nemik commited on
Commit
efa1f05
1 Parent(s): 25feb25

frostsolutions/frost-vision-v2-google_vit-base-patch16-224-v2024-11-11

Browse files
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.9411971830985916
30
  - name: F1
31
  type: f1
32
- value: 0.8474885844748858
33
  - name: Precision
34
  type: precision
35
- value: 0.836036036036036
36
  - name: Recall
37
  type: recall
38
- value: 0.8592592592592593
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
45
 
46
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the webdataset dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.1712
49
- - Accuracy: 0.9412
50
- - F1: 0.8475
51
- - Precision: 0.8360
52
- - Recall: 0.8593
53
 
54
  ## Model description
55
 
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.9320422535211268
30
  - name: F1
31
  type: f1
32
+ value: 0.8224471021159153
33
  - name: Precision
34
  type: precision
35
+ value: 0.8171846435100548
36
  - name: Recall
37
  type: recall
38
+ value: 0.8277777777777777
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
45
 
46
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the webdataset dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.1658
49
+ - Accuracy: 0.9320
50
+ - F1: 0.8224
51
+ - Precision: 0.8172
52
+ - Recall: 0.8278
53
 
54
  ## Model description
55
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.9320422535211268,
4
+ "eval_f1": 0.8224471021159153,
5
+ "eval_loss": 0.16577637195587158,
6
+ "eval_precision": 0.8171846435100548,
7
+ "eval_recall": 0.8277777777777777,
8
+ "eval_runtime": 3.2818,
9
+ "eval_samples_per_second": 86.538,
10
+ "eval_steps_per_second": 10.97,
11
+ "total_flos": 2.6364665116584346e+18,
12
+ "train_loss": 0.09721689578932775,
13
+ "train_runtime": 614.0464,
14
+ "train_samples_per_second": 55.403,
15
+ "train_steps_per_second": 3.469
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.9320422535211268,
4
+ "eval_f1": 0.8224471021159153,
5
+ "eval_loss": 0.16577637195587158,
6
+ "eval_precision": 0.8171846435100548,
7
+ "eval_recall": 0.8277777777777777,
8
+ "eval_runtime": 3.2818,
9
+ "eval_samples_per_second": 86.538,
10
+ "eval_steps_per_second": 10.97
11
+ }
runs/Nov11_16-10-55_5c04057bead0/events.out.tfevents.1731342120.5c04057bead0.355.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33d145e196659509ccc7b08b356b0a20aebe6dee023d915c14dbffe1dcbaf3f
3
+ size 560
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "total_flos": 2.6364665116584346e+18,
4
+ "train_loss": 0.09721689578932775,
5
+ "train_runtime": 614.0464,
6
+ "train_samples_per_second": 55.403,
7
+ "train_steps_per_second": 3.469
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.16577637195587158,
3
+ "best_model_checkpoint": "frostsolutions/frost-vision-v2-google_vit-base-patch16-224-v2024-11-11/checkpoint-500",
4
+ "epoch": 30.0,
5
+ "eval_steps": 100,
6
+ "global_step": 2130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14084507042253522,
13
+ "grad_norm": 2.1837456226348877,
14
+ "learning_rate": 2.3474178403755868e-06,
15
+ "loss": 0.7828,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.28169014084507044,
20
+ "grad_norm": 2.2785279750823975,
21
+ "learning_rate": 4.6948356807511736e-06,
22
+ "loss": 0.7397,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.4225352112676056,
27
+ "grad_norm": 1.786941409111023,
28
+ "learning_rate": 7.042253521126762e-06,
29
+ "loss": 0.6827,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.5633802816901409,
34
+ "grad_norm": 1.804363489151001,
35
+ "learning_rate": 9.389671361502347e-06,
36
+ "loss": 0.6092,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.704225352112676,
41
+ "grad_norm": 1.2980760335922241,
42
+ "learning_rate": 1.1737089201877934e-05,
43
+ "loss": 0.5265,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.8450704225352113,
48
+ "grad_norm": 1.0985078811645508,
49
+ "learning_rate": 1.4084507042253523e-05,
50
+ "loss": 0.461,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.9859154929577465,
55
+ "grad_norm": 0.966576099395752,
56
+ "learning_rate": 1.643192488262911e-05,
57
+ "loss": 0.4112,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.1267605633802817,
62
+ "grad_norm": 1.0513771772384644,
63
+ "learning_rate": 1.8779342723004694e-05,
64
+ "loss": 0.3653,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.267605633802817,
69
+ "grad_norm": 0.9769287109375,
70
+ "learning_rate": 2.112676056338028e-05,
71
+ "loss": 0.3547,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.408450704225352,
76
+ "grad_norm": 0.9427245259284973,
77
+ "learning_rate": 2.347417840375587e-05,
78
+ "loss": 0.3127,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.408450704225352,
83
+ "eval_accuracy": 0.8940140845070422,
84
+ "eval_f1": 0.6724700761697497,
85
+ "eval_loss": 0.29324474930763245,
86
+ "eval_precision": 0.8153034300791556,
87
+ "eval_recall": 0.5722222222222222,
88
+ "eval_runtime": 5.8994,
89
+ "eval_samples_per_second": 48.14,
90
+ "eval_steps_per_second": 6.102,
91
+ "step": 100
92
+ },
93
+ {
94
+ "epoch": 1.5492957746478875,
95
+ "grad_norm": 0.8860771059989929,
96
+ "learning_rate": 2.5821596244131456e-05,
97
+ "loss": 0.2867,
98
+ "step": 110
99
+ },
100
+ {
101
+ "epoch": 1.6901408450704225,
102
+ "grad_norm": 0.816124439239502,
103
+ "learning_rate": 2.8169014084507046e-05,
104
+ "loss": 0.2808,
105
+ "step": 120
106
+ },
107
+ {
108
+ "epoch": 1.8309859154929577,
109
+ "grad_norm": 0.8954053521156311,
110
+ "learning_rate": 3.0516431924882634e-05,
111
+ "loss": 0.2948,
112
+ "step": 130
113
+ },
114
+ {
115
+ "epoch": 1.971830985915493,
116
+ "grad_norm": 1.4889060258865356,
117
+ "learning_rate": 3.286384976525822e-05,
118
+ "loss": 0.2359,
119
+ "step": 140
120
+ },
121
+ {
122
+ "epoch": 2.112676056338028,
123
+ "grad_norm": 1.1245497465133667,
124
+ "learning_rate": 3.5211267605633805e-05,
125
+ "loss": 0.2217,
126
+ "step": 150
127
+ },
128
+ {
129
+ "epoch": 2.2535211267605635,
130
+ "grad_norm": 0.6540855765342712,
131
+ "learning_rate": 3.755868544600939e-05,
132
+ "loss": 0.228,
133
+ "step": 160
134
+ },
135
+ {
136
+ "epoch": 2.3943661971830985,
137
+ "grad_norm": 0.9159438014030457,
138
+ "learning_rate": 3.990610328638498e-05,
139
+ "loss": 0.2061,
140
+ "step": 170
141
+ },
142
+ {
143
