ChiefTheLord commited on
Commit
839592d
verified
1 Parent(s): 93e243d

Upload folder using huggingface_hub

Browse files
flickr30k_checkpoints/checkpoint-776-2/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc347a2bab4a46b74543f35032a0f05fdfbea49d54d24cd51fa19cbaf26f114e
3
+ size 17064856
flickr30k_checkpoints/checkpoint-776-2/eval_state.json ADDED
The diff for this file is too large to render. See raw diff
 
flickr30k_checkpoints/checkpoint-776-2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0129e3b7e1d199d9be4203430f1cea0eb140727b128f0ba3484f195080bd1e2
3
+ size 8714492
flickr30k_checkpoints/checkpoint-776-2/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
flickr30k_checkpoints/checkpoint-776-2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9f6a4c8809a015370be304dede2b10a5832bd4270a1f831dbabeb3464cc168
3
+ size 1064
flickr30k_checkpoints/checkpoint-776-2/trainer_state.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 776,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.041237113402061855,
13
+ "grad_norm": 0.651349663734436,
14
+ "learning_rate": 0.0006666666666666666,
15
+ "loss": 4.8949,
16
+ "step": 16
17
+ },
18
+ {
19
+ "epoch": 0.08247422680412371,
20
+ "grad_norm": 0.1445673555135727,
21
+ "learning_rate": 0.0009999301905929286,
22
+ "loss": 4.8663,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.12371134020618557,
27
+ "grad_norm": 0.1684003323316574,
28
+ "learning_rate": 0.0009982557393033759,
29
+ "loss": 4.9032,
30
+ "step": 48
31
+ },
32
+ {
33
+ "epoch": 0.16494845360824742,
34
+ "grad_norm": 0.1190505176782608,
35
+ "learning_rate": 0.0009943559569286732,
36
+ "loss": 4.8437,
37
+ "step": 64
38
+ },
39
+ {
40
+ "epoch": 0.20618556701030927,
41
+ "grad_norm": 0.127385675907135,
42
+ "learning_rate": 0.0009882482608435923,
43
+ "loss": 4.8599,
44
+ "step": 80
45
+ },
46
+ {
47
+ "epoch": 0.24742268041237114,
48
+ "grad_norm": 0.1187027171254158,
49
+ "learning_rate": 0.0009799599295015153,
50
+ "loss": 4.9368,
51
+ "step": 96
52
+ },
53
+ {
54
+ "epoch": 0.28865979381443296,
55
+ "grad_norm": 0.14755752682685852,
56
+ "learning_rate": 0.000969527980602239,
57
+ "loss": 4.8873,
58
+ "step": 112
59
+ },
60
+ {
61
+ "epoch": 0.32989690721649484,
62
+ "grad_norm": 0.12241631001234055,
63
+ "learning_rate": 0.0009569990057619413,
64
+ "loss": 4.8978,
65
+ "step": 128
66
+ },
67
+ {
68
+ "epoch": 0.3711340206185567,
69
+ "grad_norm": 0.24350175261497498,
70
+ "learning_rate": 0.0009424289624237143,
71
+ "loss": 4.9195,
72
+ "step": 144
73
+ },
74
+ {
75
+ "epoch": 0.41237113402061853,
76
+ "grad_norm": 0.26752641797065735,
77
+ "learning_rate": 0.0009258829239380381,
78
+ "loss": 4.8751,
79
+ "step": 160
80
+ },
81
+ {
82
+ "epoch": 0.4536082474226804,
83
+ "grad_norm": 0.1479790061712265,
