Raihan004 commited on
Commit
c33b7d2
1 Parent(s): d328d69

🍻 cheers

Browse files
README.md CHANGED
@@ -2,6 +2,7 @@
2
  license: apache-2.0
3
  base_model: Raihan004/Action_model
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
@@ -14,7 +15,7 @@ model-index:
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
- name: imagefolder
18
  type: imagefolder
19
  config: default
20
  split: train
@@ -22,7 +23,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8488576449912126
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # Action_model
32
 
33
- This model is a fine-tuned version of [Raihan004/Action_model](https://huggingface.co/Raihan004/Action_model) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5034
36
- - Accuracy: 0.8489
37
 
38
  ## Model description
39
 
 
2
  license: apache-2.0
3
  base_model: Raihan004/Action_model
4
  tags:
5
+ - image-classification
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
 
15
  name: Image Classification
16
  type: image-classification
17
  dataset:
18
+ name: action_class
19
  type: imagefolder
20
  config: default
21
  split: train
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8629173989455184
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # Action_model
33
 
34
+ This model is a fine-tuned version of [Raihan004/Action_model](https://huggingface.co/Raihan004/Action_model) on the action_class dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.4790
37
+ - Accuracy: 0.8629
38
 
39
  ## Model description
40
 
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_accuracy": 0.789103690685413,
4
- "eval_loss": 1.1399264335632324,
5
- "eval_runtime": 7.7057,
6
- "eval_samples_per_second": 73.841,
7
- "eval_steps_per_second": 9.344,
8
- "total_flos": 3.3230947683690086e+17,
9
- "train_loss": 1.549544946471257,
10
- "train_runtime": 145.4848,
11
- "train_samples_per_second": 29.474,
12
- "train_steps_per_second": 0.921
13
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.8629173989455184,
4
+ "eval_loss": 0.47900134325027466,
5
+ "eval_runtime": 7.7338,
6
+ "eval_samples_per_second": 73.573,
7
+ "eval_steps_per_second": 9.31,
8
+ "total_flos": 3.3230947683690086e+18,
9
+ "train_loss": 0.3864157530798841,
10
+ "train_runtime": 1135.6162,
11
+ "train_samples_per_second": 37.759,
12
+ "train_steps_per_second": 1.18
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_accuracy": 0.789103690685413,
4
- "eval_loss": 1.1399264335632324,
5
- "eval_runtime": 7.7057,
6
- "eval_samples_per_second": 73.841,
7
- "eval_steps_per_second": 9.344
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.8629173989455184,
4
+ "eval_loss": 0.47900134325027466,
5
+ "eval_runtime": 7.7338,
6
+ "eval_samples_per_second": 73.573,
7
+ "eval_steps_per_second": 9.31
8
  }
runs/May07_17-56-54_6cf576645707/events.out.tfevents.1715105780.6cf576645707.35.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cdc157a6730f9c81f5e20fb065b2e56919f0e2d3b644fe639361065b02d7e79