+ "epoch": 2.535211267605634,
144
+ "grad_norm": 1.1491577625274658,
145
+ "learning_rate": 4.225352112676056e-05,
146
+ "loss": 0.246,
147
+ "step": 180
148
+ },
149
+ {
150
+ "epoch": 2.676056338028169,
151
+ "grad_norm": 1.0928665399551392,
152
+ "learning_rate": 4.4600938967136154e-05,
153
+ "loss": 0.2159,
154
+ "step": 190
155
+ },
156
+ {
157
+ "epoch": 2.816901408450704,
158
+ "grad_norm": 0.8002581000328064,
159
+ "learning_rate": 4.694835680751174e-05,
160
+ "loss": 0.193,
161
+ "step": 200
162
+ },
163
+ {
164
+ "epoch": 2.816901408450704,
165
+ "eval_accuracy": 0.9190140845070423,
166
+ "eval_f1": 0.783427495291902,
167
+ "eval_loss": 0.21363618969917297,
168
+ "eval_precision": 0.7969348659003831,
169
+ "eval_recall": 0.7703703703703704,
170
+ "eval_runtime": 2.8854,
171
+ "eval_samples_per_second": 98.426,
172
+ "eval_steps_per_second": 12.477,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 2.9577464788732395,
177
+ "grad_norm": 0.8501047492027283,
178
+ "learning_rate": 4.929577464788733e-05,
179
+ "loss": 0.1954,
180
+ "step": 210
181
+ },
182
+ {
183
+ "epoch": 3.0985915492957745,
184
+ "grad_norm": 1.074354648590088,
185
+ "learning_rate": 4.981742305685968e-05,
186
+ "loss": 0.1855,
187
+ "step": 220
188
+ },
189
+ {
190
+ "epoch": 3.23943661971831,
191
+ "grad_norm": 0.6893348097801208,
192
+ "learning_rate": 4.9556598852373504e-05,
193
+ "loss": 0.166,
194
+ "step": 230
195
+ },
196
+ {
197
+ "epoch": 3.380281690140845,
198
+ "grad_norm": 1.0960265398025513,
199
+ "learning_rate": 4.929577464788733e-05,
200
+ "loss": 0.1862,
201
+ "step": 240
202
+ },
203
+ {
204
+ "epoch": 3.52112676056338,
205
+ "grad_norm": 1.657496690750122,
206
+ "learning_rate": 4.903495044340115e-05,
207
+ "loss": 0.1844,
208
+ "step": 250
209
+ },
210
+ {
211
+ "epoch": 3.6619718309859155,
212
+ "grad_norm": 0.9198503494262695,
213
+ "learning_rate": 4.8774126238914976e-05,
214
+ "loss": 0.1841,
215
+ "step": 260
216
+ },
217
+ {
218
+ "epoch": 3.802816901408451,
219
+ "grad_norm": 0.6908796429634094,
220
+ "learning_rate": 4.85133020344288e-05,
221
+ "loss": 0.1796,
222
+ "step": 270
223
+ },
224
+ {
225
+ "epoch": 3.943661971830986,
226
+ "grad_norm": 1.0879693031311035,
227
+ "learning_rate": 4.8252477829942624e-05,
228
+ "loss": 0.1699,
229
+ "step": 280
230
+ },
231
+ {
232
+ "epoch": 4.084507042253521,
233
+ "grad_norm": 0.7113975286483765,
234
+ "learning_rate": 4.799165362545645e-05,
235
+ "loss": 0.135,
236
+ "step": 290
237
+ },
238
+ {
239
+ "epoch": 4.225352112676056,
240
+ "grad_norm": 0.956768274307251,
241
+ "learning_rate": 4.773082942097027e-05,
242
+ "loss": 0.1503,
243
+ "step": 300
244
+ },
245
+ {
246
+ "epoch": 4.225352112676056,
247
+ "eval_accuracy": 0.9278169014084507,
248
+ "eval_f1": 0.8100092678405931,
249
+ "eval_loss": 0.18146201968193054,
250
+ "eval_precision": 0.8107606679035251,
251
+ "eval_recall": 0.8092592592592592,
252
+ "eval_runtime": 1.9894,
253
+ "eval_samples_per_second": 142.754,
254
+ "eval_steps_per_second": 18.096,
255
+ "step": 300
256
+ },
257
+ {
258
+ "epoch": 4.366197183098592,
259
+ "grad_norm": 1.119613528251648,
260
+ "learning_rate": 4.747000521648409e-05,
261
+ "loss": 0.1639,
262
+ "step": 310
263
+ },
264
+ {
265
+ "epoch": 4.507042253521127,
266
+ "grad_norm": 1.3519386053085327,
267
+ "learning_rate": 4.720918101199791e-05,
268
+ "loss": 0.1769,
269
+ "step": 320
270
+ },
271
+ {
272
+ "epoch": 4.647887323943662,
273
+ "grad_norm": 1.2561410665512085,
274
+ "learning_rate": 4.694835680751174e-05,
275
+ "loss": 0.1495,
276
+ "step": 330
277
+ },
278
+ {
279
+ "epoch": 4.788732394366197,
280
+ "grad_norm": 0.8973093032836914,
281
+ "learning_rate": 4.668753260302556e-05,
282
+ "loss": 0.1603,
283
+ "step": 340
284
+ },
285
+ {
286
+ "epoch": 4.929577464788732,
287
+ "grad_norm": 0.5152555108070374,
288
+ "learning_rate": 4.6426708398539385e-05,
289
+ "loss": 0.148,
290
+ "step": 350
291
+ },
292
+ {
293
+ "epoch": 5.070422535211268,
294
+ "grad_norm": 0.6774557828903198,
295
+ "learning_rate": 4.616588419405321e-05,
296
+ "loss": 0.1369,
297
+ "step": 360
298
+ },
299
+ {
300
+ "epoch": 5.211267605633803,
301
+ "grad_norm": 0.7763332724571228,
302
+ "learning_rate": 4.5905059989567033e-05,
303
+ "loss": 0.119,
304
+ "step": 370
305
+ },
306
+ {
307
+ "epoch": 5.352112676056338,
308
+ "grad_norm": 0.9512709975242615,
309
+ "learning_rate": 4.564423578508086e-05,
310
+ "loss": 0.1448,
311
+ "step": 380
312
+ },
313
+ {
314
+ "epoch": 5.492957746478873,
315
+ "grad_norm": 1.2080267667770386,
316
+ "learning_rate": 4.538341158059468e-05,
317
+ "loss": 0.1278,
318
+ "step": 390
319
+ },
320
+ {
321
+ "epoch": 5.633802816901408,
322
+ "grad_norm": 0.7148259282112122,
323
+ "learning_rate": 4.5122587376108505e-05,
324
+ "loss": 0.1313,
325
+ "step": 400
326
+ },
327
+ {
328
+ "epoch": 5.633802816901408,
329
+ "eval_accuracy": 0.9327464788732395,
330
+ "eval_f1": 0.8182683158896289,
331
+ "eval_loss": 0.16230623424053192,
332
+ "eval_precision": 0.8414872798434442,
333
+ "eval_recall": 0.7962962962962963,
334
+ "eval_runtime": 2.7042,
335
+ "eval_samples_per_second": 105.022,
336
+ "eval_steps_per_second": 13.313,
337
+ "step": 400
338
+ },
339
+ {
340
+ "epoch": 5.774647887323944,
341
+ "grad_norm": 0.9253571033477783,
342
+ "learning_rate": 4.486176317162233e-05,
343
+ "loss": 0.1489,
344
+ "step": 410
345
+ },
346
+ {
347
+ "epoch": 5.915492957746479,
348
+ "grad_norm": 1.0267525911331177,
349
+ "learning_rate": 4.4600938967136154e-05,
350
+ "loss": 0.1426,
351
+ "step": 420
352
+ },
353
+ {
354
+ "epoch": 6.056338028169014,
355
+ "grad_norm": 0.9201334118843079,
356
+ "learning_rate": 4.434011476264998e-05,
357
+ "loss": 0.1458,
358
+ "step": 430
359
+ },
360
+ {
361
+ "epoch": 6.197183098591549,
362
+ "grad_norm": 0.6784873604774475,
363
+ "learning_rate": 4.40792905581638e-05,
364
+ "loss": 0.1387,
365
+ "step": 440
366
+ },
367
+ {
368
+ "epoch": 6.338028169014084,
369
+ "grad_norm": 0.7604418992996216,
370
+ "learning_rate": 4.3818466353677626e-05,
371
+ "loss": 0.1087,
372
+ "step": 450
373
+ },
374
+ {
375
+ "epoch": 6.47887323943662,
376
+ "grad_norm": 0.8017091751098633,
377
+ "learning_rate": 4.355764214919145e-05,
378
+ "loss": 0.1071,
379
+ "step": 460
380
+ },
381
+ {
382
+ "epoch": 6.619718309859155,
383
