Kelum commited on
Commit
36e6edc
1 Parent(s): 8d81f8d

Initial commit

Browse files
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.26.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
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:ae0dc74aa83f6d865a591b681f10a0461aae3c2cce34ef28e431f92ae2d8fdcf
3
+ size 615801861
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d729a3c77a934fa6473031799eadc554df2feb12ab6b52a7ea5b9a81a933c44e
3
+ size 307910149
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fda64680013d00b7041cbb274114200d3102d9b1da86cc5d3ceb199989d5dcf
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc0507fc23d71dc554541fd8db76bf3d612114157992f11a0f371b721f57a268
3
+ size 627
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
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 512,
107
+ "name_or_path": "google/flan-t5-small",
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
trainer_state.json ADDED
@@ -0,0 +1,584 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.27209922671318054,
3
+ "best_model_checkpoint": "Flan-T5-Model/checkpoint-9296",
4
+ "epoch": 2.0,
5
+ "global_step": 9296,
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": 4.9784853700516356e-05,
13
+ "loss": 1.5191,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.95697074010327e-05,
19
+ "loss": 1.0605,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.9354561101549056e-05,
25
+ "loss": 0.8389,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 4.913941480206541e-05,
31
+ "loss": 0.8411,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 4.892426850258176e-05,
37
+ "loss": 0.666,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 4.870912220309811e-05,
43
+ "loss": 0.644,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 4.8493975903614455e-05,
49
+ "loss": 0.5768,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 4.827882960413081e-05,
55
+ "loss": 0.7174,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.19,
60
+ "learning_rate": 4.806368330464716e-05,
61
+ "loss": 0.5645,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.22,
66
+ "learning_rate": 4.7848537005163515e-05,
67
+ "loss": 0.5373,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.24,
72
+ "learning_rate": 4.763339070567986e-05,
73
+ "loss": 0.59,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 4.7418244406196215e-05,
79
+ "loss": 0.5877,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.28,
84
+ "learning_rate": 4.720309810671257e-05,
85
+ "loss": 0.5796,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "learning_rate": 4.698795180722892e-05,
91
+ "loss": 0.7316,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.32,
96
+ "learning_rate": 4.677280550774527e-05,
97
+ "loss": 0.5634,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.34,
102
+ "learning_rate": 4.655765920826162e-05,
103
+ "loss": 0.4977,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.37,
108
+ "learning_rate": 4.634251290877797e-05,
109
+ "loss": 0.6237,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.39,
114
+ "learning_rate": 4.612736660929432e-05,
115
+ "loss": 0.3823,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.41,
120
+ "learning_rate": 4.5912220309810675e-05,
121
+ "loss": 0.6031,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.43,
126
+ "learning_rate": 4.569707401032702e-05,
127
+ "loss": 0.5063,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "learning_rate": 4.5481927710843374e-05,
133
+ "loss": 0.5459,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.47,
138
+ "learning_rate": 4.526678141135973e-05,
139
+ "loss": 0.6065,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.49,
144
+ "learning_rate": 4.505163511187608e-05,
145
+ "loss": 0.4847,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.52,
150
+ "learning_rate": 4.483648881239243e-05,
151
+ "loss": 0.4463,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.54,
156
+ "learning_rate": 4.462134251290878e-05,
157
+ "loss": 0.4284,
158
+ "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.56,
162
+ "learning_rate": 4.4406196213425134e-05,
163
+ "loss": 0.4366,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.58,
168
+ "learning_rate": 4.419104991394149e-05,
169
+ "loss": 0.3905,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "learning_rate": 4.3975903614457834e-05,
175
