gowitheflow-1998 commited on
Commit
b62a0d6
1 Parent(s): 5f7ef31
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
37
+ 763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 filter=lfs diff=lfs merge=lfs -text
38
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
3
+ size 15645492
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - parallel-pt-nl-pl
6
+ model-index:
7
+ - name: allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400
15
+
16
+ This model is a fine-tuned version of [zxh4546/allnli_wikispan_unsup_ensemble_last](https://huggingface.co/zxh4546/allnli_wikispan_unsup_ensemble_last) on the PARALLEL-PT-NL-PL dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 3e-05
36
+ - train_batch_size: 128
37
+ - eval_batch_size: 16
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_steps: 1000
42
+ - training_steps: 9400
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.17.0
51
+ - Pytorch 1.11.0
52
+ - Datasets 2.14.6
53
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 8.931647637549867,
4
+ "train_runtime": 5062.6195,
5
+ "train_samples": 1201407,
6
+ "train_samples_per_second": 237.664,
7
+ "train_steps_per_second": 1.857
8
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "zxh4546/allnli_wikispan_unsup_ensemble_last",
3
+ "architectures": [
4
+ "PIXELForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 16,
10
+ "decoder_num_hidden_layers": 8,
11
+ "finetuning_task": "parallel-pt-nl-pl",
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "Entailment",
17
+ "1": "Neutral",
18
+ "2": "Contradiction"
19
+ },
20
+ "image_size": [
21
+ 16,
22
+ 1024
23
+ ],
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "interpolate_pos_encoding": false,
27
+ "label2id": {
28
+ "Contradiction": 2,
29
+ "Entailment": 0,
30
+ "Neutral": 1
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "mask_ratio": 0.25,
34
+ "model_type": "pixel",
35
+ "norm_pix_loss": true,
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "qkv_bias": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.17.0"
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b967736f6cbc69dba1819c0eb486d659782a6322ce214677f8f203af9f7f1a
3
+ size 345238445
text_renderer_config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": "white",
3
+ "dpi": 120,
4
+ "font_color": "black",
5
+ "font_file": "763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
6
+ "font_size": 8,
7
+ "fonts_list": [
8
+ "Abyssinica SIL",
9
+ "Ani",
10
+ "AnjaliOldLipi",
11
+ "C059",
12
+ "Chandas",
13
+ "Chilanka",
14
+ "D050000L",
15
+ "DejaVu Math TeX Gyre",
16
+ "DejaVu Sans",
17
+ "DejaVu Sans Mono",
18
+ "DejaVu Serif",
19
+ "Dhurjati",
20
+ "Droid Sans Fallback",
21
+ "Dyuthi",
22
+ "FreeMono",
23
+ "FreeSans",
24
+ "FreeSerif",
25
+ "Gargi",
26
+ "Garuda",
27
+ "Gayathri",
28
+ "Gidugu",
29
+ "Go Noto Current",
30
+ "Gubbi",
31
+ "Gurajada",
32
+ "Inconsolata",
33
+ "Jamrul",
34
+ "KacstArt",
35
+ "KacstBook",
36
+ "KacstDecorative",
37
+ "KacstDigital",
38
+ "KacstFarsi",
39
+ "KacstLetter",
40
+ "KacstNaskh",
41
+ "KacstOffice",
42
+ "KacstOne",
43
+ "KacstPen",
44
+ "KacstPoster",
45
+ "KacstQurn",