+ "grad_norm": 0.8712729215621948,
384
+ "learning_rate": 4.329681794470527e-05,
385
+ "loss": 0.1084,
386
+ "step": 470
387
+ },
388
+ {
389
+ "epoch": 6.76056338028169,
390
+ "grad_norm": 0.8843014240264893,
391
+ "learning_rate": 4.303599374021909e-05,
392
+ "loss": 0.1176,
393
+ "step": 480
394
+ },
395
+ {
396
+ "epoch": 6.901408450704225,
397
+ "grad_norm": 0.7635127305984497,
398
+ "learning_rate": 4.2775169535732915e-05,
399
+ "loss": 0.1213,
400
+ "step": 490
401
+ },
402
+ {
403
+ "epoch": 7.042253521126761,
404
+ "grad_norm": 0.6069650053977966,
405
+ "learning_rate": 4.251434533124674e-05,
406
+ "loss": 0.1166,
407
+ "step": 500
408
+ },
409
+ {
410
+ "epoch": 7.042253521126761,
411
+ "eval_accuracy": 0.9320422535211268,
412
+ "eval_f1": 0.8224471021159153,
413
+ "eval_loss": 0.16577637195587158,
414
+ "eval_precision": 0.8171846435100548,
415
+ "eval_recall": 0.8277777777777777,
416
+ "eval_runtime": 2.043,
417
+ "eval_samples_per_second": 139.008,
418
+ "eval_steps_per_second": 17.621,
419
+ "step": 500
420
+ },
421
+ {
422
+ "epoch": 7.183098591549296,
423
+ "grad_norm": 0.9951217770576477,
424
+ "learning_rate": 4.225352112676056e-05,
425
+ "loss": 0.1125,
426
+ "step": 510
427
+ },
428
+ {
429
+ "epoch": 7.323943661971831,
430
+ "grad_norm": 0.4932935833930969,
431
+ "learning_rate": 4.199269692227439e-05,
432
+ "loss": 0.1221,
433
+ "step": 520
434
+ },
435
+ {
436
+ "epoch": 7.464788732394366,
437
+ "grad_norm": 0.9160825610160828,
438
+ "learning_rate": 4.173187271778821e-05,
439
+ "loss": 0.1058,
440
+ "step": 530
441
+ },
442
+ {
443
+ "epoch": 7.605633802816901,
444
+ "grad_norm": 0.8885666131973267,
445
+ "learning_rate": 4.1471048513302035e-05,
446
+ "loss": 0.1033,
447
+ "step": 540
448
+ },
449
+ {
450
+ "epoch": 7.746478873239437,
451
+ "grad_norm": 0.49906080961227417,
452
+ "learning_rate": 4.121022430881586e-05,
453
+ "loss": 0.0983,
454
+ "step": 550
455
+ },
456
+ {
457
+ "epoch": 7.887323943661972,
458
+ "grad_norm": 0.825618326663971,
459
+ "learning_rate": 4.094940010432968e-05,
460
+ "loss": 0.1093,
461
+ "step": 560
462
+ },
463
+ {
464
+ "epoch": 8.028169014084508,
465
+ "grad_norm": 0.8402373194694519,
466
+ "learning_rate": 4.068857589984351e-05,
467
+ "loss": 0.112,
468
+ "step": 570
469
+ },
470
+ {
471
+ "epoch": 8.169014084507042,
472
+ "grad_norm": 0.5090510249137878,
473
+ "learning_rate": 4.042775169535733e-05,
474
+ "loss": 0.0828,
475
+ "step": 580
476
+ },
477
+ {
478
+ "epoch": 8.309859154929578,
479
+ "grad_norm": 0.9439256191253662,
480
+ "learning_rate": 4.0166927490871155e-05,
481
+ "loss": 0.1069,
482
+ "step": 590
483
+ },
484
+ {
485
+ "epoch": 8.450704225352112,
486
+ "grad_norm": 0.47647300362586975,
487
+ "learning_rate": 3.990610328638498e-05,
488
+ "loss": 0.093,
489
+ "step": 600
490
+ },
491
+ {
492
+ "epoch": 8.450704225352112,
493
+ "eval_accuracy": 0.9383802816901409,
494
+ "eval_f1": 0.8404740200546946,
495
+ "eval_loss": 0.1605876386165619,
496
+ "eval_precision": 0.8276481149012568,
497
+ "eval_recall": 0.8537037037037037,
498
+ "eval_runtime": 2.9556,
499
+ "eval_samples_per_second": 96.09,
500
+ "eval_steps_per_second": 12.18,
501
+ "step": 600
502
+ },
503
+ {
504
+ "epoch": 8.591549295774648,
505
+ "grad_norm": 0.6321811676025391,
506
+ "learning_rate": 3.96452790818988e-05,
507
+ "loss": 0.0942,
508
+ "step": 610
509
+ },
510
+ {
511
+ "epoch": 8.732394366197184,
512
+ "grad_norm": 0.7512757778167725,
513
+ "learning_rate": 3.938445487741263e-05,
514
+ "loss": 0.0991,
515
+ "step": 620
516
+ },
517
+ {
518
+ "epoch": 8.873239436619718,
519
+ "grad_norm": 0.5704978108406067,
520
+ "learning_rate": 3.912363067292645e-05,
521
+ "loss": 0.0988,
522
+ "step": 630
523
+ },
524
+ {
525
+ "epoch": 9.014084507042254,
526
+ "grad_norm": 1.4220664501190186,
527
+ "learning_rate": 3.886280646844027e-05,
528
+ "loss": 0.0947,
529
+ "step": 640
530
+ },
531
+ {
532
+ "epoch": 9.154929577464788,
533
+ "grad_norm": 1.9923653602600098,
534
+ "learning_rate": 3.860198226395409e-05,
535
+ "loss": 0.0987,
536
+ "step": 650
537
+ },
538
+ {
539
+ "epoch": 9.295774647887324,
540
+ "grad_norm": 1.0009934902191162,
541
+ "learning_rate": 3.8341158059467916e-05,
542
+ "loss": 0.0826,
543
+ "step": 660
544
+ },
545
+ {
546
+ "epoch": 9.43661971830986,
547
+ "grad_norm": 0.5631663799285889,
548
+ "learning_rate": 3.808033385498174e-05,
549
+ "loss": 0.1084,
550
+ "step": 670
551
+ },
552
+ {
553
+ "epoch": 9.577464788732394,
554
+ "grad_norm": 0.6266153454780579,
555
+ "learning_rate": 3.7819509650495564e-05,
556
+ "loss": 0.0808,
557
+ "step": 680
558
+ },
559
+ {
560
+ "epoch": 9.71830985915493,
561
+ "grad_norm": 0.9451386332511902,
562
+ "learning_rate": 3.755868544600939e-05,
563
+ "loss": 0.0759,
564
+ "step": 690
565
+ },
566
+ {
567
+ "epoch": 9.859154929577464,
568
+ "grad_norm": 1.2534326314926147,
569
+ "learning_rate": 3.729786124152321e-05,
570
+ "loss": 0.0931,
571
+ "step": 700
572
+ },
573
+ {
574
+ "epoch": 9.859154929577464,
575
+ "eval_accuracy": 0.9366197183098591,
576
+ "eval_f1": 0.8369565217391305,
577
+ "eval_loss": 0.1625019609928131,
578
+ "eval_precision": 0.8191489361702128,
579
+ "eval_recall": 0.8555555555555555,
580
+ "eval_runtime": 2.0664,
581
+ "eval_samples_per_second": 137.435,
582
+ "eval_steps_per_second": 17.421,
583
+ "step": 700
584
+ },
585
+ {
586
+ "epoch": 10.0,
587
+ "grad_norm": 0.4895138144493103,
588
+ "learning_rate": 3.7037037037037037e-05,
589
+ "loss": 0.0883,
590
+ "step": 710
591
+ },
592
+ {
593
+ "epoch": 10.140845070422536,
594
+ "grad_norm": 0.7509373426437378,
595
+ "learning_rate": 3.677621283255086e-05,
596
+ "loss": 0.0816,
597
+ "step": 720
598
+ },
599
+ {
600
+ "epoch": 10.28169014084507,
601
+ "grad_norm": 0.6509613990783691,
602
+ "learning_rate": 3.6515388628064685e-05,
603
+ "loss": 0.075,
604
+ "step": 730
605
+ },
606
+ {
607
+ "epoch": 10.422535211267606,
608
+ "grad_norm": 0.655375599861145,
609
+ "learning_rate": 3.625456442357851e-05,
610
+ "loss": 0.0703,
611
+ "step": 740
612
+ },
613
+ {
614
+ "epoch": 10.56338028169014,
615
+ "grad_norm": 0.4507924020290375,
616
+ "learning_rate": 3.599374021909233e-05,
617
+ "loss": 0.0828,
618
+ "step": 750
619
+ },
620
+ {
621
+ "epoch": 10.704225352112676,
622
+ "grad_norm": 0.9039227366447449,
623
