lityops commited on
Commit
0be4fba
·
verified ·
1 Parent(s): 419c878

Upload 11 files

Browse files
README.md CHANGED
@@ -1,3 +1,106 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/flan-t5-base
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:google/flan-t5-base
6
+ - lora
7
+ - transformers
8
+ - summarization
9
+ - abstractive-summarization
10
+ - generated_from_trainer
11
+ model-index:
12
+ - name: Abstractive Style Summarizer
13
+ results: []
14
+ ---
15
+
16
+ # Abstractive Style Summarizer
17
+
18
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) using PEFT (LoRA). It is designed to generate abstractive summaries in three distinct styles: **Harsh** (concise), **Balanced** (standard), and **Detailed** (comprehensive).
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ - **Model type:** Sequence-to-Sequence Transformer (T5)
25
+ - **Language(s):** English
26
+ - **License:** Apache 2.0
27
+ - **Finetuned from model:** google/flan-t5-base
28
+ - **Training Method:** PEFT (LoRA)
29
+
30
+ ### Model Sources
31
+
32
+ - **Repository:** [Flatten](https://github.com/LityoPS/Flatten)
33
+ - **Base Model:** [google/flan-t5-base](https://huggingface.co/google/flan-t5-base)
34
+
35
+ ## Uses
36
+
37
+ ### Direct Use
38
+
39
+ The model interprets a prefixed prompt to determine the style of the summary.
40
+ - **Harsh**: Generates very short, punchy summaries (approx. 35% of input length).
41
+ - **Balanced**: Generates standard news summaries (approx. 50% of input length).
42
+ - **Detailed**: Generates in-depth summaries (approx. 70% of input length).
43
+
44
+ ### Prompt Format
45
+
46
+ The input text should be prefixed with the desired style:
47
+ ```
48
+ Summarize {Style}: {Input Text}
49
+ ```
50
+ Example: `Summarize Harsh: The Walt Disney Co. announced...`
51
+
52
+ ## Training Details
53
+
54
+ ### Training Data
55
+
56
+ The model was trained on a combined dataset of 12,000 samples, split into 80% Train, 10% Validation, and 10% Test.
57
+
58
+ | Style | Source Dataset | Size |
59
+ | :--- | :--- | :--- |
60
+ | **Harsh** | [XSum](https://huggingface.co/datasets/xsum) | 4000 |
61
+ | **Balanced** | [CNN/DailyMail](https://huggingface.co/datasets/cnn_dailymail) | 4000 |
62
+ | **Detailed** | [Multi-News](https://huggingface.co/datasets/multi_news) | 4000 |
63
+
64
+ ### Training Procedure
65
+
66
+ #### Training Hyperparameters
67
+
68
+ - **Learning Rate:** 5e-4
69
+ - **Batch Size:** 4 per device
70
+ - **Gradient Accumulation Steps:** 2
71
+ - **Num Epochs:** 5
72
+ - **Optimizer:** AdamW
73
+ - **LR Scheduler:** Linear with warmup (ratio 0.05)
74
+ - **Mixed Precision:** BF16
75
+
76
+ #### LoRA Configuration
77
+
78
+ - **r:** 32
79
+ - **lora_alpha:** 64
80
+ - **lora_dropout:** 0.05
81
+ - **target_modules:** ["q", "k", "v", "o"]
82
+ - **bias:** "none"
83
+ - **task_type:** "SEQ_2_SEQ_LM"
84
+
85
+ ### Evaluation Results
86
+
87
+ Evaluated on the held-out test set (1,200 samples) at Step 6000.
