Hugging Face's logo

IrwinD
/
flan-log-sage

Summarization
Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
IrwinD commited on
Commit
92b4293
·
verified ·
1 Parent(s): f8fd502

End of training

Browse files
Files changed (2) hide show
  1. README.md +107 -107
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Rouge1
24
  type: rouge
25
- value: 0.3829
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,12 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the hdfs_log_summary_dataset dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4037
36
- - Rouge1: 0.3829
37
- - Rouge2: 0.1129
38
- - Rougel: 0.2968
39
- - Rougelsum: 0.3082
40
- - Gen Len: 20.0
41
 
42
  ## Model description
43
 
@@ -69,106 +69,106 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
71
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
72
- | No log | 1.0 | 12 | 0.5375 | 0.0672 | 0.0252 | 0.07 | 0.0672 | 20.0 |
73
- | No log | 2.0 | 24 | 0.4705 | 0.1964 | 0.0256 | 0.1555 | 0.1555 | 19.8 |
74
- | No log | 3.0 | 36 | 0.4266 | 0.2449 | 0.0295 | 0.214 | 0.2211 | 19.8 |
75
- | No log | 4.0 | 48 | 0.3889 | 0.3408 | 0.1154 | 0.2913 | 0.2985 | 19.8 |
76
- | No log | 5.0 | 60 | 0.3618 | 0.4363 | 0.2003 | 0.3342 | 0.3588 | 19.8 |
77
- | No log | 6.0 | 72 | 0.3456 | 0.4409 | 0.2189 | 0.3272 | 0.3591 | 20.0 |
78
- | No log | 7.0 | 84 | 0.3328 | 0.4264 | 0.2258 | 0.3262 | 0.3521 | 20.0 |
79
- | No log | 8.0 | 96 | 0.3233 | 0.4264 | 0.2258 | 0.3262 | 0.3521 | 20.0 |
80
- | No log | 9.0 | 108 | 0.3185 | 0.4192 | 0.2258 | 0.3262 | 0.3433 | 20.0 |
81
- | No log | 10.0 | 120 | 0.3142 | 0.4273 | 0.2077 | 0.332 | 0.3645 | 20.0 |
82
- | No log | 11.0 | 132 | 0.3141 | 0.4495 | 0.2203 | 0.3423 | 0.3867 | 20.0 |
83
- | No log | 12.0 | 144 | 0.3143 | 0.4609 | 0.2256 | 0.3671 | 0.4064 | 20.0 |
84
- | No log | 13.0 | 156 | 0.3106 | 0.477 | 0.2492 | 0.3589 | 0.3989 | 20.0 |
85
- | No log | 14.0 | 168 | 0.3085 | 0.432 | 0.2089 | 0.307 | 0.3448 | 20.0 |
86
- | No log | 15.0 | 180 | 0.3080 | 0.4391 | 0.2207 | 0.3181 | 0.3533 | 20.0 |
87
- | No log | 16.0 | 192 | 0.3063 | 0.4179 | 0.2089 | 0.3027 | 0.3337 | 20.0 |
88
- | No log | 17.0 | 204 | 0.3072 | 0.4179 | 0.2089 | 0.3027 | 0.3337 | 20.0 |
89
- | No log | 18.0 | 216 | 0.3104 | 0.4462 | 0.2281 | 0.3247 | 0.3589 | 20.0 |
90
- | No log | 19.0 | 228 | 0.3094 | 0.4462 | 0.2281 | 0.3247 | 0.3589 | 20.0 |
91
- | No log | 20.0 | 240 | 0.3119 | 0.4457 | 0.2029 | 0.3242 | 0.3452 | 20.0 |
92
- | No log | 21.0 | 252 | 0.3158 | 0.4657 | 0.2356 | 0.3445 | 0.3749 | 20.0 |
93
- | No log | 22.0 | 264 | 0.3153 | 0.4657 | 0.2356 | 0.3445 | 0.3749 | 20.0 |
94