3
+ size 411
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "total_flos": 3.3230947683690086e+17,
4
- "train_loss": 1.549544946471257,
5
- "train_runtime": 145.4848,
6
- "train_samples_per_second": 29.474,
7
- "train_steps_per_second": 0.921
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "total_flos": 3.3230947683690086e+18,
4
+ "train_loss": 0.3864157530798841,
5
+ "train_runtime": 1135.6162,
6
+ "train_samples_per_second": 37.759,
7
+ "train_steps_per_second": 1.18
8
  }
trainer_state.json CHANGED
@@ -1,80 +1,615 @@
1
  {
2
- "best_metric": 1.1399264335632324,
3
- "best_model_checkpoint": "Action_model/checkpoint-100",
4
- "epoch": 1.0,
5
  "eval_steps": 100,
6
- "global_step": 134,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.15,
13
- "grad_norm": 1.509538173675537,
14
- "learning_rate": 8.507462686567164e-05,
15
- "loss": 2.1872,
16
  "step": 20
17
  },
18
  {
19
  "epoch": 0.3,
20
- "grad_norm": 1.6843363046646118,
21
- "learning_rate": 7.014925373134329e-05,
22
- "loss": 1.872,
23
  "step": 40
24
  },
25
  {
26
  "epoch": 0.45,
27
- "grad_norm": 1.891447901725769,
28
- "learning_rate": 5.5223880597014934e-05,
29
- "loss": 1.5872,
30
  "step": 60
31
  },
32
  {
33
  "epoch": 0.6,
34
- "grad_norm": 1.9932177066802979,
35
- "learning_rate": 4.029850746268657e-05,
36
- "loss": 1.3864,
37
  "step": 80
38
  },
39
  {
40
  "epoch": 0.75,
41
- "grad_norm": 1.7128252983093262,
42
- "learning_rate": 2.537313432835821e-05,
43
- "loss": 1.2948,
44
  "step": 100
45
  },
46
  {
47
  "epoch": 0.75,
48
- "eval_accuracy": 0.789103690685413,
49
- "eval_loss": 1.1399264335632324,
50
- "eval_runtime": 11.9209,
51
- "eval_samples_per_second": 47.731,
52
- "eval_steps_per_second": 6.04,
53
  "step": 100
54
  },
55
  {
56
  "epoch": 0.9,
57
- "grad_norm": 2.182009696960449,
58
- "learning_rate": 1.0447761194029851e-05,
59
- "loss": 1.2271,
60
  "step": 120
61
  },
62
  {
63
- "epoch": 1.0,
64
- "step": 134,
65
- "total_flos": 3.3230947683690086e+17,
66
- "train_loss": 1.549544946471257,
67
- "train_runtime": 145.4848,
68
- "train_samples_per_second": 29.474,
69
- "train_steps_per_second": 0.921
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  }
71
  ],
72
  "logging_steps": 20,
73
- "max_steps": 134,
74
  "num_input_tokens_seen": 0,
75
- "num_train_epochs": 1,
76
  "save_steps": 100,
77
- "total_flos": 3.3230947683690086e+17,
78
  "train_batch_size": 32,
79
  "trial_name": null,
80
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.47900134325027466,
3
+ "best_model_checkpoint": "Action_model/checkpoint-800",
4
+ "epoch": 10.0,
5
  "eval_steps": 100,
6
+ "global_step": 1340,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.15,
13
+ "grad_norm": 1.667541265487671,
14
+ "learning_rate": 9.850746268656717e-05,
15
+ "loss": 1.0751,
16
