nemik commited on
Commit
f814d59
1 Parent(s): f5002c0

End of training

Browse files
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.9297777777777778
30
  - name: F1
31
  type: f1
32
- value: 0.8175519630484989
33
  - name: Precision
34
  type: precision
35
- value: 0.8119266055045872
36
  - name: Recall
37
  type: recall
38
- value: 0.8232558139534883
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 [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on the webdataset dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.1708
49
- - Accuracy: 0.9298
50
- - F1: 0.8176
51
- - Precision: 0.8119
52
- - Recall: 0.8233
53
 
54
  ## Model description
55
 
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.9337777777777778
30
  - name: F1
31
  type: f1
32
+ value: 0.826945412311266
33
  - name: Precision
34
  type: precision
35
+ value: 0.8259860788863109
36
  - name: Recall
37
  type: recall
38
+ value: 0.827906976744186
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 [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on the webdataset dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.1725
49
+ - Accuracy: 0.9338
50
+ - F1: 0.8269
51
+ - Precision: 0.8260
52
+ - Recall: 0.8279
53
 
54
  ## Model description
55
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.9337777777777778,
4
+ "eval_f1": 0.826945412311266,
5
+ "eval_loss": 0.1725098043680191,
6
+ "eval_precision": 0.8259860788863109,
7
+ "eval_recall": 0.827906976744186,
8
+ "eval_runtime": 2.2237,
9
+ "eval_samples_per_second": 101.181,
10
+ "eval_steps_per_second": 13.041,
11
+ "total_flos": 3.8465920659456e+16,
12
+ "train_loss": 0.2702594916025797,
13
+ "train_runtime": 403.8981,
14
+ "train_samples_per_second": 66.849,
15
+ "train_steps_per_second": 4.234
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.9337777777777778,
4
+ "eval_f1": 0.826945412311266,
5
+ "eval_loss": 0.1725098043680191,
6
+ "eval_precision": 0.8259860788863109,
7
+ "eval_recall": 0.827906976744186,
8
+ "eval_runtime": 2.2237,
9
+ "eval_samples_per_second": 101.181,
10
+ "eval_steps_per_second": 13.041
11
+ }
runs/Oct22_15-45-30_2ae384978577/events.out.tfevents.1729612359.2ae384978577.344.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817aa14a668e23887148c3620906888b17e0c596b1cf224f9f5f48e67717e9a0
3
+ size 560
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "total_flos": 3.8465920659456e+16,
4
+ "train_loss": 0.2702594916025797,
5
+ "train_runtime": 403.8981,
6
+ "train_samples_per_second": 66.849,
7
+ "train_steps_per_second": 4.234
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1725098043680191,
3
+ "best_model_checkpoint": "frost-mobile-apple/mobilevit-xx-small-v2024-10-22/checkpoint-1500",
4
+ "epoch": 30.0,
5
+ "eval_steps": 100,
6
+ "global_step": 1710,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.17543859649122806,
13
+ "grad_norm": 0.2625730037689209,
14
+ "learning_rate": 1.1695906432748537e-05,
15
+ "loss": 0.6928,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.3508771929824561,
20
+ "grad_norm": 0.2961116135120392,
21
+ "learning_rate": 2.3391812865497074e-05,
22
+ "loss": 0.6936,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.5263157894736842,
27
+ "grad_norm": 0.24333663284778595,
28
+ "learning_rate": 3.508771929824561e-05,
29
+ "loss": 0.6917,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.7017543859649122,
34
+ "grad_norm": 0.2218523770570755,
35
+ "learning_rate": 4.678362573099415e-05,
36
+ "loss": 0.6887,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.8771929824561403,
41
+ "grad_norm": 0.23965124785900116,
42
+ "learning_rate": 5.847953216374269e-05,
43
+ "loss": 0.685,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.0526315789473684,
48
+ "grad_norm": 0.23081418871879578,
49
+ "learning_rate": 7.017543859649122e-05,
50
+ "loss": 0.6815,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.2280701754385965,
55
+ "grad_norm": 0.23212119936943054,
56
+ "learning_rate": 8.187134502923976e-05,
57
+ "loss": 0.676,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.4035087719298245,
62
+ "grad_norm": 0.2775309383869171,
63
+ "learning_rate": 9.35672514619883e-05,
64
+ "loss": 0.6711,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.5789473684210527,
69
+ "grad_norm": 0.38230618834495544,
70
+ "learning_rate": 0.00010526315789473685,
71
+ "loss": 0.6617,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.7543859649122808,
76
+ "grad_norm": 0.29050251841545105,
77
+ "learning_rate": 0.00011695906432748539,
78
+ "loss": 0.6549,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.7543859649122808,
83
+ "eval_accuracy": 0.82,
84
+ "eval_f1": 0.6260387811634349,
85
+ "eval_loss": 0.6288657784461975,
86
+ "eval_precision": 0.5191424196018377,
87
+ "eval_recall": 0.7883720930232558,
88
+ "eval_runtime": 2.6915,
89
+ "eval_samples_per_second": 83.597,
90
+ "eval_steps_per_second": 10.775,
91
+ "step": 100
92
+ },
93
+ {
94
+ "epoch": 1.9298245614035088,
95
+ "grad_norm": 0.3310299217700958,
96
+ "learning_rate": 0.0001286549707602339,
97
+ "loss": 0.6389,
98
+ "step": 110