88
+
89
+ | Metric | Score |
90
+ | :--- | :--- |
91
+ | **ROUGE-1** | 0.3925 |
92
+ | **ROUGE-2** | 0.1608 |
93
+ | **ROUGE-L** | 0.2776 |
94
+ | **Validation Loss** | 0.7824 |
95
+
96
+ ## Environmental Impact
97
+
98
+ - **Hardware Type:** CUDA-enabled GPU
99
+ - **Compute:** LoRA fine-tuning (Parameters: 7M trainable / 254M total)
100
+
101
+ ## Framework Versions
102
+
103
+ - Datasets==3.6.0
104
+ - Pytorch>=2.5.1
105
+ - Transformers>=4.36.0
106
+ - PEFT>=0.8.0
adapter_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "google/flan-t5-base",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v",
33
+ "q",
34
+ "o",
35
+ "k"
36
+ ],
37
+ "target_parameters": null,
38
+ "task_type": "SEQ_2_SEQ_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_qalora": false,
42
+ "use_rslora": false
43
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:905b2e3b6eff0043debe9f958db53c502ff26ad5d36957a65ea7607b0e084f98
3
+ size 28352216
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79818728369d542bfb17151257188499ea54574be78b60cb97f295d0f4f1e9cb
3
+ size 56865163
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98e9e77b014d89538f954062543caceb860d7b1cf129088021c934d476734be
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca40ea6dcb18a1a27acfcacc7d1a643fe4222424ca728640933c251b0bfe14ff
3
+ size 1465
special_tokens_map.json CHANGED
@@ -1,125 +1,125 @@
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": {
105
- "content": "</s>",
106
- "lstrip": false,
107
- "normalized": false,
108
- "rstrip": false,
109
- "single_word": false
110
- },
111
- "pad_token": {
112
- "content": "<pad>",
113
- "lstrip": false,
114
- "normalized": false,
115
- "rstrip": false,
116
- "single_word": false
117
- },
118
- "unk_token": {
119
- "content": "<unk>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false
124
- }
125
- }
 
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": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 150,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 150
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 256
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -1,940 +1,940 @@
1
- {
2
- "add_prefix_space": null,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<unk>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "32000": {
29
- "content": "<extra_id_99>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "32001": {
37
- "content": "<extra_id_98>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "32002": {
45
- "content": "<extra_id_97>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "32003": {
53
- "content": "<extra_id_96>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "32004": {
61
- "content": "<extra_id_95>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "32005": {
69
- "content": "<extra_id_94>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "32006": {
77
- "content": "<extra_id_93>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "32007": {
85
- "content": "<extra_id_92>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "32008": {
93
- "content": "<extra_id_91>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "32009": {
101
- "content": "<extra_id_90>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "32010": {
109
- "content": "<extra_id_89>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "32011": {
117
- "content": "<extra_id_88>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "32012": {
125
- "content": "<extra_id_87>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "32013": {
133
- "content": "<extra_id_86>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "32014": {
141
- "content": "<extra_id_85>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "32015": {
149
- "content": "<extra_id_84>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "32016": {
157
- "content": "<extra_id_83>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "32017": {
165
- "content": "<extra_id_82>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "32018": {
173
- "content": "<extra_id_81>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "32019": {
181
- "content": "<extra_id_80>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "32020": {
189
- "content": "<extra_id_79>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": true
195
- },
196
- "32021": {
197
- "content": "<extra_id_78>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": true
203
- },
204
- "32022": {
205
- "content": "<extra_id_77>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "32023": {
213
- "content": "<extra_id_76>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "32024": {
221
