DewiBrynJones commited on
Commit
c024852
1 Parent(s): de9bbcb

End of training

Browse files
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
@@ -15,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # wav2vec2-xlsr-53-ft-btb-cy
17
 
18
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.4589
21
  - Wer: 0.3743
 
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
+ - automatic-speech-recognition
6
+ - DewiBrynJones/banc-trawsgrifiadau-bangor-normalized
7
  - generated_from_trainer
8
  metrics:
9
  - wer
 
17
 
18
  # wav2vec2-xlsr-53-ft-btb-cy
19
 
20
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-NORMALIZED - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 0.4589
23
  - Wer: 0.3743
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "epoch": 3.536067892503536,
3
- "eval_loss": 0.4583967626094818,
4
- "eval_runtime": 161.895,
5
  "eval_samples": 5656,
6
- "eval_samples_per_second": 34.936,
7
- "eval_steps_per_second": 4.367,
8
- "eval_wer": 0.37831418116453747,
9
  "total_flos": 9.55169606524761e+18,
10
- "train_loss": 1.2462444946289062,
11
- "train_runtime": 6962.0027,
12
  "train_samples": 22621,
13
- "train_samples_per_second": 11.491,
14
- "train_steps_per_second": 0.359
15
  }
 
1
  {
2
  "epoch": 3.536067892503536,
3
+ "eval_loss": 0.4588949382305145,
4
+ "eval_runtime": 153.3999,
5
  "eval_samples": 5656,
6
+ "eval_samples_per_second": 36.871,
7
+ "eval_steps_per_second": 4.609,
8
+ "eval_wer": 0.3742697566925595,
9
  "total_flos": 9.55169606524761e+18,
10
+ "train_loss": 1.2622116821289062,
11
+ "train_runtime": 6522.8506,
12
  "train_samples": 22621,
13
+ "train_samples_per_second": 12.265,
14
+ "train_steps_per_second": 0.383
15
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.536067892503536,
3
- "eval_loss": 0.4583967626094818,
4
- "eval_runtime": 161.895,
5
  "eval_samples": 5656,
6
- "eval_samples_per_second": 34.936,
7
- "eval_steps_per_second": 4.367,
8
- "eval_wer": 0.37831418116453747
9
  }
 
1
  {
2
  "epoch": 3.536067892503536,
3
+ "eval_loss": 0.4588949382305145,
4
+ "eval_runtime": 153.3999,
5
  "eval_samples": 5656,
6
+ "eval_samples_per_second": 36.871,
7
+ "eval_steps_per_second": 4.609,
8
+ "eval_wer": 0.3742697566925595
9
  }
runs/May16_08-14-26_2e698a9c250f/events.out.tfevents.1715850411.2e698a9c250f.233.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32c40b2b9131b58fbffd90fb39b2a35a1ffd6bb07bca4c083c735df411d2c55
3
+ size 406
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.536067892503536,
3
  "total_flos": 9.55169606524761e+18,
4
- "train_loss": 1.2462444946289062,
5
- "train_runtime": 6962.0027,
6
  "train_samples": 22621,
7
- "train_samples_per_second": 11.491,
8
- "train_steps_per_second": 0.359
9
  }
 
1
  {
2
  "epoch": 3.536067892503536,
3
  "total_flos": 9.55169606524761e+18,
4
+ "train_loss": 1.2622116821289062,
5
+ "train_runtime": 6522.8506,
6
  "train_samples": 22621,
7
+ "train_samples_per_second": 12.265,
8
+ "train_steps_per_second": 0.383
9
  }
trainer_state.json CHANGED