46
+ "KacstScreen",
47
+ "KacstTitle",
48
+ "KacstTitleL",
49
+ "Kalapi",
50
+ "Kalimati",
51
+ "Karumbi",
52
+ "Keraleeyam",
53
+ "Khmer OS",
54
+ "Khmer OS System",
55
+ "Kinnari",
56
+ "LKLUG",
57
+ "LakkiReddy",
58
+ "Laksaman",
59
+ "Liberation Mono",
60
+ "Liberation Sans",
61
+ "Liberation Sans Narrow",
62
+ "Liberation Serif",
63
+ "Likhan",
64
+ "Lohit Assamese",
65
+ "Lohit Bengali",
66
+ "Lohit Devanagari",
67
+ "Lohit Gujarati",
68
+ "Lohit Gurmukhi",
69
+ "Lohit Kannada",
70
+ "Lohit Malayalam",
71
+ "Lohit Odia",
72
+ "Lohit Tamil",
73
+ "Lohit Tamil Classical",
74
+ "Lohit Telugu",
75
+ "Loma",
76
+ "Mallanna",
77
+ "Mandali",
78
+ "Manjari",
79
+ "Meera",
80
+ "Mitra Mono",
81
+ "Monospace",
82
+ "Mukti Narrow",
83
+ "NATS",
84
+ "NTR",
85
+ "Nakula",
86
+ "Navilu",
87
+ "Nimbus Mono PS",
88
+ "Nimbus Roman",
89
+ "Nimbus Sans",
90
+ "Nimbus Sans Narrow",
91
+ "Norasi",
92
+ "Noto Color Emoji",
93
+ "Noto Mono",
94
+ "Noto Sans CJK HK",
95
+ "Noto Sans CJK JP",
96
+ "Noto Sans CJK KR",
97
+ "Noto Sans CJK SC",
98
+ "Noto Sans CJK TC",
99
+ "Noto Sans Mono",
100
+ "Noto Sans Mono CJK HK",
101
+ "Noto Sans Mono CJK JP",
102
+ "Noto Sans Mono CJK KR",
103
+ "Noto Sans Mono CJK SC",
104
+ "Noto Sans Mono CJK TC",
105
+ "Noto Serif CJK JP",
106
+ "Noto Serif CJK KR",
107
+ "Noto Serif CJK SC",
108
+ "Noto Serif CJK TC",
109
+ "OpenSymbol",
110
+ "P052",
111
+ "Padauk",
112
+ "Padauk Book",
113
+ "Pagul",
114
+ "Peddana",
115
+ "Phetsarath OT",
116
+ "Ponnala",
117
+ "Pothana2000",
118
+ "Potti Sreeramulu",
119
+ "Purisa",
120
+ "Rachana",
121
+ "RaghuMalayalamSans",
122
+ "Ramabhadra",
123
+ "Ramaraja",
124
+ "Rasa",
125
+ "RaviPrakash",
126
+ "Rekha",
127
+ "Saab",
128
+ "Sahadeva",
129
+ "Samanata",
130
+ "Samyak Devanagari",
131
+ "Samyak Gujarati",
132
+ "Samyak Malayalam",
133
+ "Samyak Tamil",
134
+ "Sans",
135
+ "Sarai",
136
+ "Sawasdee",
137
+ "Serif",
138
+ "Source Code Pro",
139
+ "Sree Krushnadevaraya",
140
+ "Standard Symbols PS",
141
+ "Suranna",
142
+ "Suravaram",
143
+ "Suruma",
144
+ "Syamala Ramana",
145
+ "System-ui",
146
+ "TenaliRamakrishna",
147
+ "Tibetan Machine Uni",
148
+ "Timmana",
149
+ "Tlwg Mono",
150
+ "Tlwg Typewriter",
151
+ "Tlwg Typist",
152
+ "Tlwg Typo",
153
+ "URW Bookman",
154
+ "URW Gothic",
155
+ "Ubuntu",
156
+ "Ubuntu Condensed",
157
+ "Ubuntu Mono",
158
+ "Umpush",
159
+ "Uroob",
160
+ "Vemana2000",
161
+ "Waree",
162
+ "Yrsa",
163
+ "Z003",
164
+ "aakar",
165
+ "mry_KacstQurn",
166
+ "ori1Uni",
167
+ "padmaa",
168
+ "padmaa-Bold.1.1"
169
+ ],
170
+ "max_seq_length": 64,
171
+ "pad_size": 3,
172
+ "pixels_per_patch": 16,
173
+ "rgb": false,
174
+ "text_renderer_type": "PangoCairoTextRenderer"
175
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 8.931647637549867,
4
+ "train_runtime": 5062.6195,
5
+ "train_samples": 1201407,
6
+ "train_samples_per_second": 237.664,
7
+ "train_steps_per_second": 1.857
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7769453778278917,
3
+ "best_model_checkpoint": "2-parallel-pt-nl-pl-**zxh4546/allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400/checkpoint-9200",
