selmamalak commited on
Commit
1f856a9
1 Parent(s): 88479c6

Model save

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. all_results.json +16 -0
  3. eval_results.json +11 -0
  4. train_results.json +8 -0
  5. trainer_state.json +1676 -0
README.md CHANGED
@@ -23,11 +23,11 @@ should probably proofread and complete it, then remove this comment. -->
23
 
24
  This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the medmnist-v2 dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.2590
27
- - Accuracy: 0.9050
28
- - Precision: 0.8524
29
- - Recall: 0.8468
30
- - F1: 0.8468
31
 
32
  ## Model description
33
 
 
23
 
24
  This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the medmnist-v2 dataset.
25
  It achieves the following results on the evaluation set:
26
+ - Loss: 0.4609
27
+ - Accuracy: 0.8240
28
+ - Precision: 0.7895
29
+ - Recall: 0.7821
30
+ - F1: 0.7852
31
 
32
  ## Model description
33
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.8239891267414203,
4
+ "eval_f1": 0.7852027158639473,
5
+ "eval_loss": 0.4609430432319641,
6
+ "eval_precision": 0.7894503286617733,
7
+ "eval_recall": 0.7820860597039324,
8
+ "eval_runtime": 74.5465,
9
+ "eval_samples_per_second": 118.436,
10
+ "eval_steps_per_second": 7.405,
11
+ "total_flos": 1.087396245164114e+19,
12
+ "train_loss": 0.7537981033325195,
13
+ "train_runtime": 2484.6922,
14
+ "train_samples_per_second": 56.104,
15
+ "train_steps_per_second": 0.877
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.8239891267414203,
4
+ "eval_f1": 0.7852027158639473,
5
+ "eval_loss": 0.4609430432319641,
6
+ "eval_precision": 0.7894503286617733,
7
+ "eval_recall": 0.7820860597039324,
8
+ "eval_runtime": 74.5465,
9
+ "eval_samples_per_second": 118.436,
10
+ "eval_steps_per_second": 7.405
11
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 1.087396245164114e+19,
4
+ "train_loss": 0.7537981033325195,
5
+ "train_runtime": 2484.6922,
6
+ "train_samples_per_second": 56.104,
7
+ "train_steps_per_second": 0.877
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1676 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9049755301794453,
3
+ "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-lora-medmnistv2/checkpoint-2180",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2180,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 5.959507465362549,
14
+ "learning_rate": 0.004977064220183487,
15
+ "loss": 1.9585,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.09,
20
+ "grad_norm": 3.8976335525512695,
21
+ "learning_rate": 0.004954128440366973,
22
+ "loss": 1.3768,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.14,
27
+ "grad_norm": 2.9822118282318115,
28
+ "learning_rate": 0.004931192660550459,
29
+ "loss": 1.4236,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.18,
34
+ "grad_norm": 3.5010669231414795,
35
+ "learning_rate": 0.004908256880733945,
36
+ "loss": 1.2595,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.23,
41
+ "grad_norm": 4.538541793823242,
42
+ "learning_rate": 0.004887614678899083,
43
+ "loss": 1.4165,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.28,
48
+ "grad_norm": 3.172377586364746,
49
+ "learning_rate": 0.004864678899082569,
50
+ "loss": 1.1823,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.32,
55
+ "grad_norm": 2.388909101486206,
56
+ "learning_rate": 0.004841743119266055,
57
+ "loss": 1.1399,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.37,
62
+ "grad_norm": 2.9836621284484863,
63
+ "learning_rate": 0.004818807339449541,
64
+ "loss": 1.1484,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.41,
69
+ "grad_norm": 2.9791626930236816,
70
+ "learning_rate": 0.004795871559633028,
71
+ "loss": 1.1652,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.46,
76
+ "grad_norm": 2.8931291103363037,
77
+ "learning_rate": 0.004772935779816514,
78
+ "loss": 1.0614,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.5,
83
+ "grad_norm": 4.281805515289307,
84
+ "learning_rate": 0.00475,
85
+ "loss": 1.1816,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.55,
90
+ "grad_norm": 1.8973846435546875,
91
+ "learning_rate": 0.0047270642201834865,
92
+ "loss": 1.0441,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.6,
97
+ "grad_norm": 2.476250648498535,
98
+ "learning_rate": 0.004704128440366973,
99
+ "loss": 1.1724,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.64,
104
+ "grad_norm": 3.405545711517334,
105
+ "learning_rate": 0.004681192660550459,
106
+ "loss": 1.1089,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.69,
111
+ "grad_norm": 3.545285940170288,
112
+ "learning_rate": 0.0046582568807339445,
113
+ "loss": 0.9702,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.73,
118
+ "grad_norm": 2.000765085220337,
119
+ "learning_rate": 0.004635321100917431,
120
+ "loss": 1.0029,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.78,
125
+ "grad_norm": 3.3316946029663086,
126
+ "learning_rate": 0.004612385321100918,
127
+ "loss": 1.003,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.83,
132
+ "grad_norm": 2.2348740100860596,
133
+ "learning_rate": 0.004589449541284404,
134
+ "loss": 1.0428,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.87,
139
+ "grad_norm": 2.1600568294525146,
140
+ "learning_rate": 0.00456651376146789,
141
+ "loss": 1.0674,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.92,