99
+ },
100
+ {
101
+ "epoch": 2.1052631578947367,
102
+ "grad_norm": 0.35385212302207947,
103
+ "learning_rate": 0.00014035087719298245,
104
+ "loss": 0.6276,
105
+ "step": 120
106
+ },
107
+ {
108
+ "epoch": 2.280701754385965,
109
+ "grad_norm": 0.31887122988700867,
110
+ "learning_rate": 0.00015204678362573098,
111
+ "loss": 0.6068,
112
+ "step": 130
113
+ },
114
+ {
115
+ "epoch": 2.456140350877193,
116
+ "grad_norm": 0.38656044006347656,
117
+ "learning_rate": 0.00016374269005847952,
118
+ "loss": 0.5876,
119
+ "step": 140
120
+ },
121
+ {
122
+ "epoch": 2.6315789473684212,
123
+ "grad_norm": 0.40553656220436096,
124
+ "learning_rate": 0.00017543859649122806,
125
+ "loss": 0.5782,
126
+ "step": 150
127
+ },
128
+ {
129
+ "epoch": 2.807017543859649,
130
+ "grad_norm": 0.5055739879608154,
131
+ "learning_rate": 0.0001871345029239766,
132
+ "loss": 0.546,
133
+ "step": 160
134
+ },
135
+ {
136
+ "epoch": 2.982456140350877,
137
+ "grad_norm": 0.6473321318626404,
138
+ "learning_rate": 0.00019883040935672513,
139
+ "loss": 0.5322,
140
+ "step": 170
141
+ },
142
+ {
143
+ "epoch": 3.1578947368421053,
144
+ "grad_norm": 0.5542100667953491,
145
+ "learning_rate": 0.00019883040935672513,
146
+ "loss": 0.5081,
147
+ "step": 180
148
+ },
149
+ {
150
+ "epoch": 3.3333333333333335,
151
+ "grad_norm": 0.525965690612793,
152
+ "learning_rate": 0.00019753086419753085,
153
+ "loss": 0.4906,
154
+ "step": 190
155
+ },
156
+ {
157
+ "epoch": 3.5087719298245617,
158
+ "grad_norm": 0.6686927676200867,
159
+ "learning_rate": 0.00019623131903833657,
160
+ "loss": 0.4616,
161
+ "step": 200
162
+ },
163
+ {
164
+ "epoch": 3.5087719298245617,
165
+ "eval_accuracy": 0.8866666666666667,
166
+ "eval_f1": 0.7295864262990456,
167
+ "eval_loss": 0.41918542981147766,
168
+ "eval_precision": 0.6705653021442495,
169
+ "eval_recall": 0.8,
170
+ "eval_runtime": 2.7897,
171
+ "eval_samples_per_second": 80.654,
172
+ "eval_steps_per_second": 10.395,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 3.6842105263157894,
177
+ "grad_norm": 1.5412182807922363,
178
+ "learning_rate": 0.0001949317738791423,
179
+ "loss": 0.4506,
180
+ "step": 210
181
+ },
182
+ {
183
+ "epoch": 3.8596491228070176,
184
+ "grad_norm": 0.4173012375831604,
185
+ "learning_rate": 0.00019363222871994802,
186
+ "loss": 0.4371,
187
+ "step": 220
188
+ },
189
+ {
190
+ "epoch": 4.035087719298246,
191
+ "grad_norm": 0.42248570919036865,
192
+ "learning_rate": 0.00019233268356075374,
193
+ "loss": 0.4064,
194
+ "step": 230
195
+ },
196
+ {
197
+ "epoch": 4.2105263157894735,
198
+ "grad_norm": 0.5491617918014526,
199
+ "learning_rate": 0.00019103313840155946,
200
+ "loss": 0.3724,
201
+ "step": 240
202
+ },
203
+ {
204
+ "epoch": 4.385964912280702,
205
+ "grad_norm": 0.35062703490257263,
206
+ "learning_rate": 0.00018973359324236518,
207
+ "loss": 0.3671,
208
+ "step": 250
209
+ },
210
+ {
211
+ "epoch": 4.56140350877193,
212
+ "grad_norm": 0.40491071343421936,
213
+ "learning_rate": 0.0001884340480831709,
214
+ "loss": 0.3683,
215
+ "step": 260
216
+ },
217
+ {
218
+ "epoch": 4.7368421052631575,
219
+ "grad_norm": 0.9965174794197083,
220
+ "learning_rate": 0.0001871345029239766,
221
+ "loss": 0.3402,
222
+ "step": 270
223
+ },
224
+ {
225
+ "epoch": 4.912280701754386,
226
+ "grad_norm": 0.7184051275253296,
227
+ "learning_rate": 0.00018583495776478232,
228
+ "loss": 0.3348,
229
+ "step": 280
230
+ },
231
+ {
232
+ "epoch": 5.087719298245614,
233
+ "grad_norm": 1.8915038108825684,
234
+ "learning_rate": 0.00018453541260558804,
235
+ "loss": 0.32,
236
+ "step": 290
237
+ },
238
+ {
239
+ "epoch": 5.2631578947368425,
240
+ "grad_norm": 0.5761589407920837,
241
+ "learning_rate": 0.00018323586744639376,
242
+ "loss": 0.3101,
243
+ "step": 300
244
+ },
245
+ {
246
+ "epoch": 5.2631578947368425,
247
+ "eval_accuracy": 0.9035555555555556,
248
+ "eval_f1": 0.7317676143386898,
249
+ "eval_loss": 0.30708780884742737,
250
+ "eval_precision": 0.7810026385224275,
251
+ "eval_recall": 0.6883720930232559,
252
+ "eval_runtime": 2.8811,
253
+ "eval_samples_per_second": 78.095,
254
+ "eval_steps_per_second": 10.066,
255
+ "step": 300
256
+ },
257
+ {
258
+ "epoch": 5.43859649122807,
259
+ "grad_norm": 1.1592423915863037,
260
+ "learning_rate": 0.00018193632228719948,
261
+ "loss": 0.3258,
262
+ "step": 310
263
+ },
264
+ {
265
+ "epoch": 5.614035087719298,
266
+ "grad_norm": 0.8307028412818909,
267
+ "learning_rate": 0.0001806367771280052,
268
+ "loss": 0.3149,
269
+ "step": 320
270
+ },
271
+ {
272
+ "epoch": 5.7894736842105265,
273
+ "grad_norm": 0.9469823837280273,
274
+ "learning_rate": 0.00017933723196881092,
275
+ "loss": 0.3033,
276
+ "step": 330
277
+ },
278
+ {
279
+ "epoch": 5.964912280701754,
280
+ "grad_norm": 2.199500322341919,
281
+ "learning_rate": 0.00017803768680961664,
282
+ "loss": 0.3164,
283
+ "step": 340
284
+ },
285
+ {
286
+ "epoch": 6.140350877192983,
287
+ "grad_norm": 0.6772398948669434,
288
+ "learning_rate": 0.00017673814165042236,
289
+ "loss": 0.2806,
290
+ "step": 350
291
+ },
292
+ {
293
+ "epoch": 6.315789473684211,
294
+ "grad_norm": 0.4862241744995117,