- | No log | 23.0 | 276 | 0.3160 | 0.4657 | 0.2356 | 0.3445 | 0.3749 | 20.0 |
95
- | No log | 24.0 | 288 | 0.3173 | 0.4752 | 0.2416 | 0.3594 | 0.39 | 20.0 |
96
- | No log | 25.0 | 300 | 0.3173 | 0.4325 | 0.1942 | 0.3352 | 0.3508 | 20.0 |
97
- | No log | 26.0 | 312 | 0.3185 | 0.4624 | 0.2042 | 0.3527 | 0.3704 | 20.0 |
98
- | No log | 27.0 | 324 | 0.3202 | 0.4798 | 0.2486 | 0.3656 | 0.3883 | 20.0 |
99
- | No log | 28.0 | 336 | 0.3243 | 0.4763 | 0.2284 | 0.3779 | 0.4026 | 20.0 |
100
- | No log | 29.0 | 348 | 0.3241 | 0.4763 | 0.2284 | 0.3779 | 0.4026 | 20.0 |
101
- | No log | 30.0 | 360 | 0.3276 | 0.4726 | 0.2038 | 0.3505 | 0.3674 | 20.0 |
102
- | No log | 31.0 | 372 | 0.3250 | 0.4726 | 0.2038 | 0.3579 | 0.3795 | 20.0 |
103
- | No log | 32.0 | 384 | 0.3273 | 0.4741 | 0.2293 | 0.3661 | 0.3896 | 20.0 |
104
- | No log | 33.0 | 396 | 0.3282 | 0.4726 | 0.2267 | 0.3594 | 0.3768 | 20.0 |
105
- | No log | 34.0 | 408 | 0.3341 | 0.4726 | 0.2267 | 0.3594 | 0.3768 | 20.0 |
106
- | No log | 35.0 | 420 | 0.3356 | 0.4726 | 0.2038 | 0.3505 | 0.3674 | 20.0 |
107
- | No log | 36.0 | 432 | 0.3326 | 0.4726 | 0.2038 | 0.3505 | 0.3674 | 20.0 |
108
- | No log | 37.0 | 444 | 0.3356 | 0.4726 | 0.2038 | 0.3505 | 0.3674 | 20.0 |
109
- | No log | 38.0 | 456 | 0.3374 | 0.4785 | 0.1735 | 0.3409 | 0.3656 | 20.0 |
110
- | No log | 39.0 | 468 | 0.3395 | 0.4356 | 0.1714 | 0.3394 | 0.3658 | 20.0 |
111
- | No log | 40.0 | 480 | 0.3497 | 0.4273 | 0.1714 | 0.3322 | 0.3482 | 20.0 |
112
- | No log | 41.0 | 492 | 0.3479 | 0.4276 | 0.1714 | 0.3586 | 0.372 | 20.0 |
113
- | 0.2605 | 42.0 | 504 | 0.3442 | 0.4617 | 0.2074 | 0.3749 | 0.3948 | 20.0 |
114
- | 0.2605 | 43.0 | 516 | 0.3450 | 0.4617 | 0.2074 | 0.3749 | 0.3948 | 20.0 |
115
- | 0.2605 | 44.0 | 528 | 0.3443 | 0.4325 | 0.1824 | 0.3352 | 0.358 | 20.0 |
116
- | 0.2605 | 45.0 | 540 | 0.3553 | 0.4277 | 0.1714 | 0.3322 | 0.355 | 20.0 |
117
- | 0.2605 | 46.0 | 552 | 0.3527 | 0.4299 | 0.163 | 0.3335 | 0.3563 | 20.0 |
118
- | 0.2605 | 47.0 | 564 | 0.3561 | 0.4227 | 0.163 | 0.3335 | 0.349 | 20.0 |
119
- | 0.2605 | 48.0 | 576 | 0.3554 | 0.4398 | 0.1834 | 0.3212 | 0.3403 | 20.0 |
120
- | 0.2605 | 49.0 | 588 | 0.3511 | 0.433 | 0.1757 | 0.3147 | 0.3307 | 20.0 |
121
- | 0.2605 | 50.0 | 600 | 0.3620 | 0.4011 | 0.1232 | 0.2925 | 0.3011 | 20.0 |
122
- | 0.2605 | 51.0 | 612 | 0.3549 | 0.3804 | 0.0873 | 0.2922 | 0.2873 | 20.0 |
123
- | 0.2605 | 52.0 | 624 | 0.3562 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
124
- | 0.2605 | 53.0 | 636 | 0.3616 | 0.4398 | 0.1834 | 0.3212 | 0.3403 | 20.0 |
125
- | 0.2605 | 54.0 | 648 | 0.3645 | 0.4398 | 0.192 | 0.3404 | 0.3618 | 20.0 |
126
