CodeIsAbstract commited on
Commit
24144f9
·
verified ·
1 Parent(s): 6a1844d

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridTimeScaleLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "chunk_size": 128,
7
+ "dropout": 0.05,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "latent_dim": 768,
11
+ "layer_types": [
12
+ "linear",
13
+ "linear",
14
+ "linear",
15
+ "softmax",
16
+ "linear",
17
+ "linear",
18
+ "linear",
19
+ "softmax",
20
+ "linear",
21
+ "linear",
22
+ "linear",
23
+ "softmax"
24
+ ],
25
+ "model_type": "hybrid_fourier_lm",
26
+ "num_layers": 12,
27
+ "num_modes": 64,
28
+ "pad_token_id": 2,
29
+ "tie_word_embeddings": true,
30
+ "time_scale": 128.0,
31
+ "transformers_version": "5.14.1",
32
+ "use_cache": false,
33
+ "vocab_size": 32768
34
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 2,
8
+ "transformers_version": "5.14.1"
9
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7541735d5e9d8c33410671197b69601baf1f7bfaf847a94bfb0fbdb47b3eedd3
3
+ size 570000656
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c37e4eeb50675d66b7579910e8ef366ab939eacc5536c34e499d637ba820ca6a
3
+ size 1622091
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8240d8e7c40a25ab569f8841f86f8f0b9b92c8a6114e1a6a88700b838ff5647
3
+ size 14469
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1858737ad79f73944a50140efcaa32183f35b6e802a7ac6ca9bad49fc3da1308
3
+ size 14469
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdff72239e8083b5bde7b6fdef8c9ae10fdcdd13a88552a33909ea10b31ff0e7
3
+ size 14469
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5319d6e8bbe1c30f3e35b1bbbc714208ce7a57197036d9ad215d7e16940b8c1
3
+ size 14469
last-checkpoint/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87bc6b3b9f736b6964f5ea0001ca273b4ef07665bbef97f319039dc5a7915aa2
3
+ size 14469
last-checkpoint/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81261579de83835e3e3425db956a8ea691893c5be182d539336dbf765a987f6e
3
+ size 14469
last-checkpoint/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a662daf0dec0571a4d0e6f363387f2f32b89d4dbd52fc163b7e367defb6bb094
3
+ size 14469
last-checkpoint/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4191f1c72d5163fe96cd3a5706a588a5fa301ffa53904e4415c5e46d1f2ac1b1
3
+ size 14469
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899ab97511d0e21be97a2d87a9698c3d8bea9c4b76df29fbfa02ea0530b878e3
3
+ size 1465
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,814 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.09090909090909091,
6
+ "eval_steps": 100,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": false,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0009090909090909091,
14
+ "grad_norm": 73365171732480.0,
15
+ "learning_rate": 9.999983482695944e-07,
16
+ "loss": 26.594210815429687,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0018181818181818182,
21
+ "grad_norm": 51667001147392.0,
22
+ "learning_rate": 9.999926385982519e-07,
23
+ "loss": 26.803173828125,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0027272727272727275,
