Hugging Face's logo

TakalaWang
/
Discussion-Phi-4-multimodal-instruct-audio-dimp-tag-beta2

Text Generation
Transformers
TensorBoard
Safetensors
phi4mm
Generated from Trainer
conversational
custom_code
Model card Files
xet
Metrics Community
TakalaWang commited on
Commit
d58b350
·
verified ·
1 Parent(s): 0d7283f

End of training

Browse files
Files changed (7) hide show
  1. README.md +27 -27
  2. eval_after.json +46 -46
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. runs/May20_02-22-01_70e5a6d483fc/events.out.tfevents.1747707722.70e5a6d483fc.70154.0 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/Phi-4-multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 48.3394
20
 
21
  ## Model description
22
 
@@ -50,32 +50,32 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 14.0829 | 0.1117 | 10 | 46.8853 |
54
- | 0.7741 | 0.2235 | 20 | 47.3081 |
55
- | 0.876 | 0.3352 | 30 | 48.3186 |
56
- | 1.0887 | 0.4469 | 40 | 47.7892 |
57
- | 0.6082 | 0.5587 | 50 | 46.4885 |
58
- | 0.8817 | 0.6704 | 60 | 47.2439 |
59
- | 0.8147 | 0.7821 | 70 | 46.8149 |
60
- | 0.6175 | 0.8939 | 80 | 47.4410 |
61
- | 0.2105 | 1.0 | 90 | 47.7826 |
62
- | 0.5276 | 1.1117 | 100 | 48.2947 |
63
- | 0.7959 | 1.2235 | 110 | 48.0451 |
64
- | 0.8612 | 1.3352 | 120 | 47.9742 |
65
- | 0.3952 | 1.4469 | 130 | 47.9626 |
66
- | 1.1267 | 1.5587 | 140 | 47.9388 |
67
- | 0.2708 | 1.6704 | 150 | 47.9476 |
68
- | 0.1558 | 1.7821 | 160 | 47.3955 |
69
- | 0.137 | 1.8939 | 170 | 47.7359 |
70
- | 0.0656 | 2.0 | 180 | 47.8262 |
71
- | 0.1751 | 2.1117 | 190 | 47.9413 |
72
- | 0.0949 | 2.2235 | 200 | 48.1090 |
73
- | 0.6903 | 2.3352 | 210 | 48.4911 |
74
- | 0.1881 | 2.4469 | 220 | 48.4990 |
75
- | 0.0442 | 2.5587 | 230 | 48.6476 |
76
- | 0.0067 | 2.6704 | 240 | 48.5267 |
77
- | 0.1231 | 2.7821 | 250 | 48.2628 |
78
- | 0.1328 | 2.8939 | 260 | 48.3394 |
79
 
80
 
81
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/Phi-4-multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 64.7609
20
 
21
  ## Model description
22
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 18.6928 | 0.1117 | 10 | 61.6581 |
54
+ | 1.052 | 0.2235 | 20 | 63.4050 |
55
+ | 1.1376 | 0.3352 | 30 | 64.3377 |
56
+ | 1.5265 | 0.4469 | 40 | 63.9444 |
57
+ | 0.6799 | 0.5587 | 50 | 63.1666 |
58
+ | 0.473 | 0.6704 | 60 | 62.6391 |
59
+ | 1.2576 | 0.7821 | 70 | 63.7490 |
60
+ | 0.8403 | 0.8939 | 80 | 64.2257 |
61
+ | 0.4058 | 1.0 | 90 | 64.4357 |
62
+ | 0.5312 | 1.1117 | 100 | 63.8560 |
63
+ | 1.2907 | 1.2235 | 110 | 64.1551 |
64
+ | 0.8236 | 1.3352 | 120 | 64.0494 |
65
+ | 0.1754 | 1.4469 | 130 | 63.3870 |
66
+ | 1.1399 | 1.5587 | 140 | 64.8109 |
67
+ | 0.3292 | 1.6704 | 150 | 64.4111 |
68
+ | 0.2727 | 1.7821 | 160 | 64.3778 |
69
+ | 0.3446 | 1.8939 | 170 | 64.5114 |
70
+ | 0.1415 | 2.0 | 180 | 63.8008 |
71
+ | 0.1643 | 2.1117 | 190 | 64.4455 |
72
+ | 0.1808 | 2.2235 | 200 | 64.3928 |
73
+ | 0.9262 | 2.3352 | 210 | 64.9215 |
74
+ | 0.5461 | 2.4469 | 220 | 63.8797 |
75
+ | 0.0242 | 2.5587 | 230 | 64.8023 |
76
+ | 0.0245 | 2.6704 | 240 | 64.4380 |
77
+ | 0.1154 | 2.7821 | 250 | 64.2387 |
78
+ | 0.2359 | 2.8939 | 260 | 64.7609 |
79
 