@@ -10,272 +10,272 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.14144271570014144,
13
- "eval_loss": 4.031618595123291,
14
- "eval_runtime": 161.4756,
15
- "eval_samples_per_second": 35.027,
16
- "eval_steps_per_second": 4.378,
17
  "eval_wer": 1.0,
18
  "step": 100
19
  },
20
  {
21
  "epoch": 0.2828854314002829,
22
- "eval_loss": 3.0548782348632812,
23
- "eval_runtime": 158.3539,
24
- "eval_samples_per_second": 35.717,
25
- "eval_steps_per_second": 4.465,
26
  "eval_wer": 1.0,
27
  "step": 200
28
  },
29
  {
30
  "epoch": 0.4243281471004243,
31
- "eval_loss": 2.5533947944641113,
32
- "eval_runtime": 158.9465,
33
- "eval_samples_per_second": 35.584,
34
- "eval_steps_per_second": 4.448,
35
- "eval_wer": 0.9862296976311228,
36
  "step": 300
37
  },
38
  {
39
  "epoch": 0.5657708628005658,
40
- "eval_loss": 1.4279608726501465,
41
- "eval_runtime": 159.2587,
42
- "eval_samples_per_second": 35.515,
43
- "eval_steps_per_second": 4.439,
44
- "eval_wer": 0.8846536560313283,
45
  "step": 400
46
  },
47
  {
48
  "epoch": 0.7072135785007072,
49
- "grad_norm": 1.9099421501159668,
50
- "learning_rate": 0.00029699999999999996,
51
- "loss": 3.6818,
52
  "step": 500
53
  },
54
  {
55
  "epoch": 0.7072135785007072,
56
- "eval_loss": 1.1378353834152222,
57
- "eval_runtime": 160.4319,
58
- "eval_samples_per_second": 35.255,
59
- "eval_steps_per_second": 4.407,
60
- "eval_wer": 0.7958368106824164,
61
  "step": 500
62
  },
63
  {
64
  "epoch": 0.8486562942008486,
65
- "eval_loss": 0.9263126254081726,
66
- "eval_runtime": 159.8222,
67
- "eval_samples_per_second": 35.389,
68
- "eval_steps_per_second": 4.424,
69
- "eval_wer": 0.6777299865185851,
70
  "step": 600
71
  },
72
  {
73
  "epoch": 0.9900990099009901,
74
- "eval_loss": 0.8501134514808655,
75
- "eval_runtime": 160.338,
76
- "eval_samples_per_second": 35.275,
77
- "eval_steps_per_second": 4.409,
78
- "eval_wer": 0.6388104256275278,
79
  "step": 700
80
  },
81
  {
82
  "epoch": 1.1315417256011315,
83
- "eval_loss": 0.6984566450119019,
84
- "eval_runtime": 159.8325,
85
- "eval_samples_per_second": 35.387,
86
- "eval_steps_per_second": 4.423,
87
- "eval_wer": 0.5563972523592476,
88
  "step": 800
89
  },
90
  {
91
  "epoch": 1.272984441301273,
92
- "eval_loss": 0.6664860248565674,
93
- "eval_runtime": 162.9316,
94
- "eval_samples_per_second": 34.714,
95
- "eval_steps_per_second": 4.339,
96
- "eval_wer": 0.5401393079540348,
97
  "step": 900
98
  },
99
  {
100
  "epoch": 1.4144271570014144,
101
- "grad_norm": 0.8423302173614502,
102
- "learning_rate": 0.00022574999999999996,
103
- "loss": 0.895,
104
  "step": 1000
105
  },
106
  {
107
  "epoch": 1.4144271570014144,
108
- "eval_loss": 0.6228350400924683,
109
- "eval_runtime": 161.5875,
110
- "eval_samples_per_second": 35.003,
111
- "eval_steps_per_second": 4.375,
112
- "eval_wer": 0.5000802465173011,
113
  "step": 1000
114
  },
115
  {
116
  "epoch": 1.5558698727015559,
117
- "eval_loss": 0.5974757075309753,
118
- "eval_runtime": 160.961,
119
- "eval_samples_per_second": 35.139,
