Eunice333 commited on
Commit
90af62b
·
verified ·
1 Parent(s): 84225cc

Upload 12 files

Browse files

checkpoint-40000

config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Eunice333/meeting_t5small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 8,
22
+ "num_layers": 6,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.26.0",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.26.0"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4f9a127284e998142cd8c231cda5ce981e67ad8c3bc3683445c769229b0537
3
+ size 484129461
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b1e1c6eb13383670b5c58c01ef047c8f46213451fc23a4bd47beebc1bf384a
3
+ size 242070267
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc5470c5abd93d802e2f4f943950584739da00be798d315292e6fef6ec513d0
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae63a7bf73d9290adaffd22924b53561fe67d21fbfaeddbac555f03f58268a59
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "name_or_path": "google-t5/t5-small",
109
+ "pad_token": "<pad>",
110
+ "special_tokens_map_file": null,
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
trainer_state.json ADDED
@@ -0,0 +1,496 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6913836314925245,
5
+ "global_step": 40000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.9913577046063434e-05,
13
+ "loss": 2.9531,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 4.982715409212687e-05,
19
+ "loss": 2.7985,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 4.97407311381903e-05,
25
+ "loss": 2.7573,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 4.965430818425374e-05,
31
+ "loss": 2.7173,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 4.956788523031717e-05,
37
+ "loss": 2.7035,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "learning_rate": 4.948146227638061e-05,
43
+ "loss": 2.6966,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.06,
48
+ "learning_rate": 4.939503932244404e-05,
49
+ "loss": 2.6763,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.07,
54
+ "learning_rate": 4.930861636850748e-05,
55
+ "loss": 2.6809,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.08,
60
+ "learning_rate": 4.922219341457091e-05,
61
+ "loss": 2.6415,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.09,
66
+ "learning_rate": 4.913577046063435e-05,
67
+ "loss": 2.6747,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.1,
72
+ "learning_rate": 4.904934750669778e-05,
73
+ "loss": 2.6637,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.1,
78
+ "learning_rate": 4.896292455276122e-05,
79
+ "loss": 2.6527,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "learning_rate": 4.887650159882465e-05,
85
+ "loss": 2.6423,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.12,
90
+ "learning_rate": 4.879007864488808e-05,
91
+ "loss": 2.6331,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.13,
96
+ "learning_rate": 4.8703655690951524e-05,
97
+ "loss": 2.5868,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.14,
102
+ "learning_rate": 4.8617232737014955e-05,
103
+ "loss": 2.5901,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.15,
108
+ "learning_rate": 4.853080978307839e-05,
109
+ "loss": 2.5846,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.16,
114
+ "learning_rate": 4.8444386829141824e-05,
115
+ "loss": 2.6172,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.16,
120
+ "learning_rate": 4.835796387520526e-05,
121
+ "loss": 2.6035,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "learning_rate": 4.827154092126869e-05,
127
+ "loss": 2.6213,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.18,
132
+ "learning_rate": 4.8185117967332124e-05,
133
+ "loss": 2.5827,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.19,
138
+ "learning_rate": 4.809869501339556e-05,
139
+ "loss": 2.606,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.2,
144
+ "learning_rate": 4.801227205945899e-05,
145
+ "loss": 2.5827,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.21,
150
+ "learning_rate": 4.792584910552243e-05,
151
+ "loss": 2.5601,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.22,
156
+ "learning_rate": 4.783942615158586e-05,
157
+ "loss": 2.554,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.22,
162
+ "learning_rate": 4.77530031976493e-05,
163
+ "loss": 2.5501,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "learning_rate": 4.766658024371273e-05,
169
+ "loss": 2.5841,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.24,
174
+ "learning_rate": 4.758015728977617e-05,
175
+ "loss": 2.547,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.25,
180
+ "learning_rate": 4.74937343358396e-05,
181
+ "loss": 2.5823,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.26,
186
+ "learning_rate": 4.740731138190304e-05,
187
+ "loss": 2.5408,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.27,
192
+ "learning_rate": 4.732088842796647e-05,
193
+ "loss": 2.5678,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.28,
198
+ "learning_rate": 4.72344654740299e-05,
199
+ "loss": 2.5628,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.29,
204
+ "learning_rate": 4.714804252009334e-05,
205
+ "loss": 2.5549,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "learning_rate": 4.706161956615677e-05,
211
+ "loss": 2.5335,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.3,
216
+ "learning_rate": 4.697519661222021e-05,
217
+ "loss": 2.5287,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.31,
222
+ "learning_rate": 4.688877365828364e-05,
223
+ "loss": 2.5478,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.32,
228
+ "learning_rate": 4.680235070434708e-05,
229
+ "loss": 2.5501,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.33,