4
+ "epoch": 1.0014915832090348,
5
+ "global_step": 9400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 6e-06,
13
+ "loss": 68.9386,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 1.2e-05,
19
+ "loss": 29.743,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 1.8e-05,
25
+ "loss": 22.6828,
26
+ "step": 600
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 2.4e-05,
31
+ "loss": 18.3538,
32
+ "step": 800
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 3e-05,
37
+ "loss": 16.8795,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 2.9285714285714284e-05,
43
+ "loss": 15.0949,
44
+ "step": 1200
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 2.857142857142857e-05,
49
+ "loss": 13.1123,
50
+ "step": 1400
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 2.7857142857142858e-05,
55
+ "loss": 11.6076,
56
+ "step": 1600
57
+ },
58
+ {
59
+ "epoch": 0.19,
60
+ "learning_rate": 2.7142857142857144e-05,
61
+ "loss": 11.0653,
62
+ "step": 1800
63
+ },
64
+ {
65
+ "epoch": 0.21,
66
+ "learning_rate": 2.6428571428571428e-05,
67
+ "loss": 10.2023,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 0.23,
72
+ "learning_rate": 2.5714285714285714e-05,
73
+ "loss": 9.4697,
74
+ "step": 2200
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 2.5e-05,
79
+ "loss": 9.073,
80
+ "step": 2400
81
+ },
82
+ {
83
+ "epoch": 0.28,
84
+ "learning_rate": 2.4285714285714288e-05,
85
+ "loss": 8.2219,
86
+ "step": 2600
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "learning_rate": 2.357142857142857e-05,
91
+ "loss": 8.1709,
92
+ "step": 2800
93
+ },
94
+ {
95
+ "epoch": 0.32,
96
+ "learning_rate": 2.2857142857142858e-05,
97
+ "loss": 7.6007,
98
+ "step": 3000
99
+ },
100
+ {
101
+ "epoch": 0.34,
102
+ "learning_rate": 2.2142857142857145e-05,
103
+ "loss": 7.3222,
104
+ "step": 3200
105
+ },
106
+ {
107
+ "epoch": 0.36,
108
+ "learning_rate": 2.1428571428571428e-05,
109
+ "loss": 6.8397,
110
+ "step": 3400
111
+ },
112
+ {
113
+ "epoch": 0.38,
114
+ "learning_rate": 2.0714285714285715e-05,
115
+ "loss": 6.7136,
116
+ "step": 3600
117
+ },
118
+ {
119
+ "epoch": 0.4,
120
+ "learning_rate": 1.9999999999999998e-05,
121
+ "loss": 6.4772,
122
+ "step": 3800
123
+ },
124
+ {
125
+ "epoch": 0.43,
126
+ "learning_rate": 1.928571428571429e-05,
127
+ "loss": 6.136,
128
+ "step": 4000
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "learning_rate": 1.8571428571428572e-05,
133
+ "loss": 6.3031,
134
+ "step": 4200
135
+ },
136
+ {
137
+ "epoch": 0.47,
138
+ "learning_rate": 1.785714285714286e-05,
139
+ "loss": 5.8973,
140
+ "step": 4400
141
+ },
142
+ {
143
+ "epoch": 0.49,
144
+ "learning_rate": 1.7142857142857142e-05,
145
+ "loss": 5.849,
146
+ "step": 4600
147
+ },
148
+ {
149
+ "epoch": 0.51,
150
+ "learning_rate": 1.6428571428571432e-05,
151
+ "loss": 5.7724,
152
+ "step": 4800
153
+ },
154
+ {
155
+ "epoch": 0.53,
156
+ "learning_rate": 1.5714285714285715e-05,
157
+ "loss": 5.5508,
158
+ "step": 5000
159
+ },
160
+ {
161
+ "epoch": 0.55,
162
+ "learning_rate": 1.5e-05,
163
+ "loss": 5.1375,
164
+ "step": 5200
165
+ },
166
+ {
167
+ "epoch": 0.58,
168