120
- "eval_steps_per_second": 4.392,
121
- "eval_wer": 0.48359761186364514,
122
  "step": 1100
123
  },
124
  {
125
  "epoch": 1.6973125884016973,
126
- "eval_loss": 0.5826218128204346,
127
- "eval_runtime": 162.2219,
128
- "eval_samples_per_second": 34.866,
129
- "eval_steps_per_second": 4.358,
130
- "eval_wer": 0.4677248507414778,
131
  "step": 1200
132
  },
133
  {
134
  "epoch": 1.8387553041018387,
135
- "eval_loss": 0.5473496317863464,
136
- "eval_runtime": 164.7294,
137
- "eval_samples_per_second": 34.335,
138
- "eval_steps_per_second": 4.292,
139
- "eval_wer": 0.4512903639982025,
140
  "step": 1300
141
  },
142
  {
143
  "epoch": 1.9801980198019802,
144
- "eval_loss": 0.5284178256988525,
145
- "eval_runtime": 168.0547,
146
- "eval_samples_per_second": 33.656,
147
- "eval_steps_per_second": 4.207,
148
- "eval_wer": 0.4376966039673878,
149
  "step": 1400
150
  },
151
  {
152
  "epoch": 2.1216407355021216,
153
- "grad_norm": 1.0099021196365356,
154
- "learning_rate": 0.0001512,
155
- "loss": 0.687,
156
  "step": 1500
157
  },
158
  {
159
  "epoch": 2.1216407355021216,
160
- "eval_loss": 0.5137470960617065,
161
- "eval_runtime": 160.3266,
162
- "eval_samples_per_second": 35.278,
163
- "eval_steps_per_second": 4.41,
164
- "eval_wer": 0.42363741413622646,
165
  "step": 1500
166
  },
167
  {
168
  "epoch": 2.263083451202263,
169
- "eval_loss": 0.5110819339752197,
170
- "eval_runtime": 161.254,
171
- "eval_samples_per_second": 35.075,
172
- "eval_steps_per_second": 4.384,
173
- "eval_wer": 0.4103004429607755,
174
  "step": 1600
175
  },
176
  {
177
  "epoch": 2.4045261669024045,
178
- "eval_loss": 0.49603915214538574,
179
- "eval_runtime": 160.5657,
180
- "eval_samples_per_second": 35.225,
181
- "eval_steps_per_second": 4.403,
182
- "eval_wer": 0.4084226744559286,
183
  "step": 1700
184
  },
185
  {
186
  "epoch": 2.545968882602546,
187
- "eval_loss": 0.4876905679702759,
188
- "eval_runtime": 161.8676,
189
- "eval_samples_per_second": 34.942,
190
- "eval_steps_per_second": 4.368,
191
- "eval_wer": 0.40148937536110935,
192
  "step": 1800
193
  },
194
  {
195
  "epoch": 2.6874115983026874,
196
- "eval_loss": 0.47859108448028564,
197
- "eval_runtime": 161.5548,
198
- "eval_samples_per_second": 35.01,
199
- "eval_steps_per_second": 4.376,
200
- "eval_wer": 0.39929062078705785,
201
  "step": 1900
202
  },
203
  {
204
  "epoch": 2.828854314002829,
205
- "grad_norm": 0.5755736231803894,
206
- "learning_rate": 7.664999999999999e-05,
207
- "loss": 0.5319,
208
  "step": 2000
209
  },
210
  {
211
  "epoch": 2.828854314002829,
212
- "eval_loss": 0.47312092781066895,
213
- "eval_runtime": 162.5051,
214
- "eval_samples_per_second": 34.805,
215
- "eval_steps_per_second": 4.351,
216
- "eval_wer": 0.39299929383064774,
217
  "step": 2000
218
  },
219
  {
220
  "epoch": 2.9702970297029703,
221
- "eval_loss": 0.4668172001838684,
222
- "eval_runtime": 162.21,
223
- "eval_samples_per_second": 34.868,
224
- "eval_steps_per_second": 4.359,
225
- "eval_wer": 0.3877190729922321,