  "step": 20
17
  },
18
  {
19
  "epoch": 0.3,
20
+ "grad_norm": 4.206006050109863,
21
+ "learning_rate": 9.701492537313434e-05,
22
+ "loss": 0.8775,
23
  "step": 40
24
  },
25
  {
26
  "epoch": 0.45,
27
+ "grad_norm": 2.1778831481933594,
28
+ "learning_rate": 9.552238805970149e-05,
29
+ "loss": 0.7614,
30
  "step": 60
31
  },
32
  {
33
  "epoch": 0.6,
34
+ "grad_norm": 2.380641222000122,
35
+ "learning_rate": 9.402985074626867e-05,
36
+ "loss": 0.701,
37
  "step": 80
38
  },
39
  {
40
  "epoch": 0.75,
41
+ "grad_norm": 3.6440467834472656,
42
+ "learning_rate": 9.253731343283582e-05,
43
+ "loss": 0.7766,
44
  "step": 100
45
  },
46
  {
47
  "epoch": 0.75,
48
+ "eval_accuracy": 0.8224956063268892,
49
+ "eval_loss": 0.6780304312705994,
50
+ "eval_runtime": 8.1524,
51
+ "eval_samples_per_second": 69.796,
52
+ "eval_steps_per_second": 8.832,
53
  "step": 100
54
  },
55
  {
56
  "epoch": 0.9,
57
+ "grad_norm": 3.5913617610931396,
58
+ "learning_rate": 9.104477611940299e-05,
59
+ "loss": 0.8058,
60
  "step": 120
61
  },
62
  {
63
+ "epoch": 1.04,
64
+ "grad_norm": 3.761014938354492,
65
+ "learning_rate": 8.955223880597016e-05,
66
+ "loss": 0.7853,
67
+ "step": 140
68
+ },
69
+ {
70
+ "epoch": 1.19,
71
+ "grad_norm": 2.7116057872772217,
72
+ "learning_rate": 8.813432835820896e-05,
73
+ "loss": 0.6584,
74
+ "step": 160
75
+ },
76
+ {
77
+ "epoch": 1.34,
78
+ "grad_norm": 4.109683990478516,
79
+ "learning_rate": 8.664179104477612e-05,
80
+ "loss": 0.6056,
81
+ "step": 180
82
+ },
83
+ {
84
+ "epoch": 1.49,
85
+ "grad_norm": 3.7420246601104736,
86
+ "learning_rate": 8.514925373134329e-05,
87
+ "loss": 0.61,
88
+ "step": 200
89
+ },
90
+ {
91
+ "epoch": 1.49,
92
+ "eval_accuracy": 0.8242530755711776,
93
+ "eval_loss": 0.6279409527778625,
94
+ "eval_runtime": 7.7566,
95
+ "eval_samples_per_second": 73.357,
96
+ "eval_steps_per_second": 9.282,
97
+ "step": 200
98
+ },
99
+ {
100
+ "epoch": 1.64,
101
+ "grad_norm": 4.6456379890441895,
102
+ "learning_rate": 8.365671641791046e-05,
103
+ "loss": 0.6016,
104
+ "step": 220
105
+ },
106
+ {
107
+ "epoch": 1.79,
108
+ "grad_norm": 3.174193859100342,
109
+ "learning_rate": 8.216417910447761e-05,
110
+ "loss": 0.5734,
111
+ "step": 240
112
+ },
113
+ {
114
+ "epoch": 1.94,
115
+ "grad_norm": 4.6657304763793945,
116
+ "learning_rate": 8.067164179104479e-05,
117
+ "loss": 0.5684,
118
+ "step": 260
119
+ },
120
+ {
121
+ "epoch": 2.09,
122
+ "grad_norm": 4.963318347930908,
123
+ "learning_rate": 7.917910447761194e-05,
124
+ "loss": 0.5957,
125
+ "step": 280
126
+ },
127
+ {
128
+ "epoch": 2.24,
129
+ "grad_norm": 5.692253589630127,
130
+ "learning_rate": 7.776119402985074e-05,
131
+ "loss": 0.4734,
132
+ "step": 300
133
+ },
134
+ {
135
+ "epoch": 2.24,
136
+ "eval_accuracy": 0.827768014059754,
137
+ "eval_loss": 0.5593364834785461,
138
+ "eval_runtime": 7.7448,
139
+ "eval_samples_per_second": 73.468,