80
 
81
  ### Framework versions
eval_after.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "predictions_and_labels": [
3
  {
4
- "prediction": "4",
5
  "label": "3"
6
  },
7
  {
@@ -13,7 +13,7 @@
13
  "label": "4"
14
  },
15
  {
16
- "prediction": "4",
17
  "label": "3"
18
  },
19
  {
@@ -21,7 +21,7 @@
21
  "label": "4"
22
  },
23
  {
24
- "prediction": "2",
25
  "label": "3"
26
  },
27
  {
@@ -29,11 +29,11 @@
29
  "label": "3"
30
  },
31
  {
32
- "prediction": "3",
33
  "label": "4"
34
  },
35
  {
36
- "prediction": "4",
37
  "label": "3"
38
  },
39
  {
@@ -41,7 +41,7 @@
41
  "label": "3"
42
  },
43
  {
44
- "prediction": "4",
45
  "label": "3"
46
  },
47
  {
@@ -49,7 +49,7 @@
49
  "label": "3"
50
  },
51
  {
52
- "prediction": "4",
53
  "label": "3"
54
  },
55
  {
@@ -57,7 +57,7 @@
57
  "label": "4"
58
  },
59
  {
60
- "prediction": "4",
61
  "label": "3"
62
  },
63
  {
@@ -65,7 +65,7 @@
65
  "label": "4"
66
  },
67
  {
68
- "prediction": "2",
69
  "label": "3"
70
  },
71
  {
@@ -73,7 +73,7 @@
73
  "label": "4"
74
  },
75
  {
76
- "prediction": "4",
77
  "label": "3"
78
  },
79
  {
@@ -81,7 +81,7 @@
81
  "label": "4"
82
  },
83
  {
84
- "prediction": "4",
85
  "label": "3"
86
  },
87
  {
@@ -89,19 +89,19 @@
89
  "label": "4"
90
  },
91
  {
92
- "prediction": "2",
93
  "label": "4"
94
  },
95
  {
96
- "prediction": "2",
97
  "label": "3"
98
  },
99
  {
100
- "prediction": "2",
101
  "label": "3"
102
  },
103
  {
104
- "prediction": "4",
105
  "label": "4"
106
  },
107
  {
@@ -113,7 +113,7 @@
113
  "label": "3"
114
  },
115
  {
116
- "prediction": "2",
117
  "label": "3"
118
  },
119
  {
@@ -129,7 +129,7 @@
129
  "label": "3"
130
  },
131
  {
132
- "prediction": "2",
133
  "label": "3"
134
  },
135
  {
@@ -149,19 +149,19 @@
149
  "label": "3"
150
  },
151
  {
152
- "prediction": "4",
153
  "label": "3"
154
  },
155
  {
156
- "prediction": "2",
157
  "label": "3"
158
  },
159
  {
160
- "prediction": "2",
161
  "label": "3"
162
  },
163
  {
164
- "prediction": "4",
165
  "label": "3"
166
  },
167
  {
@@ -177,11 +177,11 @@
177
  "label": "4"
178
  },
179
  {
180
- "prediction": "3",
181
  "label": "4"
182
  },
183
  {
184
- "prediction": "4",
185
  "label": "4"
186
  },
187
  {
@@ -197,11 +197,11 @@
197
  "label": "3"
198
  },
199
  {
200
- "prediction": "2",
201
  "label": "3"
202
  },
203
  {
204
- "prediction": "2",
205
  "label": "3"
206
  },
207
  {
@@ -209,11 +209,11 @@
209
  "label": "3"
210
  },
211
  {
212
- "prediction": "2",
213
  "label": "3"
214
  },
215
  {
216
- "prediction": "4",
217
  "label": "4"
218
  },
219
  {
@@ -221,7 +221,7 @@
221
  "label": "3"
222
  },
223
  {
224
- "prediction": "2",
225
  "label": "4"
226
  },
227
  {
@@ -237,7 +237,7 @@
237
  "label": "4"
238
  },
239
  {
240
- "prediction": "4",
241
  "label": "4"
242
  },
243
  {
@@ -245,7 +245,7 @@
245
  "label": "3"
246
  },
247
  {
248
- "prediction": "2",
249
  "label": "4"
250
  },
251
  {
@@ -253,11 +253,11 @@
253
  "label": "4"
254
  },
255
  {
256
- "prediction": "4",
257
  "label": "3"
258
  },
259
  {
260
- "prediction": "2",
261
  "label": "4"
262
  },
263
  {
@@ -269,19 +269,19 @@
269
  "label": "4"
270
  },
271
  {
272
- "prediction": "2",
273
  "label": "3"
274
  },
275
  {
276
- "prediction": "2",
277
  "label": "3"
278
  },
279
  {
280
- "prediction": "2",
281
  "label": "3"
282
  },
283
  {
284
- "prediction": "2",
285
  "label": "3"
286
  },
287
  {
@@ -289,7 +289,7 @@
289
  "label": "3"
290
  },
291
  {
292
- "prediction": "4",
293
  "label": "3"
294
  },
295
  {
@@ -301,11 +301,11 @@
301
  "label": "3"
302
  },
303
  {
304
- "prediction": "4",
305
  "label": "3"
306
  },
307
  {
308
- "prediction": "2",
309
  "label": "2"
310
  },
311
  {
@@ -317,11 +317,11 @@
317
  "label": "4"
318
  },
319
  {
320
- "prediction": "2",
321
  "label": "3"
322
  },
323
  {
324
- "prediction": "4",
325
  "label": "4"
326
  },
327
  {
@@ -329,11 +329,11 @@
329
  "label": "4"
330
  },
331
  {
332
- "prediction": "4",
333
  "label": "4"
334
  },
335
  {
336
- "prediction": "4",
337
  "label": "4"
338
  },
339
  {
@@ -361,8 +361,8 @@
361
  "label": "3"
362
  }
363
  ],
364
- "accuracy": 0.4444444444444444,
365
- "absolute_accuracy": 0.4444444444444444,
366
- "binary_accuracy": 0.6333333333333333,
367
  "num_samples": 90
368
  }
 