226
  "step": 2100
227
  },
228
  {
229
  "epoch": 3.1117397454031117,
230
- "eval_loss": 0.46727854013442993,
231
- "eval_runtime": 161.4684,
232
- "eval_samples_per_second": 35.029,
233
- "eval_steps_per_second": 4.379,
234
- "eval_wer": 0.3849585927970726,
235
  "step": 2200
236
  },
237
  {
238
  "epoch": 3.253182461103253,
239
- "eval_loss": 0.46300554275512695,
240
- "eval_runtime": 161.1936,
241
- "eval_samples_per_second": 35.088,
242
- "eval_steps_per_second": 4.386,
243
- "eval_wer": 0.3804326892212878,
244
  "step": 2300
245
  },
246
  {
247
  "epoch": 3.3946251768033946,
248
- "eval_loss": 0.4593857228755951,
249
- "eval_runtime": 161.5089,
250
- "eval_samples_per_second": 35.02,
251
- "eval_steps_per_second": 4.377,
252
- "eval_wer": 0.3768697438531168,
253
  "step": 2400
254
  },
255
  {
256
  "epoch": 3.536067892503536,
257
- "grad_norm": 0.887208104133606,
258
- "learning_rate": 1.9499999999999995e-06,
259
- "loss": 0.4355,
260
  "step": 2500
261
  },
262
  {
263
  "epoch": 3.536067892503536,
264
- "eval_loss": 0.4583967626094818,
265
- "eval_runtime": 162.1219,
266
- "eval_samples_per_second": 34.887,
267
- "eval_steps_per_second": 4.361,
268
- "eval_wer": 0.37831418116453747,
269
  "step": 2500
270
  },
271
  {
272
  "epoch": 3.536067892503536,
273
  "step": 2500,
274
  "total_flos": 9.55169606524761e+18,
275
- "train_loss": 1.2462444946289062,
276
- "train_runtime": 6962.0027,
277
- "train_samples_per_second": 11.491,
278
- "train_steps_per_second": 0.359
279
  }
280
  ],
281
  "logging_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.14144271570014144,
13
+ "eval_loss": 4.035430908203125,
14
+ "eval_runtime": 153.5895,
15
+ "eval_samples_per_second": 36.825,
16
+ "eval_steps_per_second": 4.603,
17
  "eval_wer": 1.0,
18
  "step": 100
19
  },
20
  {
21
  "epoch": 0.2828854314002829,
22
+ "eval_loss": 3.097731590270996,
23
+ "eval_runtime": 149.7934,
24
+ "eval_samples_per_second": 37.759,
25
+ "eval_steps_per_second": 4.72,
26
  "eval_wer": 1.0,
27
  "step": 200
28
  },
29
  {
30
  "epoch": 0.4243281471004243,
31
+ "eval_loss": 3.0768725872039795,
32
+ "eval_runtime": 151.0662,
33
+ "eval_samples_per_second": 37.441,
34
+ "eval_steps_per_second": 4.68,
35
+ "eval_wer": 1.0,
36
  "step": 300
37
  },
38
  {
39
  "epoch": 0.5657708628005658,
40
+ "eval_loss": 1.373844027519226,
41
+ "eval_runtime": 150.8632,
42
+ "eval_samples_per_second": 37.491,
43
+ "eval_steps_per_second": 4.686,
44
+ "eval_wer": 0.8913622648777043,
45
  "step": 400
46
  },
47
  {
48
  "epoch": 0.7072135785007072,
49
+ "grad_norm": 2.2486917972564697,
50
+ "learning_rate": 0.0002964,
51
+ "loss": 3.7586,
52
  "step": 500
53
  },
54
  {
55
  "epoch": 0.7072135785007072,
56
+ "eval_loss": 1.0915191173553467,
57
+ "eval_runtime": 151.7555,
58
+ "eval_samples_per_second": 37.27,
59
+ "eval_steps_per_second": 4.659,
60
+ "eval_wer": 0.7692431148488156,
61
  "step": 500
62
  },
63
  {
64
  "epoch": 0.8486562942008486,
65
+ "eval_loss": 0.9360549449920654,
66
