LiamvL commited on
Commit
82e266d
·
verified ·
1 Parent(s): 1cf3e5a

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +95 -3
  2. metadata.json +9 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +734 -0
  8. training_args.bin +3 -0
README.md CHANGED
@@ -1,3 +1,95 @@
1
- ---
2
- license: unknown
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
+ tags:
5
+ - Image Regression
6
+ datasets:
7
+ - "LiamvL/foodplates"
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: "fine-vlees-zorband25"
12
+ results: []
13
+ ---
14
+
15
+ # fine-vlees-zorband25
16
+ ## Image Regression Model
17
+
18
+ This model was trained with [Image Regression Model Trainer](https://github.com/TonyAssi/ImageRegression/tree/main). It takes an image as input and outputs a float value.
19
+
20
+ ```python
21
+ from ImageRegression import predict
22
+ predict(repo_id='LiamvL/fine_vlees',image_path='image.jpg')
23
+ ```
24
+
25
+ ---
26
+
27
+ ## Dataset
28
+ Dataset: LiamvL/foodplates\
29
+ Value Column: 'rest_weight_Vlees/Vis'\
30
+ Train Test Split: 0.2
31
+
32
+ ---
33
+
34
+ ## Training
35
+ Base Model: [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224)\
36
+ Epochs: 50\
37
+ Learning Rate: 0.0001
38
+
39
+ ---
40
+
41
+ ## Usage
42
+
43
+ ### Download
44
+ ```bash
45
+ git clone https://github.com/TonyAssi/ImageRegression.git
46
+ cd ImageRegression
47
+ ```
48
+
49
+ ### Installation
50
+ ```bash
51
+ pip install -r requirements.txt
52
+ ```
53
+
54
+ ### Import
55
+ ```python
56
+ from ImageRegression import train_model, upload_model, predict
57
+ ```
58
+
59
+ ### Inference (Prediction)
60
+ - **repo_id** 🤗 repo id of the model
61
+ - **image_path** path to image
62
+ ```python
63
+ predict(repo_id='LiamvL/fine_vlees',
64
+ image_path='image.jpg')
65
+ ```
66
+ The first time this function is called it'll download the safetensor model. Subsequent function calls will run faster.
67
+
68
+ ### Train Model
69
+ - **dataset_id** 🤗 dataset id
70
+ - **value_column_name** column name of prediction values in dataset
71
+ - **test_split** test split of the train/test split
72
+ - **output_dir** the directory where the checkpoints will be saved
73
+ - **num_train_epochs** training epochs
74
+ - **learning_rate** learning rate
75
+ ```python
76
+ train_model(dataset_id='LiamvL/foodplates',
77
+ value_column_name='rest_weight_Vlees/Vis',
78
+ test_split=0.2,
79
+ output_dir='./results',
80
+ num_train_epochs=50,
81
+ learning_rate=0.0001)
82
+
83
+ ```
84
+ The trainer will save the checkpoints in the output_dir location. The model.safetensors are the trained weights you'll use for inference (predicton).
85
+
86
+ ### Upload Model
87
+ This function will upload your model to the 🤗 Hub.