295
+ "learning_rate": 0.00017543859649122806,
296
+ "loss": 0.2817,
297
+ "step": 360
298
+ },
299
+ {
300
+ "epoch": 6.491228070175438,
301
+ "grad_norm": 1.2349482774734497,
302
+ "learning_rate": 0.00017413905133203378,
303
+ "loss": 0.288,
304
+ "step": 370
305
+ },
306
+ {
307
+ "epoch": 6.666666666666667,
308
+ "grad_norm": 2.9781813621520996,
309
+ "learning_rate": 0.00017296946068875895,
310
+ "loss": 0.3039,
311
+ "step": 380
312
+ },
313
+ {
314
+ "epoch": 6.842105263157895,
315
+ "grad_norm": 0.7632750272750854,
316
+ "learning_rate": 0.00017166991552956468,
317
+ "loss": 0.2836,
318
+ "step": 390
319
+ },
320
+ {
321
+ "epoch": 7.017543859649122,
322
+ "grad_norm": 1.2420198917388916,
323
+ "learning_rate": 0.00017037037037037037,
324
+ "loss": 0.2932,
325
+ "step": 400
326
+ },
327
+ {
328
+ "epoch": 7.017543859649122,
329
+ "eval_accuracy": 0.908,
330
+ "eval_f1": 0.7460122699386503,
331
+ "eval_loss": 0.24856920540332794,
332
+ "eval_precision": 0.7896103896103897,
333
+ "eval_recall": 0.7069767441860465,
334
+ "eval_runtime": 2.8347,
335
+ "eval_samples_per_second": 79.373,
336
+ "eval_steps_per_second": 10.23,
337
+ "step": 400
338
+ },
339
+ {
340
+ "epoch": 7.192982456140351,
341
+ "grad_norm": 0.8554529547691345,
342
+ "learning_rate": 0.0001690708252111761,
343
+ "loss": 0.2583,
344
+ "step": 410
345
+ },
346
+ {
347
+ "epoch": 7.368421052631579,
348
+ "grad_norm": 0.5736662745475769,
349
+ "learning_rate": 0.0001677712800519818,
350
+ "loss": 0.2809,
351
+ "step": 420
352
+ },
353
+ {
354
+ "epoch": 7.543859649122807,
355
+ "grad_norm": 0.7552086114883423,
356
+ "learning_rate": 0.00016647173489278753,
357
+ "loss": 0.2774,
358
+ "step": 430
359
+ },
360
+ {
361
+ "epoch": 7.719298245614035,
362
+ "grad_norm": 0.6094131469726562,
363
+ "learning_rate": 0.00016517218973359325,
364
+ "loss": 0.2771,
365
+ "step": 440
366
+ },
367
+ {
368
+ "epoch": 7.894736842105263,
369
+ "grad_norm": 0.5392113924026489,
370
+ "learning_rate": 0.00016387264457439898,
371
+ "loss": 0.2755,
372
+ "step": 450
373
+ },
374
+ {
375
+ "epoch": 8.070175438596491,
376
+ "grad_norm": 0.4927959740161896,
377
+ "learning_rate": 0.0001625730994152047,
378
+ "loss": 0.2572,
379
+ "step": 460
380
+ },
381
+ {
382
+ "epoch": 8.24561403508772,
383
+ "grad_norm": 0.9484465718269348,
384
+ "learning_rate": 0.00016127355425601042,
385
+ "loss": 0.2354,
386
+ "step": 470
387
+ },
388
+ {
389
+ "epoch": 8.421052631578947,
390
+ "grad_norm": 0.71286940574646,
391
+ "learning_rate": 0.0001599740090968161,
392
+ "loss": 0.2611,
393
+ "step": 480
394
+ },
395
+ {
396
+ "epoch": 8.596491228070175,
397
+ "grad_norm": 1.9641995429992676,
398
+ "learning_rate": 0.00015867446393762183,
399
+ "loss": 0.2547,
400
+ "step": 490
401
+ },
402
+ {
403
+ "epoch": 8.771929824561404,
404
+ "grad_norm": 1.1893583536148071,
405
+ "learning_rate": 0.00015737491877842755,
406
+ "loss": 0.2652,
407
+ "step": 500
408
+ },
409
+ {
410
+ "epoch": 8.771929824561404,
411
+ "eval_accuracy": 0.9137777777777778,
412
+ "eval_f1": 0.7673860911270983,
413
+ "eval_loss": 0.22792504727840424,
414
+ "eval_precision": 0.7920792079207921,
415
+ "eval_recall": 0.7441860465116279,
416
+ "eval_runtime": 1.8141,
417
+ "eval_samples_per_second": 124.03,
418
+ "eval_steps_per_second": 15.986,
419
+ "step": 500
420
+ },
421
+ {
422
+ "epoch": 8.947368421052632,
423
+ "grad_norm": 1.0071460008621216,
424
+ "learning_rate": 0.00015607537361923327,
425
+ "loss": 0.244,
426
+ "step": 510
427
+ },
428
+ {
429
+ "epoch": 9.12280701754386,
430
+ "grad_norm": 1.22650146484375,
431
+ "learning_rate": 0.000154775828460039,
432
+ "loss": 0.2377,
433
+ "step": 520
434
+ },
435
+ {
436
+ "epoch": 9.298245614035087,
437
+ "grad_norm": 2.428567886352539,
438
+ "learning_rate": 0.00015347628330084472,
439
+ "loss": 0.2494,
440
+ "step": 530
441
+ },
442
+ {
443
+ "epoch": 9.473684210526315,
444
+ "grad_norm": 1.8254860639572144,
445
+ "learning_rate": 0.00015217673814165044,
446
+ "loss": 0.2603,
447
+ "step": 540
448
+ },
449
+ {
450
+ "epoch": 9.649122807017545,
451
+ "grad_norm": 0.6592786908149719,
452
+ "learning_rate": 0.00015087719298245616,
453
+ "loss": 0.2597,
454
+ "step": 550
455
+ },
456
+ {
457
+ "epoch": 9.824561403508772,
458
+ "grad_norm": 1.3194756507873535,
459
+ "learning_rate": 0.00014957764782326188,
460
+ "loss": 0.2313,
461
+ "step": 560
462
+ },
463
+ {
464
+ "epoch": 10.0,
465
+ "grad_norm": 2.1871612071990967,
466
+ "learning_rate": 0.00014827810266406757,
467
+ "loss": 0.282,
468
+ "step": 570
469
+ },
470
+ {
471
+ "epoch": 10.175438596491228,
472
+ "grad_norm": 0.759860098361969,
473
+ "learning_rate": 0.0001469785575048733,
474
+ "loss": 0.2319,
475
+ "step": 580
476
+ },
477
+ {
478
+ "epoch": 10.350877192982455,
479
+ "grad_norm": 1.447387933731079,
480
+ "learning_rate": 0.00014567901234567902,
481
+ "loss": 0.2457,
482
+ "step": 590
483
+ },
484
+ {
485
+ "epoch": 10.526315789473685,
486
+ "grad_norm": 0.9954220056533813,
487
+ "learning_rate": 0.00014437946718648474,
488
+ "loss": 0.2253,
489
+ "step": 600
490
+ },
491
+ {
492