+ "learning_rate": 3.573291601460616e-05,
624
+ "loss": 0.0732,
625
+ "step": 760
626
+ },
627
+ {
628
+ "epoch": 10.845070422535212,
629
+ "grad_norm": 0.5821270942687988,
630
+ "learning_rate": 3.547209181011998e-05,
631
+ "loss": 0.0747,
632
+ "step": 770
633
+ },
634
+ {
635
+ "epoch": 10.985915492957746,
636
+ "grad_norm": 0.9370685815811157,
637
+ "learning_rate": 3.5211267605633805e-05,
638
+ "loss": 0.072,
639
+ "step": 780
640
+ },
641
+ {
642
+ "epoch": 11.126760563380282,
643
+ "grad_norm": 0.729614794254303,
644
+ "learning_rate": 3.495044340114763e-05,
645
+ "loss": 0.0733,
646
+ "step": 790
647
+ },
648
+ {
649
+ "epoch": 11.267605633802816,
650
+ "grad_norm": 0.5709458589553833,
651
+ "learning_rate": 3.4689619196661446e-05,
652
+ "loss": 0.0733,
653
+ "step": 800
654
+ },
655
+ {
656
+ "epoch": 11.267605633802816,
657
+ "eval_accuracy": 0.9355633802816902,
658
+ "eval_f1": 0.8310249307479224,
659
+ "eval_loss": 0.17139478027820587,
660
+ "eval_precision": 0.8287292817679558,
661
+ "eval_recall": 0.8333333333333334,
662
+ "eval_runtime": 2.0599,
663
+ "eval_samples_per_second": 137.87,
664
+ "eval_steps_per_second": 17.476,
665
+ "step": 800
666
+ },
667
+ {
668
+ "epoch": 11.408450704225352,
669
+ "grad_norm": 1.1286197900772095,
670
+ "learning_rate": 3.442879499217527e-05,
671
+ "loss": 0.0666,
672
+ "step": 810
673
+ },
674
+ {
675
+ "epoch": 11.549295774647888,
676
+ "grad_norm": 0.9596506953239441,
677
+ "learning_rate": 3.4167970787689094e-05,
678
+ "loss": 0.0849,
679
+ "step": 820
680
+ },
681
+ {
682
+ "epoch": 11.690140845070422,
683
+ "grad_norm": 0.8838114142417908,
684
+ "learning_rate": 3.3907146583202925e-05,
685
+ "loss": 0.0693,
686
+ "step": 830
687
+ },
688
+ {
689
+ "epoch": 11.830985915492958,
690
+ "grad_norm": 0.573143482208252,
691
+ "learning_rate": 3.364632237871675e-05,
692
+ "loss": 0.0688,
693
+ "step": 840
694
+ },
695
+ {
696
+ "epoch": 11.971830985915492,
697
+ "grad_norm": 0.4819594919681549,
698
+ "learning_rate": 3.338549817423057e-05,
699
+ "loss": 0.0708,
700
+ "step": 850
701
+ },
702
+ {
703
+ "epoch": 12.112676056338028,
704
+ "grad_norm": 0.672797679901123,
705
+ "learning_rate": 3.31246739697444e-05,
706
+ "loss": 0.0741,
707
+ "step": 860
708
+ },
709
+ {
710
+ "epoch": 12.253521126760564,
711
+ "grad_norm": 0.3752357065677643,
712
+ "learning_rate": 3.286384976525822e-05,
713
+ "loss": 0.0794,
714
+ "step": 870
715
+ },
716
+ {
717
+ "epoch": 12.394366197183098,
718
+ "grad_norm": 0.7455435991287231,
719
+ "learning_rate": 3.2603025560772045e-05,
720
+ "loss": 0.0719,
721
+ "step": 880
722
+ },
723
+ {
724
+ "epoch": 12.535211267605634,
725
+ "grad_norm": 0.6346479654312134,
726
+ "learning_rate": 3.234220135628587e-05,
727
+ "loss": 0.062,
728
+ "step": 890
729
+ },
730
+ {
731
+ "epoch": 12.676056338028168,
732
+ "grad_norm": 1.10377836227417,
733
+ "learning_rate": 3.208137715179969e-05,
734
+ "loss": 0.0693,
735
+ "step": 900
736
+ },
737
+ {
738
+ "epoch": 12.676056338028168,
739
+ "eval_accuracy": 0.9397887323943662,
740
+ "eval_f1": 0.8403361344537815,
741
+ "eval_loss": 0.1568107008934021,
742
+ "eval_precision": 0.847457627118644,
743
+ "eval_recall": 0.8333333333333334,
744
+ "eval_runtime": 2.0263,
745
+ "eval_samples_per_second": 140.158,
746
+ "eval_steps_per_second": 17.767,
747
+ "step": 900
748
+ },
749
+ {
750
+ "epoch": 12.816901408450704,
751
+ "grad_norm": 0.4753211736679077,
752
+ "learning_rate": 3.182055294731352e-05,
753
+ "loss": 0.0577,
754
+ "step": 910
755
+ },
756
+ {
757
+ "epoch": 12.95774647887324,
758
+ "grad_norm": 0.6100496053695679,
759
+ "learning_rate": 3.155972874282734e-05,
760
+ "loss": 0.0715,
761
+ "step": 920
762
+ },
763
+ {
764
+ "epoch": 13.098591549295774,
765
+ "grad_norm": 0.3752472698688507,
766
+ "learning_rate": 3.1298904538341165e-05,
767
+ "loss": 0.0683,
768
+ "step": 930
769
+ },
770
+ {
771
+ "epoch": 13.23943661971831,
772
+ "grad_norm": 1.3385846614837646,
773
+ "learning_rate": 3.103808033385498e-05,
774
+ "loss": 0.0578,
775
+ "step": 940
776
+ },
777
+ {
778
+ "epoch": 13.380281690140846,
779
+ "grad_norm": 0.5425249934196472,
780
+ "learning_rate": 3.0777256129368806e-05,
781
+ "loss": 0.0601,
782
+ "step": 950
783
+ },
784
+ {
785
+ "epoch": 13.52112676056338,
786
+ "grad_norm": 0.8623884320259094,
787
+ "learning_rate": 3.0516431924882634e-05,
788
+ "loss": 0.0673,
789
+ "step": 960
790
+ },
791
+ {
792
+ "epoch": 13.661971830985916,
793
+ "grad_norm": 0.7758656144142151,
794
+ "learning_rate": 3.0255607720396458e-05,
795
+ "loss": 0.0707,
796
+ "step": 970
797
+ },
798
+ {
799
+ "epoch": 13.80281690140845,
800
+ "grad_norm": 0.6038694381713867,
801
+ "learning_rate": 2.999478351591028e-05,
802
+ "loss": 0.0631,
803
+ "step": 980
804
+ },
805
+ {
806
+ "epoch": 13.943661971830986,
807
+ "grad_norm": 0.7183906435966492,
808
+ "learning_rate": 2.9733959311424102e-05,
809
+ "loss": 0.0647,
810
+ "step": 990
811
+ },
812
+ {
813
+ "epoch": 14.084507042253522,
814
+ "grad_norm": 0.6927624940872192,
815
+ "learning_rate": 2.9473135106937926e-05,
816
+ "loss": 0.0615,
817
+ "step": 1000
818
+ },
819
+ {
820
+ "epoch": 14.084507042253522,
821
+ "eval_accuracy": 0.9341549295774648,
822
+ "eval_f1": 0.8270120259019427,
823
+ "eval_loss": 0.1666344702243805,
824
+ "eval_precision": 0.8262476894639557,
825
+ "eval_recall": 0.8277777777777777,
826
+ "eval_runtime": 2.4957,
827
+ "eval_samples_per_second": 113.795,
828
+ "eval_steps_per_second": 14.425,
829
+ "step": 1000
830
+ },
831
+ {
832
+ "epoch": 14.225352112676056,
833
+ "grad_norm": 0.937294065952301,
834
+ "learning_rate": 2.921231090245175e-05,
835
+ "loss": 0.0545,
836
+ "step": 1010
837
+ },
838
+ {
839
+ "epoch": 14.366197183098592,
840
+ "grad_norm": 0.9548676013946533,
841
+ "learning_rate": 2.8951486697965574e-05,
842
+ "loss": 0.0601,
843
+ "step": 1020
844
+ },
845
+ {
846
+ "epoch": 14.507042253521126,
847
+ "grad_norm": 0.5984657406806946,
848
+ "learning_rate": 2.86906624934794e-05,
849
+ "loss": 0.0522,
850
+ "step": 1030
851
+ },
852
+ {
853
+ "epoch": 14.647887323943662,
854
+ "grad_norm": 0.6830617785453796,
855
+ "learning_rate": 2.8429838288993222e-05,
856
+ "loss": 0.0689,
857
+ "step": 1040
858
+ },
859
+ {
860
+ "epoch": 14.788732394366198,
861
+ "grad_norm": 1.328912615776062,
862
