0.0004120874075312033,
264
- "loss": 71.38079223632812,
265
- "original_ce_loss": 4.4607,
266
- "step": 320
267
- },
268
- {
269
- "epoch": 0.17113408744692574,
270
- "grad_norm": 16.110937118530273,
271
- "learning_rate": 0.00041080506628815295,
272
- "loss": 69.8762939453125,
273
- "original_ce_loss": 4.3667,
274
- "step": 330
275
- },
276
- {
277
- "epoch": 0.17631996888471138,
278
- "grad_norm": 19.29561424255371,
279
- "learning_rate": 0.00040946421971064156,
280
- "loss": 68.62410888671874,
281
- "original_ce_loss": 4.2884,
282
- "step": 340
283
- },
284
- {
285
- "epoch": 0.181505850322497,
286
- "grad_norm": 24.205785751342773,
287
- "learning_rate": 0.0004080652633845155,
288
- "loss": 67.31400756835937,
289
- "original_ce_loss": 4.2065,
290
- "step": 350
291
- },
292
- {
293
- "epoch": 0.18669173176028264,
294
- "grad_norm": 22.90777587890625,
295
- "learning_rate": 0.00040660861003956165,
296
- "loss": 66.45149536132813,
297
- "original_ce_loss": 4.1526,
298
- "step": 360
299
- },
300
- {
301
- "epoch": 0.19187761319806826,
302
- "grad_norm": 23.12751007080078,
303
- "learning_rate": 0.0004050946894277412,
304
- "loss": 65.15361938476562,
305
- "original_ce_loss": 4.0715,
306
- "step": 370
307
- },
308
- {
309
- "epoch": 0.19706349463585388,
310
- "grad_norm": 21.39095687866211,
311
- "learning_rate": 0.0004035239481964011,
312
- "loss": 64.37594604492188,
313
- "original_ce_loss": 4.0229,
314
- "step": 380
315
- },
316
- {
317
- "epoch": 0.20224937607363952,
318
- "grad_norm": 21.83388900756836,
319
- "learning_rate": 0.000401896849756501,
320
- "loss": 63.70396728515625,
321
- "original_ce_loss": 3.9809,
322
- "step": 390
323
- },
324
- {
325
- "epoch": 0.20743525751142514,
326
- "grad_norm": 20.973325729370117,
327
- "learning_rate": 0.0004002138741458948,
328
- "loss": 62.312738037109376,
329
- "original_ce_loss": 3.894,
330
- "step": 400
331
- }
332
- ],
333
- "logging_steps": 10,
334
- "max_steps": 1929,
335
- "num_input_tokens_seen": 0,
336
- "num_train_epochs": 1,
337
- "save_steps": 200,
338
- "stateful_callbacks": {
339
- "TrainerControl": {
340
- "args": {
341
- "should_epoch_stop": false,
342
- "should_evaluate": false,
343
- "should_log": false,
344
- "should_save": true,
345
- "should_training_stop": false
346
- },
347
- "attributes": {}
348
- }
349
- },
350
- "total_flos": 4249361190838272.0,
351
- "train_batch_size": 16,
352
- "trial_name": null,
353
- "trial_params": null
354
- }