140
+ "eval_steps_per_second": 9.297,
141
+ "step": 300
142
+ },
143
+ {
144
+ "epoch": 2.39,
145
+ "grad_norm": 3.6985843181610107,
146
+ "learning_rate": 7.626865671641792e-05,
147
+ "loss": 0.4646,
148
+ "step": 320
149
+ },
150
+ {
151
+ "epoch": 2.54,
152
+ "grad_norm": 3.7862443923950195,
153
+ "learning_rate": 7.477611940298508e-05,
154
+ "loss": 0.4568,
155
+ "step": 340
156
+ },
157
+ {
158
+ "epoch": 2.69,
159
+ "grad_norm": 4.695005893707275,
160
+ "learning_rate": 7.328358208955224e-05,
161
+ "loss": 0.4876,
162
+ "step": 360
163
+ },
164
+ {
165
+ "epoch": 2.84,
166
+ "grad_norm": 3.9707813262939453,
167
+ "learning_rate": 7.179104477611941e-05,
168
+ "loss": 0.4723,
169
+ "step": 380
170
+ },
171
+ {
172
+ "epoch": 2.99,
173
+ "grad_norm": 3.133072853088379,
174
+ "learning_rate": 7.029850746268657e-05,
175
+ "loss": 0.5275,
176
+ "step": 400
177
+ },
178
+ {
179
+ "epoch": 2.99,
180
+ "eval_accuracy": 0.8418277680140598,
181
+ "eval_loss": 0.5148488879203796,
182
+ "eval_runtime": 7.8181,
183
+ "eval_samples_per_second": 72.78,
184
+ "eval_steps_per_second": 9.209,
185
+ "step": 400
186
+ },
187
+ {
188
+ "epoch": 3.13,
189
+ "grad_norm": 3.1703858375549316,
190
+ "learning_rate": 6.880597014925374e-05,
191
+ "loss": 0.353,
192
+ "step": 420
193
+ },
194
+ {
195
+ "epoch": 3.28,
196
+ "grad_norm": 3.551959276199341,
197
+ "learning_rate": 6.73134328358209e-05,
198
+ "loss": 0.3559,
199
+ "step": 440
200
+ },
201
+ {
202
+ "epoch": 3.43,
203
+ "grad_norm": 3.8375322818756104,
204
+ "learning_rate": 6.582089552238806e-05,
205
+ "loss": 0.376,
206
+ "step": 460
207
+ },
208
+ {
209
+ "epoch": 3.58,
210
+ "grad_norm": 4.613718032836914,
211
+ "learning_rate": 6.432835820895523e-05,
212
+ "loss": 0.4183,
213
+ "step": 480
214
+ },
215
+ {
216
+ "epoch": 3.73,
217
+ "grad_norm": 9.122322082519531,
218
+ "learning_rate": 6.283582089552239e-05,
219
+ "loss": 0.3767,
220
+ "step": 500
221
+ },
222
+ {
223
+ "epoch": 3.73,
224
+ "eval_accuracy": 0.843585237258348,
225
+ "eval_loss": 0.5129419565200806,
226
+ "eval_runtime": 7.7011,
227
+ "eval_samples_per_second": 73.886,
228
+ "eval_steps_per_second": 9.349,
229
+ "step": 500
230
+ },
231
+ {
232
+ "epoch": 3.88,
233
+ "grad_norm": 1.9917536973953247,
234
+ "learning_rate": 6.134328358208955e-05,
235
+ "loss": 0.3943,
236
+ "step": 520
237
+ },
238
+ {
239
+ "epoch": 4.03,
240
+ "grad_norm": 3.007828712463379,
241
+ "learning_rate": 5.985074626865672e-05,
242
+ "loss": 0.3885,
243
+ "step": 540
244
+ },
245
+ {
246
+ "epoch": 4.18,
247
+ "grad_norm": 6.075244426727295,
248
+ "learning_rate": 5.835820895522388e-05,
249
+ "loss": 0.3312,
250
+ "step": 560
251
+ },
252
+ {
253
+ "epoch": 4.33,
254
+ "grad_norm": 4.8264641761779785,
255
+ "learning_rate": 5.686567164179105e-05,
256
+ "loss": 0.3408,
257
+ "step": 580
258
+ },
259
+ {
260
+ "epoch": 4.48,
261