84
+ "learning_rate": 0.0009074347889294017,
85
+ "loss": 4.8514,
86
+ "step": 176
87
+ },
88
+ {
89
+ "epoch": 0.4948453608247423,
90
+ "grad_norm": 0.2047603875398636,
91
+ "learning_rate": 0.0008871669512471068,
92
+ "loss": 4.857,
93
+ "step": 192
94
+ },
95
+ {
96
+ "epoch": 0.5360824742268041,
97
+ "grad_norm": 0.16178925335407257,
98
+ "learning_rate": 0.0008651699319743347,
99
+ "loss": 4.8986,
100
+ "step": 208
101
+ },
102
+ {
103
+ "epoch": 0.5773195876288659,
104
+ "grad_norm": 0.14003640413284302,
105
+ "learning_rate": 0.0008415419751390154,
106
+ "loss": 4.8395,
107
+ "step": 224
108
+ },
109
+ {
110
+ "epoch": 0.6185567010309279,
111
+ "grad_norm": 0.14736343920230865,
112
+ "learning_rate": 0.0008163886089321493,
113
+ "loss": 4.8982,
114
+ "step": 240
115
+ },
116
+ {
117
+ "epoch": 0.6597938144329897,
118
+ "grad_norm": 0.1361091136932373,
119
+ "learning_rate": 0.0007898221743932888,
120
+ "loss": 4.9129,
121
+ "step": 256
122
+ },
123
+ {
124
+ "epoch": 0.7010309278350515,
125
+ "grad_norm": 0.1403878629207611,
126
+ "learning_rate": 0.0007619613236681844,
127
+ "loss": 4.8745,
128
+ "step": 272
129
+ },
130
+ {
131
+ "epoch": 0.7422680412371134,
132
+ "grad_norm": 0.1756931096315384,
133
+ "learning_rate": 0.000732930490079499,
134
+ "loss": 4.9091,
135
+ "step": 288
136
+ },
137
+ {
138
+ "epoch": 0.7835051546391752,
139
+ "grad_norm": 0.1545019894838333,
140
+ "learning_rate": 0.0007028593323773818,
141
+ "loss": 4.8666,
142
+ "step": 304
143
+ },
144
+ {
145
+ "epoch": 0.8247422680412371,
146
+ "grad_norm": 0.13788259029388428,
147
+ "learning_rate": 0.0006718821556520151,
148
+ "loss": 4.8873,
149
+ "step": 320
150
+ },
151
+ {
152
+ "epoch": 0.865979381443299,
153
+ "grad_norm": 0.1487036943435669,
154
+ "learning_rate": 0.000640137311494478,
155
+ "loss": 4.8503,
156
+ "step": 336
157
+ },
158
+ {
159
+ "epoch": 0.9072164948453608,
160
+ "grad_norm": 0.11844358593225479,
161
+ "learning_rate": 0.0006077665800849568,
162
+ "loss": 4.8911,
163
+ "step": 352
164
+ },
165
+ {
166
+ "epoch": 0.9484536082474226,
167
+ "grad_norm": 0.14698012173175812,
168
+ "learning_rate": 0.0005749145369680407,
169
+ "loss": 4.8839,
170
+ "step": 368
171
+ },
172
+ {
173
+ "epoch": 0.9896907216494846,
174
+ "grad_norm": 0.15790720283985138,
175
+ "learning_rate": 0.0005417279073432449,
176
+ "loss": 4.8374,
177
+ "step": 384
178
+ },
179
+ {
180
+ "epoch": 1.0,
181
+ "eval_bleu": 0.08333557407549637,
182
+ "eval_cap_loss": 1.7252829168567951,
183
+ "eval_con_loss": 1.9740812087181918,
184
+ "eval_loss": 3.699364125728607,
185
+ "step": 388
186
+ },
187
+ {
188
+ "epoch": 1.0,
189
+ "eval_bleu": 0.08333557407549637,
190
+ "eval_cap_loss": 1.7252829168567951,
191
+ "eval_con_loss": 1.9740812087181918,