- | 0.2605 | 55.0 | 660 | 0.3704 | 0.4398 | 0.1834 | 0.3293 | 0.3507 | 20.0 |
127
- | 0.2605 | 56.0 | 672 | 0.3656 | 0.4128 | 0.1331 | 0.2987 | 0.3115 | 20.0 |
128
- | 0.2605 | 57.0 | 684 | 0.3632 | 0.3748 | 0.1134 | 0.2818 | 0.2929 | 20.0 |
129
- | 0.2605 | 58.0 | 696 | 0.3690 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
130
- | 0.2605 | 59.0 | 708 | 0.3729 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
131
- | 0.2605 | 60.0 | 720 | 0.3763 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
132
- | 0.2605 | 61.0 | 732 | 0.3743 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
133
- | 0.2605 | 62.0 | 744 | 0.3715 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
134
- | 0.2605 | 63.0 | 756 | 0.3725 | 0.4398 | 0.1834 | 0.3212 | 0.3403 | 20.0 |
135
- | 0.2605 | 64.0 | 768 | 0.3650 | 0.4184 | 0.1735 | 0.344 | 0.3514 | 20.0 |
136
- | 0.2605 | 65.0 | 780 | 0.3673 | 0.4197 | 0.163 | 0.313 | 0.3358 | 20.0 |
137
- | 0.2605 | 66.0 | 792 | 0.3813 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
138
- | 0.2605 | 67.0 | 804 | 0.3874 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
139
- | 0.2605 | 68.0 | 816 | 0.3852 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
140
- | 0.2605 | 69.0 | 828 | 0.3895 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
141
- | 0.2605 | 70.0 | 840 | 0.3947 | 0.3961 | 0.1129 | 0.3205 | 0.3287 | 20.0 |
142
- | 0.2605 | 71.0 | 852 | 0.3826 | 0.4168 | 0.123 | 0.3365 | 0.3552 | 20.0 |
143
- | 0.2605 | 72.0 | 864 | 0.3811 | 0.4168 | 0.123 | 0.3365 | 0.3552 | 20.0 |
144
- | 0.2605 | 73.0 | 876 | 0.3836 | 0.3961 | 0.1129 | 0.3205 | 0.3287 | 20.0 |
145
- | 0.2605 | 74.0 | 888 | 0.3820 | 0.4398 | 0.1834 | 0.3212 | 0.3403 | 20.0 |
146
- | 0.2605 | 75.0 | 900 | 0.3866 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
147
- | 0.2605 | 76.0 | 912 | 0.3906 | 0.4227 | 0.163 | 0.3335 | 0.349 | 20.0 |
148
- | 0.2605 | 77.0 | 924 | 0.3936 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
149
- | 0.2605 | 78.0 | 936 | 0.3906 | 0.4124 | 0.163 | 0.313 | 0.3285 | 20.0 |
150
- | 0.2605 | 79.0 | 948 | 0.3931 | 0.4128 | 0.1331 | 0.3082 | 0.3165 | 20.0 |
151
- | 0.2605 | 80.0 | 960 | 0.3966 | 0.4128 | 0.1331 | 0.3082 | 0.3165 | 20.0 |
152
- | 0.2605 | 81.0 | 972 | 0.3935 | 0.4128 | 0.1331 | 0.2987 | 0.3115 | 20.0 |
153
- | 0.2605 | 82.0 | 984 | 0.3951 | 0.4128 | 0.1331 | 0.2987 | 0.3115 | 20.0 |
154
- | 0.2605 | 83.0 | 996 | 0.3954 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
155
- | 0.0959 | 84.0 | 1008 | 0.3960 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
156