+ "grad_norm": 2.8609578609466553,
262
+ "learning_rate": 5.537313432835821e-05,
263
+ "loss": 0.3207,
264
+ "step": 600
265
+ },
266
+ {
267
+ "epoch": 4.48,
268
+ "eval_accuracy": 0.8558875219683656,
269
+ "eval_loss": 0.4966126084327698,
270
+ "eval_runtime": 7.6408,
271
+ "eval_samples_per_second": 74.468,
272
+ "eval_steps_per_second": 9.423,
273
+ "step": 600
274
+ },
275
+ {
276
+ "epoch": 4.63,
277
+ "grad_norm": 5.234914302825928,
278
+ "learning_rate": 5.388059701492537e-05,
279
+ "loss": 0.3306,
280
+ "step": 620
281
+ },
282
+ {
283
+ "epoch": 4.78,
284
+ "grad_norm": 4.566553592681885,
285
+ "learning_rate": 5.238805970149254e-05,
286
+ "loss": 0.3532,
287
+ "step": 640
288
+ },
289
+ {
290
+ "epoch": 4.93,
291
+ "grad_norm": 4.077399253845215,
292
+ "learning_rate": 5.08955223880597e-05,
293
+ "loss": 0.3501,
294
+ "step": 660
295
+ },
296
+ {
297
+ "epoch": 5.07,
298
+ "grad_norm": 3.5527923107147217,
299
+ "learning_rate": 4.940298507462687e-05,
300
+ "loss": 0.3147,
301
+ "step": 680
302
+ },
303
+ {
304
+ "epoch": 5.22,
305
+ "grad_norm": 4.944146633148193,
306
+ "learning_rate": 4.7910447761194035e-05,
307
+ "loss": 0.3155,
308
+ "step": 700
309
+ },
310
+ {
311
+ "epoch": 5.22,
312
+ "eval_accuracy": 0.8453427065026362,
313
+ "eval_loss": 0.5251042246818542,
314
+ "eval_runtime": 7.8327,
315
+ "eval_samples_per_second": 72.644,
316
+ "eval_steps_per_second": 9.192,
317
+ "step": 700
318
+ },
319
+ {
320
+ "epoch": 5.37,
321
+ "grad_norm": 2.9990365505218506,
322
+ "learning_rate": 4.6417910447761195e-05,
323
+ "loss": 0.3121,
324
+ "step": 720
325
+ },
326
+ {
327
+ "epoch": 5.52,
328
+ "grad_norm": 1.7021130323410034,
329
+ "learning_rate": 4.492537313432836e-05,
330
+ "loss": 0.3563,
331
+ "step": 740
332
+ },
333
+ {
334
+ "epoch": 5.67,
335
+ "grad_norm": 4.41218376159668,
336
+ "learning_rate": 4.343283582089552e-05,
337
+ "loss": 0.3447,
338
+ "step": 760
339
+ },
340
+ {
341
+ "epoch": 5.82,
342
+ "grad_norm": 2.955658197402954,
343
+ "learning_rate": 4.194029850746269e-05,
344
+ "loss": 0.2839,
345
+ "step": 780
346
+ },
347
+ {
348
+ "epoch": 5.97,
349
+ "grad_norm": 3.0852389335632324,
350
+ "learning_rate": 4.044776119402985e-05,
351
+ "loss": 0.2565,
352
+ "step": 800
353
+ },
354
+ {
355
+ "epoch": 5.97,
356
+ "eval_accuracy": 0.8629173989455184,
357
+ "eval_loss": 0.47900134325027466,
358
+ "eval_runtime": 7.78,
359
+ "eval_samples_per_second": 73.136,
360
+ "eval_steps_per_second": 9.255,
361
+ "step": 800
362
+ },
363
+ {
364
+ "epoch": 6.12,
365
+ "grad_norm": 2.099174976348877,
366
+ "learning_rate": 3.895522388059702e-05,
367
+ "loss": 0.2818,
368
+ "step": 820
369
+ },
370
+ {
371
+ "epoch": 6.27,
372
+ "grad_norm": 3.712127685546875,
373
+ "learning_rate": 3.746268656716418e-05,
374
+ "loss": 0.2444,
375
+ "step": 840
376
+ },
377
+ {
378
+ "epoch": 6.42,
379
+ "grad_norm": 2.1818361282348633,
380