+ "epoch": 10.526315789473685,
493
+ "eval_accuracy": 0.9217777777777778,
494
+ "eval_f1": 0.7858880778588808,
495
+ "eval_loss": 0.21004962921142578,
496
+ "eval_precision": 0.8239795918367347,
497
+ "eval_recall": 0.7511627906976744,
498
+ "eval_runtime": 4.2925,
499
+ "eval_samples_per_second": 52.417,
500
+ "eval_steps_per_second": 6.756,
501
+ "step": 600
502
+ },
503
+ {
504
+ "epoch": 10.701754385964913,
505
+ "grad_norm": 0.715815544128418,
506
+ "learning_rate": 0.00014307992202729046,
507
+ "loss": 0.2391,
508
+ "step": 610
509
+ },
510
+ {
511
+ "epoch": 10.87719298245614,
512
+ "grad_norm": 0.6449007391929626,
513
+ "learning_rate": 0.00014178037686809618,
514
+ "loss": 0.2516,
515
+ "step": 620
516
+ },
517
+ {
518
+ "epoch": 11.052631578947368,
519
+ "grad_norm": 0.9613096117973328,
520
+ "learning_rate": 0.0001404808317089019,
521
+ "loss": 0.2157,
522
+ "step": 630
523
+ },
524
+ {
525
+ "epoch": 11.228070175438596,
526
+ "grad_norm": 2.206623077392578,
527
+ "learning_rate": 0.00013918128654970762,
528
+ "loss": 0.2365,
529
+ "step": 640
530
+ },
531
+ {
532
+ "epoch": 11.403508771929825,
533
+ "grad_norm": 1.8694980144500732,
534
+ "learning_rate": 0.00013788174139051334,
535
+ "loss": 0.2263,
536
+ "step": 650
537
+ },
538
+ {
539
+ "epoch": 11.578947368421053,
540
+ "grad_norm": 0.7060205340385437,
541
+ "learning_rate": 0.00013658219623131904,
542
+ "loss": 0.2173,
543
+ "step": 660
544
+ },
545
+ {
546
+ "epoch": 11.75438596491228,
547
+ "grad_norm": 0.8581671714782715,
548
+ "learning_rate": 0.00013528265107212476,
549
+ "loss": 0.2204,
550
+ "step": 670
551
+ },
552
+ {
553
+ "epoch": 11.929824561403509,
554
+ "grad_norm": 1.196590781211853,
555
+ "learning_rate": 0.00013398310591293048,
556
+ "loss": 0.2519,
557
+ "step": 680
558
+ },
559
+ {
560
+ "epoch": 12.105263157894736,
561
+ "grad_norm": 1.0726817846298218,
562
+ "learning_rate": 0.0001326835607537362,
563
+ "loss": 0.2184,
564
+ "step": 690
565
+ },
566
+ {
567
+ "epoch": 12.280701754385966,
568
+ "grad_norm": 0.6241493821144104,
569
+ "learning_rate": 0.00013138401559454192,
570
+ "loss": 0.2257,
571
+ "step": 700
572
+ },
573
+ {
574
+ "epoch": 12.280701754385966,
575
+ "eval_accuracy": 0.9248888888888889,
576
+ "eval_f1": 0.8018757327080891,
577
+ "eval_loss": 0.19510744512081146,
578
+ "eval_precision": 0.8085106382978723,
579
+ "eval_recall": 0.7953488372093023,
580
+ "eval_runtime": 2.9139,
581
+ "eval_samples_per_second": 77.217,
582
+ "eval_steps_per_second": 9.952,
583
+ "step": 700
584
+ },
585
+ {
586
+ "epoch": 12.456140350877194,
587
+ "grad_norm": 1.382541298866272,
588
+ "learning_rate": 0.00013008447043534764,
589
+ "loss": 0.217,
590
+ "step": 710
591
+ },
592
+ {
593
+ "epoch": 12.631578947368421,
594
+ "grad_norm": 0.7372106909751892,
595
+ "learning_rate": 0.00012878492527615336,
596
+ "loss": 0.2209,
597
+ "step": 720
598
+ },
599
+ {
600
+ "epoch": 12.807017543859649,
601
+ "grad_norm": 1.3437495231628418,
602
+ "learning_rate": 0.00012748538011695908,
603
+ "loss": 0.2215,
604
+ "step": 730
605
+ },
606
+ {
607
+ "epoch": 12.982456140350877,
608
+ "grad_norm": 0.8328105807304382,
609
+ "learning_rate": 0.0001261858349577648,
610
+ "loss": 0.247,
611
+ "step": 740
612
+ },
613
+ {
614
+ "epoch": 13.157894736842104,
615
+ "grad_norm": 1.166037917137146,
616
+ "learning_rate": 0.0001248862897985705,
617
+ "loss": 0.2362,
618
+ "step": 750
619
+ },
620
+ {
621
+ "epoch": 13.333333333333334,
622
+ "grad_norm": 1.8687838315963745,
623
+ "learning_rate": 0.00012358674463937622,
624
+ "loss": 0.2247,
625
+ "step": 760
626
+ },
627
+ {
628
+ "epoch": 13.508771929824562,
629
+ "grad_norm": 1.2782139778137207,
630
+ "learning_rate": 0.00012228719948018194,
631
+ "loss": 0.2134,
632
+ "step": 770
633
+ },
634
+ {
635
+ "epoch": 13.68421052631579,
636
+ "grad_norm": 1.114933967590332,
637
+ "learning_rate": 0.00012098765432098766,
638
+ "loss": 0.1965,
639
+ "step": 780
640
+ },
641
+ {
642
+ "epoch": 13.859649122807017,
643
+ "grad_norm": 1.7937145233154297,
644
+ "learning_rate": 0.00011968810916179338,
645
+ "loss": 0.2124,
646
+ "step": 790
647
+ },
648
+ {
649
+ "epoch": 14.035087719298245,
650
+ "grad_norm": 1.6698014736175537,
651
+ "learning_rate": 0.0001183885640025991,
652
+ "loss": 0.2468,
653
+ "step": 800
654
+ },
655
+ {
656
+ "epoch": 14.035087719298245,
657
+ "eval_accuracy": 0.9306666666666666,
658
+ "eval_f1": 0.8198614318706697,
659
+ "eval_loss": 0.19064003229141235,
660
+ "eval_precision": 0.8142201834862385,
661
+ "eval_recall": 0.8255813953488372,
662
+ "eval_runtime": 2.8315,
663
+ "eval_samples_per_second": 79.464,
664
+ "eval_steps_per_second": 10.242,
665
+ "step": 800
666
+ },
667
+ {
668
+ "epoch": 14.210526315789474,
669
+ "grad_norm": 0.6950424313545227,
670
+ "learning_rate": 0.00011708901884340481,
671
+ "loss": 0.2004,
672
+ "step": 810
673
+ },
674
+ {
675
+ "epoch": 14.385964912280702,
676
+ "grad_norm": 1.5043634176254272,
677
+ "learning_rate": 0.00011578947368421053,
678
+ "loss": 0.2317,
679
+ "step": 820
680
+ },
681
+ {
682
+ "epoch": 14.56140350877193,
683
+ "grad_norm": 1.2491843700408936,