192
+ "eval_loss": 3.699364125728607,
193
+ "eval_runtime": 146.0914,
194
+ "eval_samples_per_second": 21.226,
195
+ "eval_steps_per_second": 2.656,
196
+ "step": 388
197
+ },
198
+ {
199
+ "epoch": 1.0309278350515463,
200
+ "grad_norm": 0.2379327416419983,
201
+ "learning_rate": 0.0005083549107546504,
202
+ "loss": 4.8517,
203
+ "step": 400
204
+ },
205
+ {
206
+ "epoch": 1.0721649484536082,
207
+ "grad_norm": 0.19742196798324585,
208
+ "learning_rate": 0.00047494459910644044,
209
+ "loss": 4.8684,
210
+ "step": 416
211
+ },
212
+ {
213
+ "epoch": 1.1134020618556701,
214
+ "grad_norm": 0.16078642010688782,
215
+ "learning_rate": 0.0004416461909609119,
216
+ "loss": 4.8392,
217
+ "step": 432
218
+ },
219
+ {
220
+ "epoch": 1.1546391752577319,
221
+ "grad_norm": 0.08572334796190262,
222
+ "learning_rate": 0.00040860840509215494,
223
+ "loss": 4.8405,
224
+ "step": 448
225
+ },
226
+ {
227
+ "epoch": 1.1958762886597938,
228
+ "grad_norm": 0.1408192217350006,
229
+ "learning_rate": 0.00037597879627190335,
230
+ "loss": 4.9271,
231
+ "step": 464
232
+ },
233
+ {
234
+ "epoch": 1.2371134020618557,
235
+ "grad_norm": 0.1493539661169052,
236
+ "learning_rate": 0.00034390309625410685,
237
+ "loss": 4.8443,
238
+ "step": 480
239
+ },
240
+ {
241
+ "epoch": 1.2783505154639174,
242
+ "grad_norm": 0.1724126935005188,
243
+ "learning_rate": 0.0003125245629015395,
244
+ "loss": 4.8752,
245
+ "step": 496
246
+ },
247
+ {
248
+ "epoch": 1.3195876288659794,
249
+ "grad_norm": 0.14615976810455322,
250
+ "learning_rate": 0.00028198334036140874,
251
+ "loss": 4.8231,
252
+ "step": 512
253
+ },
254
+ {
255
+ "epoch": 1.3608247422680413,
256
+ "grad_norm": 0.13363386690616608,
257
+ "learning_rate": 0.00025241583314757326,
258
+ "loss": 4.8644,
259
+ "step": 528
260
+ },
261
+ {
262
+ "epoch": 1.402061855670103,
263
+ "grad_norm": 0.17828340828418732,
264
+ "learning_rate": 0.00022395409692487172,
265
+ "loss": 4.8331,
266
+ "step": 544
267
+ },
268
+ {
269
+ "epoch": 1.443298969072165,
270
+ "grad_norm": 0.1240629181265831,
271
+ "learning_rate": 0.0001967252487164663,
272
+ "loss": 4.8677,
273
+ "step": 560
274
+ },
275
+ {
276
+ "epoch": 1.4845360824742269,
277
+ "grad_norm": 0.16822531819343567,
278
+ "learning_rate": 0.00017085089916835921,
279
+ "loss": 4.856,
280
+ "step": 576
281
+ },
282
+ {
283
+ "epoch": 1.5257731958762886,
284
+ "grad_norm": 0.1542797088623047,
285
+ "learning_rate": 0.00014644660940672628,
286
+ "loss": 4.8461,
287
+ "step": 592
288
+ },
289
+ {
290
+ "epoch": 1.5670103092783505,
291
+ "grad_norm": 0.12938471138477325,
292
+ "learning_rate": 0.0001236213749138743,
293
+ "loss": 4.8883,
294
+ "step": 608
295
+ },
296
+ {
297
+ "epoch": 1.6082474226804124,
298
+ "grad_norm": 0.21958403289318085,
299