+ "learning_rate": 3.5970149253731346e-05,
381
+ "loss": 0.2418,
382
+ "step": 860
383
+ },
384
+ {
385
+ "epoch": 6.57,
386
+ "grad_norm": 2.211638927459717,
387
+ "learning_rate": 3.447761194029851e-05,
388
+ "loss": 0.2684,
389
+ "step": 880
390
+ },
391
+ {
392
+ "epoch": 6.72,
393
+ "grad_norm": 6.349803924560547,
394
+ "learning_rate": 3.298507462686568e-05,
395
+ "loss": 0.2791,
396
+ "step": 900
397
+ },
398
+ {
399
+ "epoch": 6.72,
400
+ "eval_accuracy": 0.8523725834797891,
401
+ "eval_loss": 0.5110830664634705,
402
+ "eval_runtime": 7.7612,
403
+ "eval_samples_per_second": 73.313,
404
+ "eval_steps_per_second": 9.277,
405
+ "step": 900
406
+ },
407
+ {
408
+ "epoch": 6.87,
409
+ "grad_norm": 4.6033759117126465,
410
+ "learning_rate": 3.149253731343284e-05,
411
+ "loss": 0.2444,
412
+ "step": 920
413
+ },
414
+ {
415
+ "epoch": 7.01,
416
+ "grad_norm": 6.079771995544434,
417
+ "learning_rate": 3e-05,
418
+ "loss": 0.2812,
419
+ "step": 940
420
+ },
421
+ {
422
+ "epoch": 7.16,
423
+ "grad_norm": 3.743011474609375,
424
+ "learning_rate": 2.8507462686567167e-05,
425
+ "loss": 0.183,
426
+ "step": 960
427
+ },
428
+ {
429
+ "epoch": 7.31,
430
+ "grad_norm": 4.840090751647949,
431
+ "learning_rate": 2.701492537313433e-05,
432
+ "loss": 0.2689,
433
+ "step": 980
434
+ },
435
+ {
436
+ "epoch": 7.46,
437
+ "grad_norm": 3.213412284851074,
438
+ "learning_rate": 2.5522388059701496e-05,
439
+ "loss": 0.1987,
440
+ "step": 1000
441
+ },
442
+ {
443
+ "epoch": 7.46,
444
+ "eval_accuracy": 0.8453427065026362,
445
+ "eval_loss": 0.5002422332763672,
446
+ "eval_runtime": 7.6836,
447
+ "eval_samples_per_second": 74.054,
448
+ "eval_steps_per_second": 9.371,
449
+ "step": 1000
450
+ },
451
+ {
452
+ "epoch": 7.61,
453
+ "grad_norm": 2.2559454441070557,
454
+ "learning_rate": 2.402985074626866e-05,
455
+ "loss": 0.2254,
456
+ "step": 1020
457
+ },
458
+ {
459
+ "epoch": 7.76,
460
+ "grad_norm": 4.895073413848877,
461
+ "learning_rate": 2.2537313432835822e-05,
462
+ "loss": 0.283,
463
+ "step": 1040
464
+ },
465
+ {
466
+ "epoch": 7.91,
467
+ "grad_norm": 3.8669703006744385,
468
+ "learning_rate": 2.1044776119402985e-05,
469
+ "loss": 0.281,
470
+ "step": 1060
471
+ },
472
+ {
473
+ "epoch": 8.06,
474
+ "grad_norm": 2.0825252532958984,
475
+ "learning_rate": 1.9552238805970148e-05,
476
+ "loss": 0.1955,
477
+ "step": 1080
478
+ },
479
+ {
480
+ "epoch": 8.21,
481
+ "grad_norm": 1.101592779159546,
482
+ "learning_rate": 1.8059701492537314e-05,
483
+ "loss": 0.2083,
484
+ "step": 1100
485
+ },
486
+ {
487
+ "epoch": 8.21,
488
+ "eval_accuracy": 0.8629173989455184,
489
+ "eval_loss": 0.5034471154212952,
490
+ "eval_runtime": 7.7486,
491
+ "eval_samples_per_second": 73.432,
492
+ "eval_steps_per_second": 9.292,
493
+ "step": 1100
494
+ },
495
+ {
496
+ "epoch": 8.36,
497
+ "grad_norm": 2.6236236095428467,
498
+ "learning_rate": 1.6567164179104477e-05,