28
+ "grad_norm": 144119808655360.0,
29
+ "learning_rate": 9.999828506408003e-07,
30
+ "loss": 26.6311767578125,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0036363636363636364,
35
+ "grad_norm": 288443594702848.0,
36
+ "learning_rate": 9.999689844770766e-07,
37
+ "loss": 26.79853210449219,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.004545454545454545,
42
+ "grad_norm": 178193478713344.0,
43
+ "learning_rate": 9.999510402201835e-07,
44
+ "loss": 26.80711669921875,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.005454545454545455,
49
+ "grad_norm": 104469937258496.0,
50
+ "learning_rate": 9.99929018016486e-07,
51
+ "loss": 26.85858154296875,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.006363636363636364,
56
+ "grad_norm": 212630258057216.0,
57
+ "learning_rate": 9.999029180456129e-07,
58
+ "loss": 26.61113586425781,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.007272727272727273,
63
+ "grad_norm": 82712153030656.0,
64
+ "learning_rate": 9.998727405204534e-07,
65
+ "loss": 26.967510986328126,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.008181818181818182,
70
+ "grad_norm": 113997894385664.0,
71
+ "learning_rate": 9.998384856871564e-07,
72
+ "loss": 26.79218444824219,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.00909090909090909,
77
+ "grad_norm": 32432866721792.0,
78
+ "learning_rate": 9.998001538251282e-07,
79
+ "loss": 26.760104370117187,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.00909090909090909,
84
+ "eval_loss": 26.33808708190918,
85
+ "eval_runtime": 15.3766,
86
+ "eval_samples_per_second": 2.341,
87
+ "eval_steps_per_second": 0.13,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.01,
92
+ "grad_norm": 86142355505152.0,
93
+ "learning_rate": 9.997577452470298e-07,
94
+ "loss": 26.885391235351562,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 0.01090909090909091,
99
+ "grad_norm": 42407483670528.0,
100
+ "learning_rate": 9.99711260298775e-07,
101
+ "loss": 26.781631469726562,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 0.011818181818181818,
106
+ "grad_norm": 87900112814080.0,
107
+ "learning_rate": 9.99660699359527e-07,
108
+ "loss": 26.478997802734376,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 0.012727272727272728,
113
+ "grad_norm": 109777954799616.0,
114
+ "learning_rate": 9.996060628416963e-07,
115
+ "loss": 26.806842041015624,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 0.013636363636363636,
120
+ "grad_norm": 49805468368896.0,
121
+ "learning_rate": 9.995473511909357e-07,
122
+ "loss": 27.047796630859374,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 0.014545454545454545,
127
+ "grad_norm": 216601408307200.0,
128
+ "learning_rate": 9.994845648861382e-07,
129
+ "loss": 26.913211059570312,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 0.015454545454545455,
134
+ "grad_norm": 207064097882112.0,
135
+ "learning_rate": 9.994177044394322e-07,
136
+ "loss": 26.413333129882812,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 0.016363636363636365,