146
+ "grad_norm": 3.6075286865234375,
147
+ "learning_rate": 0.0045435779816513765,
148
+ "loss": 1.0286,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.96,
153
+ "grad_norm": 1.731745719909668,
154
+ "learning_rate": 0.004520642201834862,
155
+ "loss": 0.9608,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 1.0,
160
+ "eval_accuracy": 0.7765089722675367,
161
+ "eval_f1": 0.7007285514340752,
162
+ "eval_loss": 0.6055155992507935,
163
+ "eval_precision": 0.7235333775207775,
164
+ "eval_recall": 0.7232886628310071,
165
+ "eval_runtime": 20.7254,
166
+ "eval_samples_per_second": 118.309,
167
+ "eval_steps_per_second": 7.43,
168
+ "step": 218
169
+ },
170
+ {
171
+ "epoch": 1.01,
172
+ "grad_norm": 2.186959981918335,
173
+ "learning_rate": 0.004497706422018349,
174
+ "loss": 1.0296,
175
+ "step": 220
176
+ },
177
+ {
178
+ "epoch": 1.06,
179
+ "grad_norm": 2.0718557834625244,
180
+ "learning_rate": 0.0044747706422018346,
181
+ "loss": 0.9602,
182
+ "step": 230
183
+ },
184
+ {
185
+ "epoch": 1.1,
186
+ "grad_norm": 2.098830461502075,
187
+ "learning_rate": 0.004451834862385321,
188
+ "loss": 0.9453,
189
+ "step": 240
190
+ },
191
+ {
192
+ "epoch": 1.15,
193
+ "grad_norm": 2.486630439758301,
194
+ "learning_rate": 0.004428899082568808,
195
+ "loss": 0.9209,
196
+ "step": 250
197
+ },
198
+ {
199
+ "epoch": 1.19,
200
+ "grad_norm": 2.0856552124023438,
201
+ "learning_rate": 0.0044059633027522934,
202
+ "loss": 1.0935,
203
+ "step": 260
204
+ },
205
+ {
206
+ "epoch": 1.24,
207
+ "grad_norm": 1.6093757152557373,
208
+ "learning_rate": 0.00438302752293578,
209
+ "loss": 1.0387,
210
+ "step": 270
211
+ },
212
+ {
213
+ "epoch": 1.28,
214
+ "grad_norm": 1.9845185279846191,
215
+ "learning_rate": 0.004360091743119266,
216
+ "loss": 0.9536,
217
+ "step": 280
218
+ },
219
+ {
220
+ "epoch": 1.33,
221
+ "grad_norm": 2.10725474357605,
222
+ "learning_rate": 0.004337155963302752,
223
+ "loss": 0.8167,
224
+ "step": 290
225
+ },
226
+ {
227
+ "epoch": 1.38,
228
+ "grad_norm": 2.1504321098327637,
229
+ "learning_rate": 0.004314220183486239,
230
+ "loss": 0.9638,
231
+ "step": 300
232
+ },
233
+ {
234
+ "epoch": 1.42,
235
+ "grad_norm": 1.8799842596054077,
236
+ "learning_rate": 0.004291284403669725,
237
+ "loss": 0.9503,
238
+ "step": 310
239
+ },
240
+ {
241
+ "epoch": 1.47,
242
+ "grad_norm": 2.466273069381714,
243
+ "learning_rate": 0.004268348623853211,
244
+ "loss": 0.9487,
245
+ "step": 320
246
+ },
247
+ {
248
+ "epoch": 1.51,
249
+ "grad_norm": 1.635208249092102,
250
+ "learning_rate": 0.004245412844036698,
251
+ "loss": 0.9618,
252
+ "step": 330
253
+ },
254
+ {
255
+ "epoch": 1.56,
256
+ "grad_norm": 1.8513455390930176,
257
+ "learning_rate": 0.0042224770642201835,
258
+ "loss": 0.9647,
259
+ "step": 340
260
+ },
261
+ {
262
+ "epoch": 1.61,
263
+ "grad_norm": 2.562163829803467,
264
+ "learning_rate": 0.004199541284403669,
265
+ "loss": 0.9159,
266
+ "step": 350
267
+ },
268
+ {
269
+ "epoch": 1.65,
270
+ "grad_norm": 3.5535786151885986,
271
+ "learning_rate": 0.004176605504587156,
272
+ "loss": 1.109,
273
+ "step": 360
274
+ },
275
+ {
276
+ "epoch": 1.7,
277
+ "grad_norm": 2.6485819816589355,
278
+ "learning_rate": 0.004153669724770642,
279
+ "loss": 1.0044,
280
+ "step": 370
281
+ },
282
+ {
283
+ "epoch": 1.74,
284
+ "grad_norm": 2.7095954418182373,
285
+ "learning_rate": 0.004130733944954129,
286
+ "loss": 0.9123,
287
+ "step": 380
288
+ },
289
+ {
290
+ "epoch": 1.79,
291
+ "grad_norm": 1.9968432188034058,
292
+ "learning_rate": 0.004107798165137615,
293
+ "loss": 0.9469,
294
+ "step": 390
295
+ },
296
+ {
297
+ "epoch": 1.83,
298
+ "grad_norm": 2.2975969314575195,
299
+ "learning_rate": 0.004084862385321101,
300
+ "loss": 0.9568,
301
+ "step": 400
302
+ },
303
+ {
304
+ "epoch": 1.88,
305
+ "grad_norm": 3.4922454357147217,
306
+ "learning_rate": 0.004061926605504587,
307
+ "loss": 0.9636,
308
+ "step": 410
309
+ },
310
+ {
311
+ "epoch": 1.93,
312
+ "grad_norm": 1.8210103511810303,
313
+ "learning_rate": 0.004038990825688074,
314
+ "loss": 0.9296,
315
+ "step": 420
316
+ },
317
+ {
318
+ "epoch": 1.97,
319
+ "grad_norm": 2.032224655151367,
320
+ "learning_rate": 0.004016055045871559,
321
+ "loss": 0.9984,
322
+ "step": 430
323
+ },
324
+ {
325
+ "epoch": 2.0,
326
+ "eval_accuracy": 0.8066884176182708,
327
+ "eval_f1": 0.7113876383080939,
328
+ "eval_loss": 0.4811672270298004,
329
+ "eval_precision": 0.7265273055775476,
330
+ "eval_recall": 0.7320681182395002,
331
+ "eval_runtime": 20.7162,
332
+ "eval_samples_per_second": 118.362,
333
+ "eval_steps_per_second": 7.434,
334
+ "step": 436
335
+ },
336
+ {
337
+ "epoch": 2.02,
338
+ "grad_norm": 1.7719513177871704,
339
+ "learning_rate": 0.003995412844036697,
340
+ "loss": 0.9865,
341
+ "step": 440
342
+ },
343
+ {
344
+ "epoch": 2.06,
345
+ "grad_norm": 2.115173578262329,
346
+ "learning_rate": 0.003972477064220183,
347
+ "loss": 0.9227,
348
+ "step": 450
349
+ },
350
+ {
351
+ "epoch": 2.11,
352
+ "grad_norm": 1.707400918006897,
353
+ "learning_rate": 0.00394954128440367,
354
+ "loss": 0.9195,
355
+ "step": 460
356
+ },
357
+ {
358
+ "epoch": 2.16,
359
+ "grad_norm": 2.7709805965423584,
360
+ "learning_rate": 0.0039266055045871565,
361
+ "loss": 0.8792,
362
+ "step": 470
363
+ },
364
+ {
365
+ "epoch": 2.2,
366
+ "grad_norm": 2.1106033325195312,