88
+ - **model_id** the name of the model id
89
+ - **token** go [here](https://huggingface.co/settings/tokens) to create a new 🤗 token
90
+ - **checkpoint_dir** checkpoint folder that will be uploaded
91
+ ```python
92
+ upload_model(model_id='fine-vlees-zorband25',
93
+ token='YOUR_HF_TOKEN',
94
+ checkpoint_dir='./results/checkpoint-940')
95
+ ```
metadata.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_id": "LiamvL/foodplates",
3
+ "value_column_name": "rest_weight_Vlees/Vis",
4
+ "test_split": 0.2,
5
+ "num_train_epochs": 50,
6
+ "learning_rate": 0.0001,
7
+ "max_value": 206,
8
+ "seed": 42
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce49b3fafe7798261ea29cf5550f31ba45e740fc133a2703c9c133f7b4b50964
3
+ size 345583444
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:960723eb0298226fd8c830e4e96abc9adbc4328d9af6cc2972cad0b52500b3ed
3
+ size 691292427
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d1b2da445bdc8c10c1c9019867ae159eaa5e9b0a6d5d406fc41a87fe242c82a
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9008af82ea2c682c9b64de9d5bd271649247b8bd3c3761983a4def45d64125f2
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 50.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5,
14
+ "grad_norm": 1.8985621929168701,
15
+ "learning_rate": 9.910000000000001e-05,
16
+ "loss": 0.2229,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "grad_norm": 2.6959447860717773,
22
+ "learning_rate": 9.81e-05,
23
+ "loss": 0.0395,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.5,
28
+ "grad_norm": 6.28496789932251,
29
+ "learning_rate": 9.71e-05,
30
+ "loss": 0.0261,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 0.8198316097259521,
36
+ "learning_rate": 9.61e-05,
37
+ "loss": 0.0346,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 2.5,
42
+ "grad_norm": 3.930227518081665,
43
+ "learning_rate": 9.51e-05,
44
+ "loss": 0.0237,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "grad_norm": 0.24117116630077362,
50
+ "learning_rate": 9.41e-05,
51
+ "loss": 0.0144,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 3.5,
56
+ "grad_norm": 2.9592466354370117,
57
+ "learning_rate": 9.310000000000001e-05,
58
+ "loss": 0.0136,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "grad_norm": 6.1739702224731445,
64
+ "learning_rate": 9.21e-05,
65
+ "loss": 0.0143,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 4.5,
70
+ "grad_norm": 1.1602582931518555,
71
+ "learning_rate": 9.11e-05,
72
+ "loss": 0.0166,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 3.7479774951934814,
78
+ "learning_rate": 9.010000000000001e-05,
79
+ "loss": 0.0174,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 5.5,
84
+ "grad_norm": 1.2943713665008545,
85
+ "learning_rate": 8.910000000000001e-05,
86
+ "loss": 0.0127,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 6.0,
91
+ "grad_norm": 1.9738529920578003,
92
+ "learning_rate": 8.81e-05,
93
+ "loss": 0.0056,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 6.5,
98
+ "grad_norm": 1.6200770139694214,
99
+ "learning_rate": 8.71e-05,
100
+ "loss": 0.0053,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 7.0,
105
+ "grad_norm": 2.116046667098999,
106
+ "learning_rate": 8.61e-05,
107
+ "loss": 0.0058,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 7.5,
112
+ "grad_norm": 1.7189213037490845,
113
+ "learning_rate": 8.510000000000001e-05,
114
+ "loss": 0.0035,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 8.0,
119
+ "grad_norm": 0.13006743788719177,
120
+ "learning_rate": 8.41e-05,
121
+ "loss": 0.0025,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 8.5,
126
+ "grad_norm": 0.35229212045669556,
127
+ "learning_rate": 8.31e-05,
128
+ "loss": 0.002,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "grad_norm": 0.5283310413360596,
134
+ "learning_rate": 8.21e-05,
135
+ "loss": 0.0026,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 9.5,
140
+ "grad_norm": 1.4066272974014282,
141
+ "learning_rate": 8.11e-05,
142
+ "loss": 0.0028,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 10.0,
147
+ "grad_norm": 0.6277774572372437,
148
+ "learning_rate": 8.010000000000001e-05,
149
+ "loss": 0.0018,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 10.5,
154
+ "grad_norm": 1.3672561645507812,
155
+ "learning_rate": 7.910000000000001e-05,
156
