tonyassi commited on
Commit
c11ba2c
1 Parent(s): cd87a5e

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +108 -0
  2. metadata.json +8 -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 +484 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
+ tags:
5
+ - Image Regression
6
+ datasets:
7
+ - "tonyassi/tony__assi-ig-ds200"
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: "tony__assi-ig-prediction200"
12
+ results: []
13
+ ---
14
+
15
+ # tony__assi-ig-prediction200
16
+ ## IG Prediction
17
+
18
+ This model was trained with [IGPrediction](https://github.com/TonyAssi/IGPrediction). It predicts how many likes an image will get.
19
+
20
+ ```python
21
+ from IGPredict import predict_ig
22
+ predict_ig(repo_id='tonyassi/tony__assi-ig-prediction200',image_path='image.jpg')
23
+ ```
24
+
25
+ ---
26
+
27
+ ## Dataset
28
+ Dataset: tonyassi/tony__assi-ig-ds200\
29
+ Value Column:\
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: 20\
37
+ Learning Rate: 0.0001
38
+
39
+ ---
40
+
41
+ ## Usage
42
+
43
+ ### Download
44
+ ```bash
45
+ git clone https://github.com/TonyAssi/IGPrediction.git
46
+ cd IGPrediction
47
+ ```
48
+
49
+ ### Installation
50
+ ```bash
51
+ pip install -r requirements.txt
52
+ ```
53
+
54
+ ### Import
55
+ ```python
56
+ from IGPredict import ig_download, upload_dataset, train_ig_model, upload_ig_model, predict_ig
57
+ ```
58
+
59
+ ### Download Instagram Images
60
+ - **username** Instagram username
61
+ - **num_images** maximum number of images to download
62
+ ```python
63
+ ig_download(username='instagarm_username', num_images=100)
64
+ ```
65
+ Instagram images will be downloaded to *'./images'* folder, each one named like so *"index-likes.jpg"*. E.g. *"3-17.jpg"* is the third image and has 17 likes.
66
+
67
+ ### Upload Dataset
68
+ - **dataset_name** name of dataset to be uploaded
69
+ - **token** go [here](https://huggingface.co/settings/tokens) to create a new 🤗 token
70
+ ```python
71
+ upload_dataset(dataset_name='tonyassi/tony__assi-ig-ds200', token='YOUR_HF_TOKEN')
72
+ ```
73
+ Go to your 🤗 profile to find your uploaded dataset, it should look similar to [tonyassi/tony__assi-ig-ds](https://huggingface.co/datasets/tonyassi/tony__assi-ig-ds).
74
+
75
+
76
+ ### Train Model
77
+ - **dataset_id** 🤗 dataset id
78
+ - **test_split** test split of the train/test split
79
+ - **num_train_epochs** training epochs
80
+ - **learning_rate** learning rate
81
+ ```python
82
+ train_ig_model(dataset_id='tonyassi/tony__assi-ig-ds200',
83
+ test_split=0.2,
84
+ num_train_epochs=20,
85
+ learning_rate=0.0001)
86
+
87
+ ```
88
+ The trainer will save the checkpoints in the 'results' folder. The model.safetensors are the trained weights you'll use for inference (predicton).
89
+
90
+ ### Upload Model
91
+ This function will upload your model to the 🤗 Hub.
92
+ - **model_id** the name of the model id
93
+ - **token** go [here](https://huggingface.co/settings/tokens) to create a new 🤗 token
94
+ - **checkpoint_dir** checkpoint folder that will be uploaded
95
+ ```python
96
+ upload_ig_model(model_id='tony__assi-ig-prediction200',
97
+ token='YOUR_HF_TOKEN',
98
+ checkpoint_dir='./results/checkpoint-940')
99
+ ```
100
+
101
+ ### Inference (Prediction)
102
+ - **repo_id** 🤗 repo id of the model
103
+ - **image_path** path to image
104
+ ```python
105
+ predict_ig(repo_id='tonyassi/tony__assi-ig-prediction200',
106
+ image_path='image.jpg')
107
+ ```
108
+ The first time this function is called it'll download the safetensor model. Subsequent function calls will run faster.