+ "eval_runtime": 152.9408,
67
+ "eval_samples_per_second": 36.982,
68
+ "eval_steps_per_second": 4.623,
69
+ "eval_wer": 0.6854818000898761,
70
  "step": 600
71
  },
72
  {
73
  "epoch": 0.9900990099009901,
74
+ "eval_loss": 0.8494995832443237,
75
+ "eval_runtime": 151.5832,
76
+ "eval_samples_per_second": 37.313,
77
+ "eval_steps_per_second": 4.664,
78
+ "eval_wer": 0.6247191371894459,
79
  "step": 700
80
  },
81
  {
82
  "epoch": 1.1315417256011315,
83
+ "eval_loss": 0.6885886788368225,
84
+ "eval_runtime": 151.913,
85
+ "eval_samples_per_second": 37.232,
86
+ "eval_steps_per_second": 4.654,
87
+ "eval_wer": 0.5397059767606086,
88
  "step": 800
89
  },
90
  {
91
  "epoch": 1.272984441301273,
92
+ "eval_loss": 0.6703779101371765,
93
+ "eval_runtime": 153.2384,
94
+ "eval_samples_per_second": 36.91,
95
+ "eval_steps_per_second": 4.614,
96
+ "eval_wer": 0.531215895230147,
97
  "step": 900
98
  },
99
  {
100
  "epoch": 1.4144271570014144,
101
+ "grad_norm": 0.8719882369041443,
102
+ "learning_rate": 0.0002259,
103
+ "loss": 0.8877,
104
  "step": 1000
105
  },
106
  {
107
  "epoch": 1.4144271570014144,
108
+ "eval_loss": 0.62369304895401,
109
+ "eval_runtime": 153.3779,
110
+ "eval_samples_per_second": 36.876,
111
+ "eval_steps_per_second": 4.61,
112
+ "eval_wer": 0.495040765230789,
113
  "step": 1000
114
  },
115
  {
116
  "epoch": 1.5558698727015559,
117
+ "eval_loss": 0.5992260575294495,
118
+ "eval_runtime": 152.5492,
119
+ "eval_samples_per_second": 37.077,
120
+ "eval_steps_per_second": 4.635,
121
+ "eval_wer": 0.4767606085895872,
122
  "step": 1100
123
  },
124
  {
125
  "epoch": 1.6973125884016973,
126
+ "eval_loss": 0.5729629397392273,
127
+ "eval_runtime": 152.035,
128
+ "eval_samples_per_second": 37.202,
129
+ "eval_steps_per_second": 4.65,
130
+ "eval_wer": 0.4521730756885151,
131
  "step": 1200
132
  },
133
  {
134
  "epoch": 1.8387553041018387,
135
+ "eval_loss": 0.5504249930381775,
136
+ "eval_runtime": 152.762,
137
+ "eval_samples_per_second": 37.025,
138
+ "eval_steps_per_second": 4.628,
139
+ "eval_wer": 0.4417891763497464,
140
  "step": 1300
141
  },
142
  {
143
  "epoch": 1.9801980198019802,
144
+ "eval_loss": 0.5288310050964355,
145
+ "eval_runtime": 152.1876,
146
+ "eval_samples_per_second": 37.165,
147
+ "eval_steps_per_second": 4.646,
148
+ "eval_wer": 0.42586826731719846,
149
  "step": 1400
150
  },
151
  {
152
  "epoch": 2.1216407355021216,
153
+ "grad_norm": 0.7933566570281982,
154
+ "learning_rate": 0.00015134999999999997,
155
+ "loss": 0.6844,
156
  "step": 1500
157
  },
158
  {
159
  "epoch": 2.1216407355021216,
160
+ "eval_loss": 0.5165240168571472,
161
+ "eval_runtime": 152.8573,
162
+ "eval_samples_per_second": 37.002,
163
+ "eval_steps_per_second": 4.625,
164
+ "eval_wer": 0.4216633498106182,
165
  "step": 1500
166
  },
167
  {
168
  "epoch": 2.263083451202263,
169
+ "eval_loss": 0.5071681141853333,
170
+ "eval_runtime": 152.7102,
171
+ "eval_samples_per_second": 37.037,
172
+ "eval_steps_per_second": 4.63,
173