+ "loss": 0.0019,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 11.0,
161
+ "grad_norm": 0.849717915058136,
162
+ "learning_rate": 7.81e-05,
163
+ "loss": 0.0014,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 11.5,
168
+ "grad_norm": 1.2382935285568237,
169
+ "learning_rate": 7.71e-05,
170
+ "loss": 0.0017,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 12.0,
175
+ "grad_norm": 0.3568917512893677,
176
+ "learning_rate": 7.61e-05,
177
+ "loss": 0.0015,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 12.5,
182
+ "grad_norm": 0.02996239811182022,
183
+ "learning_rate": 7.510000000000001e-05,
184
+ "loss": 0.0009,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 13.0,
189
+ "grad_norm": 0.3278927206993103,
190
+ "learning_rate": 7.41e-05,
191
+ "loss": 0.0016,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 13.5,
196
+ "grad_norm": 0.78089839220047,
197
+ "learning_rate": 7.31e-05,
198
+ "loss": 0.0015,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 14.0,
203
+ "grad_norm": 1.049814224243164,
204
+ "learning_rate": 7.21e-05,
205
+ "loss": 0.0008,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 14.5,
210
+ "grad_norm": 0.05354577675461769,
211
+ "learning_rate": 7.11e-05,
212
+ "loss": 0.0012,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 15.0,
217
+ "grad_norm": 0.7721472978591919,
218
+ "learning_rate": 7.01e-05,
219
+ "loss": 0.0007,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 15.5,
224
+ "grad_norm": 0.5011315941810608,
225
+ "learning_rate": 6.91e-05,
226
+ "loss": 0.0006,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 16.0,
231
+ "grad_norm": 0.2097933441400528,
232
+ "learning_rate": 6.81e-05,
233
+ "loss": 0.001,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 16.5,
238
+ "grad_norm": 0.6485989689826965,
239
+ "learning_rate": 6.71e-05,
240
+ "loss": 0.0011,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 17.0,
245
+ "grad_norm": 0.46603426337242126,
246
+ "learning_rate": 6.610000000000001e-05,
247
+ "loss": 0.0008,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 17.5,
252
+ "grad_norm": 1.16153883934021,
253
+ "learning_rate": 6.510000000000001e-05,
254
+ "loss": 0.0012,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 18.0,
259
+ "grad_norm": 0.509899377822876,
260
+ "learning_rate": 6.41e-05,
261
+ "loss": 0.001,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 18.5,
266
+ "grad_norm": 0.22210121154785156,
267
+ "learning_rate": 6.31e-05,
268
+ "loss": 0.0006,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 19.0,
273
+ "grad_norm": 1.4337605237960815,
274
+ "learning_rate": 6.21e-05,
275
+ "loss": 0.0014,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 19.5,
280
+ "grad_norm": 0.6034935116767883,
281
+ "learning_rate": 6.110000000000001e-05,
282
+ "loss": 0.0006,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 20.0,
287
+ "grad_norm": 0.27057749032974243,
288
+ "learning_rate": 6.0100000000000004e-05,
289
+ "loss": 0.0009,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 20.5,
294
+ "grad_norm": 0.6695419549942017,
295
+ "learning_rate": 5.91e-05,
296
+ "loss": 0.0004,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 21.0,
301
+ "grad_norm": 1.8617427349090576,
302
+ "learning_rate": 5.8099999999999996e-05,
303
+ "loss": 0.002,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 21.5,
308
+ "grad_norm": 0.7135971784591675,
309
+ "learning_rate": 5.71e-05,
310
+ "loss": 0.0022,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 22.0,
315
+ "grad_norm": 1.104410171508789,
316
+ "learning_rate": 5.610000000000001e-05,
317
+ "loss": 0.0018,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 22.5,
322
+ "grad_norm": 0.5932751297950745,
323
+ "learning_rate": 5.5100000000000004e-05,
324
+ "loss": 0.0014,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 23.0,
329
+ "grad_norm": 0.4027913510799408,
330
+ "learning_rate": 5.410000000000001e-05,
331
+ "loss": 0.0008,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 23.5,
336
+ "grad_norm": 0.7953199148178101,
337
+ "learning_rate": 5.31e-05,
338
+ "loss": 0.0011,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 24.0,
343
+ "grad_norm": 0.25498589873313904,
344
+ "learning_rate": 5.2100000000000006e-05,
345
+ "loss": 0.0004,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 24.5,
350