+ "learning_rate": 0.0001024771387279585,
300
+ "loss": 4.8829,
301
+ "step": 624
302
+ },
303
+ {
304
+ "epoch": 1.6494845360824741,
305
+ "grad_norm": 0.13377727568149567,
306
+ "learning_rate": 8.310833614062651e-05,
307
+ "loss": 4.8772,
308
+ "step": 640
309
+ },
310
+ {
311
+ "epoch": 1.690721649484536,
312
+ "grad_norm": 0.124494768679142,
313
+ "learning_rate": 6.560147292608176e-05,
314
+ "loss": 4.8758,
315
+ "step": 656
316
+ },
317
+ {
318
+ "epoch": 1.731958762886598,
319
+ "grad_norm": 0.1438254714012146,
320
+ "learning_rate": 5.003473898529609e-05,
321
+ "loss": 4.8465,
322
+ "step": 672
323
+ },
324
+ {
325
+ "epoch": 1.7731958762886597,
326
+ "grad_norm": 0.12780630588531494,
327
+ "learning_rate": 3.6477659130931316e-05,
328
+ "loss": 4.8857,
329
+ "step": 688
330
+ },
331
+ {
332
+ "epoch": 1.8144329896907216,
333
+ "grad_norm": 0.12371128052473068,
334
+ "learning_rate": 2.4990782572647973e-05,
335
+ "loss": 4.9022,
336
+ "step": 704
337
+ },
338
+ {
339
+ "epoch": 1.8556701030927836,
340
+ "grad_norm": 0.14497648179531097,
341
+ "learning_rate": 1.5625412489637337e-05,
342
+ "loss": 4.8414,
343
+ "step": 720
344
+ },
345
+ {
346
+ "epoch": 1.8969072164948453,
347
+ "grad_norm": 0.13651418685913086,
348
+ "learning_rate": 8.423376898168244e-06,
349
+ "loss": 4.8314,
350
+ "step": 736
351
+ },
352
+ {
353
+ "epoch": 1.9381443298969072,
354
+ "grad_norm": 0.1279928982257843,
355
+ "learning_rate": 3.416841837512952e-06,
356
+ "loss": 4.9007,
357
+ "step": 752
358
+ },
359
+ {
360
+ "epoch": 1.9793814432989691,
361
+ "grad_norm": 0.13989858329296112,
362
+ "learning_rate": 6.281677086071303e-07,
363
+ "loss": 4.8226,
364
+ "step": 768
365
+ },
366
+ {
367
+ "epoch": 2.0,
368
+ "eval_bleu": 0.08337060838622823,
369
+ "eval_cap_loss": 1.716913080246178,
370
+ "eval_con_loss": 1.969243642288385,
371
+ "eval_loss": 3.6861567269895494,
372
+ "step": 776
373
+ },
374
+ {
375
+ "epoch": 2.0,
376
+ "eval_bleu": 0.08337060838622823,
377
+ "eval_cap_loss": 1.716913080246178,
378
+ "eval_con_loss": 1.969243642288385,
379
+ "eval_loss": 3.6861567269895494,
380
+ "eval_runtime": 142.9819,
381
+ "eval_samples_per_second": 21.688,
382
+ "eval_steps_per_second": 2.714,
383
+ "step": 776
384
+ }
385
+ ],
386
+ "logging_steps": 16,
387
+ "max_steps": 776,
388
+ "num_input_tokens_seen": 0,
389
+ "num_train_epochs": 2,
390
+ "save_steps": 500,
391
+ "stateful_callbacks": {
392
+ "TrainerControl": {
393
+ "args": {
394
+ "should_epoch_stop": false,
395
+ "should_evaluate": false,
396
+ "should_log": false,
397
+ "should_save": true,
398
+ "should_training_stop": true
399
+ },
400
+ "attributes": {}
401
+ }
402
+ },
403
+ "total_flos": 0.0,
404
+ "train_batch_size": 32,
405
+ "trial_name": null,
406
+ "trial_params": null
407
+ }