141
+ "grad_norm": 82221604012032.0,
142
+ "learning_rate": 9.993467703961784e-07,
143
+ "loss": 26.159014892578124,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 0.017272727272727273,
148
+ "grad_norm": 54769984995328.0,
149
+ "learning_rate": 9.992717633349635e-07,
150
+ "loss": 26.39976806640625,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 0.01818181818181818,
155
+ "grad_norm": 91138409103360.0,
156
+ "learning_rate": 9.99192683867597e-07,
157
+ "loss": 26.521871948242186,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 0.01818181818181818,
162
+ "eval_loss": 26.33262825012207,
163
+ "eval_runtime": 2.2052,
164
+ "eval_samples_per_second": 16.325,
165
+ "eval_steps_per_second": 0.907,
166
+ "step": 200
167
+ },
168
+ {
169
+ "epoch": 0.019090909090909092,
170
+ "grad_norm": 226673442160640.0,
171
+ "learning_rate": 9.99109532639106e-07,
172
+ "loss": 26.42662353515625,
173
+ "step": 210
174
+ },
175
+ {
176
+ "epoch": 0.02,
177
+ "grad_norm": 178545447927808.0,
178
+ "learning_rate": 9.99022310327729e-07,
179
+ "loss": 27.001919555664063,
180
+ "step": 220
181
+ },
182
+ {
183
+ "epoch": 0.02090909090909091,
184
+ "grad_norm": 37310276042752.0,
185
+ "learning_rate": 9.98931017644912e-07,
186
+ "loss": 26.3681884765625,
187
+ "step": 230
188
+ },
189
+ {
190
+ "epoch": 0.02181818181818182,
191
+ "grad_norm": 169656073584640.0,
192
+ "learning_rate": 9.988356553353017e-07,
193
+ "loss": 26.52265625,
194
+ "step": 240
195
+ },
196
+ {
197
+ "epoch": 0.022727272727272728,
198
+ "grad_norm": 119822314635264.0,
199
+ "learning_rate": 9.987362241767383e-07,
200
+ "loss": 26.739306640625,
201
+ "step": 250
202
+ },
203
+ {
204
+ "epoch": 0.023636363636363636,
205
+ "grad_norm": 135106542960640.0,
206
+ "learning_rate": 9.986327249802515e-07,
207
+ "loss": 26.929629516601562,
208
+ "step": 260
209
+ },
210
+ {
211
+ "epoch": 0.024545454545454544,
212
+ "grad_norm": 141070599979008.0,
213
+ "learning_rate": 9.985251585900525e-07,
214
+ "loss": 26.869723510742187,
215
+ "step": 270
216
+ },
217
+ {
218
+ "epoch": 0.025454545454545455,
219
+ "grad_norm": 168756110163968.0,
220
+ "learning_rate": 9.984135258835272e-07,
221
+ "loss": 26.432122802734376,
222
+ "step": 280
223
+ },
224
+ {
225
+ "epoch": 0.026363636363636363,
226
+ "grad_norm": 51225978470400.0,
227
+ "learning_rate": 9.98297827771229e-07,
228
+ "loss": 26.779403686523438,
229
+ "step": 290
230
+ },
231
+ {
232
+ "epoch": 0.02727272727272727,
233
+ "grad_norm": 203997088579584.0,
234
+ "learning_rate": 9.981780651968722e-07,
235
+ "loss": 26.73297119140625,
236
+ "step": 300
237
+ },
238
+ {
239
+ "epoch": 0.02727272727272727,
240
+ "eval_loss": 26.32358741760254,
241
+ "eval_runtime": 2.1675,
242
+ "eval_samples_per_second": 16.609,
243
+ "eval_steps_per_second": 0.923,
244
+ "step": 300
245
+ },
246
+ {
247
+ "epoch": 0.028181818181818183,
248
+ "grad_norm": 211993462046720.0,
249
+ "learning_rate": 9.980542391373232e-07,
250
+ "loss": 26.3818603515625,