367
+ "learning_rate": 0.003903669724770642,
368
+ "loss": 0.9282,
369
+ "step": 480
370
+ },
371
+ {
372
+ "epoch": 2.25,
373
+ "grad_norm": 2.2281219959259033,
374
+ "learning_rate": 0.0038807339449541283,
375
+ "loss": 0.8242,
376
+ "step": 490
377
+ },
378
+ {
379
+ "epoch": 2.29,
380
+ "grad_norm": 1.9189764261245728,
381
+ "learning_rate": 0.003857798165137615,
382
+ "loss": 0.8428,
383
+ "step": 500
384
+ },
385
+ {
386
+ "epoch": 2.34,
387
+ "grad_norm": 2.04294753074646,
388
+ "learning_rate": 0.003834862385321101,
389
+ "loss": 0.8726,
390
+ "step": 510
391
+ },
392
+ {
393
+ "epoch": 2.39,
394
+ "grad_norm": 2.139575481414795,
395
+ "learning_rate": 0.003811926605504587,
396
+ "loss": 0.9184,
397
+ "step": 520
398
+ },
399
+ {
400
+ "epoch": 2.43,
401
+ "grad_norm": 2.527928113937378,
402
+ "learning_rate": 0.0037889908256880734,
403
+ "loss": 0.934,
404
+ "step": 530
405
+ },
406
+ {
407
+ "epoch": 2.48,
408
+ "grad_norm": 1.9021204710006714,
409
+ "learning_rate": 0.00376605504587156,
410
+ "loss": 0.9117,
411
+ "step": 540
412
+ },
413
+ {
414
+ "epoch": 2.52,
415
+ "grad_norm": 2.099567174911499,
416
+ "learning_rate": 0.003743119266055046,
417
+ "loss": 0.7403,
418
+ "step": 550
419
+ },
420
+ {
421
+ "epoch": 2.57,
422
+ "grad_norm": 1.6857088804244995,
423
+ "learning_rate": 0.003720183486238532,
424
+ "loss": 0.8173,
425
+ "step": 560
426
+ },
427
+ {
428
+ "epoch": 2.61,
429
+ "grad_norm": 2.216789960861206,
430
+ "learning_rate": 0.0036972477064220184,
431
+ "loss": 0.9077,
432
+ "step": 570
433
+ },
434
+ {
435
+ "epoch": 2.66,
436
+ "grad_norm": 1.2876479625701904,
437
+ "learning_rate": 0.0036743119266055045,
438
+ "loss": 0.8218,
439
+ "step": 580
440
+ },
441
+ {
442
+ "epoch": 2.71,
443
+ "grad_norm": 1.7834821939468384,
444
+ "learning_rate": 0.003651376146788991,
445
+ "loss": 0.8954,
446
+ "step": 590
447
+ },
448
+ {
449
+ "epoch": 2.75,
450
+ "grad_norm": 2.3635175228118896,
451
+ "learning_rate": 0.003628440366972477,
452
+ "loss": 0.8818,
453
+ "step": 600
454
+ },
455
+ {
456
+ "epoch": 2.8,
457
+ "grad_norm": 1.9978779554367065,
458
+ "learning_rate": 0.0036055045871559634,
459
+ "loss": 0.9062,
460
+ "step": 610
461
+ },
462
+ {
463
+ "epoch": 2.84,
464
+ "grad_norm": 2.9038476943969727,
465
+ "learning_rate": 0.0035825688073394496,
466
+ "loss": 0.8452,
467
+ "step": 620
468
+ },
469
+ {
470
+ "epoch": 2.89,
471
+ "grad_norm": 1.843595027923584,
472
+ "learning_rate": 0.003559633027522936,
473
+ "loss": 0.8291,
474
+ "step": 630
475
+ },
476
+ {
477
+ "epoch": 2.94,
478
+ "grad_norm": 2.618366241455078,
479
+ "learning_rate": 0.003536697247706422,
480
+ "loss": 0.8661,
481
+ "step": 640
482
+ },
483
+ {
484
+ "epoch": 2.98,
485
+ "grad_norm": 1.8442063331604004,
486
+ "learning_rate": 0.003513761467889908,
487
+ "loss": 0.8265,
488
+ "step": 650
489
+ },
490
+ {
491
+ "epoch": 3.0,
492
+ "eval_accuracy": 0.851957585644372,
493
+ "eval_f1": 0.768301171782241,
494
+ "eval_loss": 0.3725639581680298,
495
+ "eval_precision": 0.800477076178721,
496
+ "eval_recall": 0.771278337679668,
497
+ "eval_runtime": 20.7103,
498
+ "eval_samples_per_second": 118.395,
499
+ "eval_steps_per_second": 7.436,
500
+ "step": 654
501
+ },
502
+ {
503
+ "epoch": 3.03,
504
+ "grad_norm": 2.050394058227539,
505
+ "learning_rate": 0.0034908256880733946,
506
+ "loss": 0.7888,
507
+ "step": 660
508
+ },
509
+ {
510
+ "epoch": 3.07,
511
+ "grad_norm": 2.184720993041992,
512
+ "learning_rate": 0.003467889908256881,
513
+ "loss": 0.8631,
514
+ "step": 670
515
+ },
516
+ {
517
+ "epoch": 3.12,
518
+ "grad_norm": 1.606249213218689,
519
+ "learning_rate": 0.003444954128440367,
520
+ "loss": 0.7822,
521
+ "step": 680
522
+ },
523
+ {
524
+ "epoch": 3.17,
525
+ "grad_norm": 2.3371753692626953,
526
+ "learning_rate": 0.003422018348623853,
527
+ "loss": 0.7497,
528
+ "step": 690
529
+ },
530
+ {
531
+ "epoch": 3.21,
532
+ "grad_norm": 2.1213464736938477,
533
+ "learning_rate": 0.0033990825688073397,
534
+ "loss": 0.8359,
535
+ "step": 700
536
+ },
537
+ {
538
+ "epoch": 3.26,
539
+ "grad_norm": 2.4342410564422607,
540
+ "learning_rate": 0.003376146788990826,
541
+ "loss": 0.8393,
542
+ "step": 710
543
+ },
544
+ {
545
+ "epoch": 3.3,
546
+ "grad_norm": 2.252201557159424,
547
+ "learning_rate": 0.003353211009174312,
548
+ "loss": 0.771,
549
+ "step": 720
550
+ },
551
+ {
552
+ "epoch": 3.35,
553
+ "grad_norm": 2.0991744995117188,
554
+ "learning_rate": 0.003330275229357798,
555
+ "loss": 0.8322,
556
+ "step": 730
557
+ },
558
+ {
559
+ "epoch": 3.39,
560
+ "grad_norm": 1.4995887279510498,
561
+ "learning_rate": 0.0033073394495412847,
562
+ "loss": 0.8652,
563
+ "step": 740
564
+ },
565
+ {
566
+ "epoch": 3.44,
567
+ "grad_norm": 1.8054556846618652,
568
+ "learning_rate": 0.003284403669724771,
569
+ "loss": 0.8594,
570
+ "step": 750
571
+ },
572
+ {
573
+ "epoch": 3.49,
574
+ "grad_norm": 1.846091389656067,
575
+ "learning_rate": 0.0032614678899082566,
576
+ "loss": 0.8507,
577
+ "step": 760
578
+ },
579
+ {
580
+ "epoch": 3.53,
581
+ "grad_norm": 2.486276149749756,
582
+ "learning_rate": 0.003238532110091743,
583
+ "loss": 0.8608,
584
+ "step": 770
585
+ },
586
+ {
587
+ "epoch": 3.58,
588
+ "grad_norm": 1.9299883842468262,
589
+ "learning_rate": 0.0032155963302752293,
590
+ "loss": 0.7887,
591
+ "step": 780
592
+ },
593
+ {