- "content": "<extra_id_75>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "32025": {
229
- "content": "<extra_id_74>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "32026": {
237
- "content": "<extra_id_73>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "32027": {
245
- "content": "<extra_id_72>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "32028": {
253
- "content": "<extra_id_71>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "32029": {
261
- "content": "<extra_id_70>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- },
268
- "32030": {
269
- "content": "<extra_id_69>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": true
275
- },
276
- "32031": {
277
- "content": "<extra_id_68>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": true
283
- },
284
- "32032": {
285
- "content": "<extra_id_67>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": true
291
- },
292
- "32033": {
293
- "content": "<extra_id_66>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": true
299
- },
300
- "32034": {
301
- "content": "<extra_id_65>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": true
307
- },
308
- "32035": {
309
- "content": "<extra_id_64>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": true
315
- },
316
- "32036": {
317
- "content": "<extra_id_63>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": true
323
- },
324
- "32037": {
325
- "content": "<extra_id_62>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": true
331
- },
332
- "32038": {
333
- "content": "<extra_id_61>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": true
339
- },
340
- "32039": {
341
- "content": "<extra_id_60>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": true
347
- },
348
- "32040": {
349
- "content": "<extra_id_59>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": true
355
- },
356
- "32041": {
357
- "content": "<extra_id_58>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": true
363
- },
364
- "32042": {
365
- "content": "<extra_id_57>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": true
371
- },
372
- "32043": {
373
- "content": "<extra_id_56>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": true
379
- },
380
- "32044": {
381
- "content": "<extra_id_55>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": true
387
- },
388
- "32045": {
389
- "content": "<extra_id_54>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": true
395
- },
396
- "32046": {
397
- "content": "<extra_id_53>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": true
403
- },
404
- "32047": {
405
- "content": "<extra_id_52>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": true
411
- },
412
- "32048": {
413
- "content": "<extra_id_51>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": true
419
- },
420
- "32049": {
421
- "content": "<extra_id_50>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": true
427
- },
428
- "32050": {
429
- "content": "<extra_id_49>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": true
435
- },
436
- "32051": {
437
- "content": "<extra_id_48>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": true
443
- },
444
- "32052": {
445
- "content": "<extra_id_47>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": true
451
- },
452
- "32053": {
453
- "content": "<extra_id_46>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": true
459
- },
460
- "32054": {
461
- "content": "<extra_id_45>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": true
467
- },
468
- "32055": {
469
- "content": "<extra_id_44>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": true
475
- },
476
- "32056": {
477
- "content": "<extra_id_43>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": true
483
- },
484
- "32057": {
485
- "content": "<extra_id_42>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": true
491
- },
492
- "32058": {
493
- "content": "<extra_id_41>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": true
499
- },
500
- "32059": {
501
- "content": "<extra_id_40>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": true
507
- },
508
- "32060": {
509
- "content": "<extra_id_39>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": true
515
- },
516
- "32061": {
517
- "content": "<extra_id_38>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": true
523
- },
524
- "32062": {
525
- "content": "<extra_id_37>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": true
531
- },
532
- "32063": {
533
- "content": "<extra_id_36>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": true
539
- },
540
- "32064": {
541