+ "grad_norm": 0.8258208632469177,
351
+ "learning_rate": 5.11e-05,
352
+ "loss": 0.0007,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 25.0,
357
+ "grad_norm": 0.18510620296001434,
358
+ "learning_rate": 5.0100000000000005e-05,
359
+ "loss": 0.0007,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 25.5,
364
+ "grad_norm": 0.8307366371154785,
365
+ "learning_rate": 4.91e-05,
366
+ "loss": 0.0007,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 26.0,
371
+ "grad_norm": 0.7541914582252502,
372
+ "learning_rate": 4.8100000000000004e-05,
373
+ "loss": 0.0007,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 26.5,
378
+ "grad_norm": 0.3338281214237213,
379
+ "learning_rate": 4.71e-05,
380
+ "loss": 0.0004,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 27.0,
385
+ "grad_norm": 0.06798086315393448,
386
+ "learning_rate": 4.61e-05,
387
+ "loss": 0.0007,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 27.5,
392
+ "grad_norm": 0.15522146224975586,
393
+ "learning_rate": 4.5100000000000005e-05,
394
+ "loss": 0.0004,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 28.0,
399
+ "grad_norm": 0.4013696610927582,
400
+ "learning_rate": 4.41e-05,
401
+ "loss": 0.0006,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 28.5,
406
+ "grad_norm": 0.40657514333724976,
407
+ "learning_rate": 4.3100000000000004e-05,
408
+ "loss": 0.0007,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 29.0,
413
+ "grad_norm": 0.14566798508167267,
414
+ "learning_rate": 4.21e-05,
415
+ "loss": 0.0001,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 29.5,
420
+ "grad_norm": 0.4930070638656616,
421
+ "learning_rate": 4.11e-05,
422
+ "loss": 0.0003,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 30.0,
427
+ "grad_norm": 0.2327234447002411,
428
+ "learning_rate": 4.0100000000000006e-05,
429
+ "loss": 0.0005,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 30.5,
434
+ "grad_norm": 0.5080268383026123,
435
+ "learning_rate": 3.91e-05,
436
+ "loss": 0.0003,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 31.0,
441
+ "grad_norm": 0.5666539669036865,
442
+ "learning_rate": 3.8100000000000005e-05,
443
+ "loss": 0.0004,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 31.5,
448
+ "grad_norm": 0.03347349166870117,
449
+ "learning_rate": 3.71e-05,
450
+ "loss": 0.0006,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 32.0,
455
+ "grad_norm": 0.4377991557121277,
456
+ "learning_rate": 3.61e-05,
457
+ "loss": 0.0001,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 32.5,
462
+ "grad_norm": 0.19413357973098755,
463
+ "learning_rate": 3.51e-05,
464
+ "loss": 0.0005,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 33.0,
469
+ "grad_norm": 0.18701113760471344,
470
+ "learning_rate": 3.41e-05,
471
+ "loss": 0.0001,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 33.5,
476
+ "grad_norm": 0.31651440262794495,
477
+ "learning_rate": 3.3100000000000005e-05,
478
+ "loss": 0.0005,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 34.0,
483
+ "grad_norm": 0.02828579768538475,
484
+ "learning_rate": 3.21e-05,
485
+ "loss": 0.0,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 34.5,
490
+ "grad_norm": 0.34173232316970825,
491
+ "learning_rate": 3.1100000000000004e-05,
492
+ "loss": 0.0006,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 35.0,
497
+ "grad_norm": 0.09027812629938126,
498
+ "learning_rate": 3.01e-05,
499
+ "loss": 0.0001,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 35.5,
504
+ "grad_norm": 0.22914953529834747,
505
+ "learning_rate": 2.91e-05,
506
+ "loss": 0.0001,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 36.0,
511
+ "grad_norm": 0.2684924900531769,
512
+ "learning_rate": 2.8100000000000005e-05,
513
+ "loss": 0.0006,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 36.5,
518
+ "grad_norm": 0.29140010476112366,
519
+ "learning_rate": 2.7100000000000005e-05,
520
+ "loss": 0.0003,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 37.0,
525
+ "grad_norm": 0.39679646492004395,
526
+ "learning_rate": 2.61e-05,
527
+ "loss": 0.0003,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 37.5,
532
+ "grad_norm": 0.08030686527490616,
533
+ "learning_rate": 2.51e-05,
534
+ "loss": 0.0005,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 38.0,
539
+ "grad_norm": 0.06952106207609177,
540