594
+ "epoch": 3.62,
595
+ "grad_norm": 1.7495784759521484,
596
+ "learning_rate": 0.003192660550458716,
597
+ "loss": 0.8364,
598
+ "step": 790
599
+ },
600
+ {
601
+ "epoch": 3.67,
602
+ "grad_norm": 1.4023948907852173,
603
+ "learning_rate": 0.0031697247706422016,
604
+ "loss": 0.8239,
605
+ "step": 800
606
+ },
607
+ {
608
+ "epoch": 3.72,
609
+ "grad_norm": 2.4405996799468994,
610
+ "learning_rate": 0.003146788990825688,
611
+ "loss": 0.7324,
612
+ "step": 810
613
+ },
614
+ {
615
+ "epoch": 3.76,
616
+ "grad_norm": 2.8213984966278076,
617
+ "learning_rate": 0.0031238532110091743,
618
+ "loss": 0.8305,
619
+ "step": 820
620
+ },
621
+ {
622
+ "epoch": 3.81,
623
+ "grad_norm": 1.9884538650512695,
624
+ "learning_rate": 0.003100917431192661,
625
+ "loss": 0.823,
626
+ "step": 830
627
+ },
628
+ {
629
+ "epoch": 3.85,
630
+ "grad_norm": 1.3576688766479492,
631
+ "learning_rate": 0.0030779816513761466,
632
+ "loss": 0.7203,
633
+ "step": 840
634
+ },
635
+ {
636
+ "epoch": 3.9,
637
+ "grad_norm": 1.8440253734588623,
638
+ "learning_rate": 0.0030550458715596328,
639
+ "loss": 0.7564,
640
+ "step": 850
641
+ },
642
+ {
643
+ "epoch": 3.94,
644
+ "grad_norm": 1.383427381515503,
645
+ "learning_rate": 0.0030321100917431194,
646
+ "loss": 0.7679,
647
+ "step": 860
648
+ },
649
+ {
650
+ "epoch": 3.99,
651
+ "grad_norm": 2.3057126998901367,
652
+ "learning_rate": 0.003009174311926606,
653
+ "loss": 0.7938,
654
+ "step": 870
655
+ },
656
+ {
657
+ "epoch": 4.0,
658
+ "eval_accuracy": 0.8507340946166395,
659
+ "eval_f1": 0.7554407269192587,
660
+ "eval_loss": 0.39133650064468384,
661
+ "eval_precision": 0.7811773459124496,
662
+ "eval_recall": 0.7830608562256607,
663
+ "eval_runtime": 20.8094,
664
+ "eval_samples_per_second": 117.831,
665
+ "eval_steps_per_second": 7.4,
666
+ "step": 872
667
+ },
668
+ {
669
+ "epoch": 4.04,
670
+ "grad_norm": 1.3315050601959229,
671
+ "learning_rate": 0.0029862385321100917,
672
+ "loss": 0.7701,
673
+ "step": 880
674
+ },
675
+ {
676
+ "epoch": 4.08,
677
+ "grad_norm": 2.4050934314727783,
678
+ "learning_rate": 0.002963302752293578,
679
+ "loss": 0.7967,
680
+ "step": 890
681
+ },
682
+ {
683
+ "epoch": 4.13,
684
+ "grad_norm": 1.3627427816390991,
685
+ "learning_rate": 0.0029403669724770644,
686
+ "loss": 0.8184,
687
+ "step": 900
688
+ },
689
+ {
690
+ "epoch": 4.17,
691
+ "grad_norm": 2.152087688446045,
692
+ "learning_rate": 0.0029174311926605506,
693
+ "loss": 0.7987,
694
+ "step": 910
695
+ },
696
+ {
697
+ "epoch": 4.22,
698
+ "grad_norm": 2.42413067817688,
699
+ "learning_rate": 0.0028944954128440367,
700
+ "loss": 0.7772,
701
+ "step": 920
702
+ },
703
+ {
704
+ "epoch": 4.27,
705
+ "grad_norm": 1.8017699718475342,
706
+ "learning_rate": 0.002871559633027523,
707
+ "loss": 0.7587,
708
+ "step": 930
709
+ },
710
+ {
711
+ "epoch": 4.31,
712
+ "grad_norm": 1.805237889289856,
713
+ "learning_rate": 0.0028486238532110094,
714
+ "loss": 0.7326,
715
+ "step": 940
716
+ },
717
+ {
718
+ "epoch": 4.36,
719
+ "grad_norm": 2.2268106937408447,
720
+ "learning_rate": 0.0028256880733944956,
721
+ "loss": 0.7293,
722
+ "step": 950
723
+ },
724
+ {
725
+ "epoch": 4.4,
726
+ "grad_norm": 2.386366605758667,
727
+ "learning_rate": 0.0028027522935779813,
728
+ "loss": 0.7396,
729
+ "step": 960
730
+ },
731
+ {
732
+ "epoch": 4.45,
733
+ "grad_norm": 2.0315840244293213,
734
+ "learning_rate": 0.002779816513761468,
735
+ "loss": 0.7131,
736
+ "step": 970
737
+ },
738
+ {
739
+ "epoch": 4.5,
740
+ "grad_norm": 2.1899399757385254,
741
+ "learning_rate": 0.002756880733944954,
742
+ "loss": 0.8073,
743
+ "step": 980
744
+ },
745
+ {
746
+ "epoch": 4.54,
747
+ "grad_norm": 1.614035725593567,
748
+ "learning_rate": 0.0027339449541284406,
749
+ "loss": 0.7168,
750
+ "step": 990
751
+ },
752
+ {
753
+ "epoch": 4.59,
754
+ "grad_norm": 2.4006643295288086,
755
+ "learning_rate": 0.0027110091743119263,
756
+ "loss": 0.7774,
757
+ "step": 1000
758
+ },
759
+ {
760
+ "epoch": 4.63,
761
+ "grad_norm": 2.3257529735565186,
762
+ "learning_rate": 0.002688073394495413,
763
+ "loss": 0.7808,
764
+ "step": 1010
765
+ },
766
+ {
767
+ "epoch": 4.68,
768
+ "grad_norm": 1.6664689779281616,
769
+ "learning_rate": 0.002665137614678899,
770
+ "loss": 0.717,
771
+ "step": 1020
772
+ },
773
+ {
774
+ "epoch": 4.72,
775
+ "grad_norm": 1.7779196500778198,
776
+ "learning_rate": 0.0026422018348623857,
777
+ "loss": 0.7697,
778
+ "step": 1030
779
+ },
780
+ {
781
+ "epoch": 4.77,
782
+ "grad_norm": 1.8458689451217651,
783
+ "learning_rate": 0.0026192660550458714,
784
+ "loss": 0.7384,
785
+ "step": 1040
786
+ },
787
+ {
788
+ "epoch": 4.82,
789
+ "grad_norm": 1.5530970096588135,
790
+ "learning_rate": 0.0025963302752293575,
791
+ "loss": 0.7411,
792
+ "step": 1050
793
+ },
794
+ {
795
+ "epoch": 4.86,
796
+ "grad_norm": 2.550743341445923,
797
+ "learning_rate": 0.002573394495412844,
798
+ "loss": 0.6985,
799
+ "step": 1060
800
+ },
801
+ {
802
+ "epoch": 4.91,
803
+ "grad_norm": 1.284894347190857,
804
+ "learning_rate": 0.0025504587155963303,
805
+ "loss": 0.7961,
806
+ "step": 1070
807
+ },
808
+ {
809
+ "epoch": 4.95,
810
+ "grad_norm": 1.5528652667999268,
811
+ "learning_rate": 0.0025275229357798164,
812
+ "loss": 0.8198,
813
+ "step": 1080
814
+ },
815
+ {
816
+ "epoch": 5.0,
817
+ "grad_norm": 2.2907180786132812,
818