251
+ "step": 310
252
+ },
253
+ {
254
+ "epoch": 0.02909090909090909,
255
+ "grad_norm": 67605180186624.0,
256
+ "learning_rate": 9.979263506025929e-07,
257
+ "loss": 26.753466796875,
258
+ "step": 320
259
+ },
260
+ {
261
+ "epoch": 0.03,
262
+ "grad_norm": 83690625433600.0,
263
+ "learning_rate": 9.977944006358285e-07,
264
+ "loss": 26.70177001953125,
265
+ "step": 330
266
+ },
267
+ {
268
+ "epoch": 0.03090909090909091,
269
+ "grad_norm": 234856529264640.0,
270
+ "learning_rate": 9.976583903133059e-07,
271
+ "loss": 26.383956909179688,
272
+ "step": 340
273
+ },
274
+ {
275
+ "epoch": 0.031818181818181815,
276
+ "grad_norm": 74805898379264.0,
277
+ "learning_rate": 9.975183207444189e-07,
278
+ "loss": 26.859848022460938,
279
+ "step": 350
280
+ },
281
+ {
282
+ "epoch": 0.03272727272727273,
283
+ "grad_norm": 216309870624768.0,
284
+ "learning_rate": 9.97374193071672e-07,
285
+ "loss": 26.3761474609375,
286
+ "step": 360
287
+ },
288
+ {
289
+ "epoch": 0.03363636363636364,
290
+ "grad_norm": 132342337241088.0,
291
+ "learning_rate": 9.972260084706704e-07,
292
+ "loss": 26.71666564941406,
293
+ "step": 370
294
+ },
295
+ {
296
+ "epoch": 0.034545454545454546,
297
+ "grad_norm": 131501941325824.0,
298
+ "learning_rate": 9.970737681501104e-07,
299
+ "loss": 26.52633056640625,
300
+ "step": 380
301
+ },
302
+ {
303
+ "epoch": 0.035454545454545454,
304
+ "grad_norm": 262768951296000.0,
305
+ "learning_rate": 9.969174733517693e-07,
306
+ "loss": 26.515576171875,
307
+ "step": 390
308
+ },
309
+ {
310
+ "epoch": 0.03636363636363636,
311
+ "grad_norm": 47626049290240.0,
312
+ "learning_rate": 9.967571253504956e-07,
313
+ "loss": 26.491845703125,
314
+ "step": 400
315
+ },
316
+ {
317
+ "epoch": 0.03636363636363636,
318
+ "eval_loss": 26.31351089477539,
319
+ "eval_runtime": 2.1949,
320
+ "eval_samples_per_second": 16.402,
321
+ "eval_steps_per_second": 0.911,
322
+ "step": 400
323
+ },
324
+ {
325
+ "epoch": 0.03727272727272727,
326
+ "grad_norm": 82015571410944.0,
327
+ "learning_rate": 9.965927254541986e-07,
328
+ "loss": 26.79627380371094,
329
+ "step": 410
330
+ },
331
+ {
332
+ "epoch": 0.038181818181818185,
333
+ "grad_norm": 48217920110592.0,
334
+ "learning_rate": 9.964242750038379e-07,
335
+ "loss": 26.478103637695312,
336
+ "step": 420
337
+ },
338
+ {
339
+ "epoch": 0.03909090909090909,
340
+ "grad_norm": 240027619557376.0,
341
+ "learning_rate": 9.96251775373412e-07,
342
+ "loss": 27.031826782226563,
343
+ "step": 430
344
+ },
345
+ {
346
+ "epoch": 0.04,
347
+ "grad_norm": 85748241924096.0,
348
+ "learning_rate": 9.960752279699469e-07,
349
+ "loss": 26.60472412109375,
350
+ "step": 440
351
+ },
352
+ {
353
+ "epoch": 0.04090909090909091,
354
+ "grad_norm": 149027999973376.0,
355
+ "learning_rate": 9.958946342334858e-07,
356
+ "loss": 26.631716918945312,
357
+ "step": 450
358
+ },
359
+ {
360
+ "epoch": 0.04181818181818182,
361
+ "grad_norm": 145542986334208.0,
362
+ "learning_rate": 9.957099956370761e-07,
363
+ "loss": 26.688156127929688,
364
+ "step": 460