- | 0.0959 | 85.0 | 1020 | 0.3980 | 0.3829 | 0.1237 | 0.3008 | 0.3135 | 20.0 |
157
- | 0.0959 | 86.0 | 1032 | 0.4003 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
158
- | 0.0959 | 87.0 | 1044 | 0.4018 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
159
- | 0.0959 | 88.0 | 1056 | 0.4056 | 0.3829 | 0.1129 | 0.2905 | 0.3 | 20.0 |
160
- | 0.0959 | 89.0 | 1068 | 0.4086 | 0.4128 | 0.1448 | 0.304 | 0.3193 | 20.0 |
161
- | 0.0959 | 90.0 | 1080 | 0.4081 | 0.4128 | 0.1448 | 0.3161 | 0.3275 | 20.0 |
162
- | 0.0959 | 91.0 | 1092 | 0.4060 | 0.3961 | 0.1246 | 0.3284 | 0.3398 | 20.0 |
163
- | 0.0959 | 92.0 | 1104 | 0.4045 | 0.3829 | 0.1246 | 0.3068 | 0.3193 | 20.0 |
164
- | 0.0959 | 93.0 | 1116 | 0.4051 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
165
- | 0.0959 | 94.0 | 1128 | 0.4038 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
166
- | 0.0959 | 95.0 | 1140 | 0.4025 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
167
- | 0.0959 | 96.0 | 1152 | 0.4026 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
168
- | 0.0959 | 97.0 | 1164 | 0.4034 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
169
- | 0.0959 | 98.0 | 1176 | 0.4032 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
170
- | 0.0959 | 99.0 | 1188 | 0.4036 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
171
- | 0.0959 | 100.0 | 1200 | 0.4037 | 0.3829 | 0.1129 | 0.2968 | 0.3082 | 20.0 |
172
 
173
 
174
  ### Framework versions
 
22
  metrics:
23
  - name: Rouge1
24
  type: rouge
25
+ value: 0.481
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the hdfs_log_summary_dataset dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.3180
36
+ - Rouge1: 0.481
37
+ - Rouge2: 0.199
38
+ - Rougel: 0.3851
39
+ - Rougelsum: 0.3851
40
+ - Gen Len: 19.0
41
 
42
  ## Model description
43
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
71
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
72
+ | No log | 1.0 | 12 | 2.6793 | 0.256 | 0.0371 | 0.1994 | 0.1972 | 19.0 |
73
+ | No log | 2.0 | 24 | 2.3598 | 0.2673 | 0.0242 | 0.2029 | 0.2026 | 19.0 |
74
+ | No log | 3.0 | 36 | 2.0954 | 0.3574 | 0.1335 | 0.3082 | 0.3103 | 19.0 |
75
+ | No log | 4.0 | 48 | 1.8625 | 0.5067 | 0.2011 | 0.4555 | 0.4555 | 19.0 |
76
+ | No log | 5.0 | 60 | 1.7234 | 0.5084 | 0.1774 | 0.4692 | 0.4692 | 19.0 |
77
+ | No log | 6.0 | 72 | 1.6112 | 0.5076 | 0.2292 | 0.4759 | 0.4758 | 19.0 |
78
+ | No log | 7.0 | 84 | 1.5393 | 0.4973 | 0.149 | 0.4351 | 0.4351 | 19.0 |
79
+ | No log | 8.0 | 96 | 1.4568 | 0.5201 | 0.1813 | 0.455 | 0.455 | 19.0 |
80
+ | No log | 9.0 | 108 | 1.3843 | 0.5201 | 0.1713 | 0.4646 | 0.4646 | 19.0 |
81
