Kerem P commited on
Commit
819a6e6
1 Parent(s): f578949

End of training

Browse files
Files changed (5) hide show
  1. README.md +5 -0
  2. all_results.json +14 -0
  3. eval_results.json +9 -0
  4. train_results.json +8 -0
  5. trainer_state.json +250 -0
README.md CHANGED
@@ -3,6 +3,8 @@ license: mit
3
  base_model: BAAI/bge-base-en-v1.5
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: opus-em-bge-base
8
  results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
14
  # opus-em-bge-base
15
 
16
  This model is a fine-tuned version of [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on an unknown dataset.
 
 
 
17
 
18
  ## Model description
19
 
 
3
  base_model: BAAI/bge-base-en-v1.5
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - f1
8
  model-index:
9
  - name: opus-em-bge-base
10
  results: []
 
16
  # opus-em-bge-base
17
 
18
  This model is a fine-tuned version of [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0054
21
+ - F1: 0.9995
22
 
23
  ## Model description
24
 
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_f1": 0.9994789524201289,
4
+ "eval_loss": 0.005438507534563541,
5
+ "eval_runtime": 162.2941,
6
+ "eval_samples": 36000,
7
+ "eval_samples_per_second": 221.819,
8
+ "eval_steps_per_second": 6.932,
9
+ "train_loss": 0.004904600699804723,
10
+ "train_runtime": 10571.3602,
11
+ "train_samples": 160000,
12
+ "train_samples_per_second": 45.406,
13
+ "train_steps_per_second": 0.709
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_f1": 0.9994789524201289,
4
+ "eval_loss": 0.005438507534563541,
5
+ "eval_runtime": 162.2941,
6
+ "eval_samples": 36000,
7
+ "eval_samples_per_second": 221.819,
8
+ "eval_steps_per_second": 6.932
9
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.004904600699804723,
4
+ "train_runtime": 10571.3602,
5
+ "train_samples": 160000,
6
+ "train_samples_per_second": 45.406,
7
+ "train_steps_per_second": 0.709
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 2e-05,
14
+ "loss": 0.1014,
15
+ "step": 200
16
+ },
17
+ {
18
+ "epoch": 0.16,
19
+ "learning_rate": 2e-05,
20
+ "loss": 0.0067,
21
+ "step": 400
22
+ },
23
+ {
24
+ "epoch": 0.24,
25
+ "learning_rate": 2e-05,
26
+ "loss": 0.0054,
27
+ "step": 600
28
+ },
29
+ {
30
+ "epoch": 0.32,
31
+ "learning_rate": 2e-05,
32
+ "loss": 0.0072,
33
+ "step": 800
34
+ },
35
+ {
36
+ "epoch": 0.4,
37
+ "learning_rate": 2e-05,
38
+ "loss": 0.0082,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.48,
43
+ "learning_rate": 2e-05,
44
+ "loss": 0.0017,
45
+ "step": 1200
46
+ },
47
+ {
48
+ "epoch": 0.56,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.0044,
51
+ "step": 1400
52
+ },
53
+ {
54
+ "epoch": 0.64,
55
+ "learning_rate": 2e-05,
56
+ "loss": 0.0019,
57
+ "step": 1600
58
+ },
59
+ {
60
+ "epoch": 0.72,
61
+ "learning_rate": 2e-05,
62
+ "loss": 0.0027,
63
+ "step": 1800
64
+ },
65
+ {
66
+ "epoch": 0.8,
67
+ "learning_rate": 2e-05,
68
+ "loss": 0.0012,
69
+ "step": 2000
70
+ },
71
+ {
72
+ "epoch": 0.88,
73
+ "learning_rate": 2e-05,
74
+ "loss": 0.0031,
75
+ "step": 2200
76
+ },
77
+ {
78
+ "epoch": 0.96,
79
+ "learning_rate": 2e-05,
80
+ "loss": 0.0005,
81
+ "step": 2400
82
+ },
83