234
+ "learning_rate": 4.671592775041051e-05,
235
+ "loss": 2.5335,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.34,
240
+ "learning_rate": 4.6629504796473946e-05,
241
+ "loss": 2.5057,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.35,
246
+ "learning_rate": 4.654308184253738e-05,
247
+ "loss": 2.5316,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.35,
252
+ "learning_rate": 4.6456658888600815e-05,
253
+ "loss": 2.5584,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.36,
258
+ "learning_rate": 4.6370235934664246e-05,
259
+ "loss": 2.5184,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.37,
264
+ "learning_rate": 4.6283812980727684e-05,
265
+ "loss": 2.5301,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.38,
270
+ "learning_rate": 4.6197390026791115e-05,
271
+ "loss": 2.5337,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.39,
276
+ "learning_rate": 4.611096707285455e-05,
277
+ "loss": 2.5136,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.4,
282
+ "learning_rate": 4.602454411891799e-05,
283
+ "loss": 2.4641,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.41,
288
+ "learning_rate": 4.593812116498142e-05,
289
+ "loss": 2.5473,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.41,
294
+ "learning_rate": 4.585169821104486e-05,
295
+ "loss": 2.5219,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.42,
300
+ "learning_rate": 4.576527525710829e-05,
301
+ "loss": 2.5111,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.43,
306
+ "learning_rate": 4.567885230317173e-05,
307
+ "loss": 2.5045,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.44,
312
+ "learning_rate": 4.559242934923516e-05,
313
+ "loss": 2.4803,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.45,
318
+ "learning_rate": 4.550600639529859e-05,
319
+ "loss": 2.478,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.46,
324
+ "learning_rate": 4.541958344136203e-05,
325
+ "loss": 2.502,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.47,
330
+ "learning_rate": 4.533316048742546e-05,
331
+ "loss": 2.5121,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.48,
336
+ "learning_rate": 4.52467375334889e-05,
337
+ "loss": 2.4963,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.48,
342
+ "learning_rate": 4.516031457955233e-05,
343
+ "loss": 2.4793,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.49,
348
+ "learning_rate": 4.507389162561577e-05,
349
+ "loss": 2.5068,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.5,
354
+ "learning_rate": 4.49874686716792e-05,
355
+ "loss": 2.5034,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.51,
360
+ "learning_rate": 4.490104571774264e-05,
361
+ "loss": 2.4744,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.52,
366
+ "learning_rate": 4.481462276380607e-05,
367
+ "loss": 2.4565,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.53,
372
+ "learning_rate": 4.4728199809869506e-05,
373
+ "loss": 2.491,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.54,
378
+ "learning_rate": 4.464177685593294e-05,
379
+ "loss": 2.5165,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.54,
384
+ "learning_rate": 4.4555353901996375e-05,
385
+ "loss": 2.4936,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.55,
390
+ "learning_rate": 4.4468930948059806e-05,
391
+ "loss": 2.4991,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.56,
396
+ "learning_rate": 4.438250799412324e-05,
397
+ "loss": 2.454,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.57,
402
+ "learning_rate": 4.4296085040186675e-05,
403
+ "loss": 2.4699,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.58,
408
+ "learning_rate": 4.4209662086250106e-05,
409
+ "loss": 2.4951,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.59,
414
+ "learning_rate": 4.4123239132313544e-05,
415
+ "loss": 2.4536,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 0.6,
420
+ "learning_rate": 4.4036816178376975e-05,
421
+ "loss": 2.4745,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 0.6,
426
+ "learning_rate": 4.395039322444041e-05,
427
+ "loss": 2.4752,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 0.61,
432
+ "learning_rate": 4.3863970270503844e-05,
433
+ "loss": 2.4757,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 0.62,
438
+ "learning_rate": 4.377754731656728e-05,
439
+ "loss": 2.5043,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 0.63,
444
+ "learning_rate": 4.3691124362630714e-05,
445
+ "loss": 2.4513,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 0.64,
450
+ "learning_rate": 4.360470140869415e-05,
451
+ "loss": 2.4683,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 0.65,
456
+ "learning_rate": 4.351827845475759e-05,
457
+ "loss": 2.4723,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 0.66,
462
+ "learning_rate": 4.343185550082102e-05,
463
+ "loss": 2.4607,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 0.67,
468
+ "learning_rate": 4.334543254688446e-05,
469
+ "loss": 2.4937,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 0.67,
474
+ "learning_rate": 4.325900959294789e-05,
475
+ "loss": 2.4491,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 0.68,
480
+ "learning_rate": 4.317258663901133e-05,
481
+ "loss": 2.4476,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 0.69,
486
+ "learning_rate": 4.308616368507476e-05,
487
+ "loss": 2.479,
488
+ "step": 40000
489
+ }
490
+ ],
491
+ "max_steps": 289275,
492
+ "num_train_epochs": 5,
493
+ "total_flos": 3.2856743048380416e+16,
494
+ "trial_name": null,
495
+ "trial_params": null
496
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e329530181305e86a5a322013d3d7b7e97e2b75d4e08021b149cf1edfb40f8e8
3
+ size 3631