684
+ "learning_rate": 0.00011448992852501626,
685
+ "loss": 0.2027,
686
+ "step": 830
687
+ },
688
+ {
689
+ "epoch": 14.736842105263158,
690
+ "grad_norm": 0.6502349376678467,
691
+ "learning_rate": 0.00011319038336582198,
692
+ "loss": 0.2112,
693
+ "step": 840
694
+ },
695
+ {
696
+ "epoch": 14.912280701754385,
697
+ "grad_norm": 0.40061789751052856,
698
+ "learning_rate": 0.0001118908382066277,
699
+ "loss": 0.1756,
700
+ "step": 850
701
+ },
702
+ {
703
+ "epoch": 15.087719298245615,
704
+ "grad_norm": 2.8378994464874268,
705
+ "learning_rate": 0.0001105912930474334,
706
+ "loss": 0.2216,
707
+ "step": 860
708
+ },
709
+ {
710
+ "epoch": 15.263157894736842,
711
+ "grad_norm": 1.7187498807907104,
712
+ "learning_rate": 0.00010929174788823913,
713
+ "loss": 0.2072,
714
+ "step": 870
715
+ },
716
+ {
717
+ "epoch": 15.43859649122807,
718
+ "grad_norm": 1.774376392364502,
719
+ "learning_rate": 0.00010799220272904485,
720
+ "loss": 0.239,
721
+ "step": 880
722
+ },
723
+ {
724
+ "epoch": 15.614035087719298,
725
+ "grad_norm": 1.5812989473342896,
726
+ "learning_rate": 0.00010669265756985057,
727
+ "loss": 0.2191,
728
+ "step": 890
729
+ },
730
+ {
731
+ "epoch": 15.789473684210526,
732
+ "grad_norm": 0.9877386689186096,
733
+ "learning_rate": 0.00010539311241065628,
734
+ "loss": 0.1796,
735
+ "step": 900
736
+ },
737
+ {
738
+ "epoch": 15.789473684210526,
739
+ "eval_accuracy": 0.9275555555555556,
740
+ "eval_f1": 0.81199538638985,
741
+ "eval_loss": 0.19485591351985931,
742
+ "eval_precision": 0.8054919908466819,
743
+ "eval_recall": 0.8186046511627907,
744
+ "eval_runtime": 1.8216,
745
+ "eval_samples_per_second": 123.517,
746
+ "eval_steps_per_second": 15.92,
747
+ "step": 900
748
+ },
749
+ {
750
+ "epoch": 15.964912280701755,
751
+ "grad_norm": 1.059669017791748,
752
+ "learning_rate": 0.000104093567251462,
753
+ "loss": 0.1838,
754
+ "step": 910
755
+ },
756
+ {
757
+ "epoch": 16.140350877192983,
758
+ "grad_norm": 1.4218086004257202,
759
+ "learning_rate": 0.00010279402209226772,
760
+ "loss": 0.2281,
761
+ "step": 920
762
+ },
763
+ {
764
+ "epoch": 16.31578947368421,
765
+ "grad_norm": 1.2070213556289673,
766
+ "learning_rate": 0.00010149447693307344,
767
+ "loss": 0.1997,
768
+ "step": 930
769
+ },
770
+ {
771
+ "epoch": 16.49122807017544,
772
+ "grad_norm": 2.351250410079956,
773
+ "learning_rate": 0.00010019493177387915,
774
+ "loss": 0.1843,
775
+ "step": 940
776
+ },
777
+ {
778
+ "epoch": 16.666666666666668,
779
+ "grad_norm": 0.8852570056915283,
780
+ "learning_rate": 9.889538661468485e-05,
781
+ "loss": 0.2357,
782
+ "step": 950
783
+ },
784
+ {
785
+ "epoch": 16.842105263157894,
786
+ "grad_norm": 2.0466091632843018,
787
+ "learning_rate": 9.759584145549058e-05,
788
+ "loss": 0.2277,
789
+ "step": 960
790
+ },
791
+ {
792
+ "epoch": 17.017543859649123,
793
+ "grad_norm": 5.798379898071289,
794
+ "learning_rate": 9.62962962962963e-05,
795
+ "loss": 0.2246,
796
+ "step": 970
797
+ },
798
+ {
799
+ "epoch": 17.19298245614035,
800
+ "grad_norm": 1.6754958629608154,
801
+ "learning_rate": 9.499675113710202e-05,
802
+ "loss": 0.1904,
803
+ "step": 980
804
+ },
805
+ {
806
+ "epoch": 17.36842105263158,
807
+ "grad_norm": 0.6962611675262451,
808
+ "learning_rate": 9.369720597790773e-05,
809
+ "loss": 0.202,
810
+ "step": 990
811
+ },
812
+ {
813
+ "epoch": 17.54385964912281,
814
+ "grad_norm": 0.5351881384849548,
815
+ "learning_rate": 9.239766081871345e-05,
816
+ "loss": 0.1888,
817
+ "step": 1000
818
+ },
819
+ {
820
+ "epoch": 17.54385964912281,
821
+ "eval_accuracy": 0.9306666666666666,
822
+ "eval_f1": 0.8177570093457944,
823
+ "eval_loss": 0.18066002428531647,
824
+ "eval_precision": 0.8215962441314554,
825
+ "eval_recall": 0.813953488372093,
826
+ "eval_runtime": 1.8596,
827
+ "eval_samples_per_second": 120.996,
828
+ "eval_steps_per_second": 15.595,
829
+ "step": 1000
830
+ },
831
+ {
832
+ "epoch": 17.719298245614034,
833
+ "grad_norm": 1.2162110805511475,
834
+ "learning_rate": 9.109811565951917e-05,
835
+ "loss": 0.1789,
836
+ "step": 1010
837
+ },
838
+ {
839
+ "epoch": 17.894736842105264,
840
+ "grad_norm": 1.2040334939956665,
841
+ "learning_rate": 8.979857050032489e-05,
842
+ "loss": 0.2109,
843
+ "step": 1020
844
+ },
845
+ {
846
+ "epoch": 18.07017543859649,
847
+ "grad_norm": 0.8599823117256165,
848
+ "learning_rate": 8.849902534113061e-05,
849
+ "loss": 0.2113,
850
+ "step": 1030
851
+ },
852
+ {
853
+ "epoch": 18.24561403508772,
854
+ "grad_norm": 1.0291296243667603,
855
+ "learning_rate": 8.719948018193632e-05,
856
+ "loss": 0.1981,
857
+ "step": 1040
858
+ },
859
+ {
860
+ "epoch": 18.42105263157895,
861
+ "grad_norm": 3.214996576309204,
862
+ "learning_rate": 8.589993502274204e-05,
863
+ "loss": 0.1903,
864
+ "step": 1050
865
+ },
866
+ {
867
+ "epoch": 18.596491228070175,
868
+ "grad_norm": 1.1698780059814453,
869
+ "learning_rate": 8.460038986354776e-05,
870
+ "loss": 0.192,
871
+ "step": 1060
872
+ },
873
+ {
874
+ "epoch": 18.771929824561404,
875
+ "grad_norm": 3.0040793418884277,
876
+ "learning_rate": 8.330084470435348e-05,
877
+ "loss": 0.2062,
878