- "content": "<extra_id_35>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": true
547
- },
548
- "32065": {
549
- "content": "<extra_id_34>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": true
555
- },
556
- "32066": {
557
- "content": "<extra_id_33>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": true
563
- },
564
- "32067": {
565
- "content": "<extra_id_32>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": true
571
- },
572
- "32068": {
573
- "content": "<extra_id_31>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": true
579
- },
580
- "32069": {
581
- "content": "<extra_id_30>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": true
587
- },
588
- "32070": {
589
- "content": "<extra_id_29>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": true
595
- },
596
- "32071": {
597
- "content": "<extra_id_28>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": true
603
- },
604
- "32072": {
605
- "content": "<extra_id_27>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": true
611
- },
612
- "32073": {
613
- "content": "<extra_id_26>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": true
619
- },
620
- "32074": {
621
- "content": "<extra_id_25>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": true
627
- },
628
- "32075": {
629
- "content": "<extra_id_24>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": true
635
- },
636
- "32076": {
637
- "content": "<extra_id_23>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": true
643
- },
644
- "32077": {
645
- "content": "<extra_id_22>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": true
651
- },
652
- "32078": {
653
- "content": "<extra_id_21>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": true
659
- },
660
- "32079": {
661
- "content": "<extra_id_20>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": true
667
- },
668
- "32080": {
669
- "content": "<extra_id_19>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": true
675
- },
676
- "32081": {
677
- "content": "<extra_id_18>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": true
683
- },
684
- "32082": {
685
- "content": "<extra_id_17>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": true
691
- },
692
- "32083": {
693
- "content": "<extra_id_16>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": true
699
- },
700
- "32084": {
701
- "content": "<extra_id_15>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": true
707
- },
708
- "32085": {
709
- "content": "<extra_id_14>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": true
715
- },
716
- "32086": {
717
- "content": "<extra_id_13>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": true
723
- },
724
- "32087": {
725
- "content": "<extra_id_12>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": true
731
- },
732
- "32088": {
733
- "content": "<extra_id_11>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": true
739
- },
740
- "32089": {
741
- "content": "<extra_id_10>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": true
747
- },
748
- "32090": {
749
- "content": "<extra_id_9>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": true
755
- },
756
- "32091": {
757
- "content": "<extra_id_8>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": true
763
- },
764
- "32092": {
765
- "content": "<extra_id_7>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": true
771
- },
772
- "32093": {
773
- "content": "<extra_id_6>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": true
779
- },
780
- "32094": {
781
- "content": "<extra_id_5>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": true
787
- },
788
- "32095": {
789
- "content": "<extra_id_4>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": true
795
- },
796
- "32096": {
797
- "content": "<extra_id_3>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": true
803
- },
804
- "32097": {
805
- "content": "<extra_id_2>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": true
811
- },
812
- "32098": {
813
- "content": "<extra_id_1>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": true
819
- },
820
- "32099": {
821
- "content": "<extra_id_0>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": true
827
- }
828
- },
829
- "additional_special_tokens": [
830
- "<extra_id_0>",
831
- "<extra_id_1>",
832
- "<extra_id_2>",
833
- "<extra_id_3>",
834
- "<extra_id_4>",
835
- "<extra_id_5>",
836
- "<extra_id_6>",
837
- "<extra_id_7>",
838
- "<extra_id_8>",
839
- "<extra_id_9>",
840
- "<extra_id_10>",
841
- "<extra_id_11>",
842
- "<extra_id_12>",
843
- "<extra_id_13>",
844
- "<extra_id_14>",
845
- "<extra_id_15>",
846
- "<extra_id_16>",
847
- "<extra_id_17>",