+ | No log | 10.0 | 120 | 1.3334 | 0.528 | 0.1902 | 0.4448 | 0.4417 | 19.0 |
82
+ | No log | 11.0 | 132 | 1.2955 | 0.5015 | 0.1675 | 0.4281 | 0.4281 | 19.0 |
83
+ | No log | 12.0 | 144 | 1.2696 | 0.504 | 0.1997 | 0.4622 | 0.4609 | 19.0 |
84
+ | No log | 13.0 | 156 | 1.2270 | 0.5333 | 0.2097 | 0.4521 | 0.4514 | 19.0 |
85
+ | No log | 14.0 | 168 | 1.2085 | 0.5208 | 0.183 | 0.4389 | 0.4389 | 19.0 |
86
+ | No log | 15.0 | 180 | 1.2109 | 0.5117 | 0.2378 | 0.484 | 0.4788 | 19.0 |
87
+ | No log | 16.0 | 192 | 1.1832 | 0.5012 | 0.1858 | 0.448 | 0.4472 | 19.0 |
88
+ | No log | 17.0 | 204 | 1.1816 | 0.5033 | 0.172 | 0.4216 | 0.4216 | 19.0 |
89
+ | No log | 18.0 | 216 | 1.1876 | 0.5012 | 0.1916 | 0.4391 | 0.4391 | 19.0 |
90
+ | No log | 19.0 | 228 | 1.1663 | 0.4935 | 0.1806 | 0.4333 | 0.4333 | 19.0 |
91
+ | No log | 20.0 | 240 | 1.1703 | 0.525 | 0.2545 | 0.4589 | 0.4571 | 19.0 |
92
+ | No log | 21.0 | 252 | 1.1784 | 0.5223 | 0.1939 | 0.3871 | 0.3871 | 19.0 |
93
+ | No log | 22.0 | 264 | 1.1585 | 0.5006 | 0.2246 | 0.4209 | 0.4209 | 19.0 |
94
+ | No log | 23.0 | 276 | 1.1419 | 0.5049 | 0.2173 | 0.4533 | 0.4533 | 19.0 |
95
+ | No log | 24.0 | 288 | 1.1602 | 0.4805 | 0.1934 | 0.4115 | 0.4115 | 19.0 |
96
+ | No log | 25.0 | 300 | 1.1415 | 0.5079 | 0.23 | 0.4278 | 0.4278 | 19.0 |
97
+ | No log | 26.0 | 312 | 1.1466 | 0.503 | 0.2143 | 0.4121 | 0.4121 | 19.0 |
98
+ | No log | 27.0 | 324 | 1.1420 | 0.504 | 0.1978 | 0.4413 | 0.4413 | 19.0 |
99
+ | No log | 28.0 | 336 | 1.1342 | 0.4754 | 0.161 | 0.4249 | 0.4249 | 19.0 |
100
+ | No log | 29.0 | 348 | 1.1296 | 0.4597 | 0.1781 | 0.4106 | 0.4106 | 19.0 |
101
+ | No log | 30.0 | 360 | 1.1316 | 0.4536 | 0.1596 | 0.3946 | 0.3946 | 19.0 |
102
+ | No log | 31.0 | 372 | 1.1128 | 0.4605 | 0.1943 | 0.4136 | 0.4136 | 19.0 |
103
+ | No log | 32.0 | 384 | 1.1265 | 0.4776 | 0.2088 | 0.4386 | 0.4386 | 19.0 |
104
+ | No log | 33.0 | 396 | 1.1519 | 0.4905 | 0.2251 | 0.4514 | 0.4514 | 19.0 |
105
+ | No log | 34.0 | 408 | 1.1620 | 0.4923 | 0.2256 | 0.427 | 0.4337 | 19.0 |
106
+ | No log | 35.0 | 420 | 1.1482 | 0.4702 | 0.1633 | 0.3997 | 0.3997 | 19.0 |
107
+ | No log | 36.0 | 432 | 1.1282 | 0.4573 | 0.1526 | 0.3877 | 0.3877 | 19.0 |
108
+ | No log | 37.0 | 444 | 1.1415 | 0.4684 | 0.1628 | 0.4213 | 0.4173 | 19.0 |
109
+ | No log | 38.0 | 456 | 1.1382 | 0.4583 | 0.1642 | 0.3977 | 0.3977 | 19.0 |
110
+ | No log | 39.0 | 468 | 1.1410 | 0.4922 | 0.1628 | 0.4212 | 0.4212 | 19.0 |
111
+ | No log | 40.0 | 480 | 1.1469 | 0.4619 | 0.1642 | 0.3836 | 0.3836 | 19.0 |
112
+ | No log | 41.0 | 492 | 1.1670 | 0.4417 | 0.1354 | 0.3808 | 0.3808 | 19.0 |
113
