Hugging Face's logo

shorecode
/
t5-efficient-tiny-summarizer-general-purpose-v2

Transformers
PyTorch
TensorFlow
ONNX
Safetensors
English
t5
text2text-generation
summary
summarizer
Eval Results (legacy)
text-generation-inference
Model card Files
xet
Community
shorecode commited on
Commit
3a7ddb5
·
verified ·
1 Parent(s): 78fdc81

Delete checkpoint-latest/trainer_state.json

Browse files
Files changed (1) hide show
  1. checkpoint-latest/trainer_state.json +0 -210
checkpoint-latest/trainer_state.json DELETED
@@ -1,210 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.4331348132106118,
6
- "eval_steps": 500,
7
- "global_step": 4000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.02707092582566324,
14
- "grad_norm": 0.8431992530822754,
15
- "learning_rate": 9.910124526258799e-05,
16
- "loss": 4.3576,
17
- "step": 250
18
- },
19
- {
20
- "epoch": 0.05414185165132648,
21
- "grad_norm": 0.8061181306838989,
22
- "learning_rate": 9.819888106839921e-05,
23
- "loss": 4.2775,
24
- "step": 500
25
- },
26
- {
27
- "epoch": 0.05414185165132648,
28
- "eval_loss": 3.5462777614593506,
29
- "eval_runtime": 87.734,
30
- "eval_samples_per_second": 112.271,
31
- "eval_steps_per_second": 7.021,
32
- "step": 500
33
- },
34
- {
35
- "epoch": 0.08121277747698971,
36
- "grad_norm": 0.7875335812568665,
37
- "learning_rate": 9.729651687421044e-05,
38
- "loss": 4.1927,
39
- "step": 750
40
- },
41
- {
42
- "epoch": 0.10828370330265295,
43
- "grad_norm": 1.0330173969268799,
44
- "learning_rate": 9.639415268002166e-05,
45
- "loss": 4.1178,
46
- "step": 1000
47
- },
48
- {
49
- "epoch": 0.10828370330265295,
50
- "eval_loss": 3.3765828609466553,
51
- "eval_runtime": 87.6227,
52
- "eval_samples_per_second": 112.414,
53
- "eval_steps_per_second": 7.03,
54
- "step": 1000
55
- },
56
- {
57
- "epoch": 0.1353546291283162,
58
- "grad_norm": 1.041638731956482,
59
- "learning_rate": 9.549178848583288e-05,
60
- "loss": 4.0201,
61
- "step": 1250
62
- },
63
- {
64
- "epoch": 0.16242555495397942,
65
- "grad_norm": 0.8976061940193176,
66
- "learning_rate": 9.458942429164411e-05,
67
- "loss": 3.9802,
68
- "step": 1500
69
- },
70
- {
71
- "epoch": 0.16242555495397942,
72
- "eval_loss": 3.2597038745880127,
73
- "eval_runtime": 87.5921,
74
- "eval_samples_per_second": 112.453,
75
- "eval_steps_per_second": 7.033,
76
- "step": 1500
77
- },
78
- {
79
- "epoch": 0.18949648077964265,
80
- "grad_norm": 1.0333911180496216,
81
- "learning_rate": 9.368706009745533e-05,
82
- "loss": 3.9335,
83
- "step": 1750
84
- },
85
- {
86
- "epoch": 0.2165674066053059,
87
- "grad_norm": 0.9179081320762634,
88
- "learning_rate": 9.278469590326656e-05,
89
- "loss": 3.8709,
90
- "step": 2000
91
- },
92
- {
93
- "epoch": 0.2165674066053059,
94
- "eval_loss": 3.1846394538879395,
95
- "eval_runtime": 87.5421,
96
- "eval_samples_per_second": 112.517,
97
- "eval_steps_per_second": 7.037,
98
- "step": 2000
99
- },
100
- {
101
- "epoch": 0.24363833243096913,
102
- "grad_norm": 1.0419113636016846,
103
- "learning_rate": 9.188233170907778e-05,
104
- "loss": 3.8416,
105
- "step": 2250
106
- },
107
- {
108
- "epoch": 0.2707092582566324,
109
- "grad_norm": 0.9652225375175476,
110
- "learning_rate": 9.0979967514889e-05,
111
- "loss": 3.807,
112
- "step": 2500
113
- },
114
- {
115
- "epoch": 0.2707092582566324,
116
- "eval_loss": 3.119335174560547,
117
- "eval_runtime": 87.4769,
118
- "eval_samples_per_second": 112.601,
119
- "eval_steps_per_second": 7.042,
120
- "step": 2500
121
- },
122
- {
123
- "epoch": 0.2977801840822956,
124
- "grad_norm": 0.8792561888694763,
125
- "learning_rate": 9.007760332070024e-05,
126
- "loss": 3.7754,
127
- "step": 2750
128
- },
129
- {
130
- "epoch": 0.32485110990795885,
131
- "grad_norm": 0.9625837206840515,
132
- "learning_rate": 8.917523912651147e-05,
133
- "loss": 3.7471,
134
- "step": 3000
135
- },
136
- {
137
- "epoch": 0.32485110990795885,
138
- "eval_loss": 3.0782463550567627,
139
- "eval_runtime": 87.7273,
140
- "eval_samples_per_second": 112.28,
141
- "eval_steps_per_second": 7.022,
142
- "step": 3000
143
- },
144
- {
145
- "epoch": 0.3519220357336221,
146
- "grad_norm": 1.0289523601531982,
147
- "learning_rate": 8.827287493232269e-05,
148
- "loss": 3.7326,
149
- "step": 3250
150
- },
151
- {
152
- "epoch": 0.3789929615592853,
153
- "grad_norm": 0.9764179587364197,
154
- "learning_rate": 8.737051073813391e-05,
155
- "loss": 3.6939,
156
- "step": 3500
157
- },
158
- {
159
- "epoch": 0.3789929615592853,
160
- "eval_loss": 3.052320718765259,
161
- "eval_runtime": 87.6344,
162
- "eval_samples_per_second": 112.399,
163
- "eval_steps_per_second": 7.029,
164
- "step": 3500
165
- },
166
- {
167
- "epoch": 0.4060638873849486,
168
- "grad_norm": 0.9247903227806091,
169
- "learning_rate": 8.646814654394514e-05,
170
- "loss": 3.6782,
171
- "step": 3750
172
- },
173
- {
174
- "epoch": 0.4331348132106118,
175
- "grad_norm": 0.9769233465194702,
176
- "learning_rate": 8.556578234975636e-05,
177
- "loss": 3.6654,
178
- "step": 4000
179
- },
180
- {
181
- "epoch": 0.4331348132106118,
182
- "eval_loss": 3.0321156978607178,
183
- "eval_runtime": 87.6462,
184
- "eval_samples_per_second": 112.384,
185
- "eval_steps_per_second": 7.028,
186
- "step": 4000
187
- }
188
- ],
189
- "logging_steps": 250,
190
- "max_steps": 27705,
191
- "num_input_tokens_seen": 0,
192
- "num_train_epochs": 3,
193
- "save_steps": 1000,
194
- "stateful_callbacks": {
195
- "TrainerControl": {
196
- "args": {
197
- "should_epoch_stop": false,
198
- "should_evaluate": false,
199
- "should_log": false,
200
- "should_save": true,
201
- "should_training_stop": false
202
- },
203
- "attributes": {}
204
- }
205
- },
206
- "total_flos": 1444216307712000.0,
207
- "train_batch_size": 16,
208
- "trial_name": null,
209
- "trial_params": null
210
- }