365
+ },
366
+ {
367
+ "epoch": 0.042727272727272725,
368
+ "grad_norm": 119765381152768.0,
369
+ "learning_rate": 9.95521313686758e-07,
370
+ "loss": 26.73491516113281,
371
+ "step": 470
372
+ },
373
+ {
374
+ "epoch": 0.04363636363636364,
375
+ "grad_norm": 42115639803904.0,
376
+ "learning_rate": 9.953285899215524e-07,
377
+ "loss": 26.4789306640625,
378
+ "step": 480
379
+ },
380
+ {
381
+ "epoch": 0.04454545454545455,
382
+ "grad_norm": 174389194653696.0,
383
+ "learning_rate": 9.951318259134473e-07,
384
+ "loss": 26.395907592773437,
385
+ "step": 490
386
+ },
387
+ {
388
+ "epoch": 0.045454545454545456,
389
+ "grad_norm": 126755364929536.0,
390
+ "learning_rate": 9.949310232673867e-07,
391
+ "loss": 26.444671630859375,
392
+ "step": 500
393
+ },
394
+ {
395
+ "epoch": 0.045454545454545456,
396
+ "eval_loss": 26.300777435302734,
397
+ "eval_runtime": 2.1863,
398
+ "eval_samples_per_second": 16.466,
399
+ "eval_steps_per_second": 0.915,
400
+ "step": 500
401
+ },
402
+ {
403
+ "epoch": 0.046363636363636364,
404
+ "grad_norm": 89457617272832.0,
405
+ "learning_rate": 9.947261836212555e-07,
406
+ "loss": 26.633724975585938,
407
+ "step": 510
408
+ },
409
+ {
410
+ "epoch": 0.04727272727272727,
411
+ "grad_norm": 357854594727936.0,
412
+ "learning_rate": 9.94517308645868e-07,
413
+ "loss": 26.50592956542969,
414
+ "step": 520
415
+ },
416
+ {
417
+ "epoch": 0.04818181818181818,
418
+ "grad_norm": 145786406961152.0,
419
+ "learning_rate": 9.94304400044953e-07,
420
+ "loss": 26.608950805664062,
421
+ "step": 530
422
+ },
423
+ {
424
+ "epoch": 0.04909090909090909,
425
+ "grad_norm": 63449291816960.0,
426
+ "learning_rate": 9.940874595551404e-07,
427
+ "loss": 26.23621826171875,
428
+ "step": 540
429
+ },
430
+ {
431
+ "epoch": 0.05,
432
+ "grad_norm": 35186595069952.0,
433
+ "learning_rate": 9.938664889459468e-07,
434
+ "loss": 26.354998779296874,
435
+ "step": 550
436
+ },
437
+ {
438
+ "epoch": 0.05090909090909091,
439
+ "grad_norm": 171478263791616.0,
440
+ "learning_rate": 9.936414900197618e-07,
441
+ "loss": 26.57105712890625,
442
+ "step": 560
443
+ },
444
+ {
445
+ "epoch": 0.05181818181818182,
446
+ "grad_norm": 424193384513536.0,
447
+ "learning_rate": 9.934124646118324e-07,
448
+ "loss": 26.597015380859375,
449
+ "step": 570
450
+ },
451
+ {
452
+ "epoch": 0.05272727272727273,
453
+ "grad_norm": 69734649298944.0,
454
+ "learning_rate": 9.931794145902485e-07,
455
+ "loss": 26.793948364257812,
456
+ "step": 580
457
+ },
458
+ {
459
+ "epoch": 0.053636363636363635,
460
+ "grad_norm": 71048951234560.0,
461
+ "learning_rate": 9.92942341855927e-07,
462
+ "loss": 26.852621459960936,
463
+ "step": 590
464
+ },
465
+ {
466
+ "epoch": 0.05454545454545454,
467
+ "grad_norm": 265954290302976.0,
468
+ "learning_rate": 9.927012483425976e-07,
469
+ "loss": 26.4174072265625,
470
+ "step": 600
471
+ },
472
+ {
473
+ "epoch": 0.05454545454545454,
474
+ "eval_loss": 26.291404724121094,
475
+ "eval_runtime": 2.1954,
476
+ "eval_samples_per_second": 16.398,
477
+ "eval_steps_per_second": 0.911,