+ "learning_rate": 2.8169014084507046e-05,
863
+ "loss": 0.0753,
864
+ "step": 1050
865
+ },
866
+ {
867
+ "epoch": 14.929577464788732,
868
+ "grad_norm": 0.7891097664833069,
869
+ "learning_rate": 2.7908189880020867e-05,
870
+ "loss": 0.0696,
871
+ "step": 1060
872
+ },
873
+ {
874
+ "epoch": 15.070422535211268,
875
+ "grad_norm": 0.7651441693305969,
876
+ "learning_rate": 2.764736567553469e-05,
877
+ "loss": 0.0546,
878
+ "step": 1070
879
+ },
880
+ {
881
+ "epoch": 15.211267605633802,
882
+ "grad_norm": 0.9666036367416382,
883
+ "learning_rate": 2.7386541471048515e-05,
884
+ "loss": 0.0493,
885
+ "step": 1080
886
+ },
887
+ {
888
+ "epoch": 15.352112676056338,
889
+ "grad_norm": 0.4921013414859772,
890
+ "learning_rate": 2.712571726656234e-05,
891
+ "loss": 0.0478,
892
+ "step": 1090
893
+ },
894
+ {
895
+ "epoch": 15.492957746478874,
896
+ "grad_norm": 0.6497583389282227,
897
+ "learning_rate": 2.6864893062076163e-05,
898
+ "loss": 0.0562,
899
+ "step": 1100
900
+ },
901
+ {
902
+ "epoch": 15.492957746478874,
903
+ "eval_accuracy": 0.9394366197183098,
904
+ "eval_f1": 0.8404452690166976,
905
+ "eval_loss": 0.16357889771461487,
906
+ "eval_precision": 0.8420074349442379,
907
+ "eval_recall": 0.8388888888888889,
908
+ "eval_runtime": 2.0468,
909
+ "eval_samples_per_second": 138.756,
910
+ "eval_steps_per_second": 17.589,
911
+ "step": 1100
912
+ },
913
+ {
914
+ "epoch": 15.633802816901408,
915
+ "grad_norm": 2.279696226119995,
916
+ "learning_rate": 2.6604068857589987e-05,
917
+ "loss": 0.0591,
918
+ "step": 1110
919
+ },
920
+ {
921
+ "epoch": 15.774647887323944,
922
+ "grad_norm": 0.450811505317688,
923
+ "learning_rate": 2.634324465310381e-05,
924
+ "loss": 0.0502,
925
+ "step": 1120
926
+ },
927
+ {
928
+ "epoch": 15.915492957746478,
929
+ "grad_norm": 0.4582817554473877,
930
+ "learning_rate": 2.6082420448617635e-05,
931
+ "loss": 0.0576,
932
+ "step": 1130
933
+ },
934
+ {
935
+ "epoch": 16.056338028169016,
936
+ "grad_norm": 0.46688681840896606,
937
+ "learning_rate": 2.5821596244131456e-05,
938
+ "loss": 0.0461,
939
+ "step": 1140
940
+ },
941
+ {
942
+ "epoch": 16.197183098591548,
943
+ "grad_norm": 0.4218389093875885,
944
+ "learning_rate": 2.556077203964528e-05,
945
+ "loss": 0.0516,
946
+ "step": 1150
947
+ },
948
+ {
949
+ "epoch": 16.338028169014084,
950
+ "grad_norm": 0.9011832475662231,
951
+ "learning_rate": 2.5299947835159104e-05,
952
+ "loss": 0.0486,
953
+ "step": 1160
954
+ },
955
+ {
956
+ "epoch": 16.47887323943662,
957
+ "grad_norm": 0.542711079120636,
958
+ "learning_rate": 2.5039123630672928e-05,
959
+ "loss": 0.052,
960
+ "step": 1170
961
+ },
962
+ {
963
+ "epoch": 16.619718309859156,
964
+ "grad_norm": 0.45541244745254517,
965
+ "learning_rate": 2.4778299426186752e-05,
966
+ "loss": 0.046,
967
+ "step": 1180
968
+ },
969
+ {
970
+ "epoch": 16.760563380281692,
971
+ "grad_norm": 0.6403104662895203,
972
+ "learning_rate": 2.4517475221700576e-05,
973
+ "loss": 0.055,
974
+ "step": 1190
975
+ },
976
+ {
977
+ "epoch": 16.901408450704224,
978
+ "grad_norm": 0.8532978296279907,
979
+ "learning_rate": 2.42566510172144e-05,
980
+ "loss": 0.0507,
981
+ "step": 1200
982
+ },
983
+ {
984
+ "epoch": 16.901408450704224,
985
+ "eval_accuracy": 0.9401408450704225,
986
+ "eval_f1": 0.8434622467771639,
987
+ "eval_loss": 0.1612667739391327,
988
+ "eval_precision": 0.8388278388278388,
989
+ "eval_recall": 0.8481481481481481,
990
+ "eval_runtime": 1.994,
991
+ "eval_samples_per_second": 142.429,
992
+ "eval_steps_per_second": 18.054,
993
+ "step": 1200
994
+ },
995
+ {
996
+ "epoch": 17.04225352112676,
997
+ "grad_norm": 1.2943941354751587,
998
+ "learning_rate": 2.3995826812728224e-05,
999
+ "loss": 0.058,
1000
+ "step": 1210
1001
+ },
1002
+ {
1003
+ "epoch": 17.183098591549296,
1004
+ "grad_norm": 0.5414674282073975,
1005
+ "learning_rate": 2.3735002608242045e-05,
1006
+ "loss": 0.0462,
1007
+ "step": 1220
1008
+ },
1009
+ {
1010
+ "epoch": 17.323943661971832,
1011
+ "grad_norm": 0.7418174743652344,
1012
+ "learning_rate": 2.347417840375587e-05,
1013
+ "loss": 0.0408,
1014
+ "step": 1230
1015
+ },
1016
+ {
1017
+ "epoch": 17.464788732394368,
1018
+ "grad_norm": 0.339821457862854,
1019
+ "learning_rate": 2.3213354199269693e-05,
1020
+ "loss": 0.0407,
1021
+ "step": 1240
1022
+ },
1023
+ {
1024
+ "epoch": 17.6056338028169,
1025
+ "grad_norm": 0.779461145401001,
1026
+ "learning_rate": 2.2952529994783517e-05,
1027
+ "loss": 0.058,
1028
+ "step": 1250
1029
+ },
1030
+ {
1031
+ "epoch": 17.746478873239436,
1032
+ "grad_norm": 0.719028651714325,
1033
+ "learning_rate": 2.269170579029734e-05,
1034
+ "loss": 0.048,
1035
+ "step": 1260
1036
+ },
1037
+ {
1038
+ "epoch": 17.887323943661972,
1039
+ "grad_norm": 0.6600283980369568,
1040
+ "learning_rate": 2.2430881585811165e-05,
1041
+ "loss": 0.0573,
1042
+ "step": 1270
1043
+ },
1044
+ {
1045
+ "epoch": 18.028169014084508,
1046
+ "grad_norm": 0.8104175925254822,
1047
+ "learning_rate": 2.217005738132499e-05,
1048
+ "loss": 0.0494,
1049
+ "step": 1280
1050
+ },
1051
+ {
1052
+ "epoch": 18.169014084507044,
1053
+ "grad_norm": 0.7185409665107727,
1054
+ "learning_rate": 2.1909233176838813e-05,
1055
+ "loss": 0.0571,
1056
+ "step": 1290
1057
+ },
1058
+ {
1059
+ "epoch": 18.309859154929576,
1060
+ "grad_norm": 0.32650864124298096,
1061
+ "learning_rate": 2.1648408972352633e-05,
1062
+ "loss": 0.0552,
1063
+ "step": 1300
1064
+ },
1065
+ {
1066
+ "epoch": 18.309859154929576,
1067
+ "eval_accuracy": 0.9411971830985916,
1068
+ "eval_f1": 0.845513413506013,
1069
+ "eval_loss": 0.15904362499713898,
1070
+ "eval_precision": 0.844731977818854,
1071
+ "eval_recall": 0.8462962962962963,
1072
+ "eval_runtime": 2.6258,
1073
+ "eval_samples_per_second": 108.157,
1074
+ "eval_steps_per_second": 13.71,
1075
+ "step": 1300
1076
+ },
1077
+ {
1078
+ "epoch": 18.450704225352112,
1079
+ "grad_norm": 1.3154155015945435,
1080
+ "learning_rate": 2.1387584767866457e-05,
1081
+ "loss": 0.0454,
1082
+ "step": 1310
1083
+ },
1084
+ {
1085
+ "epoch": 18.591549295774648,
1086
+ "grad_norm": 0.4282239079475403,
1087
+ "learning_rate": 2.112676056338028e-05,
1088
+ "loss": 0.0431,
1089
+ "step": 1320
1090
+ },
1091
+ {
1092
+ "epoch": 18.732394366197184,
1093
+ "grad_norm": 1.1309629678726196,
1094
+ "learning_rate": 2.0865936358894105e-05,