+ {
84
+ "epoch": 1.04,
85
+ "learning_rate": 2e-05,
86
+ "loss": 0.0026,
87
+ "step": 2600
88
+ },
89
+ {
90
+ "epoch": 1.12,
91
+ "learning_rate": 2e-05,
92
+ "loss": 0.0006,
93
+ "step": 2800
94
+ },
95
+ {
96
+ "epoch": 1.2,
97
+ "learning_rate": 2e-05,
98
+ "loss": 0.0027,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 1.28,
103
+ "learning_rate": 2e-05,
104
+ "loss": 0.0027,
105
+ "step": 3200
106
+ },
107
+ {
108
+ "epoch": 1.36,
109
+ "learning_rate": 2e-05,
110
+ "loss": 0.0025,
111
+ "step": 3400
112
+ },
113
+ {
114
+ "epoch": 1.44,
115
+ "learning_rate": 2e-05,
116
+ "loss": 0.0028,
117
+ "step": 3600
118
+ },
119
+ {
120
+ "epoch": 1.52,
121
+ "learning_rate": 2e-05,
122
+ "loss": 0.0006,
123
+ "step": 3800
124
+ },
125
+ {
126
+ "epoch": 1.6,
127
+ "learning_rate": 2e-05,
128
+ "loss": 0.0019,
129
+ "step": 4000
130
+ },
131
+ {
132
+ "epoch": 1.68,
133
+ "learning_rate": 2e-05,
134
+ "loss": 0.0005,
135
+ "step": 4200
136
+ },
137
+ {
138
+ "epoch": 1.76,
139
+ "learning_rate": 2e-05,
140
+ "loss": 0.0004,
141
+ "step": 4400
142
+ },
143
+ {
144
+ "epoch": 1.84,
145
+ "learning_rate": 2e-05,
146
+ "loss": 0.0009,
147
+ "step": 4600
148
+ },
149
+ {
150
+ "epoch": 1.92,
151
+ "learning_rate": 2e-05,
152
+ "loss": 0.0025,
153
+ "step": 4800
154
+ },
155
+ {
156
+ "epoch": 2.0,
157
+ "learning_rate": 2e-05,
158
+ "loss": 0.0016,
159
+ "step": 5000
160
+ },
161
+ {
162
+ "epoch": 2.08,
163
+ "learning_rate": 2e-05,
164
+ "loss": 0.0007,
165
+ "step": 5200
166
+ },
167
+ {
168
+ "epoch": 2.16,
169
+ "learning_rate": 2e-05,
170
+ "loss": 0.0022,
171
+ "step": 5400
172
+ },
173
+ {
174
+ "epoch": 2.24,
175
+ "learning_rate": 2e-05,
176
+ "loss": 0.0043,
177
+ "step": 5600
178
+ },
179
+ {
180
+ "epoch": 2.32,
181
+ "learning_rate": 2e-05,
182
+ "loss": 0.0017,
183
+ "step": 5800
184
+ },
185
+ {
186
+ "epoch": 2.4,
187
+ "learning_rate": 2e-05,
188
+ "loss": 0.0015,
189
+ "step": 6000
190
+ },
191
+ {
192
+ "epoch": 2.48,
193
+ "learning_rate": 2e-05,
194
+ "loss": 0.0003,
195
+ "step": 6200
196
+ },
197
+ {
198
+ "epoch": 2.56,
199
+ "learning_rate": 2e-05,
200
+ "loss": 0.0013,
201
+ "step": 6400
202
+ },
203
+ {
204
+ "epoch": 2.64,
205
+ "learning_rate": 2e-05,
206
+ "loss": 0.0019,
207
+ "step": 6600
208
+ },
209
+ {
210
+ "epoch": 2.72,
211
+ "learning_rate": 2e-05,
212
+ "loss": 0.0009,
213
+ "step": 6800
214
+ },
215
+ {
216
+ "epoch": 2.8,
217
+ "learning_rate": 2e-05,
218
+ "loss": 0.0,
219
+ "step": 7000
220
+ },
221
+ {
222
+ "epoch": 2.88,
223
+ "learning_rate": 2e-05,
224
+ "loss": 0.0011,
225
+ "step": 7200
226
+ },
227
+ {
228
+ "epoch": 2.96,
229
+ "learning_rate": 2e-05,
230
+ "loss": 0.0011,
231
+ "step": 7400
232
+ },
233
+ {
234
+ "epoch": 3.0,
235
+ "step": 7500,
236
+ "total_flos": 182323266453504.0,
237
+ "train_loss": 0.004904600699804723,
238
+ "train_runtime": 10571.3602,
239
+ "train_samples_per_second": 45.406,
240
+ "train_steps_per_second": 0.709
241
+ }
242
+ ],
243
+ "logging_steps": 200,
244
+ "max_steps": 7500,
245
+ "num_train_epochs": 3,
246
+ "save_steps": 500,
247
+ "total_flos": 182323266453504.0,
248
+ "trial_name": null,
249
+ "trial_params": null
250
+ }