1
  {
2
  "predictions_and_labels": [
3
  {
4
+ "prediction": "3",
5
  "label": "3"
6
  },
7
  {
 
13
  "label": "4"
14
  },
15
  {
16
+ "prediction": "3",
17
  "label": "3"
18
  },
19
  {
 
21
  "label": "4"
22
  },
23
  {
24
+ "prediction": "3",
25
  "label": "3"
26
  },
27
  {
 
29
  "label": "3"
30
  },
31
  {
32
+ "prediction": "4",
33
  "label": "4"
34
  },
35
  {
36
+ "prediction": "3",
37
  "label": "3"
38
  },
39
  {
 
41
  "label": "3"
42
  },
43
  {
44
+ "prediction": "3",
45
  "label": "3"
46
  },
47
  {
 
49
  "label": "3"
50
  },
51
  {
52
+ "prediction": "3",
53
  "label": "3"
54
  },
55
  {
 
57
  "label": "4"
58
  },
59
  {
60
+ "prediction": "3",
61
  "label": "3"
62
  },
63
  {
 
65
  "label": "4"
66
  },
67
  {
68
+ "prediction": "3",
69
  "label": "3"
70
  },
71
  {
 
73
  "label": "4"
74
  },
75
  {
76
+ "prediction": "3",
77
  "label": "3"
78
  },
79
  {
 
81
  "label": "4"
82
  },
83
  {
84
+ "prediction": "3",
85
  "label": "3"
86
  },
87
  {
 
89
  "label": "4"
90
  },
91
  {
92
+ "prediction": "3",
93
  "label": "4"
94
  },
95
  {
96
+ "prediction": "3",
97
  "label": "3"
98
  },
99
  {
100
+ "prediction": "3",
101
  "label": "3"
102
  },
103
  {
104
+ "prediction": "3",
105
  "label": "4"
106
  },
107
  {
 
113
  "label": "3"
114
  },
115
  {
116
+ "prediction": "3",
117
  "label": "3"
118
  },
119
  {
 
129
  "label": "3"
130
  },
131
  {
132
+ "prediction": "3",
133
  "label": "3"
134
  },
135
  {
 