1095
+ "loss": 0.0395,
1096
+ "step": 1330
1097
+ },
1098
+ {
1099
+ "epoch": 18.87323943661972,
1100
+ "grad_norm": 0.5871407985687256,
1101
+ "learning_rate": 2.060511215440793e-05,
1102
+ "loss": 0.0477,
1103
+ "step": 1340
1104
+ },
1105
+ {
1106
+ "epoch": 19.014084507042252,
1107
+ "grad_norm": 0.30267587304115295,
1108
+ "learning_rate": 2.0344287949921754e-05,
1109
+ "loss": 0.0349,
1110
+ "step": 1350
1111
+ },
1112
+ {
1113
+ "epoch": 19.154929577464788,
1114
+ "grad_norm": 1.5481466054916382,
1115
+ "learning_rate": 2.0083463745435578e-05,
1116
+ "loss": 0.0436,
1117
+ "step": 1360
1118
+ },
1119
+ {
1120
+ "epoch": 19.295774647887324,
1121
+ "grad_norm": 0.6972795724868774,
1122
+ "learning_rate": 1.98226395409494e-05,
1123
+ "loss": 0.0494,
1124
+ "step": 1370
1125
+ },
1126
+ {
1127
+ "epoch": 19.43661971830986,
1128
+ "grad_norm": 0.332928866147995,
1129
+ "learning_rate": 1.9561815336463226e-05,
1130
+ "loss": 0.0367,
1131
+ "step": 1380
1132
+ },
1133
+ {
1134
+ "epoch": 19.577464788732396,
1135
+ "grad_norm": 0.5983466506004333,
1136
+ "learning_rate": 1.9300991131977046e-05,
1137
+ "loss": 0.0389,
1138
+ "step": 1390
1139
+ },
1140
+ {
1141
+ "epoch": 19.718309859154928,
1142
+ "grad_norm": 0.734262228012085,
1143
+ "learning_rate": 1.904016692749087e-05,
1144
+ "loss": 0.0439,
1145
+ "step": 1400
1146
+ },
1147
+ {
1148
+ "epoch": 19.718309859154928,
1149
+ "eval_accuracy": 0.9394366197183098,
1150
+ "eval_f1": 0.8424908424908425,
1151
+ "eval_loss": 0.17035430669784546,
1152
+ "eval_precision": 0.8333333333333334,
1153
+ "eval_recall": 0.8518518518518519,
1154
+ "eval_runtime": 2.448,
1155
+ "eval_samples_per_second": 116.015,
1156
+ "eval_steps_per_second": 14.706,
1157
+ "step": 1400
1158
+ },
1159
+ {
1160
+ "epoch": 19.859154929577464,
1161
+ "grad_norm": 0.6112886667251587,
1162
+ "learning_rate": 1.8779342723004694e-05,
1163
+ "loss": 0.0385,
1164
+ "step": 1410
1165
+ },
1166
+ {
1167
+ "epoch": 20.0,
1168
+ "grad_norm": 1.010438323020935,
1169
+ "learning_rate": 1.8518518518518518e-05,
1170
+ "loss": 0.0456,
1171
+ "step": 1420
1172
+ },
1173
+ {
1174
+ "epoch": 20.140845070422536,
1175
+ "grad_norm": 0.5202921032905579,
1176
+ "learning_rate": 1.8257694314032342e-05,
1177
+ "loss": 0.0397,
1178
+ "step": 1430
1179
+ },
1180
+ {
1181
+ "epoch": 20.281690140845072,
1182
+ "grad_norm": 0.9659579992294312,
1183
+ "learning_rate": 1.7996870109546166e-05,
1184
+ "loss": 0.0465,
1185
+ "step": 1440
1186
+ },
1187
+ {
1188
+ "epoch": 20.422535211267604,
1189
+ "grad_norm": 0.5208175182342529,
1190
+ "learning_rate": 1.773604590505999e-05,
1191
+ "loss": 0.0435,
1192
+ "step": 1450
1193
+ },
1194
+ {
1195
+ "epoch": 20.56338028169014,
1196
+ "grad_norm": 0.5702980756759644,
1197
+ "learning_rate": 1.7475221700573814e-05,
1198
+ "loss": 0.0486,
1199
+ "step": 1460
1200
+ },
1201
+ {
1202
+ "epoch": 20.704225352112676,
1203
+ "grad_norm": 0.5662500262260437,
1204
+ "learning_rate": 1.7214397496087635e-05,
1205
+ "loss": 0.0358,
1206
+ "step": 1470
1207
+ },
1208
+ {
1209
+ "epoch": 20.845070422535212,
1210
+ "grad_norm": 0.901360034942627,
1211
+ "learning_rate": 1.6953573291601462e-05,
1212
+ "loss": 0.0339,
1213
+ "step": 1480
1214
+ },
1215
+ {
1216
+ "epoch": 20.985915492957748,
1217
+ "grad_norm": 0.8144014477729797,
1218
+ "learning_rate": 1.6692749087115286e-05,
1219
+ "loss": 0.0483,
1220
+ "step": 1490
1221
+ },
1222
+ {
1223
+ "epoch": 21.12676056338028,
1224
+ "grad_norm": 0.357433021068573,
1225
+ "learning_rate": 1.643192488262911e-05,
1226
+ "loss": 0.0367,
1227
+ "step": 1500
1228
+ },
1229
+ {
1230
+ "epoch": 21.12676056338028,
1231
+ "eval_accuracy": 0.9426056338028169,
1232
+ "eval_f1": 0.8483720930232558,
1233
+ "eval_loss": 0.170222669839859,
1234
+ "eval_precision": 0.8523364485981308,
1235
+ "eval_recall": 0.8444444444444444,
1236
+ "eval_runtime": 2.014,
1237
+ "eval_samples_per_second": 141.013,
1238
+ "eval_steps_per_second": 17.875,
1239
+ "step": 1500
1240
+ },
1241
+ {
1242
+ "epoch": 21.267605633802816,
1243
+ "grad_norm": 0.521035373210907,
1244
+ "learning_rate": 1.6171100678142934e-05,
1245
+ "loss": 0.0342,
1246
+ "step": 1510
1247
+ },
1248
+ {
1249
+ "epoch": 21.408450704225352,
1250
+ "grad_norm": 0.47409939765930176,
1251
+ "learning_rate": 1.591027647365676e-05,
1252
+ "loss": 0.0474,
1253
+ "step": 1520
1254
+ },
1255
+ {
1256
+ "epoch": 21.549295774647888,
1257
+ "grad_norm": 0.3274288773536682,
1258
+ "learning_rate": 1.5649452269170582e-05,
1259
+ "loss": 0.0358,
1260
+ "step": 1530
1261
+ },
1262
+ {
1263
+ "epoch": 21.690140845070424,
1264
+ "grad_norm": 0.5142138004302979,
1265
+ "learning_rate": 1.5388628064684403e-05,
1266
+ "loss": 0.038,
1267
+ "step": 1540
1268
+ },
1269
+ {
1270
+ "epoch": 21.830985915492956,
1271
+ "grad_norm": 0.5675768256187439,
1272
+ "learning_rate": 1.5127803860198229e-05,
1273
+ "loss": 0.0343,
1274
+ "step": 1550
1275
+ },
1276
+ {
1277
+ "epoch": 21.971830985915492,
1278
+ "grad_norm": 0.46324819326400757,
1279
+ "learning_rate": 1.4866979655712051e-05,
1280
+ "loss": 0.0393,
1281
+ "step": 1560
1282
+ },
1283
+ {
1284
+ "epoch": 22.112676056338028,
1285
+ "grad_norm": 0.3789016604423523,
1286
+ "learning_rate": 1.4606155451225875e-05,
1287
+ "loss": 0.0355,
1288
+ "step": 1570
1289
+ },
1290
+ {
1291
+ "epoch": 22.253521126760564,
1292
+ "grad_norm": 0.2880994379520416,
1293
+ "learning_rate": 1.43453312467397e-05,
1294
+ "loss": 0.0284,
1295
+ "step": 1580
1296
+ },
1297
+ {
1298
+ "epoch": 22.3943661971831,
1299
+ "grad_norm": 0.6509861350059509,
1300
+ "learning_rate": 1.4084507042253523e-05,
1301
+ "loss": 0.0367,
1302
+ "step": 1590
1303
+ },
1304
+ {
1305
+ "epoch": 22.535211267605632,
1306
+ "grad_norm": 1.1531139612197876,
1307
+ "learning_rate": 1.3823682837767346e-05,
1308
+ "loss": 0.0424,
1309
+ "step": 1600
1310
+ },
1311
+ {
1312
+ "epoch": 22.535211267605632,
1313
+ "eval_accuracy": 0.9394366197183098,
1314
+ "eval_f1": 0.8419117647058824,
1315
+ "eval_loss": 0.1684611290693283,
1316
+ "eval_precision": 0.8357664233576643,
1317
+ "eval_recall": 0.8481481481481481,
1318
+ "eval_runtime": 2.1171,
1319
+ "eval_samples_per_second": 134.146,
1320
+ "eval_steps_per_second": 17.004,
1321
+ "step": 1600
1322
+ },
1323
+ {
1324
+ "epoch": 22.676056338028168,
1325