+ "learning_rate": 1.4285714285714285e-05,
169
+ "loss": 5.3564,
170
+ "step": 5400
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "learning_rate": 1.3571428571428572e-05,
175
+ "loss": 5.173,
176
+ "step": 5600
177
+ },
178
+ {
179
+ "epoch": 0.62,
180
+ "learning_rate": 1.2857142857142857e-05,
181
+ "loss": 4.8572,
182
+ "step": 5800
183
+ },
184
+ {
185
+ "epoch": 0.64,
186
+ "learning_rate": 1.2142857142857144e-05,
187
+ "loss": 5.0517,
188
+ "step": 6000
189
+ },
190
+ {
191
+ "epoch": 0.66,
192
+ "learning_rate": 1.1428571428571429e-05,
193
+ "loss": 4.8886,
194
+ "step": 6200
195
+ },
196
+ {
197
+ "epoch": 0.68,
198
+ "learning_rate": 1.0714285714285714e-05,
199
+ "loss": 4.7235,
200
+ "step": 6400
201
+ },
202
+ {
203
+ "epoch": 0.7,
204
+ "learning_rate": 9.999999999999999e-06,
205
+ "loss": 4.4131,
206
+ "step": 6600
207
+ },
208
+ {
209
+ "epoch": 0.72,
210
+ "learning_rate": 9.285714285714286e-06,
211
+ "loss": 4.6411,
212
+ "step": 6800
213
+ },
214
+ {
215
+ "epoch": 0.75,
216
+ "learning_rate": 8.571428571428571e-06,
217
+ "loss": 4.3489,
218
+ "step": 7000
219
+ },
220
+ {
221
+ "epoch": 0.77,
222
+ "learning_rate": 7.857142857142858e-06,
223
+ "loss": 4.4199,
224
+ "step": 7200
225
+ },
226
+ {
227
+ "epoch": 0.79,
228
+ "learning_rate": 7.142857142857143e-06,
229
+ "loss": 4.2557,
230
+ "step": 7400
231
+ },
232
+ {
233
+ "epoch": 0.81,
234
+ "learning_rate": 6.428571428571429e-06,
235
+ "loss": 3.9598,
236
+ "step": 7600
237
+ },
238
+ {
239
+ "epoch": 0.83,
240
+ "learning_rate": 5.7142857142857145e-06,
241
+ "loss": 4.1423,
242
+ "step": 7800
243
+ },
244
+ {
245
+ "epoch": 0.85,
246
+ "learning_rate": 4.9999999999999996e-06,
247
+ "loss": 3.9408,
248
+ "step": 8000
249
+ },
250
+ {
251
+ "epoch": 0.87,
252
+ "learning_rate": 4.2857142857142855e-06,
253
+ "loss": 4.1499,
254
+ "step": 8200
255
+ },
256
+ {
257
+ "epoch": 0.89,
258
+ "learning_rate": 3.5714285714285714e-06,
259
+ "loss": 4.0065,
260
+ "step": 8400
261
+ },
262
+ {
263
+ "epoch": 0.92,
264
+ "learning_rate": 2.8571428571428573e-06,
265
+ "loss": 3.7546,
266
+ "step": 8600
267
+ },
268
+ {
269
+ "epoch": 0.94,
270
+ "learning_rate": 2.1428571428571427e-06,
271
+ "loss": 3.8722,
272
+ "step": 8800
273
+ },
274
+ {
275
+ "epoch": 0.96,
276
+ "learning_rate": 1.4285714285714286e-06,
277
+ "loss": 3.7097,
278
+ "step": 9000
279
+ },
280
+ {
281
+ "epoch": 0.98,
282
+ "learning_rate": 7.142857142857143e-07,
283
+ "loss": 4.0694,
284
+ "step": 9200
285
+ },
286
+ {
287
+ "epoch": 1.0,
288
+ "learning_rate": 0.0,
289
+ "loss": 3.8382,
290
+ "step": 9400
291
+ },
292
+ {
293
+ "epoch": 1.0,
294
+ "step": 9400,
295
+ "total_flos": 622939976497152.0,
296
+ "train_loss": 8.931647637549867,
297
+ "train_runtime": 5062.6195,
298
+ "train_samples_per_second": 237.664,
299
+ "train_steps_per_second": 1.857
300
+ }
301
+ ],
302
+ "max_steps": 9400,
303
+ "num_train_epochs": 2,
304
+ "total_flos": 622939976497152.0,
305
+ "trial_name": null,
306
+ "trial_params": null
307
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862ebe7e2ca11c0caed3b20966cc710bcee68f4e444ab132f69bf4d348128a61
3
+ size 3311