478
+ "step": 600
479
+ },
480
+ {
481
+ "epoch": 0.05545454545454546,
482
+ "grad_norm": 172292495638528.0,
483
+ "learning_rate": 9.924561360167858e-07,
484
+ "loss": 27.017904663085936,
485
+ "step": 610
486
+ },
487
+ {
488
+ "epoch": 0.056363636363636366,
489
+ "grad_norm": 146552655970304.0,
490
+ "learning_rate": 9.922070068777972e-07,
491
+ "loss": 26.3694091796875,
492
+ "step": 620
493
+ },
494
+ {
495
+ "epoch": 0.057272727272727274,
496
+ "grad_norm": 238492990832640.0,
497
+ "learning_rate": 9.91953862957702e-07,
498
+ "loss": 26.68968505859375,
499
+ "step": 630
500
+ },
501
+ {
502
+ "epoch": 0.05818181818181818,
503
+ "grad_norm": 277039399567360.0,
504
+ "learning_rate": 9.91696706321317e-07,
505
+ "loss": 26.37095947265625,
506
+ "step": 640
507
+ },
508
+ {
509
+ "epoch": 0.05909090909090909,
510
+ "grad_norm": 185654575104000.0,
511
+ "learning_rate": 9.914355390661895e-07,
512
+ "loss": 26.30018005371094,
513
+ "step": 650
514
+ },
515
+ {
516
+ "epoch": 0.06,
517
+ "grad_norm": 310576869801984.0,
518
+ "learning_rate": 9.91170363322581e-07,
519
+ "loss": 26.79898681640625,
520
+ "step": 660
521
+ },
522
+ {
523
+ "epoch": 0.060909090909090906,
524
+ "grad_norm": 67033240698880.0,
525
+ "learning_rate": 9.90901181253448e-07,
526
+ "loss": 26.819778442382812,
527
+ "step": 670
528
+ },
529
+ {
530
+ "epoch": 0.06181818181818182,
531
+ "grad_norm": 56443759755264.0,
532
+ "learning_rate": 9.906279950544258e-07,
533
+ "loss": 26.365707397460938,
534
+ "step": 680
535
+ },
536
+ {
537
+ "epoch": 0.06272727272727273,
538
+ "grad_norm": 60853546123264.0,
539
+ "learning_rate": 9.903508069538107e-07,
540
+ "loss": 26.7015869140625,
541
+ "step": 690
542
+ },
543
+ {
544
+ "epoch": 0.06363636363636363,
545
+ "grad_norm": 54322498895872.0,
546
+ "learning_rate": 9.900696192125401e-07,
547
+ "loss": 26.60201416015625,
548
+ "step": 700
549
+ },
550
+ {
551
+ "epoch": 0.06363636363636363,
552
+ "eval_loss": 26.27959442138672,
553
+ "eval_runtime": 2.1871,
554
+ "eval_samples_per_second": 16.46,
555
+ "eval_steps_per_second": 0.914,
556
+ "step": 700
557
+ },
558
+ {
559
+ "epoch": 0.06454545454545454,
560
+ "grad_norm": 86583118135296.0,
561
+ "learning_rate": 9.897844341241764e-07,
562
+ "loss": 26.674392700195312,
563
+ "step": 710
564
+ },
565
+ {
566
+ "epoch": 0.06545454545454546,
567
+ "grad_norm": 117483361009664.0,
568
+ "learning_rate": 9.894952540148861e-07,
569
+ "loss": 26.57917175292969,
570
+ "step": 720
571
+ },
572
+ {
573
+ "epoch": 0.06636363636363636,
574
+ "grad_norm": 156891263008768.0,
575
+ "learning_rate": 9.892020812434227e-07,
576
+ "loss": 26.749630737304688,
577
+ "step": 730
578
+ },
579
+ {
580
+ "epoch": 0.06727272727272728,
581
+ "grad_norm": 161708622479360.0,
582
+ "learning_rate": 9.889049182011064e-07,
583
+ "loss": 26.950381469726562,
584
+ "step": 740
585
+ },
586
+ {
587
+ "epoch": 0.06818181818181818,
588
+ "grad_norm": 132854914744320.0,
589
+ "learning_rate": 9.886037673118046e-07,
590
+ "loss": 26.209268188476564,