+ "grad_norm": 1.80601966381073,
1326
+ "learning_rate": 1.356285863328117e-05,
1327
+ "loss": 0.0327,
1328
+ "step": 1610
1329
+ },
1330
+ {
1331
+ "epoch": 22.816901408450704,
1332
+ "grad_norm": 0.5846266746520996,
1333
+ "learning_rate": 1.3302034428794994e-05,
1334
+ "loss": 0.0371,
1335
+ "step": 1620
1336
+ },
1337
+ {
1338
+ "epoch": 22.95774647887324,
1339
+ "grad_norm": 0.2390224188566208,
1340
+ "learning_rate": 1.3041210224308818e-05,
1341
+ "loss": 0.042,
1342
+ "step": 1630
1343
+ },
1344
+ {
1345
+ "epoch": 23.098591549295776,
1346
+ "grad_norm": 0.26173052191734314,
1347
+ "learning_rate": 1.278038601982264e-05,
1348
+ "loss": 0.038,
1349
+ "step": 1640
1350
+ },
1351
+ {
1352
+ "epoch": 23.239436619718308,
1353
+ "grad_norm": 0.9115623831748962,
1354
+ "learning_rate": 1.2519561815336464e-05,
1355
+ "loss": 0.0323,
1356
+ "step": 1650
1357
+ },
1358
+ {
1359
+ "epoch": 23.380281690140844,
1360
+ "grad_norm": 0.5974897742271423,
1361
+ "learning_rate": 1.2258737610850288e-05,
1362
+ "loss": 0.0347,
1363
+ "step": 1660
1364
+ },
1365
+ {
1366
+ "epoch": 23.52112676056338,
1367
+ "grad_norm": 0.9727242588996887,
1368
+ "learning_rate": 1.1997913406364112e-05,
1369
+ "loss": 0.0461,
1370
+ "step": 1670
1371
+ },
1372
+ {
1373
+ "epoch": 23.661971830985916,
1374
+ "grad_norm": 0.8638906478881836,
1375
+ "learning_rate": 1.1737089201877934e-05,
1376
+ "loss": 0.0375,
1377
+ "step": 1680
1378
+ },
1379
+ {
1380
+ "epoch": 23.802816901408452,
1381
+ "grad_norm": 0.8562279343605042,
1382
+ "learning_rate": 1.1476264997391758e-05,
1383
+ "loss": 0.0312,
1384
+ "step": 1690
1385
+ },
1386
+ {
1387
+ "epoch": 23.943661971830984,
1388
+ "grad_norm": 0.6405536532402039,
1389
+ "learning_rate": 1.1215440792905582e-05,
1390
+ "loss": 0.0306,
1391
+ "step": 1700
1392
+ },
1393
+ {
1394
+ "epoch": 23.943661971830984,
1395
+ "eval_accuracy": 0.9380281690140845,
1396
+ "eval_f1": 0.8397085610200364,
1397
+ "eval_loss": 0.1770738810300827,
1398
+ "eval_precision": 0.8261648745519713,
1399
+ "eval_recall": 0.8537037037037037,
1400
+ "eval_runtime": 2.9524,
1401
+ "eval_samples_per_second": 96.192,
1402
+ "eval_steps_per_second": 12.193,
1403
+ "step": 1700
1404
+ },
1405
+ {
1406
+ "epoch": 24.08450704225352,
1407
+ "grad_norm": 0.9799217581748962,
1408
+ "learning_rate": 1.0954616588419406e-05,
1409
+ "loss": 0.033,
1410
+ "step": 1710
1411
+ },
1412
+ {
1413
+ "epoch": 24.225352112676056,
1414
+ "grad_norm": 0.4004919230937958,
1415
+ "learning_rate": 1.0693792383933229e-05,
1416
+ "loss": 0.0334,
1417
+ "step": 1720
1418
+ },
1419
+ {
1420
+ "epoch": 24.366197183098592,
1421
+ "grad_norm": 1.033111333847046,
1422
+ "learning_rate": 1.0432968179447053e-05,
1423
+ "loss": 0.0364,
1424
+ "step": 1730
1425
+ },
1426
+ {
1427
+ "epoch": 24.507042253521128,
1428
+ "grad_norm": 0.3790343999862671,
1429
+ "learning_rate": 1.0172143974960877e-05,
1430
+ "loss": 0.0369,
1431
+ "step": 1740
1432
+ },
1433
+ {
1434
+ "epoch": 24.647887323943664,
1435
+ "grad_norm": 0.20175768435001373,
1436
+ "learning_rate": 9.9113197704747e-06,
1437
+ "loss": 0.0303,
1438
+ "step": 1750
1439
+ },
1440
+ {
1441
+ "epoch": 24.788732394366196,
1442
+ "grad_norm": 0.7406692504882812,
1443
+ "learning_rate": 9.650495565988523e-06,
1444
+ "loss": 0.0329,
1445
+ "step": 1760
1446
+ },
1447
+ {
1448
+ "epoch": 24.929577464788732,
1449
+ "grad_norm": 0.3440076410770416,
1450
+ "learning_rate": 9.389671361502347e-06,
1451
+ "loss": 0.0395,
1452
+ "step": 1770
1453
+ },
1454
+ {
1455
+ "epoch": 25.070422535211268,
1456
+ "grad_norm": 0.2520686686038971,
1457
+ "learning_rate": 9.128847157016171e-06,
1458
+ "loss": 0.0269,
1459
+ "step": 1780
1460
+ },
1461
+ {
1462
+ "epoch": 25.211267605633804,
1463
+ "grad_norm": 0.40644267201423645,
1464
+ "learning_rate": 8.868022952529995e-06,
1465
+ "loss": 0.0336,
1466
+ "step": 1790
1467
+ },
1468
+ {
1469
+ "epoch": 25.352112676056336,
1470
+ "grad_norm": 0.2972894012928009,
1471
+ "learning_rate": 8.607198748043817e-06,
1472
+ "loss": 0.0352,
1473
+ "step": 1800
1474
+ },
1475
+ {
1476
+ "epoch": 25.352112676056336,
1477
+ "eval_accuracy": 0.9401408450704225,
1478
+ "eval_f1": 0.8440366972477065,
1479
+ "eval_loss": 0.1691148281097412,
1480
+ "eval_precision": 0.8363636363636363,
1481
+ "eval_recall": 0.8518518518518519,
1482
+ "eval_runtime": 2.183,
1483
+ "eval_samples_per_second": 130.097,
1484
+ "eval_steps_per_second": 16.491,
1485
+ "step": 1800
1486
+ },
1487
+ {
1488
+ "epoch": 25.492957746478872,
1489
+ "grad_norm": 0.7162390947341919,
1490
+ "learning_rate": 8.346374543557643e-06,
1491
+ "loss": 0.0267,
1492
+ "step": 1810
1493
+ },
1494
+ {
1495
+ "epoch": 25.633802816901408,
1496
+ "grad_norm": 0.49857279658317566,
1497
+ "learning_rate": 8.085550339071467e-06,
1498
+ "loss": 0.0459,
1499
+ "step": 1820
1500
+ },
1501
+ {
1502
+ "epoch": 25.774647887323944,
1503
+ "grad_norm": 0.3226544260978699,
1504
+ "learning_rate": 7.824726134585291e-06,
1505
+ "loss": 0.0383,
1506
+ "step": 1830
1507
+ },
1508
+ {
1509
+ "epoch": 25.91549295774648,
1510
+ "grad_norm": 0.10473772883415222,
1511
+ "learning_rate": 7.563901930099114e-06,
1512
+ "loss": 0.0296,
1513
+ "step": 1840
1514
+ },
1515
+ {
1516
+ "epoch": 26.056338028169016,
1517
+ "grad_norm": 0.4618949592113495,
1518
+ "learning_rate": 7.303077725612938e-06,
1519
+ "loss": 0.0257,
1520
+ "step": 1850
1521
+ },
1522
+ {
1523
+ "epoch": 26.197183098591548,
1524
+ "grad_norm": 0.15693806111812592,
1525
+ "learning_rate": 7.042253521126762e-06,
1526
+ "loss": 0.0274,
1527
+ "step": 1860
1528
+ },
1529
+ {
1530
+ "epoch": 26.338028169014084,
1531
+ "grad_norm": 0.3008931279182434,
1532
+ "learning_rate": 6.781429316640585e-06,
1533
+ "loss": 0.0307,
1534
+ "step": 1870
1535
+ },
1536
+ {
1537
+ "epoch": 26.47887323943662,
1538
+ "grad_norm": 0.7514234185218811,
1539
+ "learning_rate": 6.520605112154409e-06,
1540
+ "loss": 0.0348,
1541
+ "step": 1880
1542
+ },
1543
+ {
1544
+ "epoch": 26.619718309859156,
1545
+ "grad_norm": 1.1500775814056396,
1546
+ "learning_rate": 6.259780907668232e-06,
1547
+ "loss": 0.0304,
1548
+ "step": 1890
1549
+ },
1550
+ {
1551
+ "epoch": 26.760563380281692,
1552
+ "grad_norm": 0.8598619103431702,
1553
+ "learning_rate": 5.998956703182056e-06,
1554
+ "loss": 0.0323,
1555
+ "step": 1900