metadata.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_id": "tonyassi/tony__assi-ig-ds200",
3
+ "value_column_name": "likes",
4
+ "test_split": 0.2,
5
+ "num_train_epochs": 20,
6
+ "learning_rate": 0.0001,
7
+ "max_value": 177
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11165000fc90d43fc659af621bd55bdac2bf8e48a855e0e3faafe53bd6f69919
3
+ size 345583444
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2f195d5daaea171bd20a884a9738f494432d6acfa0bc1cf0390ff3f9d9f488
3
+ size 686557178
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8098b3ea1099554a17a75b08e08b0801f551831d4783349401defb321e1c1c1d
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ad1e13a84e759bcc62d699a5143c5c275ee621d7d69ae8816d20e1d9121294
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "grad_norm": 14.416919708251953,
14
+ "learning_rate": 9.75e-05,
15
+ "loss": 0.3808,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "grad_norm": 14.942909240722656,
21
+ "learning_rate": 9.5e-05,
22
+ "loss": 0.1636,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.1972920000553131,
28
+ "eval_mse": 0.1972920149564743,
29
+ "eval_runtime": 1.8069,
30
+ "eval_samples_per_second": 21.584,
31
+ "eval_steps_per_second": 2.767,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 1.5,
36
+ "grad_norm": 2.4087517261505127,
37
+ "learning_rate": 9.250000000000001e-05,
38
+ "loss": 0.2302,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "grad_norm": 21.778547286987305,
44
+ "learning_rate": 9e-05,
45
+ "loss": 0.1331,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.046439673751592636,
51
+ "eval_mse": 0.046439677476882935,
52
+ "eval_runtime": 1.622,
53
+ "eval_samples_per_second": 24.044,
54
+ "eval_steps_per_second": 3.083,
55
+ "step": 40
56
+ },
57
+ {
58
+ "epoch": 2.5,
59
+ "grad_norm": 1.1269134283065796,
60
+ "learning_rate": 8.75e-05,
61
+ "loss": 0.05,
62
+ "step": 50
63
+ },
64
+ {
65
+ "epoch": 3.0,
66
+ "grad_norm": 4.305675983428955,
67
+ "learning_rate": 8.5e-05,
68
+ "loss": 0.0289,
69
+ "step": 60
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_loss": 0.03575298935174942,
74
+ "eval_mse": 0.03575298190116882,
75
+ "eval_runtime": 1.6208,
76
+ "eval_samples_per_second": 24.063,
77
+ "eval_steps_per_second": 3.085,
78
+ "step": 60
79
+ },
80
+ {
81
+ "epoch": 3.5,
82
+ "grad_norm": 1.7014061212539673,
83
+ "learning_rate": 8.25e-05,
84
+ "loss": 0.0246,
85
+ "step": 70
86
+ },
87
+ {
88
+ "epoch": 4.0,
89
+ "grad_norm": 0.39174097776412964,
90
+ "learning_rate": 8e-05,
91
+ "loss": 0.0221,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 4.0,
96
+ "eval_loss": 0.03326353803277016,
97
+ "eval_mse": 0.03326353803277016,
98
+ "eval_runtime": 1.6114,
99
+ "eval_samples_per_second": 24.203,
100
+ "eval_steps_per_second": 3.103,
101
+ "step": 80
102
+ },
103
+ {
104
+ "epoch": 4.5,
105
+ "grad_norm": 2.6145267486572266,
106
+ "learning_rate": 7.75e-05,
107
+ "loss": 0.021,
108
+ "step": 90
109
+ },
110
+ {
111
+ "epoch": 5.0,
112