+ "step": 1070
879
+ },
880
+ {
881
+ "epoch": 18.94736842105263,
882
+ "grad_norm": 1.365694522857666,
883
+ "learning_rate": 8.200129954515919e-05,
884
+ "loss": 0.1885,
885
+ "step": 1080
886
+ },
887
+ {
888
+ "epoch": 19.12280701754386,
889
+ "grad_norm": 0.5183665156364441,
890
+ "learning_rate": 8.070175438596491e-05,
891
+ "loss": 0.2089,
892
+ "step": 1090
893
+ },
894
+ {
895
+ "epoch": 19.29824561403509,
896
+ "grad_norm": 0.6474595069885254,
897
+ "learning_rate": 7.940220922677063e-05,
898
+ "loss": 0.202,
899
+ "step": 1100
900
+ },
901
+ {
902
+ "epoch": 19.29824561403509,
903
+ "eval_accuracy": 0.9342222222222222,
904
+ "eval_f1": 0.8287037037037037,
905
+ "eval_loss": 0.1772110015153885,
906
+ "eval_precision": 0.8248847926267281,
907
+ "eval_recall": 0.8325581395348837,
908
+ "eval_runtime": 2.2017,
909
+ "eval_samples_per_second": 102.193,
910
+ "eval_steps_per_second": 13.171,
911
+ "step": 1100
912
+ },
913
+ {
914
+ "epoch": 19.473684210526315,
915
+ "grad_norm": 0.7569323778152466,
916
+ "learning_rate": 7.810266406757635e-05,
917
+ "loss": 0.2037,
918
+ "step": 1110
919
+ },
920
+ {
921
+ "epoch": 19.649122807017545,
922
+ "grad_norm": 1.068310260772705,
923
+ "learning_rate": 7.680311890838207e-05,
924
+ "loss": 0.1842,
925
+ "step": 1120
926
+ },
927
+ {
928
+ "epoch": 19.82456140350877,
929
+ "grad_norm": 1.1388903856277466,
930
+ "learning_rate": 7.550357374918778e-05,
931
+ "loss": 0.2057,
932
+ "step": 1130
933
+ },
934
+ {
935
+ "epoch": 20.0,
936
+ "grad_norm": 5.906609535217285,
937
+ "learning_rate": 7.42040285899935e-05,
938
+ "loss": 0.2088,
939
+ "step": 1140
940
+ },
941
+ {
942
+ "epoch": 20.17543859649123,
943
+ "grad_norm": 0.9702988862991333,
944
+ "learning_rate": 7.290448343079922e-05,
945
+ "loss": 0.1939,
946
+ "step": 1150
947
+ },
948
+ {
949
+ "epoch": 20.350877192982455,
950
+ "grad_norm": 3.627027988433838,
951
+ "learning_rate": 7.160493827160494e-05,
952
+ "loss": 0.1953,
953
+ "step": 1160
954
+ },
955
+ {
956
+ "epoch": 20.526315789473685,
957
+ "grad_norm": 1.11257004737854,
958
+ "learning_rate": 7.030539311241065e-05,
959
+ "loss": 0.1908,
960
+ "step": 1170
961
+ },
962
+ {
963
+ "epoch": 20.70175438596491,
964
+ "grad_norm": 1.626079797744751,
965
+ "learning_rate": 6.900584795321637e-05,
966
+ "loss": 0.2011,
967
+ "step": 1180
968
+ },
969
+ {
970
+ "epoch": 20.87719298245614,
971
+ "grad_norm": 1.8711522817611694,
972
+ "learning_rate": 6.770630279402209e-05,
973
+ "loss": 0.2106,
974
+ "step": 1190
975
+ },
976
+ {
977
+ "epoch": 21.05263157894737,
978
+ "grad_norm": 2.9188010692596436,
979
+ "learning_rate": 6.640675763482781e-05,
980
+ "loss": 0.1824,
981
+ "step": 1200
982
+ },
983
+ {
984
+ "epoch": 21.05263157894737,
985
+ "eval_accuracy": 0.9275555555555556,
986
+ "eval_f1": 0.8080094228504122,
987
+ "eval_loss": 0.18258829414844513,
988
+ "eval_precision": 0.8186157517899761,
989
+ "eval_recall": 0.7976744186046512,
990
+ "eval_runtime": 1.8368,
991
+ "eval_samples_per_second": 122.496,
992
+ "eval_steps_per_second": 15.788,
993
+ "step": 1200
994
+ },
995
+ {
996
+ "epoch": 21.228070175438596,
997
+ "grad_norm": 1.2156211137771606,
998
+ "learning_rate": 6.510721247563352e-05,
999
+ "loss": 0.1926,
1000
+ "step": 1210
1001
+ },
1002
+ {
1003
+ "epoch": 21.403508771929825,
1004
+ "grad_norm": 0.5184522271156311,
1005
+ "learning_rate": 6.380766731643924e-05,
1006
+ "loss": 0.1695,
1007
+ "step": 1220
1008
+ },
1009
+ {
1010
+ "epoch": 21.57894736842105,
1011
+ "grad_norm": 1.8020312786102295,
1012
+ "learning_rate": 6.250812215724496e-05,
1013
+ "loss": 0.2222,
1014
+ "step": 1230
1015
+ },
1016
+ {
1017
+ "epoch": 21.75438596491228,
1018
+ "grad_norm": 1.808860421180725,
1019
+ "learning_rate": 6.120857699805068e-05,
1020
+ "loss": 0.2026,
1021
+ "step": 1240
1022
+ },
1023
+ {
1024
+ "epoch": 21.92982456140351,
1025
+ "grad_norm": 0.5891908407211304,
1026
+ "learning_rate": 5.99090318388564e-05,
1027
+ "loss": 0.1861,
1028
+ "step": 1250
1029
+ },
1030
+ {
1031
+ "epoch": 22.105263157894736,
1032
+ "grad_norm": 0.7829120755195618,
1033
+ "learning_rate": 5.860948667966212e-05,
1034
+ "loss": 0.1911,
1035
+ "step": 1260
1036
+ },
1037
+ {
1038
+ "epoch": 22.280701754385966,
1039
+ "grad_norm": 0.8304038643836975,
1040
+ "learning_rate": 5.7309941520467835e-05,
1041
+ "loss": 0.1595,
1042
+ "step": 1270
1043
+ },
1044
+ {
1045
+ "epoch": 22.45614035087719,
1046
+ "grad_norm": 0.9477715492248535,
1047
+ "learning_rate": 5.6010396361273556e-05,
1048
+ "loss": 0.2207,
1049
+ "step": 1280
1050
+ },
1051
+ {
1052
+ "epoch": 22.63157894736842,
1053
+ "grad_norm": 1.6679517030715942,
1054
+ "learning_rate": 5.471085120207927e-05,
1055
+ "loss": 0.1885,
1056
+ "step": 1290
1057
+ },
1058
+ {
1059
+ "epoch": 22.80701754385965,
1060
+ "grad_norm": 1.945037603378296,
1061
+ "learning_rate": 5.341130604288499e-05,
1062
+ "loss": 0.1808,
1063
+ "step": 1300
1064
+ },
1065
+ {
1066
+ "epoch": 22.80701754385965,
1067
+ "eval_accuracy": 0.9346666666666666,
1068
+ "eval_f1": 0.8296639629200464,
1069
+ "eval_loss": 0.16815528273582458,
1070