1556
+ },
1557
+ {
1558
+ "epoch": 26.760563380281692,
1559
+ "eval_accuracy": 0.9426056338028169,
1560
+ "eval_f1": 0.8508691674290942,
1561
+ "eval_loss": 0.1686810702085495,
1562
+ "eval_precision": 0.840867992766727,
1563
+ "eval_recall": 0.8611111111111112,
1564
+ "eval_runtime": 2.0406,
1565
+ "eval_samples_per_second": 139.175,
1566
+ "eval_steps_per_second": 17.642,
1567
+ "step": 1900
1568
+ },
1569
+ {
1570
+ "epoch": 26.901408450704224,
1571
+ "grad_norm": 0.2144249826669693,
1572
+ "learning_rate": 5.738132498695879e-06,
1573
+ "loss": 0.0279,
1574
+ "step": 1910
1575
+ },
1576
+ {
1577
+ "epoch": 27.04225352112676,
1578
+ "grad_norm": 0.05483362078666687,
1579
+ "learning_rate": 5.477308294209703e-06,
1580
+ "loss": 0.0273,
1581
+ "step": 1920
1582
+ },
1583
+ {
1584
+ "epoch": 27.183098591549296,
1585
+ "grad_norm": 0.3904362618923187,
1586
+ "learning_rate": 5.216484089723526e-06,
1587
+ "loss": 0.0249,
1588
+ "step": 1930
1589
+ },
1590
+ {
1591
+ "epoch": 27.323943661971832,
1592
+ "grad_norm": 0.2276570200920105,
1593
+ "learning_rate": 4.95565988523735e-06,
1594
+ "loss": 0.0284,
1595
+ "step": 1940
1596
+ },
1597
+ {
1598
+ "epoch": 27.464788732394368,
1599
+ "grad_norm": 0.49757641553878784,
1600
+ "learning_rate": 4.6948356807511736e-06,
1601
+ "loss": 0.0406,
1602
+ "step": 1950
1603
+ },
1604
+ {
1605
+ "epoch": 27.6056338028169,
1606
+ "grad_norm": 0.6939036846160889,
1607
+ "learning_rate": 4.434011476264998e-06,
1608
+ "loss": 0.0344,
1609
+ "step": 1960
1610
+ },
1611
+ {
1612
+ "epoch": 27.746478873239436,
1613
+ "grad_norm": 0.35933974385261536,
1614
+ "learning_rate": 4.173187271778822e-06,
1615
+ "loss": 0.0246,
1616
+ "step": 1970
1617
+ },
1618
+ {
1619
+ "epoch": 27.887323943661972,
1620
+ "grad_norm": 0.7418074011802673,
1621
+ "learning_rate": 3.912363067292646e-06,
1622
+ "loss": 0.0319,
1623
+ "step": 1980
1624
+ },
1625
+ {
1626
+ "epoch": 28.028169014084508,
1627
+ "grad_norm": 0.47155845165252686,
1628
+ "learning_rate": 3.651538862806469e-06,
1629
+ "loss": 0.0309,
1630
+ "step": 1990
1631
+ },
1632
+ {
1633
+ "epoch": 28.169014084507044,
1634
+ "grad_norm": 0.5308616161346436,
1635
+ "learning_rate": 3.3907146583202924e-06,
1636
+ "loss": 0.0297,
1637
+ "step": 2000
1638
+ },
1639
+ {
1640
+ "epoch": 28.169014084507044,
1641
+ "eval_accuracy": 0.9401408450704225,
1642
+ "eval_f1": 0.8454545454545455,
1643
+ "eval_loss": 0.17321611940860748,
1644
+ "eval_precision": 0.8303571428571429,
1645
+ "eval_recall": 0.8611111111111112,
1646
+ "eval_runtime": 2.0215,
1647
+ "eval_samples_per_second": 140.487,
1648
+ "eval_steps_per_second": 17.808,
1649
+ "step": 2000
1650
+ },
1651
+ {
1652
+ "epoch": 28.309859154929576,
1653
+ "grad_norm": 0.38366690278053284,
1654
+ "learning_rate": 3.129890453834116e-06,
1655
+ "loss": 0.0315,
1656
+ "step": 2010
1657
+ },
1658
+ {
1659
+ "epoch": 28.450704225352112,
1660
+ "grad_norm": 0.33385714888572693,
1661
+ "learning_rate": 2.8690662493479396e-06,
1662
+ "loss": 0.0315,
1663
+ "step": 2020
1664
+ },
1665
+ {
1666
+ "epoch": 28.591549295774648,
1667
+ "grad_norm": 0.5694302320480347,
1668
+ "learning_rate": 2.608242044861763e-06,
1669
+ "loss": 0.0267,
1670
+ "step": 2030
1671
+ },
1672
+ {
1673
+ "epoch": 28.732394366197184,
1674
+ "grad_norm": 0.7156753540039062,
1675
+ "learning_rate": 2.3474178403755868e-06,
1676
+ "loss": 0.0238,
1677
+ "step": 2040
1678
+ },
1679
+ {
1680
+ "epoch": 28.87323943661972,
1681
+ "grad_norm": 0.290353000164032,
1682
+ "learning_rate": 2.086593635889411e-06,
1683
+ "loss": 0.021,
1684
+ "step": 2050
1685
+ },
1686
+ {
1687
+ "epoch": 29.014084507042252,
1688
+ "grad_norm": 0.37377166748046875,
1689
+ "learning_rate": 1.8257694314032344e-06,
1690
+ "loss": 0.0225,
1691
+ "step": 2060
1692
+ },
1693
+ {
1694
+ "epoch": 29.154929577464788,
1695
+ "grad_norm": 0.4136624038219452,
1696
+ "learning_rate": 1.564945226917058e-06,
1697
+ "loss": 0.0326,
1698
+ "step": 2070
1699
+ },
1700
+ {
1701
+ "epoch": 29.295774647887324,
1702
+ "grad_norm": 0.2563035786151886,
1703
+ "learning_rate": 1.3041210224308816e-06,
1704
+ "loss": 0.0338,
1705
+ "step": 2080
1706
+ },
1707
+ {
1708
+ "epoch": 29.43661971830986,
1709
+ "grad_norm": 0.5630273222923279,
1710
+ "learning_rate": 1.0432968179447054e-06,
1711
+ "loss": 0.0285,
1712
+ "step": 2090
1713
+ },
1714
+ {
1715
+ "epoch": 29.577464788732396,
1716
+ "grad_norm": 0.2827240824699402,
1717
+ "learning_rate": 7.82472613458529e-07,
1718
+ "loss": 0.0229,
1719
+ "step": 2100
1720
+ },
1721
+ {
1722
+ "epoch": 29.577464788732396,
1723
+ "eval_accuracy": 0.9411971830985916,
1724
+ "eval_f1": 0.8474885844748858,
1725
+ "eval_loss": 0.17117364704608917,
1726
+ "eval_precision": 0.836036036036036,
1727
+ "eval_recall": 0.8592592592592593,
1728
+ "eval_runtime": 2.8598,
1729
+ "eval_samples_per_second": 99.308,
1730
+ "eval_steps_per_second": 12.588,
1731
+ "step": 2100
1732
+ },
1733
+ {
1734
+ "epoch": 29.718309859154928,
1735
+ "grad_norm": 0.1679154634475708,
1736
+ "learning_rate": 5.216484089723527e-07,
1737
+ "loss": 0.0263,
1738
+ "step": 2110
1739
+ },
1740
+ {
1741
+ "epoch": 29.859154929577464,
1742
+ "grad_norm": 0.21034198999404907,
1743
+ "learning_rate": 2.6082420448617635e-07,
1744
+ "loss": 0.0236,
1745
+ "step": 2120
1746
+ },
1747
+ {
1748
+ "epoch": 30.0,
1749
+ "grad_norm": 0.19389575719833374,
1750
+ "learning_rate": 0.0,
1751
+ "loss": 0.0303,
1752
+ "step": 2130
1753
+ },
1754
+ {
1755
+ "epoch": 30.0,
1756
+ "step": 2130,
1757
+ "total_flos": 2.6364665116584346e+18,
1758
+ "train_loss": 0.09721689578932775,
1759
+ "train_runtime": 614.0464,
1760
+ "train_samples_per_second": 55.403,
1761
+ "train_steps_per_second": 3.469
1762
+ }
1763
+ ],
1764
+ "logging_steps": 10,
1765
+ "max_steps": 2130,
1766
+ "num_input_tokens_seen": 0,
1767
+ "num_train_epochs": 30,
1768
+ "save_steps": 500,
1769
+ "stateful_callbacks": {
1770
+ "TrainerControl": {
1771
+ "args": {
1772
+ "should_epoch_stop": false,
1773
+ "should_evaluate": false,
1774
+ "should_log": false,
1775
+ "should_save": true,
1776
+ "should_training_stop": true
1777
+ },
1778
+ "attributes": {}
1779
+ }
1780
+ },
1781
+ "total_flos": 2.6364665116584346e+18,
1782
+ "train_batch_size": 16,
1783
+ "trial_name": null,
1784
+ "trial_params": null
1785
+ }