+ "grad_norm": 13.847771644592285,
113
+ "learning_rate": 7.500000000000001e-05,
114
+ "loss": 0.0223,
115
+ "step": 100
116
+ },
117
+ {
118
+ "epoch": 5.0,
119
+ "eval_loss": 0.03398064896464348,
120
+ "eval_mse": 0.033980656415224075,
121
+ "eval_runtime": 1.6515,
122
+ "eval_samples_per_second": 23.615,
123
+ "eval_steps_per_second": 3.028,
124
+ "step": 100
125
+ },
126
+ {
127
+ "epoch": 5.5,
128
+ "grad_norm": 0.43660324811935425,
129
+ "learning_rate": 7.25e-05,
130
+ "loss": 0.0131,
131
+ "step": 110
132
+ },
133
+ {
134
+ "epoch": 6.0,
135
+ "grad_norm": 2.1774399280548096,
136
+ "learning_rate": 7e-05,
137
+ "loss": 0.0117,
138
+ "step": 120
139
+ },
140
+ {
141
+ "epoch": 6.0,
142
+ "eval_loss": 0.04457540437579155,
143
+ "eval_mse": 0.04457540065050125,
144
+ "eval_runtime": 1.6081,
145
+ "eval_samples_per_second": 24.252,
146
+ "eval_steps_per_second": 3.109,
147
+ "step": 120
148
+ },
149
+ {
150
+ "epoch": 6.5,
151
+ "grad_norm": 2.61739182472229,
152
+ "learning_rate": 6.750000000000001e-05,
153
+ "loss": 0.0168,
154
+ "step": 130
155
+ },
156
+ {
157
+ "epoch": 7.0,
158
+ "grad_norm": 2.7107529640197754,
159
+ "learning_rate": 6.500000000000001e-05,
160
+ "loss": 0.0107,
161
+ "step": 140
162
+ },
163
+ {
164
+ "epoch": 7.0,
165
+ "eval_loss": 0.03702976927161217,
166
+ "eval_mse": 0.037029776722192764,
167
+ "eval_runtime": 1.6027,
168
+ "eval_samples_per_second": 24.334,
169
+ "eval_steps_per_second": 3.12,
170
+ "step": 140
171
+ },
172
+ {
173
+ "epoch": 7.5,
174
+ "grad_norm": 4.807140350341797,
175
+ "learning_rate": 6.25e-05,
176
+ "loss": 0.0112,
177
+ "step": 150
178
+ },
179
+ {
180
+ "epoch": 8.0,
181
+ "grad_norm": 1.6699814796447754,
182
+ "learning_rate": 6e-05,
183
+ "loss": 0.0096,
184
+ "step": 160
185
+ },
186
+ {
187
+ "epoch": 8.0,
188
+ "eval_loss": 0.03073795698583126,
189
+ "eval_mse": 0.030737943947315216,
190
+ "eval_runtime": 1.678,
191
+ "eval_samples_per_second": 23.242,
192
+ "eval_steps_per_second": 2.98,
193
+ "step": 160
194
+ },
195
+ {
196
+ "epoch": 8.5,
197
+ "grad_norm": 5.444133281707764,
198
+ "learning_rate": 5.7499999999999995e-05,
199
+ "loss": 0.0099,
200
+ "step": 170
201
+ },
202
+ {
203
+ "epoch": 9.0,
204
+ "grad_norm": 1.5312561988830566,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.0142,
207
+ "step": 180
208
+ },
209
+ {
210
+ "epoch": 9.0,
211
+ "eval_loss": 0.03504549711942673,
212
+ "eval_mse": 0.03504551202058792,
213
+ "eval_runtime": 1.6103,
214
+ "eval_samples_per_second": 24.218,
215
+ "eval_steps_per_second": 3.105,
216
+ "step": 180
217
+ },
218
+ {
219
+ "epoch": 9.5,
220
+ "grad_norm": 1.527550220489502,
221
+ "learning_rate": 5.25e-05,
222
+ "loss": 0.0051,
223
+ "step": 190
224
+ },
225
+ {
226
+ "epoch": 10.0,
227
+ "grad_norm": 1.0232219696044922,
228
+ "learning_rate": 5e-05,
229
+ "loss": 0.0069,
230
+ "step": 200
231
+ },
232
+ {
233
+ "epoch": 10.0,
234
+ "eval_loss": 0.032399099320173264,
235
+ "eval_mse": 0.03239908814430237,
236
+ "eval_runtime": 1.61,
237