+ | 1.3411 | 42.0 | 504 | 1.1810 | 0.4407 | 0.114 | 0.3615 | 0.3615 | 19.0 |
114
+ | 1.3411 | 43.0 | 516 | 1.1487 | 0.4179 | 0.1108 | 0.3556 | 0.3556 | 19.0 |
115
+ | 1.3411 | 44.0 | 528 | 1.1588 | 0.448 | 0.1428 | 0.3691 | 0.3691 | 19.0 |
116
+ | 1.3411 | 45.0 | 540 | 1.1858 | 0.4686 | 0.163 | 0.3724 | 0.3724 | 19.0 |
117
+ | 1.3411 | 46.0 | 552 | 1.1603 | 0.4535 | 0.173 | 0.3923 | 0.3923 | 19.0 |
118
+ | 1.3411 | 47.0 | 564 | 1.1895 | 0.4622 | 0.1524 | 0.4017 | 0.4017 | 19.0 |
119
+ | 1.3411 | 48.0 | 576 | 1.2088 | 0.4465 | 0.1651 | 0.379 | 0.3746 | 19.0 |
120
+ | 1.3411 | 49.0 | 588 | 1.2149 | 0.4284 | 0.1316 | 0.36 | 0.3562 | 19.0 |
121
+ | 1.3411 | 50.0 | 600 | 1.1931 | 0.4527 | 0.1424 | 0.3821 | 0.3821 | 19.0 |
122
+ | 1.3411 | 51.0 | 612 | 1.2113 | 0.4736 | 0.2429 | 0.4268 | 0.4268 | 19.0 |
123
+ | 1.3411 | 52.0 | 624 | 1.2010 | 0.4659 | 0.1847 | 0.3817 | 0.3817 | 19.0 |
124
+ | 1.3411 | 53.0 | 636 | 1.2029 | 0.4619 | 0.2017 | 0.3954 | 0.3954 | 19.0 |
125
+ | 1.3411 | 54.0 | 648 | 1.1864 | 0.4416 | 0.1599 | 0.3739 | 0.3739 | 19.0 |
126
+ | 1.3411 | 55.0 | 660 | 1.1970 | 0.458 | 0.1214 | 0.3508 | 0.3508 | 19.0 |
127
+ | 1.3411 | 56.0 | 672 | 1.2196 | 0.4244 | 0.1678 | 0.3573 | 0.3573 | 19.0 |
128
+ | 1.3411 | 57.0 | 684 | 1.2464 | 0.4527 | 0.2177 | 0.4009 | 0.3997 | 19.0 |
129
+ | 1.3411 | 58.0 | 696 | 1.2614 | 0.4527 | 0.2177 | 0.4009 | 0.3997 | 19.0 |
130
+ | 1.3411 | 59.0 | 708 | 1.2655 | 0.4171 | 0.1669 | 0.3362 | 0.3362 | 19.0 |
131
+ | 1.3411 | 60.0 | 720 | 1.2235 | 0.4244 | 0.1678 | 0.3573 | 0.3573 | 19.0 |
132
+ | 1.3411 | 61.0 | 732 | 1.2127 | 0.4597 | 0.2303 | 0.3926 | 0.3926 | 19.0 |
133
+ | 1.3411 | 62.0 | 744 | 1.2257 | 0.4989 | 0.2331 | 0.4313 | 0.4293 | 19.0 |
134
+ | 1.3411 | 63.0 | 756 | 1.2806 | 0.4408 | 0.1314 | 0.361 | 0.361 | 19.0 |
135
+ | 1.3411 | 64.0 | 768 | 1.2993 | 0.4306 | 0.1125 | 0.338 | 0.338 | 19.0 |
136
+ | 1.3411 | 65.0 | 780 | 1.2633 | 0.4306 | 0.1125 | 0.338 | 0.338 | 19.0 |
137
+ | 1.3411 | 66.0 | 792 | 1.2495 | 0.481 | 0.174 | 0.3733 | 0.3733 | 19.0 |
138
+ | 1.3411 | 67.0 | 804 | 1.2415 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
139
+ | 1.3411 | 68.0 | 816 | 1.2658 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
140
+ | 1.3411 | 69.0 | 828 | 1.2628 | 0.4715 | 0.209 | 0.3946 | 0.3946 | 19.0 |
141
+ | 1.3411 | 70.0 | 840 | 1.2368 | 0.4715 | 0.209 | 0.3946 | 0.3946 | 19.0 |
142
+ | 1.3411 | 71.0 | 852 | 1.2456 | 0.4416 | 0.1474 | 0.3739 | 0.3739 | 19.0 |
143
+ | 1.3411 | 72.0 | 864 | 1.2683 | 0.4149 | 0.1465 | 0.3593 | 0.3593 | 19.0 |
144
+ | 1.3411 | 73.0 | 876 | 1.2821 | 0.4306 | 0.1365 | 0.3498 | 0.3498 | 19.0 |
145
