Hugging Face's logo

lxuechen
/
tldr-gpt2-xl

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
1
Xuechen Li commited on
Commit
e438133
·
1 Parent(s): 0988226

Large model.

Browse files
Files changed (5) hide show
  1. config.json +40 -0
  2. log.out +0 -0
  3. pytorch_model.bin +3 -0
  4. trainer_state.json +227 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-xl",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2FlashLMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1600,
16
+ "n_head": 25,
17
+ "n_inner": null,
18
+ "n_layer": 48,
19
+ "n_positions": 1024,
20
+ "output_past": true,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.25.1",
38
+ "use_cache": true,
39
+ "vocab_size": 50258
40
+ }
log.out ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6952a3c58b216b8ef9252b5cbeefcf213ad2ed7d66b73007d39eadb6795d3094
3
+ size 6281006513
trainer_state.json ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.999023320368054,
5
+ "global_step": 2733,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 9.998862506715891e-06,
13
+ "loss": 2.3408,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.22,
18
+ "learning_rate": 9.951193630803286e-06,
19
+ "loss": 2.2705,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.33,
24
+ "learning_rate": 9.834073214196232e-06,
25
+ "loss": 2.2454,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.44,
30
+ "learning_rate": 9.649144132125768e-06,
31
+ "loss": 2.2308,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.55,
36
+ "learning_rate": 9.399000427690736e-06,
37
+ "loss": 2.222,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "eval_loss": 2.1795129776000977,
43
+ "eval_runtime": 134.9568,
44
+ "eval_samples_per_second": 47.771,
45
+ "eval_steps_per_second": 11.945,
46
+ "step": 500
47
+ },
48
+ {
49
+ "epoch": 0.66,
50
+ "learning_rate": 9.087150924613952e-06,
51
+ "loss": 2.2111,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.77,
56
+ "learning_rate": 8.717970008158547e-06,
57
+ "loss": 2.2157,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.88,
62
+ "learning_rate": 8.296636264611935e-06,
63
+ "loss": 2.1904,
64
+ "step": 800
65
+ },
66
+ {
67
+ "epoch": 0.99,
68
+ "learning_rate": 7.829059840055622e-06,
69
+ "loss": 2.1934,
70
+ "step": 900
71
+ },
72
+ {
73
+ "epoch": 1.1,
74
+ "learning_rate": 7.321799537376213e-06,
75
+ "loss": 2.1122,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 1.1,
80
+ "eval_loss": 2.1545722484588623,
81
+ "eval_runtime": 135.1839,
82
+ "eval_samples_per_second": 47.691,
83
+ "eval_steps_per_second": 11.924,
84
+ "step": 1000
85
+ },
86
+ {
87
+ "epoch": 1.21,
88
+ "learning_rate": 6.781970814417049e-06,
89
+ "loss": 2.0764,
90
+ "step": 1100
91
+ },
92
+ {
93
+ "epoch": 1.32,
94
+ "learning_rate": 6.217145973801762e-06,
95
+ "loss": 2.0787,
96
+ "step": 1200
97
+ },
98
+ {
99
+ "epoch": 1.43,
100
+ "learning_rate": 5.635247944490186e-06,
101
+ "loss": 2.0785,
102
+ "step": 1300
103
+ },
104
+ {
105
+ "epoch": 1.54,
106
+ "learning_rate": 5.044439145017379e-06,
107
+ "loss": 2.0739,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 1.65,
112
+ "learning_rate": 4.453006987356882e-06,
113
+ "loss": 2.0817,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 1.65,
118
+ "eval_loss": 2.139988422393799,
119
+ "eval_runtime": 135.0241,
120
+ "eval_samples_per_second": 47.747,
121
+ "eval_steps_per_second": 11.939,
122
+ "step": 1500
123
+ },
124
+ {
125
+ "epoch": 1.76,
126
+ "learning_rate": 3.869247627472021e-06,
127
+ "loss": 2.0758,
128
+ "step": 1600
129
+ },
130
+ {
131
+ "epoch": 1.87,
132
+ "learning_rate": 3.3013495932132446e-06,
133
+ "loss": 2.0758,
134
+ "step": 1700
135
+ },
136
+ {
137
+ "epoch": 1.97,
138
+ "learning_rate": 2.7572789219399587e-06,
139
+ "loss": 2.0732,
140
+ "step": 1800
141
+ },
142
+ {
143
+ "epoch": 2.09,
144
+ "learning_rate": 2.2446674190680336e-06,
145
+ "loss": 2.0324,
146
+ "step": 1900
147
+ },
148
+ {
149
+ "epoch": 2.2,
150
+ "learning_rate": 1.7707056049662669e-06,
151
+ "loss": 2.0075,
152
+ "step": 2000
153
+ },
154
+ {
155
+ "epoch": 2.2,
156
+ "eval_loss": 2.139112949371338,
157
+ "eval_runtime": 135.0198,
158
+ "eval_samples_per_second": 47.749,
159
+ "eval_steps_per_second": 11.939,
160
+ "step": 2000
161
+ },
162
+ {
163
+ "epoch": 2.3,
164
+ "learning_rate": 1.3420418518604827e-06,
165
+ "loss": 1.9987,
166
+ "step": 2100
167
+ },
168
+ {
169
+ "epoch": 2.41,
170
+ "learning_rate": 9.646891255752928e-07,
171
+ "loss": 2.0033,
172
+ "step": 2200
173
+ },
174
+ {
175
+ "epoch": 2.52,
176
+ "learning_rate": 6.439406402687365e-07,
177
+ "loss": 2.0071,
178
+ "step": 2300
179
+ },
180
+ {
181
+ "epoch": 2.63,
182
+ "learning_rate": 3.8429560929037044e-07,
183
+ "loss": 1.9992,
184
+ "step": 2400
185
+ },
186
+ {
187
+ "epoch": 2.74,
188
+ "learning_rate": 1.893961336727451e-07,
189
+ "loss": 2.0045,
190
+ "step": 2500
191
+ },
192
+ {
193
+ "epoch": 2.74,
194
+ "eval_loss": 2.137310743331909,
195
+ "eval_runtime": 134.9818,
196
+ "eval_samples_per_second": 47.762,
197
+ "eval_steps_per_second": 11.942,
198
+ "step": 2500
199
+ },
200
+ {
201
+ "epoch": 2.85,
202
+ "learning_rate": 6.197611353601918e-08,
203
+ "loss": 1.9924,
204
+ "step": 2600
205
+ },
206
+ {
207
+ "epoch": 2.96,
208
+ "learning_rate": 3.822899037286276e-09,
209
+ "loss": 1.997,
210
+ "step": 2700
211
+ },
212
+ {
213
+ "epoch": 3.0,
214
+ "step": 2733,
215
+ "total_flos": 1.3361242101108096e+18,
216
+ "train_loss": 2.1056736130614966,
217
+ "train_runtime": 28254.5864,
218
+ "train_samples_per_second": 12.393,
219
+ "train_steps_per_second": 0.097
220
+ }
221
+ ],
222
+ "max_steps": 2733,
223
+ "num_train_epochs": 3,
224
+ "total_flos": 1.3361242101108096e+18,
225
+ "trial_name": null,
226
+ "trial_params": null
227
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81da82535def5bf93900410d321969191979e894d3e6f0a45849821763e6c7c4
3
+ size 3579