+ "eval_precision": 0.8267898383371824,
1071
+ "eval_recall": 0.8325581395348837,
1072
+ "eval_runtime": 2.4881,
1073
+ "eval_samples_per_second": 90.429,
1074
+ "eval_steps_per_second": 11.655,
1075
+ "step": 1300
1076
+ },
1077
+ {
1078
+ "epoch": 22.982456140350877,
1079
+ "grad_norm": 0.7030972242355347,
1080
+ "learning_rate": 5.2111760883690706e-05,
1081
+ "loss": 0.1717,
1082
+ "step": 1310
1083
+ },
1084
+ {
1085
+ "epoch": 23.157894736842106,
1086
+ "grad_norm": 1.0622111558914185,
1087
+ "learning_rate": 5.081221572449643e-05,
1088
+ "loss": 0.2162,
1089
+ "step": 1320
1090
+ },
1091
+ {
1092
+ "epoch": 23.333333333333332,
1093
+ "grad_norm": 1.3687249422073364,
1094
+ "learning_rate": 4.951267056530214e-05,
1095
+ "loss": 0.197,
1096
+ "step": 1330
1097
+ },
1098
+ {
1099
+ "epoch": 23.50877192982456,
1100
+ "grad_norm": 1.218827724456787,
1101
+ "learning_rate": 4.821312540610786e-05,
1102
+ "loss": 0.1811,
1103
+ "step": 1340
1104
+ },
1105
+ {
1106
+ "epoch": 23.68421052631579,
1107
+ "grad_norm": 3.9379024505615234,
1108
+ "learning_rate": 4.691358024691358e-05,
1109
+ "loss": 0.1896,
1110
+ "step": 1350
1111
+ },
1112
+ {
1113
+ "epoch": 23.859649122807017,
1114
+ "grad_norm": 0.9299766421318054,
1115
+ "learning_rate": 4.56140350877193e-05,
1116
+ "loss": 0.1663,
1117
+ "step": 1360
1118
+ },
1119
+ {
1120
+ "epoch": 24.035087719298247,
1121
+ "grad_norm": 4.373446941375732,
1122
+ "learning_rate": 4.431448992852502e-05,
1123
+ "loss": 0.1883,
1124
+ "step": 1370
1125
+ },
1126
+ {
1127
+ "epoch": 24.210526315789473,
1128
+ "grad_norm": 1.0416285991668701,
1129
+ "learning_rate": 4.301494476933073e-05,
1130
+ "loss": 0.1884,
1131
+ "step": 1380
1132
+ },
1133
+ {
1134
+ "epoch": 24.385964912280702,
1135
+ "grad_norm": 1.9816950559616089,
1136
+ "learning_rate": 4.1715399610136454e-05,
1137
+ "loss": 0.1949,
1138
+ "step": 1390
1139
+ },
1140
+ {
1141
+ "epoch": 24.56140350877193,
1142
+ "grad_norm": 1.6888455152511597,
1143
+ "learning_rate": 4.041585445094217e-05,
1144
+ "loss": 0.1792,
1145
+ "step": 1400
1146
+ },
1147
+ {
1148
+ "epoch": 24.56140350877193,
1149
+ "eval_accuracy": 0.9364444444444444,
1150
+ "eval_f1": 0.8323563892145369,
1151
+ "eval_loss": 0.16882646083831787,
1152
+ "eval_precision": 0.8392434988179669,
1153
+ "eval_recall": 0.8255813953488372,
1154
+ "eval_runtime": 1.8209,
1155
+ "eval_samples_per_second": 123.562,
1156
+ "eval_steps_per_second": 15.926,
1157
+ "step": 1400
1158
+ },
1159
+ {
1160
+ "epoch": 24.736842105263158,
1161
+ "grad_norm": 0.6522326469421387,
1162
+ "learning_rate": 3.911630929174789e-05,
1163
+ "loss": 0.149,
1164
+ "step": 1410
1165
+ },
1166
+ {
1167
+ "epoch": 24.912280701754387,
1168
+ "grad_norm": 1.053612470626831,
1169
+ "learning_rate": 3.7816764132553604e-05,
1170
+ "loss": 0.1983,
1171
+ "step": 1420
1172
+ },
1173
+ {
1174
+ "epoch": 25.087719298245613,
1175
+ "grad_norm": 1.025525689125061,
1176
+ "learning_rate": 3.664717348927875e-05,
1177
+ "loss": 0.1973,
1178
+ "step": 1430
1179
+ },
1180
+ {
1181
+ "epoch": 25.263157894736842,
1182
+ "grad_norm": 2.1537649631500244,
1183
+ "learning_rate": 3.534762833008447e-05,
1184
+ "loss": 0.1797,
1185
+ "step": 1440
1186
+ },
1187
+ {
1188
+ "epoch": 25.43859649122807,
1189
+ "grad_norm": 2.6327617168426514,
1190
+ "learning_rate": 3.404808317089019e-05,
1191
+ "loss": 0.1693,
1192
+ "step": 1450
1193
+ },
1194
+ {
1195
+ "epoch": 25.614035087719298,
1196
+ "grad_norm": 1.1369807720184326,
1197
+ "learning_rate": 3.274853801169591e-05,
1198
+ "loss": 0.1826,
1199
+ "step": 1460
1200
+ },
1201
+ {
1202
+ "epoch": 25.789473684210527,
1203
+ "grad_norm": 2.0842247009277344,
1204
+ "learning_rate": 3.1448992852501624e-05,
1205
+ "loss": 0.1778,
1206
+ "step": 1470
1207
+ },
1208
+ {
1209
+ "epoch": 25.964912280701753,
1210
+ "grad_norm": 0.8993640542030334,
1211
+ "learning_rate": 3.014944769330734e-05,
1212
+ "loss": 0.1688,
1213
+ "step": 1480
1214
+ },
1215
+ {
1216
+ "epoch": 26.140350877192983,
1217
+ "grad_norm": 0.9640088677406311,
1218
+ "learning_rate": 2.8979857050032487e-05,
1219
+ "loss": 0.2139,
1220
+ "step": 1490
1221
+ },
1222
+ {
1223
+ "epoch": 26.31578947368421,
1224
+ "grad_norm": 1.134974718093872,
1225
+ "learning_rate": 2.7680311890838205e-05,
1226
+ "loss": 0.1852,
1227
+ "step": 1500
1228
+ },
1229
+ {
1230
+ "epoch": 26.31578947368421,
1231
+ "eval_accuracy": 0.9337777777777778,
1232
+ "eval_f1": 0.826945412311266,
1233
+ "eval_loss": 0.1725098043680191,
1234
+ "eval_precision": 0.8259860788863109,
1235
+ "eval_recall": 0.827906976744186,
1236
+ "eval_runtime": 1.8397,
1237
+ "eval_samples_per_second": 122.305,
1238
+ "eval_steps_per_second": 15.764,
1239
+ "step": 1500
1240
+ },
1241
+ {
1242
+ "epoch": 26.49122807017544,
1243
+ "grad_norm": 0.3995600640773773,
1244
+ "learning_rate": 2.6380766731643926e-05,
1245
+ "loss": 0.1703,
1246
+ "step": 1510
1247
+ },
1248
+ {
1249
+ "epoch": 26.666666666666668,
1250
+ "grad_norm": 1.8065487146377563,
1251
+ "learning_rate": 2.5081221572449644e-05,
1252
+ "loss": 0.2017,
1253
+ "step": 1520
1254
+ },
1255
+ {
1256