+ "eval_wer": 0.41930410220196446,
174
  "step": 1600
175
  },
176
  {
177
  "epoch": 2.4045261669024045,
178
+ "eval_loss": 0.49842193722724915,
179
+ "eval_runtime": 153.4952,
180
+ "eval_samples_per_second": 36.848,
181
+ "eval_steps_per_second": 4.606,
182
+ "eval_wer": 0.41546831867496953,
183
  "step": 1700
184
  },
185
  {
186
  "epoch": 2.545968882602546,
187
+ "eval_loss": 0.4882013499736786,
188
+ "eval_runtime": 152.4926,
189
+ "eval_samples_per_second": 37.09,
190
+ "eval_steps_per_second": 4.636,
191
+ "eval_wer": 0.4096905694292868,
192
  "step": 1800
193
  },
194
  {
195
  "epoch": 2.6874115983026874,
196
+ "eval_loss": 0.4803565740585327,
197
+ "eval_runtime": 152.0827,
198
+ "eval_samples_per_second": 37.19,
199
+ "eval_steps_per_second": 4.649,
200
+ "eval_wer": 0.40800539256596263,
201
  "step": 1900
202
  },
203
  {
204
  "epoch": 2.828854314002829,
205
+ "grad_norm": 0.7038583159446716,
206
+ "learning_rate": 7.68e-05,
207
+ "loss": 0.537,
208
  "step": 2000
209
  },
210
  {
211
  "epoch": 2.828854314002829,
212
+ "eval_loss": 0.470017671585083,
213
+ "eval_runtime": 152.5003,
214
+ "eval_samples_per_second": 37.088,
215
+ "eval_steps_per_second": 4.636,
216
+ "eval_wer": 0.39272645567182385,
217
  "step": 2000
218
  },
219
  {
220
  "epoch": 2.9702970297029703,
221
+ "eval_loss": 0.46773043274879456,
222
+ "eval_runtime": 152.3208,
223
+ "eval_samples_per_second": 37.132,
224
+ "eval_steps_per_second": 4.642,
225
+ "eval_wer": 0.3884573409514027,
226
  "step": 2100
227
  },
228
  {
229
  "epoch": 3.1117397454031117,
230
+ "eval_loss": 0.4683248996734619,
231
+ "eval_runtime": 152.8021,
232
+ "eval_samples_per_second": 37.015,
233
+ "eval_steps_per_second": 4.627,
234
+ "eval_wer": 0.38572895936316365,
235
  "step": 2200
236
  },
237
  {
238
  "epoch": 3.253182461103253,
239
+ "eval_loss": 0.4618384838104248,
240
+ "eval_runtime": 152.4829,
241
+ "eval_samples_per_second": 37.093,
242
+ "eval_steps_per_second": 4.637,
243
+ "eval_wer": 0.3792289914617706,
244
  "step": 2300
245
  },
246
  {
247
  "epoch": 3.3946251768033946,
248
+ "eval_loss": 0.46039119362831116,
249
+ "eval_runtime": 152.4542,
250
+ "eval_samples_per_second": 37.1,
251
+ "eval_steps_per_second": 4.637,
252
+ "eval_wer": 0.3762759196250883,
253
  "step": 2400
254
  },
255
  {
256
  "epoch": 3.536067892503536,
257
+ "grad_norm": 0.6644078493118286,
258
+ "learning_rate": 2.1e-06,
259
+ "loss": 0.4434,
260
  "step": 2500
261
  },
262
  {
263
  "epoch": 3.536067892503536,
264
+ "eval_loss": 0.4588949382305145,
265
+ "eval_runtime": 152.8982,
266
+ "eval_samples_per_second": 36.992,
267
+ "eval_steps_per_second": 4.624,
268
+ "eval_wer": 0.3742697566925595,
269
  "step": 2500
270
  },
271
  {
272
  "epoch": 3.536067892503536,
273
  "step": 2500,
274
  "total_flos": 9.55169606524761e+18,
275
+ "train_loss": 1.2622116821289062,
276
+ "train_runtime": 6522.8506,
277
+ "train_samples_per_second": 12.265,
278
+ "train_steps_per_second": 0.383
279
  }
280
  ],
281
  "logging_steps": 500,