+ | 1.3411 | 74.0 | 888 | 1.2818 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
146
+ | 1.3411 | 75.0 | 900 | 1.2872 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
147
+ | 1.3411 | 76.0 | 912 | 1.2939 | 0.4306 | 0.1365 | 0.3498 | 0.3498 | 19.0 |
148
+ | 1.3411 | 77.0 | 924 | 1.2818 | 0.4457 | 0.174 | 0.3607 | 0.3615 | 19.0 |
149
+ | 1.3411 | 78.0 | 936 | 1.2915 | 0.4306 | 0.1365 | 0.3498 | 0.3498 | 19.0 |
150
+ | 1.3411 | 79.0 | 948 | 1.2721 | 0.4306 | 0.1365 | 0.3498 | 0.3498 | 19.0 |
151
+ | 1.3411 | 80.0 | 960 | 1.2740 | 0.4306 | 0.1365 | 0.3498 | 0.3498 | 19.0 |
152
+ | 1.3411 | 81.0 | 972 | 1.2809 | 0.4306 | 0.1365 | 0.3498 | 0.3498 | 19.0 |
153
+ | 1.3411 | 82.0 | 984 | 1.2844 | 0.4457 | 0.174 | 0.3607 | 0.3615 | 19.0 |
154
+ | 1.3411 | 83.0 | 996 | 1.2838 | 0.4725 | 0.1749 | 0.3761 | 0.3761 | 19.0 |
155
+ | 0.5569 | 84.0 | 1008 | 1.2767 | 0.4725 | 0.1749 | 0.3761 | 0.3761 | 19.0 |
156
+ | 0.5569 | 85.0 | 1020 | 1.2868 | 0.4835 | 0.2049 | 0.3961 | 0.3961 | 19.0 |
157
+ | 0.5569 | 86.0 | 1032 | 1.2878 | 0.4607 | 0.1374 | 0.3644 | 0.3644 | 19.0 |
158
+ | 0.5569 | 87.0 | 1044 | 1.2906 | 0.4607 | 0.1374 | 0.3644 | 0.3644 | 19.0 |
159
+ | 0.5569 | 88.0 | 1056 | 1.3023 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
160
+ | 0.5569 | 89.0 | 1068 | 1.3053 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
161
+ | 0.5569 | 90.0 | 1080 | 1.3044 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
162
+ | 0.5569 | 91.0 | 1092 | 1.3097 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
163
+ | 0.5569 | 92.0 | 1104 | 1.3169 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
164
+ | 0.5569 | 93.0 | 1116 | 1.3269 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
165
+ | 0.5569 | 94.0 | 1128 | 1.3271 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
166
+ | 0.5569 | 95.0 | 1140 | 1.3276 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
167
+ | 0.5569 | 96.0 | 1152 | 1.3250 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
168
+ | 0.5569 | 97.0 | 1164 | 1.3211 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
169
+ | 0.5569 | 98.0 | 1176 | 1.3192 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
170
+ | 0.5569 | 99.0 | 1188 | 1.3182 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
171
+ | 0.5569 | 100.0 | 1200 | 1.3180 | 0.481 | 0.199 | 0.3851 | 0.3851 | 19.0 |
172
 
173
 
174
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab70154a183457225790b4cb448b022da372a26b721df9f901839edb09c9056e
3
  size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be17d885bf488b7e9f991f5f06b22602a9c4c53df2ffe0834edb62eed8a15f02
3
  size 990345064