Hugging Face's logo

khoon485
/
x-x

Transformers
PyTorch
t5
text2text-generation
text-generation-inference
Model card Files
xet
Community
1
khoon485 commited on
Commit
ef7c598
·
1 Parent(s): b158ba2

13 epochs

Browse files
Files changed (5) hide show
  1. optimizer.pt +1 -1
  2. pytorch_model.bin +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +117 -3
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bd2396e8c4044a89d7d3908b6e2328b297dbd08b54d1c4423bb2b01b0adaa06
3
  size 1783379133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7250ce1ab70dc1a9fd526bb4d5d8eb5222e08cdf5b654e319428c72c219d89
3
  size 1783379133
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39e746775bd36ccede686a6b781100732a1055ba403de0cba9f3d221527fb43c
3
  size 891730879
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e23f9bb16399dbb6299333937b7d2eeb28058c49c33ee3ff3a2e4f28f9930cb
3
  size 891730879
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e112daa31c8c8de4ddb29ff665b6e38a8d0f15e6d3369cad5733315afb46c5e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d5b1bae4964fb2f4d01538a124e8fa3d09ef60275a74b9b04e9572c2256028
3
  size 14503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b152c49beef70c9da2fafe4ee753ae269aeb7c1432e9692ac4001c492ac4d5a
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06cbc2ad564cf4cd4ae1683a2a75297d61e4bb88322c20b1f9c2c3540e65749c
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.282580828941746,
5
- "global_step": 1000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -22,11 +22,125 @@
22
  "eval_samples_per_second": 111.822,
23
  "eval_steps_per_second": 27.955,
24
  "step": 876
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "max_steps": 6570,
28
  "num_train_epochs": 15,
29
- "total_flos": 7.807053292240896e+16,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 14.838626976214215,
5
+ "global_step": 6500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 111.822,
23
  "eval_steps_per_second": 27.955,
24
  "step": 876
25
+ },
26
+ {
27
+ "epoch": 3.0,
28
+ "eval_loss": 0.7799285054206848,
29
+ "eval_runtime": 267.0428,
30
+ "eval_samples_per_second": 93.214,
31
+ "eval_steps_per_second": 23.303,
32
+ "step": 1314
33
+ },
34
+ {
35
+ "epoch": 4.0,
36
+ "eval_loss": 0.7528017163276672,
37
+ "eval_runtime": 225.2214,
38
+ "eval_samples_per_second": 110.522,
39
+ "eval_steps_per_second": 27.631,
40
+ "step": 1752
41
+ },
42
+ {
43
+ "epoch": 4.57,
44
+ "learning_rate": 6.9558599695586e-05,
45
+ "loss": 0.9432,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "eval_loss": 0.7184237241744995,
51
+ "eval_runtime": 225.9905,
52
+ "eval_samples_per_second": 110.146,
53
+ "eval_steps_per_second": 27.537,
54
+ "step": 2190
55
+ },
56
+ {
57
+ "epoch": 6.0,
58
+ "eval_loss": 0.6917603611946106,
59
+ "eval_runtime": 229.2094,
60
+ "eval_samples_per_second": 108.599,
61
+ "eval_steps_per_second": 27.15,
62
+ "step": 2628
63
+ },
64
+ {
65
+ "epoch": 7.0,
66
+ "eval_loss": 0.6674416065216064,
67
+ "eval_runtime": 228.8661,
68
+ "eval_samples_per_second": 108.762,
69
+ "eval_steps_per_second": 27.191,
70
+ "step": 3066
71
+ },
72
+ {
73
+ "epoch": 8.0,
74
+ "eval_loss": 0.6534304022789001,
75
+ "eval_runtime": 238.4381,
76
+ "eval_samples_per_second": 104.396,
77
+ "eval_steps_per_second": 26.099,
78
+ "step": 3504
79
+ },
80
+ {
81
+ "epoch": 9.0,
82
+ "eval_loss": 0.6406867504119873,
83
+ "eval_runtime": 235.4552,
84
+ "eval_samples_per_second": 105.719,
85
+ "eval_steps_per_second": 26.43,
86
+ "step": 3942
87
+ },
88
+ {
89
+ "epoch": 9.13,
90
+ "learning_rate": 3.9117199391171995e-05,
91
+ "loss": 0.6607,
92
+ "step": 4000
93
+ },
94
+ {
95
+ "epoch": 10.0,
96
+ "eval_loss": 0.6275271773338318,
97
+ "eval_runtime": 231.6414,
98
+ "eval_samples_per_second": 107.459,
99
+ "eval_steps_per_second": 26.865,
100
+ "step": 4380
101
+ },
102
+ {
103
+ "epoch": 11.0,
104
+ "eval_loss": 0.6164868474006653,
105
+ "eval_runtime": 229.8159,
106
+ "eval_samples_per_second": 108.313,
107
+ "eval_steps_per_second": 27.078,
108
+ "step": 4818
109
+ },
110
+ {
111
+ "epoch": 12.0,
112
+ "eval_loss": 0.610621452331543,
113
+ "eval_runtime": 234.5136,
114
+ "eval_samples_per_second": 106.143,
115
+ "eval_steps_per_second": 26.536,
116
+ "step": 5256
117
+ },
118
+ {
119
+ "epoch": 13.0,
120
+ "eval_loss": 0.6076993942260742,
121
+ "eval_runtime": 221.8665,
122
+ "eval_samples_per_second": 112.194,
123
+ "eval_steps_per_second": 28.048,
124
+ "step": 5694
125
+ },
126
+ {
127
+ "epoch": 13.7,
128
+ "learning_rate": 8.675799086757991e-06,
129
+ "loss": 0.5624,
130
+ "step": 6000
131
+ },
132
+ {
133
+ "epoch": 14.0,
134
+ "eval_loss": 0.6030386686325073,
135
+ "eval_runtime": 225.3038,
136
+ "eval_samples_per_second": 110.482,
137
+ "eval_steps_per_second": 27.62,
138
+ "step": 6132
139
  }
140
  ],
141
  "max_steps": 6570,
142
  "num_train_epochs": 15,
143
+ "total_flos": 5.075204254610227e+17,
144
  "trial_name": null,
145
  "trial_params": null
146
  }