+ "epoch": 26.842105263157894,
1257
+ "grad_norm": 2.3725926876068115,
1258
+ "learning_rate": 2.378167641325536e-05,
1259
+ "loss": 0.1926,
1260
+ "step": 1530
1261
+ },
1262
+ {
1263
+ "epoch": 27.017543859649123,
1264
+ "grad_norm": 1.9128490686416626,
1265
+ "learning_rate": 2.248213125406108e-05,
1266
+ "loss": 0.1771,
1267
+ "step": 1540
1268
+ },
1269
+ {
1270
+ "epoch": 27.19298245614035,
1271
+ "grad_norm": 1.2254141569137573,
1272
+ "learning_rate": 2.1182586094866797e-05,
1273
+ "loss": 0.1791,
1274
+ "step": 1550
1275
+ },
1276
+ {
1277
+ "epoch": 27.36842105263158,
1278
+ "grad_norm": 1.3266674280166626,
1279
+ "learning_rate": 1.9883040935672515e-05,
1280
+ "loss": 0.1671,
1281
+ "step": 1560
1282
+ },
1283
+ {
1284
+ "epoch": 27.54385964912281,
1285
+ "grad_norm": 1.2818776369094849,
1286
+ "learning_rate": 1.8583495776478232e-05,
1287
+ "loss": 0.17,
1288
+ "step": 1570
1289
+ },
1290
+ {
1291
+ "epoch": 27.719298245614034,
1292
+ "grad_norm": 1.0659555196762085,
1293
+ "learning_rate": 1.728395061728395e-05,
1294
+ "loss": 0.1712,
1295
+ "step": 1580
1296
+ },
1297
+ {
1298
+ "epoch": 27.894736842105264,
1299
+ "grad_norm": 1.0451716184616089,
1300
+ "learning_rate": 1.5984405458089668e-05,
1301
+ "loss": 0.1854,
1302
+ "step": 1590
1303
+ },
1304
+ {
1305
+ "epoch": 28.07017543859649,
1306
+ "grad_norm": 2.3844401836395264,
1307
+ "learning_rate": 1.4684860298895387e-05,
1308
+ "loss": 0.177,
1309
+ "step": 1600
1310
+ },
1311
+ {
1312
+ "epoch": 28.07017543859649,
1313
+ "eval_accuracy": 0.9351111111111111,
1314
+ "eval_f1": 0.8282352941176471,
1315
+ "eval_loss": 0.16903221607208252,
1316
+ "eval_precision": 0.8380952380952381,
1317
+ "eval_recall": 0.8186046511627907,
1318
+ "eval_runtime": 2.2907,
1319
+ "eval_samples_per_second": 98.225,
1320
+ "eval_steps_per_second": 12.66,
1321
+ "step": 1600
1322
+ },
1323
+ {
1324
+ "epoch": 28.24561403508772,
1325
+ "grad_norm": 1.8458149433135986,
1326
+ "learning_rate": 1.3385315139701105e-05,
1327
+ "loss": 0.2091,
1328
+ "step": 1610
1329
+ },
1330
+ {
1331
+ "epoch": 28.42105263157895,
1332
+ "grad_norm": 0.7621822953224182,
1333
+ "learning_rate": 1.2085769980506823e-05,
1334
+ "loss": 0.1626,
1335
+ "step": 1620
1336
+ },
1337
+ {
1338
+ "epoch": 28.596491228070175,
1339
+ "grad_norm": 0.9533030986785889,
1340
+ "learning_rate": 1.078622482131254e-05,
1341
+ "loss": 0.1872,
1342
+ "step": 1630
1343
+ },
1344
+ {
1345
+ "epoch": 28.771929824561404,
1346
+ "grad_norm": 1.495856761932373,
1347
+ "learning_rate": 9.486679662118258e-06,
1348
+ "loss": 0.1816,
1349
+ "step": 1640
1350
+ },
1351
+ {
1352
+ "epoch": 28.94736842105263,
1353
+ "grad_norm": 1.397376537322998,
1354
+ "learning_rate": 8.187134502923977e-06,
1355
+ "loss": 0.1821,
1356
+ "step": 1650
1357
+ },
1358
+ {
1359
+ "epoch": 29.12280701754386,
1360
+ "grad_norm": 2.07928729057312,
1361
+ "learning_rate": 6.887589343729694e-06,
1362
+ "loss": 0.1801,
1363
+ "step": 1660
1364
+ },
1365
+ {
1366
+ "epoch": 29.29824561403509,
1367
+ "grad_norm": 1.2872428894042969,
1368
+ "learning_rate": 5.588044184535413e-06,
1369
+ "loss": 0.1835,
1370
+ "step": 1670
1371
+ },
1372
+ {
1373
+ "epoch": 29.473684210526315,
1374
+ "grad_norm": 0.40397679805755615,
1375
+ "learning_rate": 4.2884990253411305e-06,
1376
+ "loss": 0.1597,
1377
+ "step": 1680
1378
+ },
1379
+ {
1380
+ "epoch": 29.649122807017545,
1381
+ "grad_norm": 1.12138032913208,
1382
+ "learning_rate": 2.9889538661468487e-06,
1383
+ "loss": 0.1771,
1384
+ "step": 1690
1385
+ },
1386
+ {
1387
+ "epoch": 29.82456140350877,
1388
+ "grad_norm": 1.8918460607528687,
1389
+ "learning_rate": 1.6894087069525666e-06,
1390
+ "loss": 0.1857,
1391
+ "step": 1700
1392
+ },
1393
+ {
1394
+ "epoch": 29.82456140350877,
1395
+ "eval_accuracy": 0.9297777777777778,
1396
+ "eval_f1": 0.8175519630484989,
1397
+ "eval_loss": 0.17081834375858307,
1398
+ "eval_precision": 0.8119266055045872,
1399
+ "eval_recall": 0.8232558139534883,
1400
+ "eval_runtime": 1.7795,
1401
+ "eval_samples_per_second": 126.443,
1402
+ "eval_steps_per_second": 16.297,
1403
+ "step": 1700
1404
+ },
1405
+ {
1406
+ "epoch": 30.0,
1407
+ "grad_norm": 1.7220489978790283,
1408
+ "learning_rate": 3.898635477582846e-07,
1409
+ "loss": 0.166,
1410
+ "step": 1710
1411
+ },
1412
+ {
1413
+ "epoch": 30.0,
1414
+ "step": 1710,
1415
+ "total_flos": 3.8465920659456e+16,
1416
+ "train_loss": 0.2702594916025797,
1417
+ "train_runtime": 403.8981,
1418
+ "train_samples_per_second": 66.849,
1419
+ "train_steps_per_second": 4.234
1420
+ }
1421
+ ],
1422
+ "logging_steps": 10,
1423
+ "max_steps": 1710,
1424
+ "num_input_tokens_seen": 0,
1425
+ "num_train_epochs": 30,
1426
+ "save_steps": 500,
1427
+ "stateful_callbacks": {
1428
+ "TrainerControl": {
1429
+ "args": {
1430
+ "should_epoch_stop": false,
1431
+ "should_evaluate": false,
1432
+ "should_log": false,
1433
+ "should_save": true,
1434
+ "should_training_stop": true
1435
+ },
1436
+ "attributes": {}
1437
+ }
1438
+ },
1439
+ "total_flos": 3.8465920659456e+16,
1440
+ "train_batch_size": 16,
1441
+ "trial_name": null,
1442
+ "trial_params": null
1443
+ }