591
+ "step": 750
592
+ },
593
+ {
594
+ "epoch": 0.06909090909090909,
595
+ "grad_norm": 230637545979904.0,
596
+ "learning_rate": 9.882986310319123e-07,
597
+ "loss": 26.622137451171874,
598
+ "step": 760
599
+ },
600
+ {
601
+ "epoch": 0.07,
602
+ "grad_norm": 44996547837952.0,
603
+ "learning_rate": 9.879895118503322e-07,
604
+ "loss": 26.396820068359375,
605
+ "step": 770
606
+ },
607
+ {
608
+ "epoch": 0.07090909090909091,
609
+ "grad_norm": 105779734511616.0,
610
+ "learning_rate": 9.876764122884546e-07,
611
+ "loss": 26.439730834960937,
612
+ "step": 780
613
+ },
614
+ {
615
+ "epoch": 0.07181818181818182,
616
+ "grad_norm": 142746727743488.0,
617
+ "learning_rate": 9.873593349001363e-07,
618
+ "loss": 26.420101928710938,
619
+ "step": 790
620
+ },
621
+ {
622
+ "epoch": 0.07272727272727272,
623
+ "grad_norm": 217378294071296.0,
624
+ "learning_rate": 9.870382822716797e-07,
625
+ "loss": 26.5166015625,
626
+ "step": 800
627
+ },
628
+ {
629
+ "epoch": 0.07272727272727272,
630
+ "eval_loss": 26.271564483642578,
631
+ "eval_runtime": 2.1575,
632
+ "eval_samples_per_second": 16.686,
633
+ "eval_steps_per_second": 0.927,
634
+ "step": 800
635
+ },
636
+ {
637
+ "epoch": 0.07363636363636364,
638
+ "grad_norm": 108654393032704.0,
639
+ "learning_rate": 9.867132570218127e-07,
640
+ "loss": 26.610940551757814,
641
+ "step": 810
642
+ },
643
+ {
644
+ "epoch": 0.07454545454545454,
645
+ "grad_norm": 160897595080704.0,
646
+ "learning_rate": 9.863842618016658e-07,
647
+ "loss": 26.722555541992186,
648
+ "step": 820
649
+ },
650
+ {
651
+ "epoch": 0.07545454545454545,
652
+ "grad_norm": 207793755783168.0,
653
+ "learning_rate": 9.86051299294752e-07,
654
+ "loss": 26.355166625976562,
655
+ "step": 830
656
+ },
657
+ {
658
+ "epoch": 0.07636363636363637,
659
+ "grad_norm": 73539973545984.0,
660
+ "learning_rate": 9.857143722169442e-07,
661
+ "loss": 26.54212341308594,
662
+ "step": 840
663
+ },
664
+ {
665
+ "epoch": 0.07727272727272727,
666
+ "grad_norm": 117208164335616.0,
667
+ "learning_rate": 9.853734833164525e-07,
668
+ "loss": 26.74329528808594,
669
+ "step": 850
670
+ },
671
+ {
672
+ "epoch": 0.07818181818181819,
673
+ "grad_norm": 65454479507456.0,
674
+ "learning_rate": 9.850286353738032e-07,
675
+ "loss": 26.864334106445312,
676
+ "step": 860
677
+ },
678
+ {
679
+ "epoch": 0.07909090909090909,
680
+ "grad_norm": 302659668017152.0,
681
+ "learning_rate": 9.846798312018146e-07,
682
+ "loss": 26.766177368164062,
683
+ "step": 870
684
+ },
685
+ {
686
+ "epoch": 0.08,
687
+ "grad_norm": 64990744674304.0,
688
+ "learning_rate": 9.843270736455752e-07,
689
+ "loss": 26.492599487304688,
690
+ "step": 880
691
+ },
692
+ {
693
+ "epoch": 0.0809090909090909,
694
+ "grad_norm": 143555456663552.0,
695
+ "learning_rate": 9.839703655824194e-07,
696
+ "loss": 26.37163391113281,
697
+ "step": 890
698
+ },
699
+ {
700
+ "epoch": 0.08181818181818182,
701
+ "grad_norm": 120043572559872.0,
702
+ "learning_rate": 9.836097099219057e-07,
703
+ "loss": 26.424105834960937,
704