+ "learning_rate": 0.0025045871559633026,
819
+ "loss": 0.8149,
820
+ "step": 1090
821
+ },
822
+ {
823
+ "epoch": 5.0,
824
+ "eval_accuracy": 0.8531810766721044,
825
+ "eval_f1": 0.7701622667658707,
826
+ "eval_loss": 0.3675837218761444,
827
+ "eval_precision": 0.7686624499292936,
828
+ "eval_recall": 0.8001667562361665,
829
+ "eval_runtime": 20.7465,
830
+ "eval_samples_per_second": 118.189,
831
+ "eval_steps_per_second": 7.423,
832
+ "step": 1090
833
+ },
834
+ {
835
+ "epoch": 5.05,
836
+ "grad_norm": 1.3846713304519653,
837
+ "learning_rate": 0.002481651376146789,
838
+ "loss": 0.6938,
839
+ "step": 1100
840
+ },
841
+ {
842
+ "epoch": 5.09,
843
+ "grad_norm": 1.6576237678527832,
844
+ "learning_rate": 0.0024587155963302753,
845
+ "loss": 0.7169,
846
+ "step": 1110
847
+ },
848
+ {
849
+ "epoch": 5.14,
850
+ "grad_norm": 1.8432438373565674,
851
+ "learning_rate": 0.0024357798165137614,
852
+ "loss": 0.7242,
853
+ "step": 1120
854
+ },
855
+ {
856
+ "epoch": 5.18,
857
+ "grad_norm": 1.9799226522445679,
858
+ "learning_rate": 0.002412844036697248,
859
+ "loss": 0.6667,
860
+ "step": 1130
861
+ },
862
+ {
863
+ "epoch": 5.23,
864
+ "grad_norm": 1.92507004737854,
865
+ "learning_rate": 0.002389908256880734,
866
+ "loss": 0.6681,
867
+ "step": 1140
868
+ },
869
+ {
870
+ "epoch": 5.28,
871
+ "grad_norm": 1.4437962770462036,
872
+ "learning_rate": 0.0023669724770642203,
873
+ "loss": 0.6618,
874
+ "step": 1150
875
+ },
876
+ {
877
+ "epoch": 5.32,
878
+ "grad_norm": 1.565990924835205,
879
+ "learning_rate": 0.0023440366972477065,
880
+ "loss": 0.7162,
881
+ "step": 1160
882
+ },
883
+ {
884
+ "epoch": 5.37,
885
+ "grad_norm": 1.7609509229660034,
886
+ "learning_rate": 0.0023211009174311926,
887
+ "loss": 0.6953,
888
+ "step": 1170
889
+ },
890
+ {
891
+ "epoch": 5.41,
892
+ "grad_norm": 1.402076005935669,
893
+ "learning_rate": 0.002298165137614679,
894
+ "loss": 0.7114,
895
+ "step": 1180
896
+ },
897
+ {
898
+ "epoch": 5.46,
899
+ "grad_norm": 1.542944312095642,
900
+ "learning_rate": 0.0022752293577981654,
901
+ "loss": 0.7695,
902
+ "step": 1190
903
+ },
904
+ {
905
+ "epoch": 5.5,
906
+ "grad_norm": 1.3250664472579956,
907
+ "learning_rate": 0.0022522935779816515,
908
+ "loss": 0.6984,
909
+ "step": 1200
910
+ },
911
+ {
912
+ "epoch": 5.55,
913
+ "grad_norm": 1.790968894958496,
914
+ "learning_rate": 0.0022293577981651377,
915
+ "loss": 0.7457,
916
+ "step": 1210
917
+ },
918
+ {
919
+ "epoch": 5.6,
920
+ "grad_norm": 1.8708348274230957,
921
+ "learning_rate": 0.002206422018348624,
922
+ "loss": 0.6854,
923
+ "step": 1220
924
+ },
925
+ {
926
+ "epoch": 5.64,
927
+ "grad_norm": 1.3669894933700562,
928
+ "learning_rate": 0.0021834862385321104,
929
+ "loss": 0.7601,
930
+ "step": 1230
931
+ },
932
+ {
933
+ "epoch": 5.69,
934
+ "grad_norm": 1.6164820194244385,
935
+ "learning_rate": 0.0021605504587155966,
936
+ "loss": 0.7015,
937
+ "step": 1240
938
+ },
939
+ {
940
+ "epoch": 5.73,
941
+ "grad_norm": 2.5344796180725098,
942
+ "learning_rate": 0.0021376146788990827,
943
+ "loss": 0.6816,
944
+ "step": 1250
945
+ },
946
+ {
947
+ "epoch": 5.78,
948
+ "grad_norm": 1.8224860429763794,
949
+ "learning_rate": 0.002114678899082569,
950
+ "loss": 0.7091,
951
+ "step": 1260
952
+ },
953
+ {
954
+ "epoch": 5.83,
955
+ "grad_norm": 2.3349053859710693,
956
+ "learning_rate": 0.002091743119266055,
957
+ "loss": 0.69,
958
+ "step": 1270
959
+ },
960
+ {
961
+ "epoch": 5.87,
962
+ "grad_norm": 1.742497444152832,
963
+ "learning_rate": 0.002068807339449541,
964
+ "loss": 0.6835,
965
+ "step": 1280
966
+ },
967
+ {
968
+ "epoch": 5.92,
969
+ "grad_norm": 1.6536716222763062,
970
+ "learning_rate": 0.0020458715596330277,
971
+ "loss": 0.6827,
972
+ "step": 1290
973
+ },
974
+ {
975
+ "epoch": 5.96,
976
+ "grad_norm": 1.6461354494094849,
977
+ "learning_rate": 0.002022935779816514,
978
+ "loss": 0.6737,
979
+ "step": 1300
980
+ },
981
+ {
982
+ "epoch": 6.0,
983
+ "eval_accuracy": 0.8674551386623165,
984
+ "eval_f1": 0.7933729473887552,
985
+ "eval_loss": 0.3304790258407593,
986
+ "eval_precision": 0.8306122822846135,
987
+ "eval_recall": 0.8116698887283952,
988
+ "eval_runtime": 20.7895,
989
+ "eval_samples_per_second": 117.944,
990
+ "eval_steps_per_second": 7.408,
991
+ "step": 1308
992
+ },
993
+ {
994
+ "epoch": 6.01,
995
+ "grad_norm": 1.2140992879867554,
996
+ "learning_rate": 0.002,
997
+ "loss": 0.6921,
998
+ "step": 1310
999
+ },
1000
+ {
1001
+ "epoch": 6.06,
1002
+ "grad_norm": 2.1813745498657227,
1003
+ "learning_rate": 0.001977064220183486,
1004
+ "loss": 0.7078,
1005
+ "step": 1320
1006
+ },
1007
+ {
1008
+ "epoch": 6.1,
1009
+ "grad_norm": 1.2994489669799805,
1010
+ "learning_rate": 0.0019541284403669728,
1011
+ "loss": 0.6949,
1012
+ "step": 1330
1013
+ },
1014
+ {
1015
+ "epoch": 6.15,
1016
+ "grad_norm": 1.4426566362380981,
1017
+ "learning_rate": 0.0019311926605504587,
1018
+ "loss": 0.6685,
1019
+ "step": 1340
1020
+ },
1021
+ {
1022
+ "epoch": 6.19,
1023
+ "grad_norm": 1.5542079210281372,
1024
+ "learning_rate": 0.001908256880733945,
1025
+ "loss": 0.6823,
1026
+ "step": 1350
1027
+ },
1028
+ {
1029
+ "epoch": 6.24,
1030
+ "grad_norm": 1.5096594095230103,
1031
+ "learning_rate": 0.0018853211009174312,
1032
+ "loss": 0.6203,
1033
+ "step": 1360
1034
+ },
1035
+ {
1036
+ "epoch": 6.28,
1037
+ "grad_norm": 2.132112979888916,
1038