+ "eval_samples_per_second": 24.224,
238
+ "eval_steps_per_second": 3.106,
239
+ "step": 200
240
+ },
241
+ {
242
+ "epoch": 10.5,
243
+ "grad_norm": 1.1013288497924805,
244
+ "learning_rate": 4.75e-05,
245
+ "loss": 0.0034,
246
+ "step": 210
247
+ },
248
+ {
249
+ "epoch": 11.0,
250
+ "grad_norm": 0.35051777958869934,
251
+ "learning_rate": 4.5e-05,
252
+ "loss": 0.0028,
253
+ "step": 220
254
+ },
255
+ {
256
+ "epoch": 11.0,
257
+ "eval_loss": 0.02933628484606743,
258
+ "eval_mse": 0.029336294159293175,
259
+ "eval_runtime": 1.7012,
260
+ "eval_samples_per_second": 22.925,
261
+ "eval_steps_per_second": 2.939,
262
+ "step": 220
263
+ },
264
+ {
265
+ "epoch": 11.5,
266
+ "grad_norm": 1.1170843839645386,
267
+ "learning_rate": 4.25e-05,
268
+ "loss": 0.0019,
269
+ "step": 230
270
+ },
271
+ {
272
+ "epoch": 12.0,
273
+ "grad_norm": 1.3299288749694824,
274
+ "learning_rate": 4e-05,
275
+ "loss": 0.0044,
276
+ "step": 240
277
+ },
278
+ {
279
+ "epoch": 12.0,
280
+ "eval_loss": 0.028278259560465813,
281
+ "eval_mse": 0.028278270736336708,
282
+ "eval_runtime": 1.5914,
283
+ "eval_samples_per_second": 24.506,
284
+ "eval_steps_per_second": 3.142,
285
+ "step": 240
286
+ },
287
+ {
288
+ "epoch": 12.5,
289
+ "grad_norm": 1.6604584455490112,
290
+ "learning_rate": 3.7500000000000003e-05,
291
+ "loss": 0.002,
292
+ "step": 250
293
+ },
294
+ {
295
+ "epoch": 13.0,
296
+ "grad_norm": 1.2441127300262451,
297
+ "learning_rate": 3.5e-05,
298
+ "loss": 0.0011,
299
+ "step": 260
300
+ },
301
+ {
302
+ "epoch": 13.0,
303
+ "eval_loss": 0.029920559376478195,
304
+ "eval_mse": 0.029920564964413643,
305
+ "eval_runtime": 1.6282,
306
+ "eval_samples_per_second": 23.953,
307
+ "eval_steps_per_second": 3.071,
308
+ "step": 260
309
+ },
310
+ {
311
+ "epoch": 13.5,
312
+ "grad_norm": 0.7714802026748657,
313
+ "learning_rate": 3.2500000000000004e-05,
314
+ "loss": 0.0008,
315
+ "step": 270
316
+ },
317
+ {
318
+ "epoch": 14.0,
319
+ "grad_norm": 0.5498138070106506,
320
+ "learning_rate": 3e-05,
321
+ "loss": 0.0005,
322
+ "step": 280
323
+ },
324
+ {
325
+ "epoch": 14.0,
326
+ "eval_loss": 0.027942122891545296,
327
+ "eval_mse": 0.027942117303609848,
328
+ "eval_runtime": 1.5994,
329
+ "eval_samples_per_second": 24.384,
330
+ "eval_steps_per_second": 3.126,
331
+ "step": 280
332
+ },
333
+ {
334
+ "epoch": 14.5,
335
+ "grad_norm": 0.5462870001792908,
336
+ "learning_rate": 2.7500000000000004e-05,
337
+ "loss": 0.0006,
338
+ "step": 290
339
+ },
340
+ {
341
+ "epoch": 15.0,
342
+ "grad_norm": 0.32672354578971863,
343
+ "learning_rate": 2.5e-05,
344
+ "loss": 0.0005,
345
+ "step": 300
346
+ },
347
+ {
348
+ "epoch": 15.0,
349
+ "eval_loss": 0.029117202386260033,
350
+ "eval_mse": 0.02911720797419548,
351
+ "eval_runtime": 1.595,
352
+ "eval_samples_per_second": 24.451,
353
+ "eval_steps_per_second": 3.135,
354
+ "step": 300
355
+ },
356
+ {
357
+ "epoch": 15.5,
358
+ "grad_norm": 0.7088171243667603,
359
+ "learning_rate": 2.25e-05,
360
+ "loss": 0.0012,
361
+ "step": 310