+ "learning_rate": 2.41e-05,
541
+ "loss": 0.0,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 38.5,
546
+ "grad_norm": 0.03430015593767166,
547
+ "learning_rate": 2.3100000000000002e-05,
548
+ "loss": 0.0003,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 39.0,
553
+ "grad_norm": 0.31544044613838196,
554
+ "learning_rate": 2.2100000000000002e-05,
555
+ "loss": 0.0003,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 39.5,
560
+ "grad_norm": 0.20336127281188965,
561
+ "learning_rate": 2.11e-05,
562
+ "loss": 0.0,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 40.0,
567
+ "grad_norm": 0.028785208240151405,
568
+ "learning_rate": 2.01e-05,
569
+ "loss": 0.0005,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 40.5,
574
+ "grad_norm": 0.1161634773015976,
575
+ "learning_rate": 1.91e-05,
576
+ "loss": 0.0004,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 41.0,
581
+ "grad_norm": 0.11442368477582932,
582
+ "learning_rate": 1.81e-05,
583
+ "loss": 0.0,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 41.5,
588
+ "grad_norm": 0.010891513898968697,
589
+ "learning_rate": 1.7100000000000002e-05,
590
+ "loss": 0.0002,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 42.0,
595
+ "grad_norm": 0.2547859251499176,
596
+ "learning_rate": 1.6100000000000002e-05,
597
+ "loss": 0.0003,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 42.5,
602
+ "grad_norm": 0.006857059430330992,
603
+ "learning_rate": 1.51e-05,
604
+ "loss": 0.0002,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 43.0,
609
+ "grad_norm": 0.4951632618904114,
610
+ "learning_rate": 1.4099999999999999e-05,
611
+ "loss": 0.0003,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 43.5,
616
+ "grad_norm": 0.041084468364715576,
617
+ "learning_rate": 1.3100000000000002e-05,
618
+ "loss": 0.0004,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 44.0,
623
+ "grad_norm": 0.11843769252300262,
624
+ "learning_rate": 1.2100000000000001e-05,
625
+ "loss": 0.0,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 44.5,
630
+ "grad_norm": 0.03217615187168121,
631
+ "learning_rate": 1.11e-05,
632
+ "loss": 0.0005,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 45.0,
637
+ "grad_norm": 0.018256094306707382,
638
+ "learning_rate": 1.0100000000000002e-05,
639
+ "loss": 0.0,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 45.5,
644
+ "grad_norm": 0.042205873876810074,
645
+ "learning_rate": 9.100000000000001e-06,
646
+ "loss": 0.0,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 46.0,
651
+ "grad_norm": 0.05937511846423149,
652
+ "learning_rate": 8.1e-06,
653
+ "loss": 0.0004,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 46.5,
658
+ "grad_norm": 0.10673025250434875,
659
+ "learning_rate": 7.1e-06,
660
+ "loss": 0.0002,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 47.0,
665
+ "grad_norm": 0.1283574253320694,
666
+ "learning_rate": 6.1e-06,
667
+ "loss": 0.0002,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 47.5,
672
+ "grad_norm": 0.04566584527492523,
673
+ "learning_rate": 5.1e-06,
674
+ "loss": 0.0004,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 48.0,
679
+ "grad_norm": 0.08355249464511871,
680
+ "learning_rate": 4.1000000000000006e-06,
681
+ "loss": 0.0,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 48.5,
686
+ "grad_norm": 0.12251041829586029,
687
+ "learning_rate": 3.1e-06,
688
+ "loss": 0.0002,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 49.0,
693
+ "grad_norm": 0.16482886672019958,
694
+ "learning_rate": 2.1000000000000002e-06,
695
+ "loss": 0.0002,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 49.5,
700
+ "grad_norm": 0.008726044557988644,
701
+ "learning_rate": 1.1e-06,
702
+ "loss": 0.0002,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 50.0,
707
+ "grad_norm": 0.0353192463517189,
708
+ "learning_rate": 1.0000000000000001e-07,
709
+ "loss": 0.0002,
710
+ "step": 1000
711
+ }
712
+ ],
713
+ "logging_steps": 10,
714
+ "max_steps": 1000,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 50,
717
+ "save_steps": 10,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": true
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 0.0,
731
+ "train_batch_size": 32,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43657cd5a8f9e5df721e89daeddcaef29134d5f81701c9015e5e8a59cd6a2331
3
+ size 5777