149
  "label": "3"
150
  },
151
  {
152
+ "prediction": "3",
153
  "label": "3"
154
  },
155
  {
156
+ "prediction": "3",
157
  "label": "3"
158
  },
159
  {
160
+ "prediction": "3",
161
  "label": "3"
162
  },
163
  {
164
+ "prediction": "3",
165
  "label": "3"
166
  },
167
  {
 
177
  "label": "4"
178
  },
179
  {
180
+ "prediction": "4",
181
  "label": "4"
182
  },
183
  {
184
+ "prediction": "3",
185
  "label": "4"
186
  },
187
  {
 
197
  "label": "3"
198
  },
199
  {
200
+ "prediction": "3",
201
  "label": "3"
202
  },
203
  {
204
+ "prediction": "3",
205
  "label": "3"
206
  },
207
  {
 
209
  "label": "3"
210
  },
211
  {
212
+ "prediction": "3",
213
  "label": "3"
214
  },
215
  {
216
+ "prediction": "3",
217
  "label": "4"
218
  },
219
  {
 
221
  "label": "3"
222
  },
223
  {
224
+ "prediction": "3",
225
  "label": "4"
226
  },
227
  {
 
237
  "label": "4"
238
  },
239
  {
240
+ "prediction": "3",
241
  "label": "4"
242
  },
243
  {
 
245
  "label": "3"
246
  },
247
  {
248
+ "prediction": "3",
249
  "label": "4"
250
  },
251
  {
 
253
  "label": "4"
254
  },
255
  {
256
+ "prediction": "3",
257
  "label": "3"
258
  },
259
  {
260
+ "prediction": "3",
261
  "label": "4"
262
  },
263
  {
 
269
  "label": "4"
270
  },
271
  {
272
+ "prediction": "3",
273
  "label": "3"
274
  },
275
  {
276
+ "prediction": "3",
277
  "label": "3"
278
  },
279
  {
280
+ "prediction": "3",
281
  "label": "3"
282
  },
283
  {
284
+ "prediction": "3",
285
  "label": "3"
286
  },
287
  {
 
289
  "label": "3"
290
  },
291
  {
292
+ "prediction": "3",
293
  "label": "3"
294
  },
295
  {
 
301
  "label": "3"
302
  },
303
  {
304
+ "prediction": "3",
305
  "label": "3"
306
  },
307
  {
308
+ "prediction": "3",
309
  "label": "2"
310
  },
311
  {
 
317
  "label": "4"
318
  },
319
  {
320
+ "prediction": "3",
321
  "label": "3"
322
  },
323
  {
324
+ "prediction": "3",
325
  "label": "4"
326
  },
327
  {
 
329
  "label": "4"
330
  },
331
  {
332
+ "prediction": "3",
333
  "label": "4"
334
  },
335
  {
336
+ "prediction": "3",
337
  "label": "4"
338
  },
339
  {
 
361
  "label": "3"
362
  }
363
  ],
364
+ "accuracy": 0.7,
365
+ "absolute_accuracy": 0.7,
366
+ "binary_accuracy": 0.7222222222222222,
367
  "num_samples": 90
368
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02178509c78914f67297a7330c9b928751749ea628d8446de475b9551f5a46ea
3
  size 4997504848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f84437c7a176c4a3a18495a1b6746ee09d3baa546fe09e67f31a5609593411
3
  size 4997504848
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bad6bf75beb9e80eccb892e26361c4f8dff257e27de1ce532683b1874e48de95
3
  size 4952333128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8700e1755e4613cfba246ccdc89eb23febf075be53426a3f2ee2a59bb992b85
3
  size 4952333128
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1258a3ae4992b3a9537ef8983eddf0281b34411921b77d102d6ee6b0f529caad
3
  size 1199389232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ae2137dd378386dd0ee6055c1fcd8999a9c92ae6d958749bded5471247484f
3
  size 1199389232
runs/May20_02-22-01_70e5a6d483fc/events.out.tfevents.1747707722.70e5a6d483fc.70154.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e3170dff0e1eb51af1d6f5e22c2f5579cfbf27b760e1e4415c7b1f62fc35f8f
3
+ size 72392
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51a8d7b9c70e6c25046e0573fd0bc30b74f956045c0e33119de4fc25deeb0a6c
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2737c46734336a36539e785f62db41a318c5daa9fb2ad69c233662bc2e24f691
3
  size 5432