+ "loss": 0.3835,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.62,
180
+ "learning_rate": 4.376075731497418e-05,
181
+ "loss": 0.4689,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.65,
186
+ "learning_rate": 4.3545611015490534e-05,
187
+ "loss": 0.5344,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.67,
192
+ "learning_rate": 4.333046471600689e-05,
193
+ "loss": 0.5972,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.69,
198
+ "learning_rate": 4.311531841652324e-05,
199
+ "loss": 0.3994,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.71,
204
+ "learning_rate": 4.290017211703959e-05,
205
+ "loss": 0.4842,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.73,
210
+ "learning_rate": 4.268502581755594e-05,
211
+ "loss": 0.4545,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.75,
216
+ "learning_rate": 4.2469879518072294e-05,
217
+ "loss": 0.4395,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.77,
222
+ "learning_rate": 4.225473321858865e-05,
223
+ "loss": 0.4093,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.8,
228
+ "learning_rate": 4.2039586919104993e-05,
229
+ "loss": 0.2889,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.82,
234
+ "learning_rate": 4.182444061962135e-05,
235
+ "loss": 0.358,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.84,
240
+ "learning_rate": 4.16092943201377e-05,
241
+ "loss": 0.281,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.86,
246
+ "learning_rate": 4.1394148020654047e-05,
247
+ "loss": 0.436,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.88,
252
+ "learning_rate": 4.117900172117039e-05,
253
+ "loss": 0.4277,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.9,
258
+ "learning_rate": 4.0963855421686746e-05,
259
+ "loss": 0.4493,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.93,
264
+ "learning_rate": 4.07487091222031e-05,
265
+ "loss": 0.3203,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.95,
270
+ "learning_rate": 4.053356282271945e-05,
271
+ "loss": 0.3167,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.97,
276
+ "learning_rate": 4.03184165232358e-05,
277
+ "loss": 0.4787,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.99,
282
+ "learning_rate": 4.010327022375215e-05,
283
+ "loss": 0.4655,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 1.0,
288
+ "eval_loss": 0.3198269307613373,
289
+ "eval_runtime": 32.7335,
290
+ "eval_samples_per_second": 31.558,
291
+ "eval_steps_per_second": 31.558,
292
+ "step": 4648
293
+ },
294
+ {
295
+ "epoch": 1.01,
296
+ "learning_rate": 3.9888123924268506e-05,
297
+ "loss": 0.2515,
298
+ "step": 4700
299
+ },
300
+ {
301
+ "epoch": 1.03,
302
+ "learning_rate": 3.967297762478486e-05,
303
+ "loss": 0.3286,
304
+ "step": 4800
305
+ },
306
+ {
307
+ "epoch": 1.05,
308
+ "learning_rate": 3.9457831325301206e-05,
309
+ "loss": 0.3874,
310
+ "step": 4900
311
+ },
312
+ {
313
+ "epoch": 1.08,
314
+ "learning_rate": 3.924268502581756e-05,
315
+ "loss": 0.3035,
316
+ "step": 5000
317
+ },
318
+ {
319
+ "epoch": 1.1,
320
+ "learning_rate": 3.9027538726333906e-05,
321
+ "loss": 0.3444,
322
+ "step": 5100
323
+ },
324
+ {
325
+ "epoch": 1.12,
326
+ "learning_rate": 3.881239242685026e-05,
327
+ "loss": 0.2619,
328
+ "step": 5200
329
+ },
330
+ {
331
+ "epoch": 1.14,
332
+ "learning_rate": 3.859724612736661e-05,
333
+ "loss": 0.3899,
334
+ "step": 5300
335
+ },
336
+ {
337
+ "epoch": 1.16,
338
+ "learning_rate": 3.838209982788296e-05,
339
+ "loss": 0.3697,
340
+ "step": 5400
341
+ },
342
+ {
343
+ "epoch": 1.18,
344
+ "learning_rate": 3.816695352839931e-05,
345
+ "loss": 0.3511,
346
+ "step": 5500
347
+ },
348
+ {
349
+ "epoch": 1.2,
350
+ "learning_rate": 3.7951807228915666e-05,
351
+ "loss": 0.3241,
352
+ "step": 5600
353
+ },
354
+ {
355
+ "epoch": 1.23,
356
+ "learning_rate": 3.773666092943202e-05,
357
+ "loss": 0.3355,
358
+ "step": 5700
359
+ },
360
+ {
361
+ "epoch": 1.25,
362
+ "learning_rate": 3.7521514629948365e-05,
363
+ "loss": 0.3273,
364
+ "step": 5800
365
+ },
366
+ {
367
+ "epoch": 1.27,
368
+ "learning_rate": 3.730636833046472e-05,
369
+ "loss": 0.2834,
370
+ "step": 5900
371
+ },
372
+ {
373
+ "epoch": 1.29,
374
+ "learning_rate": 3.709122203098107e-05,
375
+ "loss": 0.3982,
376
+ "step": 6000
377
+ },
378
+ {
379
+ "epoch": 1.31,
380
+ "learning_rate": 3.6876075731497425e-05,
381
+ "loss": 0.2751,
382
+ "step": 6100
383
+ },
384
+ {
