Hugging Face's logo

kargaranamir
/
T5R-base

Text Generation
Transformers
PyTorch
Safetensors
English
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
2
kargaranamir commited on
Commit
c42fef0
·
1 Parent(s): db8ad7a

add checkpoint of 11702

Browse files
Files changed (3) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +180 -0
  3. training_args.bin +2 -2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80197bb280e4040dcaee84d931b396a072626ddd751ee247d45314bae8e56935
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3ab72f6ea636e6e3de721bec36b2d30a6e749a518e2673f24deefb64f89557
3
  size 307910149
trainer_state.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3581866025924683,
3
+ "best_model_checkpoint": "flan-t5-small-prompt/checkpoint-11702",
4
+ "epoch": 2.0,
5
+ "global_step": 11702,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 4.91454452230388e-05,
13
+ "loss": 2.2473,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.17,
18
+ "learning_rate": 4.82908904460776e-05,
19
+ "loss": 1.9761,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.26,
24
+ "learning_rate": 4.7436335669116395e-05,
25
+ "loss": 1.8802,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.34,
30
+ "learning_rate": 4.658178089215519e-05,
31
+ "loss": 1.8477,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.43,
36
+ "learning_rate": 4.572722611519399e-05,
37
+ "loss": 1.8029,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.51,
42
+ "learning_rate": 4.487267133823278e-05,
43
+ "loss": 1.7633,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.6,
48
+ "learning_rate": 4.401811656127158e-05,
49
+ "loss": 1.7704,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.68,
54
+ "learning_rate": 4.3163561784310376e-05,
55
+ "loss": 1.7068,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.77,
60
+ "learning_rate": 4.230900700734917e-05,
61
+ "loss": 1.732,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.85,
66
+ "learning_rate": 4.145445223038797e-05,
67
+ "loss": 1.7168,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.94,
72
+ "learning_rate": 4.059989745342677e-05,
73
+ "loss": 1.6812,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.0,
78
+ "eval_gen_len": 14.935384615384615,
79
+ "eval_loss": 1.4240827560424805,
80
+ "eval_rouge1": 52.0316,
81
+ "eval_rouge2": 33.7896,
82
+ "eval_rougeL": 49.2826,
83
+ "eval_rougeLsum": 49.8238,
84
+ "eval_runtime": 375.6869,
85
+ "eval_samples_per_second": 13.841,
86
+ "eval_steps_per_second": 1.73,
87
+ "step": 5851
88
+ },
89
+ {
90
+ "epoch": 1.03,
91
+ "learning_rate": 3.9745342676465566e-05,
92
+ "loss": 1.6711,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 1.11,
97
+ "learning_rate": 3.889078789950436e-05,
98
+ "loss": 1.651,
99
+ "step": 6500
100
+ },
101
+ {
102
+ "epoch": 1.2,
103
+ "learning_rate": 3.803623312254316e-05,
104
+ "loss": 1.6327,
105
+ "step": 7000
106
+ },
107
+ {
108
+ "epoch": 1.28,
109
+ "learning_rate": 3.718167834558196e-05,
110
+ "loss": 1.6171,
111
+ "step": 7500
112
+ },
113
+ {
114
+ "epoch": 1.37,
115
+ "learning_rate": 3.6327123568620756e-05,
116
+ "loss": 1.6142,
117
+ "step": 8000
118
+ },
119
+ {
120
+ "epoch": 1.45,
121
+ "learning_rate": 3.5472568791659546e-05,
122
+ "loss": 1.5843,
123
+ "step": 8500
124
+ },
125
+ {
126
+ "epoch": 1.54,
127
+ "learning_rate": 3.4618014014698344e-05,
128
+ "loss": 1.6075,
129
+ "step": 9000
130
+ },
131
+ {
132
+ "epoch": 1.62,
133
+ "learning_rate": 3.376345923773714e-05,
134
+ "loss": 1.5917,
135
+ "step": 9500
136
+ },
137
+ {
138
+ "epoch": 1.71,
139
+ "learning_rate": 3.290890446077594e-05,
140
+ "loss": 1.5797,
141
+ "step": 10000
142
+ },
143
+ {
144
+ "epoch": 1.79,
145
+ "learning_rate": 3.205434968381473e-05,
146
+ "loss": 1.6037,
147
+ "step": 10500
148
+ },
149
+ {
150
+ "epoch": 1.88,
151
+ "learning_rate": 3.119979490685353e-05,
152
+ "loss": 1.5926,
153
+ "step": 11000
154
+ },
155
+ {
156
+ "epoch": 1.97,
157
+ "learning_rate": 3.0345240129892328e-05,
158
+ "loss": 1.5684,
159
+ "step": 11500
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_gen_len": 14.967115384615385,
164
+ "eval_loss": 1.3581866025924683,
165
+ "eval_rouge1": 53.5315,
166
+ "eval_rouge2": 35.1883,
167
+ "eval_rougeL": 50.7765,
168
+ "eval_rougeLsum": 51.3334,
169
+ "eval_runtime": 392.0061,
170
+ "eval_samples_per_second": 13.265,
171
+ "eval_steps_per_second": 1.658,
172
+ "step": 11702
173
+ }
174
+ ],
175
+ "max_steps": 29255,
176
+ "num_train_epochs": 5,
177
+ "total_flos": 1.7400094802313216e+16,
178
+ "trial_name": null,
179
+ "trial_params": null
180
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64295139b77ebb9e80e27524e977a5265cdccfeff934cc9e486ae5dc458d0694
3
- size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7257d6caf5b46b4cad8fdf3be2665f3c34e9f31a968dcd6c0daa21d82fff990
3
+ size 4091