362
+ },
363
+ {
364
+ "epoch": 16.0,
365
+ "grad_norm": 0.3224898874759674,
366
+ "learning_rate": 2e-05,
367
+ "loss": 0.0011,
368
+ "step": 320
369
+ },
370
+ {
371
+ "epoch": 16.0,
372
+ "eval_loss": 0.028802577406167984,
373
+ "eval_mse": 0.028802569955587387,
374
+ "eval_runtime": 1.6242,
375
+ "eval_samples_per_second": 24.012,
376
+ "eval_steps_per_second": 3.078,
377
+ "step": 320
378
+ },
379
+ {
380
+ "epoch": 16.5,
381
+ "grad_norm": 0.2536928951740265,
382
+ "learning_rate": 1.75e-05,
383
+ "loss": 0.0002,
384
+ "step": 330
385
+ },
386
+ {
387
+ "epoch": 17.0,
388
+ "grad_norm": 0.2693057060241699,
389
+ "learning_rate": 1.5e-05,
390
+ "loss": 0.0003,
391
+ "step": 340
392
+ },
393
+ {
394
+ "epoch": 17.0,
395
+ "eval_loss": 0.028974896296858788,
396
+ "eval_mse": 0.02897489443421364,
397
+ "eval_runtime": 1.5937,
398
+ "eval_samples_per_second": 24.472,
399
+ "eval_steps_per_second": 3.137,
400
+ "step": 340
401
+ },
402
+ {
403
+ "epoch": 17.5,
404
+ "grad_norm": 0.22231905162334442,
405
+ "learning_rate": 1.25e-05,
406
+ "loss": 0.0001,
407
+ "step": 350
408
+ },
409
+ {
410
+ "epoch": 18.0,
411
+ "grad_norm": 0.44173210859298706,
412
+ "learning_rate": 1e-05,
413
+ "loss": 0.0001,
414
+ "step": 360
415
+ },
416
+ {
417
+ "epoch": 18.0,
418
+ "eval_loss": 0.029911378398537636,
419
+ "eval_mse": 0.029911383986473083,
420
+ "eval_runtime": 1.5913,
421
+ "eval_samples_per_second": 24.509,
422
+ "eval_steps_per_second": 3.142,
423
+ "step": 360
424
+ },
425
+ {
426
+ "epoch": 18.5,
427
+ "grad_norm": 0.2958744764328003,
428
+ "learning_rate": 7.5e-06,
429
+ "loss": 0.0001,
430
+ "step": 370
431
+ },
432
+ {
433
+ "epoch": 19.0,
434
+ "grad_norm": 0.41316938400268555,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.0001,
437
+ "step": 380
438
+ },
439
+ {
440
+ "epoch": 19.0,
441
+ "eval_loss": 0.029724078252911568,
442
+ "eval_mse": 0.029724083840847015,
443
+ "eval_runtime": 1.5907,
444
+ "eval_samples_per_second": 24.518,
445
+ "eval_steps_per_second": 3.143,
446
+ "step": 380
447
+ },
448
+ {
449
+ "epoch": 19.5,
450
+ "grad_norm": 0.0391409695148468,
451
+ "learning_rate": 2.5e-06,
452
+ "loss": 0.0,
453
+ "step": 390
454
+ },
455
+ {
456
+ "epoch": 20.0,
457
+ "grad_norm": 0.021498844027519226,
458
+ "learning_rate": 0.0,
459
+ "loss": 0.0,
460
+ "step": 400
461
+ }
462
+ ],
463
+ "logging_steps": 10,
464
+ "max_steps": 400,
465
+ "num_input_tokens_seen": 0,
466
+ "num_train_epochs": 20,
467
+ "save_steps": 10,
468
+ "stateful_callbacks": {
469
+ "TrainerControl": {
470
+ "args": {
471
+ "should_epoch_stop": false,
472
+ "should_evaluate": false,
473
+ "should_log": false,
474
+ "should_save": true,
475
+ "should_training_stop": true
476
+ },
477
+ "attributes": {}
478
+ }
479
+ },
480
+ "total_flos": 0.0,
481
+ "train_batch_size": 8,
482
+ "trial_name": null,
483
+ "trial_params": null
484
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a19a6489ee5ffde1427142bcbf54dbb7e81a85205c07442cc69c6f9847f8b45e
3
+ size 5048