+ "step": 900
705
+ },
706
+ {
707
+ "epoch": 0.08181818181818182,
708
+ "eval_loss": 26.26393699645996,
709
+ "eval_runtime": 2.1589,
710
+ "eval_samples_per_second": 16.675,
711
+ "eval_steps_per_second": 0.926,
712
+ "step": 900
713
+ },
714
+ {
715
+ "epoch": 0.08272727272727273,
716
+ "grad_norm": 129510234128384.0,
717
+ "learning_rate": 9.832451096057912e-07,
718
+ "loss": 26.673666381835936,
719
+ "step": 910
720
+ },
721
+ {
722
+ "epoch": 0.08363636363636363,
723
+ "grad_norm": 89579042373632.0,
724
+ "learning_rate": 9.82876567608008e-07,
725
+ "loss": 26.665896606445312,
726
+ "step": 920
727
+ },
728
+ {
729
+ "epoch": 0.08454545454545455,
730
+ "grad_norm": 78381492207616.0,
731
+ "learning_rate": 9.825040869346404e-07,
732
+ "loss": 26.850192260742187,
733
+ "step": 930
734
+ },
735
+ {
736
+ "epoch": 0.08545454545454545,
737
+ "grad_norm": 88285191864320.0,
738
+ "learning_rate": 9.821276706238985e-07,
739
+ "loss": 26.515313720703126,
740
+ "step": 940
741
+ },
742
+ {
743
+ "epoch": 0.08636363636363636,
744
+ "grad_norm": 152401596121088.0,
745
+ "learning_rate": 9.81747321746094e-07,
746
+ "loss": 26.679132080078126,
747
+ "step": 950
748
+ },
749
+ {
750
+ "epoch": 0.08727272727272728,
751
+ "grad_norm": 154951682621440.0,
752
+ "learning_rate": 9.81363043403616e-07,
753
+ "loss": 26.68135986328125,
754
+ "step": 960
755
+ },
756
+ {
757
+ "epoch": 0.08818181818181818,
758
+ "grad_norm": 241076212334592.0,
759
+ "learning_rate": 9.809748387309047e-07,
760
+ "loss": 26.675436401367186,
761
+ "step": 970
762
+ },
763
+ {
764
+ "epoch": 0.0890909090909091,
765
+ "grad_norm": 109151057346560.0,
766
+ "learning_rate": 9.805827108944259e-07,
767
+ "loss": 26.623699951171876,
768
+ "step": 980
769
+ },
770
+ {
771
+ "epoch": 0.09,
772
+ "grad_norm": 133532965928960.0,
773
+ "learning_rate": 9.801866630926459e-07,
774
+ "loss": 26.52110595703125,
775
+ "step": 990
776
+ },
777
+ {
778
+ "epoch": 0.09090909090909091,
779
+ "grad_norm": 96509039214592.0,
780
+ "learning_rate": 9.797866985560049e-07,
781
+ "loss": 26.782925415039063,
782
+ "step": 1000
783
+ },
784
+ {
785
+ "epoch": 0.09090909090909091,
786
+ "eval_loss": 26.261463165283203,
787
+ "eval_runtime": 2.183,
788
+ "eval_samples_per_second": 16.491,
789
+ "eval_steps_per_second": 0.916,
790
+ "step": 1000
791
+ }
792
+ ],
793
+ "logging_steps": 10,
794
+ "max_steps": 11000,
795
+ "num_input_tokens_seen": 0,
796
+ "num_train_epochs": 9223372036854775807,
797
+ "save_steps": 1000,
798
+ "stateful_callbacks": {
799
+ "TrainerControl": {
800
+ "args": {
801
+ "should_epoch_stop": false,
802
+ "should_evaluate": false,
803
+ "should_log": false,
804
+ "should_save": true,
805
+ "should_training_stop": false
806
+ },
807
+ "attributes": {}
808
+ }
809
+ },
810
+ "total_flos": 9059847634944000.0,
811
+ "train_batch_size": 4,
812
+ "trial_name": null,
813
+ "trial_params": null
814
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6cc33346fc3b40186fca46deb8927a367be98673dea9df43f74b35d3039033e
3
+ size 5265