385
+ "epoch": 1.33,
386
+ "learning_rate": 3.666092943201377e-05,
387
+ "loss": 0.2815,
388
+ "step": 6200
389
+ },
390
+ {
391
+ "epoch": 1.36,
392
+ "learning_rate": 3.644578313253012e-05,
393
+ "loss": 0.2371,
394
+ "step": 6300
395
+ },
396
+ {
397
+ "epoch": 1.38,
398
+ "learning_rate": 3.623063683304647e-05,
399
+ "loss": 0.3046,
400
+ "step": 6400
401
+ },
402
+ {
403
+ "epoch": 1.4,
404
+ "learning_rate": 3.6015490533562825e-05,
405
+ "loss": 0.3638,
406
+ "step": 6500
407
+ },
408
+ {
409
+ "epoch": 1.42,
410
+ "learning_rate": 3.580034423407918e-05,
411
+ "loss": 0.3205,
412
+ "step": 6600
413
+ },
414
+ {
415
+ "epoch": 1.44,
416
+ "learning_rate": 3.5585197934595525e-05,
417
+ "loss": 0.3224,
418
+ "step": 6700
419
+ },
420
+ {
421
+ "epoch": 1.46,
422
+ "learning_rate": 3.537005163511188e-05,
423
+ "loss": 0.2693,
424
+ "step": 6800
425
+ },
426
+ {
427
+ "epoch": 1.48,
428
+ "learning_rate": 3.515490533562823e-05,
429
+ "loss": 0.3665,
430
+ "step": 6900
431
+ },
432
+ {
433
+ "epoch": 1.51,
434
+ "learning_rate": 3.4939759036144585e-05,
435
+ "loss": 0.3651,
436
+ "step": 7000
437
+ },
438
+ {
439
+ "epoch": 1.53,
440
+ "learning_rate": 3.472461273666093e-05,
441
+ "loss": 0.2936,
442
+ "step": 7100
443
+ },
444
+ {
445
+ "epoch": 1.55,
446
+ "learning_rate": 3.4509466437177285e-05,
447
+ "loss": 0.4318,
448
+ "step": 7200
449
+ },
450
+ {
451
+ "epoch": 1.57,
452
+ "learning_rate": 3.429432013769363e-05,
453
+ "loss": 0.2537,
454
+ "step": 7300
455
+ },
456
+ {
457
+ "epoch": 1.59,
458
+ "learning_rate": 3.4079173838209984e-05,
459
+ "loss": 0.3215,
460
+ "step": 7400
461
+ },
462
+ {
463
+ "epoch": 1.61,
464
+ "learning_rate": 3.386402753872633e-05,
465
+ "loss": 0.3507,
466
+ "step": 7500
467
+ },
468
+ {
469
+ "epoch": 1.64,
470
+ "learning_rate": 3.3648881239242684e-05,
471
+ "loss": 0.3959,
472
+ "step": 7600
473
+ },
474
+ {
475
+ "epoch": 1.66,
476
+ "learning_rate": 3.343373493975904e-05,
477
+ "loss": 0.2125,
478
+ "step": 7700
479
+ },
480
+ {
481
+ "epoch": 1.68,
482
+ "learning_rate": 3.321858864027539e-05,
483
+ "loss": 0.4155,
484
+ "step": 7800
485
+ },
486
+ {
487
+ "epoch": 1.7,
488
+ "learning_rate": 3.300344234079174e-05,
489
+ "loss": 0.367,
490
+ "step": 7900
491
+ },
492
+ {
493
+ "epoch": 1.72,
494
+ "learning_rate": 3.278829604130809e-05,
495
+ "loss": 0.3104,
496
+ "step": 8000
497
+ },
498
+ {
499
+ "epoch": 1.74,
500
+ "learning_rate": 3.2573149741824444e-05,
501
+ "loss": 0.278,
502
+ "step": 8100
503
+ },
504
+ {
505
+ "epoch": 1.76,
506
+ "learning_rate": 3.23580034423408e-05,
507
+ "loss": 0.4335,
508
+ "step": 8200
509
+ },
510
+ {
511
+ "epoch": 1.79,
512
+ "learning_rate": 3.2142857142857144e-05,
513
+ "loss": 0.2582,
514
+ "step": 8300
515
+ },
516
+ {
517
+ "epoch": 1.81,
518
+ "learning_rate": 3.192771084337349e-05,
519
+ "loss": 0.2662,
520
+ "step": 8400
521
+ },
522
+ {
523
+ "epoch": 1.83,
524
+ "learning_rate": 3.1712564543889844e-05,
525
+ "loss": 0.3093,
526
+ "step": 8500
527
+ },
528
+ {
529
+ "epoch": 1.85,
530
+ "learning_rate": 3.14974182444062e-05,
531
+ "loss": 0.338,
532
+ "step": 8600
533
+ },
534
+ {
535
+ "epoch": 1.87,
536
+ "learning_rate": 3.128227194492255e-05,
537
+ "loss": 0.2128,
538
+ "step": 8700
539
+ },
540
+ {
541
+ "epoch": 1.89,
542
+ "learning_rate": 3.10671256454389e-05,
543
+ "loss": 0.2845,
544
+ "step": 8800
545
+ },
546
+ {
547
+ "epoch": 1.91,
548
+ "learning_rate": 3.085197934595525e-05,
549
+ "loss": 0.2688,
550
+ "step": 8900
551
+ },
552
+ {
553
+ "epoch": 1.94,
554
+ "learning_rate": 3.0636833046471604e-05,
555
+ "loss": 0.2775,
556
+ "step": 9000
557
+ },
558
+ {
559
+ "epoch": 1.96,
560
+ "learning_rate": 3.0421686746987953e-05,
561
+ "loss": 0.2955,
562
+ "step": 9100
563
+ },
564
+ {
565
+ "epoch": 1.98,
566
+ "learning_rate": 3.0206540447504307e-05,
567
+ "loss": 0.2508,
568
+ "step": 9200
569
+ },
570
+ {
571
+ "epoch": 2.0,
572
+ "eval_loss": 0.27209922671318054,
573
+ "eval_runtime": 32.018,
574
+ "eval_samples_per_second": 32.263,
575
+ "eval_steps_per_second": 32.263,
576
+ "step": 9296
577
+ }
578
+ ],
579
+ "max_steps": 23240,
580
+ "num_train_epochs": 5,
581
+ "total_flos": 3455704482447360.0,
582
+ "trial_name": null,
583
+ "trial_params": null
584
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4d1303b8119a929903d8e23fdc879fdd7f3a5b6cf2a9e2587b4b9252846dc0
3
+ size 3643