+ "learning_rate": 0.0018623853211009176,
1039
+ "loss": 0.6942,
1040
+ "step": 1370
1041
+ },
1042
+ {
1043
+ "epoch": 6.33,
1044
+ "grad_norm": 2.1632845401763916,
1045
+ "learning_rate": 0.0018394495412844037,
1046
+ "loss": 0.5899,
1047
+ "step": 1380
1048
+ },
1049
+ {
1050
+ "epoch": 6.38,
1051
+ "grad_norm": 1.6782176494598389,
1052
+ "learning_rate": 0.0018165137614678901,
1053
+ "loss": 0.6316,
1054
+ "step": 1390
1055
+ },
1056
+ {
1057
+ "epoch": 6.42,
1058
+ "grad_norm": 1.1974135637283325,
1059
+ "learning_rate": 0.001793577981651376,
1060
+ "loss": 0.609,
1061
+ "step": 1400
1062
+ },
1063
+ {
1064
+ "epoch": 6.47,
1065
+ "grad_norm": 1.8140075206756592,
1066
+ "learning_rate": 0.0017706422018348624,
1067
+ "loss": 0.65,
1068
+ "step": 1410
1069
+ },
1070
+ {
1071
+ "epoch": 6.51,
1072
+ "grad_norm": 1.5135620832443237,
1073
+ "learning_rate": 0.0017477064220183486,
1074
+ "loss": 0.6201,
1075
+ "step": 1420
1076
+ },
1077
+ {
1078
+ "epoch": 6.56,
1079
+ "grad_norm": 1.6838016510009766,
1080
+ "learning_rate": 0.001724770642201835,
1081
+ "loss": 0.6044,
1082
+ "step": 1430
1083
+ },
1084
+ {
1085
+ "epoch": 6.61,
1086
+ "grad_norm": 1.55550217628479,
1087
+ "learning_rate": 0.001701834862385321,
1088
+ "loss": 0.6753,
1089
+ "step": 1440
1090
+ },
1091
+ {
1092
+ "epoch": 6.65,
1093
+ "grad_norm": 1.8122529983520508,
1094
+ "learning_rate": 0.0016788990825688074,
1095
+ "loss": 0.6608,
1096
+ "step": 1450
1097
+ },
1098
+ {
1099
+ "epoch": 6.7,
1100
+ "grad_norm": 2.207045555114746,
1101
+ "learning_rate": 0.0016559633027522936,
1102
+ "loss": 0.6132,
1103
+ "step": 1460
1104
+ },
1105
+ {
1106
+ "epoch": 6.74,
1107
+ "grad_norm": 0.9892495274543762,
1108
+ "learning_rate": 0.00163302752293578,
1109
+ "loss": 0.6177,
1110
+ "step": 1470
1111
+ },
1112
+ {
1113
+ "epoch": 6.79,
1114
+ "grad_norm": 2.4809529781341553,
1115
+ "learning_rate": 0.0016100917431192661,
1116
+ "loss": 0.5607,
1117
+ "step": 1480
1118
+ },
1119
+ {
1120
+ "epoch": 6.83,
1121
+ "grad_norm": 1.430293083190918,
1122
+ "learning_rate": 0.0015871559633027525,
1123
+ "loss": 0.6822,
1124
+ "step": 1490
1125
+ },
1126
+ {
1127
+ "epoch": 6.88,
1128
+ "grad_norm": 1.6523278951644897,
1129
+ "learning_rate": 0.0015642201834862384,
1130
+ "loss": 0.6486,
1131
+ "step": 1500
1132
+ },
1133
+ {
1134
+ "epoch": 6.93,
1135
+ "grad_norm": 1.5746197700500488,
1136
+ "learning_rate": 0.0015412844036697248,
1137
+ "loss": 0.5902,
1138
+ "step": 1510
1139
+ },
1140
+ {
1141
+ "epoch": 6.97,
1142
+ "grad_norm": 1.5833261013031006,
1143
+ "learning_rate": 0.001518348623853211,
1144
+ "loss": 0.5695,
1145
+ "step": 1520
1146
+ },
1147
+ {
1148
+ "epoch": 7.0,
1149
+ "eval_accuracy": 0.9029363784665579,
1150
+ "eval_f1": 0.8321123007962286,
1151
+ "eval_loss": 0.24805299937725067,
1152
+ "eval_precision": 0.8545669814728453,
1153
+ "eval_recall": 0.8469225407396054,
1154
+ "eval_runtime": 20.7317,
1155
+ "eval_samples_per_second": 118.273,
1156
+ "eval_steps_per_second": 7.428,
1157
+ "step": 1526
1158
+ },
1159
+ {
1160
+ "epoch": 7.02,
1161
+ "grad_norm": 1.8044548034667969,
1162
+ "learning_rate": 0.0014954128440366973,
1163
+ "loss": 0.5888,
1164
+ "step": 1530
1165
+ },
1166
+ {
1167
+ "epoch": 7.06,
1168
+ "grad_norm": 1.9052773714065552,
1169
+ "learning_rate": 0.0014724770642201835,
1170
+ "loss": 0.5968,
1171
+ "step": 1540
1172
+ },
1173
+ {
1174
+ "epoch": 7.11,
1175
+ "grad_norm": 1.835716962814331,
1176
+ "learning_rate": 0.0014495412844036698,
1177
+ "loss": 0.642,
1178
+ "step": 1550
1179
+ },
1180
+ {
1181
+ "epoch": 7.16,
1182
+ "grad_norm": 1.3683079481124878,
1183
+ "learning_rate": 0.001426605504587156,
1184
+ "loss": 0.6627,
1185
+ "step": 1560
1186
+ },
1187
+ {
1188
+ "epoch": 7.2,
1189
+ "grad_norm": 1.9506031274795532,
1190
+ "learning_rate": 0.0014036697247706423,
1191
+ "loss": 0.6054,
1192
+ "step": 1570
1193
+ },
1194
+ {
1195
+ "epoch": 7.25,
1196
+ "grad_norm": 1.300554871559143,
1197
+ "learning_rate": 0.0013807339449541285,
1198
+ "loss": 0.6375,
1199
+ "step": 1580
1200
+ },
1201
+ {
1202
+ "epoch": 7.29,
1203
+ "grad_norm": 2.0933167934417725,
1204
+ "learning_rate": 0.0013577981651376149,
1205
+ "loss": 0.5603,
1206
+ "step": 1590
1207
+ },
1208
+ {
1209
+ "epoch": 7.34,
1210
+ "grad_norm": 1.0951093435287476,
1211
+ "learning_rate": 0.0013348623853211008,
1212
+ "loss": 0.5836,
1213
+ "step": 1600
1214
+ },
1215
+ {
1216
+ "epoch": 7.39,
1217
+ "grad_norm": 1.186511516571045,
1218
+ "learning_rate": 0.0013119266055045872,
1219
+ "loss": 0.5877,
1220
+ "step": 1610
1221
+ },
1222
+ {
1223
+ "epoch": 7.43,
1224
+ "grad_norm": 1.5988391637802124,
1225
+ "learning_rate": 0.0012889908256880733,
1226
+ "loss": 0.5868,
1227
+ "step": 1620
1228
+ },
1229
+ {
1230
+ "epoch": 7.48,
1231
+ "grad_norm": 2.0407028198242188,
1232
+ "learning_rate": 0.0012660550458715597,
1233
+ "loss": 0.564,
1234
+ "step": 1630
1235
+ },
1236
+ {
1237
+ "epoch": 7.52,
1238
+ "grad_norm": 1.4676613807678223,
1239
+ "learning_rate": 0.001243119266055046,
1240
+ "loss": 0.6205,
1241
+ "step": 1640
1242
+ },
1243
+ {
1244
+ "epoch": 7.57,
1245
+ "grad_norm": 1.1794471740722656,
1246
+ "learning_rate": 0.0012201834862385322,
1247
+ "loss": 0.581,
1248
+ "step": 1650
1249
+ },
1250
+ {
1251
+ "epoch": 7.61,
1252
+ "grad_norm": 1.7204222679138184,
1253