499
+ "loss": 0.1409,
500
+ "step": 1120
501
+ },
502
+ {
503
+ "epoch": 8.51,
504
+ "grad_norm": 1.433937668800354,
505
+ "learning_rate": 1.5074626865671642e-05,
506
+ "loss": 0.2434,
507
+ "step": 1140
508
+ },
509
+ {
510
+ "epoch": 8.66,
511
+ "grad_norm": 2.8774006366729736,
512
+ "learning_rate": 1.3582089552238805e-05,
513
+ "loss": 0.2044,
514
+ "step": 1160
515
+ },
516
+ {
517
+ "epoch": 8.81,
518
+ "grad_norm": 4.404654026031494,
519
+ "learning_rate": 1.2089552238805971e-05,
520
+ "loss": 0.2153,
521
+ "step": 1180
522
+ },
523
+ {
524
+ "epoch": 8.96,
525
+ "grad_norm": 4.886945724487305,
526
+ "learning_rate": 1.0597014925373134e-05,
527
+ "loss": 0.2567,
528
+ "step": 1200
529
+ },
530
+ {
531
+ "epoch": 8.96,
532
+ "eval_accuracy": 0.8576449912126538,
533
+ "eval_loss": 0.4995073080062866,
534
+ "eval_runtime": 7.7157,
535
+ "eval_samples_per_second": 73.745,
536
+ "eval_steps_per_second": 9.332,
537
+ "step": 1200
538
+ },
539
+ {
540
+ "epoch": 9.1,
541
+ "grad_norm": 0.4216682016849518,
542
+ "learning_rate": 9.104477611940299e-06,
543
+ "loss": 0.203,
544
+ "step": 1220
545
+ },
546
+ {
547
+ "epoch": 9.25,
548
+ "grad_norm": 4.639057159423828,
549
+ "learning_rate": 7.611940298507463e-06,
550
+ "loss": 0.1934,
551
+ "step": 1240
552
+ },
553
+ {
554
+ "epoch": 9.4,
555
+ "grad_norm": 4.426870822906494,
556
+ "learning_rate": 6.119402985074627e-06,
557
+ "loss": 0.2067,
558
+ "step": 1260
559
+ },
560
+ {
561
+ "epoch": 9.55,
562
+ "grad_norm": 2.948902130126953,
563
+ "learning_rate": 4.626865671641791e-06,
564
+ "loss": 0.2065,
565
+ "step": 1280
566
+ },
567
+ {
568
+ "epoch": 9.7,
569
+ "grad_norm": 2.3631768226623535,
570
+ "learning_rate": 3.134328358208955e-06,
571
+ "loss": 0.2127,
572
+ "step": 1300
573
+ },
574
+ {
575
+ "epoch": 9.7,
576
+ "eval_accuracy": 0.8488576449912126,
577
+ "eval_loss": 0.5034462809562683,
578
+ "eval_runtime": 7.6386,
579
+ "eval_samples_per_second": 74.49,
580
+ "eval_steps_per_second": 9.426,
581
+ "step": 1300
582
+ },
583
+ {
584
+ "epoch": 9.85,
585
+ "grad_norm": 2.909392833709717,
586
+ "learning_rate": 1.6417910447761194e-06,
587
+ "loss": 0.1547,
588
+ "step": 1320
589
+ },
590
+ {
591
+ "epoch": 10.0,
592
+ "grad_norm": 2.5194036960601807,
593
+ "learning_rate": 1.4925373134328358e-07,
594
+ "loss": 0.2161,
595
+ "step": 1340
596
+ },
597
+ {
598
+ "epoch": 10.0,
599
+ "step": 1340,
600
+ "total_flos": 3.3230947683690086e+18,
601
+ "train_loss": 0.3864157530798841,
602
+ "train_runtime": 1135.6162,
603
+ "train_samples_per_second": 37.759,
604
+ "train_steps_per_second": 1.18
605
  }
606
  ],
607
  "logging_steps": 20,
608
+ "max_steps": 1340,
609
  "num_input_tokens_seen": 0,
610
+ "num_train_epochs": 10,
611
  "save_steps": 100,
612
+ "total_flos": 3.3230947683690086e+18,
613
  "train_batch_size": 32,
614
  "trial_name": null,
615
  "trial_params": null