+ "learning_rate": 0.0011972477064220183,
1254
+ "loss": 0.6433,
1255
+ "step": 1660
1256
+ },
1257
+ {
1258
+ "epoch": 7.66,
1259
+ "grad_norm": 1.7347933053970337,
1260
+ "learning_rate": 0.0011743119266055047,
1261
+ "loss": 0.6132,
1262
+ "step": 1670
1263
+ },
1264
+ {
1265
+ "epoch": 7.71,
1266
+ "grad_norm": 1.0963069200515747,
1267
+ "learning_rate": 0.0011513761467889909,
1268
+ "loss": 0.5961,
1269
+ "step": 1680
1270
+ },
1271
+ {
1272
+ "epoch": 7.75,
1273
+ "grad_norm": 1.0383723974227905,
1274
+ "learning_rate": 0.0011284403669724772,
1275
+ "loss": 0.5934,
1276
+ "step": 1690
1277
+ },
1278
+ {
1279
+ "epoch": 7.8,
1280
+ "grad_norm": 1.314132809638977,
1281
+ "learning_rate": 0.0011055045871559634,
1282
+ "loss": 0.5667,
1283
+ "step": 1700
1284
+ },
1285
+ {
1286
+ "epoch": 7.84,
1287
+ "grad_norm": 1.8448032140731812,
1288
+ "learning_rate": 0.0010825688073394495,
1289
+ "loss": 0.5999,
1290
+ "step": 1710
1291
+ },
1292
+ {
1293
+ "epoch": 7.89,
1294
+ "grad_norm": 1.187971591949463,
1295
+ "learning_rate": 0.001059633027522936,
1296
+ "loss": 0.5668,
1297
+ "step": 1720
1298
+ },
1299
+ {
1300
+ "epoch": 7.94,
1301
+ "grad_norm": 1.451027512550354,
1302
+ "learning_rate": 0.001036697247706422,
1303
+ "loss": 0.5928,
1304
+ "step": 1730
1305
+ },
1306
+ {
1307
+ "epoch": 7.98,
1308
+ "grad_norm": 1.5274406671524048,
1309
+ "learning_rate": 0.0010137614678899084,
1310
+ "loss": 0.5857,
1311
+ "step": 1740
1312
+ },
1313
+ {
1314
+ "epoch": 8.0,
1315
+ "eval_accuracy": 0.8923327895595432,
1316
+ "eval_f1": 0.8339907958679574,
1317
+ "eval_loss": 0.2911706566810608,
1318
+ "eval_precision": 0.8463533280759077,
1319
+ "eval_recall": 0.8356417778568457,
1320
+ "eval_runtime": 20.8398,
1321
+ "eval_samples_per_second": 117.66,
1322
+ "eval_steps_per_second": 7.39,
1323
+ "step": 1744
1324
+ },
1325
+ {
1326
+ "epoch": 8.03,
1327
+ "grad_norm": 1.254504919052124,
1328
+ "learning_rate": 0.0009908256880733946,
1329
+ "loss": 0.5059,
1330
+ "step": 1750
1331
+ },
1332
+ {
1333
+ "epoch": 8.07,
1334
+ "grad_norm": 1.3762636184692383,
1335
+ "learning_rate": 0.0009678899082568808,
1336
+ "loss": 0.578,
1337
+ "step": 1760
1338
+ },
1339
+ {
1340
+ "epoch": 8.12,
1341
+ "grad_norm": 1.472004771232605,
1342
+ "learning_rate": 0.0009449541284403671,
1343
+ "loss": 0.5216,
1344
+ "step": 1770
1345
+ },
1346
+ {
1347
+ "epoch": 8.17,
1348
+ "grad_norm": 1.5876396894454956,
1349
+ "learning_rate": 0.0009220183486238532,
1350
+ "loss": 0.5689,
1351
+ "step": 1780
1352
+ },
1353
+ {
1354
+ "epoch": 8.21,
1355
+ "grad_norm": 1.2409037351608276,
1356
+ "learning_rate": 0.0008990825688073395,
1357
+ "loss": 0.5571,
1358
+ "step": 1790
1359
+ },
1360
+ {
1361
+ "epoch": 8.26,
1362
+ "grad_norm": 1.2082581520080566,
1363
+ "learning_rate": 0.0008761467889908258,
1364
+ "loss": 0.5809,
1365
+ "step": 1800
1366
+ },
1367
+ {
1368
+ "epoch": 8.3,
1369
+ "grad_norm": 1.7171647548675537,
1370
+ "learning_rate": 0.000853211009174312,
1371
+ "loss": 0.5626,
1372
+ "step": 1810
1373
+ },
1374
+ {
1375
+ "epoch": 8.35,
1376
+ "grad_norm": 1.3834128379821777,
1377
+ "learning_rate": 0.0008302752293577983,
1378
+ "loss": 0.5362,
1379
+ "step": 1820
1380
+ },
1381
+ {
1382
+ "epoch": 8.39,
1383
+ "grad_norm": 1.424574375152588,
1384
+ "learning_rate": 0.0008073394495412844,
1385
+ "loss": 0.5418,
1386
+ "step": 1830
1387
+ },
1388
+ {
1389
+ "epoch": 8.44,
1390
+ "grad_norm": 1.5661699771881104,
1391
+ "learning_rate": 0.0007844036697247707,
1392
+ "loss": 0.5609,
1393
+ "step": 1840
1394
+ },
1395
+ {
1396
+ "epoch": 8.49,
1397
+ "grad_norm": 1.9551769495010376,
1398
+ "learning_rate": 0.0007614678899082569,
1399
+ "loss": 0.564,
1400
+ "step": 1850
1401
+ },
1402
+ {
1403
+ "epoch": 8.53,
1404
+ "grad_norm": 1.084270715713501,
1405
+ "learning_rate": 0.0007385321100917432,
1406
+ "loss": 0.5121,
1407
+ "step": 1860
1408
+ },
1409
+ {
1410
+ "epoch": 8.58,
1411
+ "grad_norm": 1.446973204612732,
1412
+ "learning_rate": 0.0007155963302752295,
1413
+ "loss": 0.569,
1414
+ "step": 1870
1415
+ },
1416
+ {
1417
+ "epoch": 8.62,
1418
+ "grad_norm": 1.3539941310882568,
1419
+ "learning_rate": 0.0006926605504587156,
1420
+ "loss": 0.525,
1421
+ "step": 1880
1422
+ },
1423
+ {
1424
+ "epoch": 8.67,
1425
+ "grad_norm": 1.413223147392273,
1426
+ "learning_rate": 0.0006697247706422019,
1427
+ "loss": 0.4403,
1428
+ "step": 1890
1429
+ },
1430
+ {
1431
+ "epoch": 8.72,
1432
+ "grad_norm": 1.3614115715026855,
1433
+ "learning_rate": 0.0006467889908256881,
1434
+ "loss": 0.553,
1435
+ "step": 1900
1436
+ },
1437
+ {
1438
+ "epoch": 8.76,
1439
+ "grad_norm": 1.2185453176498413,
1440
+ "learning_rate": 0.0006238532110091744,
1441
+ "loss": 0.5498,
1442
+ "step": 1910
1443
+ },
1444
+ {
1445
+ "epoch": 8.81,
1446
+ "grad_norm": 1.3884397745132446,
1447
+ "learning_rate": 0.0006009174311926606,
1448
+ "loss": 0.5092,
1449
+ "step": 1920
1450
+ },
1451
+ {
1452
+ "epoch": 8.85,
1453
+ "grad_norm": 1.2725589275360107,
1454
+ "learning_rate": 0.0005779816513761468,
1455
+ "loss": 0.5695,
1456
+ "step": 1930
1457
+ },
1458
+ {
1459
+ "epoch": 8.9,
1460
+ "grad_norm": 1.2434947490692139,
1461
+ "learning_rate": 0.000555045871559633,
1462
+ "loss": 0.4998,
1463
+ "step": 1940
1464
+ },
1465
+ {
1466
+ "epoch": 8.94,
1467
+ "grad_norm": 1.378146767616272,
1468
+ "learning_rate": 0.0005321100917431193,
1469
+ "loss": 0.5091,
1470
+ "step": 1950
1471
+ },
1472
+ {
1473
+ "epoch": 8.99,
1474
+ "grad_norm": 1.3200100660324097,
1475
+ "learning_rate": 0.0005091743119266056,
1476
+ "loss": 0.4834,
1477
+ "step": 1960
1478
+ },
1479
+ {
1480
+ "epoch": 9.0,
1481
+ "eval_accuracy": 0.899673735725938,
1482
+ "eval_f1": 0.8285783762787183,
1483
+ "eval_loss": 0.2657569944858551,
1484
+ "eval_precision": 0.8428024691807685,
1485
+ "eval_recall": 0.8409794358062922,
1486
+ "eval_runtime": 20.7116,
1487
+ "eval_samples_per_second": 118.388,
1488
+ "eval_steps_per_second": 7.435,
1489
+ "step": 1962
1490
+ },
1491
+ {
1492
+ "epoch": 9.04,
1493
+ "grad_norm": 1.1076021194458008,
1494
+ "learning_rate": 0.0004862385321100918,
1495
+ "loss": 0.5164,
1496
+ "step": 1970
1497
+ },
1498
+ {
1499
+ "epoch": 9.08,
1500
+ "grad_norm": 1.50495445728302,
1501
+ "learning_rate": 0.00046330275229357804,
1502
+ "loss": 0.4388,
1503
+ "step": 1980
1504
+ },
1505
+ {
1506
+ "epoch": 9.13,
1507
+ "grad_norm": 1.4007256031036377,
1508
+ "learning_rate": 0.00044036697247706424,
1509
+ "loss": 0.4761,
1510
+ "step": 1990
1511
+ },
1512
+ {
1513
+ "epoch": 9.17,
1514
+ "grad_norm": 1.226333737373352,
1515
+ "learning_rate": 0.0004174311926605505,
1516
+ "loss": 0.4861,
1517
+ "step": 2000
1518
+ },
1519
+ {
1520
+ "epoch": 9.22,
1521
+ "grad_norm": 1.937953233718872,
1522
+ "learning_rate": 0.0003944954128440367,
1523
+ "loss": 0.4604,
1524
+ "step": 2010
1525
+ },
1526
+ {
1527
+ "epoch": 9.27,
1528
+ "grad_norm": 1.35695219039917,
1529
+ "learning_rate": 0.00037155963302752296,
1530
+ "loss": 0.4633,
1531
+ "step": 2020
1532
+ },
1533
+ {
1534
+ "epoch": 9.31,
1535
+ "grad_norm": 1.521087884902954,
1536
+ "learning_rate": 0.0003486238532110092,
1537
+ "loss": 0.4512,
1538
+ "step": 2030
1539
+ },
1540
+ {
1541
+ "epoch": 9.36,
1542
+ "grad_norm": 1.4338667392730713,
1543
+ "learning_rate": 0.0003256880733944954,
1544
+ "loss": 0.5439,
1545
+ "step": 2040
1546
+ },
1547
+ {
1548
+ "epoch": 9.4,
1549
+ "grad_norm": 1.7897557020187378,
1550
+ "learning_rate": 0.0003027522935779817,
1551
+ "loss": 0.5278,
1552
+ "step": 2050
1553
+ },
1554
+ {
1555
+ "epoch": 9.45,
1556
+ "grad_norm": 1.0933929681777954,
1557
+ "learning_rate": 0.0002798165137614679,
1558
+ "loss": 0.4592,
1559
+ "step": 2060
1560
+ },
1561
+ {
1562
+ "epoch": 9.5,
1563
+ "grad_norm": 1.2754806280136108,
1564
+ "learning_rate": 0.00025688073394495415,
1565
+ "loss": 0.476,
1566
+ "step": 2070
1567
+ },
1568
+ {
1569
+ "epoch": 9.54,
1570
+ "grad_norm": 1.724406361579895,
1571
+ "learning_rate": 0.00023394495412844038,
1572
+ "loss": 0.4963,
1573
+ "step": 2080
1574
+ },
1575
+ {
1576
+ "epoch": 9.59,
1577
+ "grad_norm": 1.5604366064071655,
1578
+ "learning_rate": 0.0002110091743119266,
1579
+ "loss": 0.4926,
1580
+ "step": 2090
1581
+ },
1582
+ {
1583
+ "epoch": 9.63,
1584
+ "grad_norm": 1.2408415079116821,
1585
+ "learning_rate": 0.00018807339449541287,
1586
+ "loss": 0.4954,
1587
+ "step": 2100
1588
+ },
1589
+ {
1590
+ "epoch": 9.68,
1591
+ "grad_norm": 0.8950926065444946,
1592
+ "learning_rate": 0.0001651376146788991,
1593
+ "loss": 0.4444,
1594
+ "step": 2110
1595
+ },
1596
+ {
1597
+ "epoch": 9.72,
1598
+ "grad_norm": 1.2199152708053589,
1599
+ "learning_rate": 0.00014220183486238534,
1600
+ "loss": 0.4606,
1601
+ "step": 2120
1602
+ },
1603
+ {
1604
+ "epoch": 9.77,
1605
+ "grad_norm": 1.1516410112380981,
1606
+ "learning_rate": 0.00011926605504587157,
1607
+ "loss": 0.4691,
1608
+ "step": 2130
1609
+ },
1610
+ {
1611
+ "epoch": 9.82,
1612
+ "grad_norm": 2.192310333251953,
1613
+ "learning_rate": 9.63302752293578e-05,
1614
+ "loss": 0.5306,
1615
+ "step": 2140
1616
+ },
1617
+ {
1618
+ "epoch": 9.86,
1619
+ "grad_norm": 1.2649255990982056,
1620
+ "learning_rate": 7.339449541284404e-05,
1621
+ "loss": 0.5238,
1622
+ "step": 2150
1623
+ },
1624
+ {
1625
+ "epoch": 9.91,
1626
+ "grad_norm": 1.5681147575378418,
1627
+ "learning_rate": 5.0458715596330276e-05,
1628
+ "loss": 0.4631,
1629
+ "step": 2160
1630
+ },
1631
+ {
1632
+ "epoch": 9.95,
1633
+ "grad_norm": 1.3230477571487427,
1634
+ "learning_rate": 2.7522935779816515e-05,
1635
+ "loss": 0.4716,
1636
+ "step": 2170
1637
+ },
1638
+ {
1639
+ "epoch": 10.0,
1640
+ "grad_norm": 1.0949994325637817,
1641
+ "learning_rate": 4.587155963302753e-06,
1642
+ "loss": 0.5287,
1643
+ "step": 2180
1644
+ },
1645
+ {
1646
+ "epoch": 10.0,
1647
+ "eval_accuracy": 0.9049755301794453,
1648
+ "eval_f1": 0.8468363122524573,
1649
+ "eval_loss": 0.2590215504169464,
1650
+ "eval_precision": 0.8523921546408058,
1651
+ "eval_recall": 0.8468399455092634,
1652
+ "eval_runtime": 20.6801,
1653
+ "eval_samples_per_second": 118.568,
1654
+ "eval_steps_per_second": 7.447,
1655
+ "step": 2180
1656
+ },
1657
+ {
1658
+ "epoch": 10.0,
1659
+ "step": 2180,
1660
+ "total_flos": 1.087396245164114e+19,
1661
+ "train_loss": 0.7537981033325195,
1662
+ "train_runtime": 2484.6922,
1663
+ "train_samples_per_second": 56.104,
1664
+ "train_steps_per_second": 0.877
1665
+ }
1666
+ ],
1667
+ "logging_steps": 10,
1668
+ "max_steps": 2180,
1669
+ "num_input_tokens_seen": 0,
1670
+ "num_train_epochs": 10,
1671
+ "save_steps": 500,
1672
+ "total_flos": 1.087396245164114e+19,
1673
+ "train_batch_size": 16,
1674
+ "trial_name": null,
1675
+ "trial_params": null
1676
+ }