848
- "<extra_id_18>",
849
- "<extra_id_19>",
850
- "<extra_id_20>",
851
- "<extra_id_21>",
852
- "<extra_id_22>",
853
- "<extra_id_23>",
854
- "<extra_id_24>",
855
- "<extra_id_25>",
856
- "<extra_id_26>",
857
- "<extra_id_27>",
858
- "<extra_id_28>",
859
- "<extra_id_29>",
860
- "<extra_id_30>",
861
- "<extra_id_31>",
862
- "<extra_id_32>",
863
- "<extra_id_33>",
864
- "<extra_id_34>",
865
- "<extra_id_35>",
866
- "<extra_id_36>",
867
- "<extra_id_37>",
868
- "<extra_id_38>",
869
- "<extra_id_39>",
870
- "<extra_id_40>",
871
- "<extra_id_41>",
872
- "<extra_id_42>",
873
- "<extra_id_43>",
874
- "<extra_id_44>",
875
- "<extra_id_45>",
876
- "<extra_id_46>",
877
- "<extra_id_47>",
878
- "<extra_id_48>",
879
- "<extra_id_49>",
880
- "<extra_id_50>",
881
- "<extra_id_51>",
882
- "<extra_id_52>",
883
- "<extra_id_53>",
884
- "<extra_id_54>",
885
- "<extra_id_55>",
886
- "<extra_id_56>",
887
- "<extra_id_57>",
888
- "<extra_id_58>",
889
- "<extra_id_59>",
890
- "<extra_id_60>",
891
- "<extra_id_61>",
892
- "<extra_id_62>",
893
- "<extra_id_63>",
894
- "<extra_id_64>",
895
- "<extra_id_65>",
896
- "<extra_id_66>",
897
- "<extra_id_67>",
898
- "<extra_id_68>",
899
- "<extra_id_69>",
900
- "<extra_id_70>",
901
- "<extra_id_71>",
902
- "<extra_id_72>",
903
- "<extra_id_73>",
904
- "<extra_id_74>",
905
- "<extra_id_75>",
906
- "<extra_id_76>",
907
- "<extra_id_77>",
908
- "<extra_id_78>",
909
- "<extra_id_79>",
910
- "<extra_id_80>",
911
- "<extra_id_81>",
912
- "<extra_id_82>",
913
- "<extra_id_83>",
914
- "<extra_id_84>",
915
- "<extra_id_85>",
916
- "<extra_id_86>",
917
- "<extra_id_87>",
918
- "<extra_id_88>",
919
- "<extra_id_89>",
920
- "<extra_id_90>",
921
- "<extra_id_91>",
922
- "<extra_id_92>",
923
- "<extra_id_93>",
924
- "<extra_id_94>",
925
- "<extra_id_95>",
926
- "<extra_id_96>",
927
- "<extra_id_97>",
928
- "<extra_id_98>",
929
- "<extra_id_99>"
930
- ],
931
- "clean_up_tokenization_spaces": false,
932
- "eos_token": "</s>",
933
- "extra_ids": 100,
934
- "extra_special_tokens": {},
935
- "model_max_length": 512,
936
- "pad_token": "<pad>",
937
- "sp_model_kwargs": {},
938
- "tokenizer_class": "T5Tokenizer",
939
- "unk_token": "<unk>"
940
- }
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
trainer_state.json ADDED
@@ -0,0 +1,526 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6000,
3
+ "best_metric": 0.7824317216873169,
4
+ "best_model_checkpoint": "results\\checkpoint-6000",
5
+ "epoch": 5.0,
6
+ "eval_steps": 1000,
7
+ "global_step": 6000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08333333333333333,
14
+ "grad_norm": 1.8858007192611694,
15
+ "learning_rate": 0.000165,
16
+ "loss": 23.215,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.16666666666666666,
21
+ "grad_norm": 0.17990389466285706,
22
+ "learning_rate": 0.0003316666666666667,
23
+ "loss": 2.1264,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.25,
28
+ "grad_norm": 0.162213996052742,
29
+ "learning_rate": 0.0004983333333333334,
30
+ "loss": 0.9398,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.3333333333333333,
35
+ "grad_norm": 0.15034538507461548,
36
+ "learning_rate": 0.0004913157894736842,
37
+ "loss": 0.9165,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.4166666666666667,
42
+ "grad_norm": 0.1454722136259079,
43
+ "learning_rate": 0.0004825438596491228,
44
+ "loss": 0.8424,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.5,
49
+ "grad_norm": 0.12470711767673492,
50
+ "learning_rate": 0.0004737719298245614,
51
+ "loss": 0.8874,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.5833333333333334,
56
+ "grad_norm": 0.09494169801473618,
57
+ "learning_rate": 0.000465,
58
+ "loss": 0.8784,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.6666666666666666,
63
+ "grad_norm": 0.1456226408481598,
64
+ "learning_rate": 0.0004562280701754386,
65
+ "loss": 0.8622,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.75,
70
+ "grad_norm": 0.1623910665512085,
71
+ "learning_rate": 0.00044745614035087723,
72
+ "loss": 0.9006,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.8333333333333334,
77
+ "grad_norm": 0.13629059493541718,
78
+ "learning_rate": 0.0004386842105263158,
79
+ "loss": 0.8702,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.8333333333333334,
84
+ "eval_loss": 0.7877687811851501,
85
+ "eval_rouge1": 0.382,
86
+ "eval_rouge2": 0.1541,
87
+ "eval_rougeL": 0.2714,
88
+ "eval_rougeLsum": 0.2715,
89
+ "eval_runtime": 1349.6776,
90
+ "eval_samples_per_second": 0.889,
91
+ "eval_steps_per_second": 0.222,
92
+ "step": 1000
93
+ },
94
+ {
95
+ "epoch": 0.9166666666666666,
96
+ "grad_norm": 0.14377427101135254,
97
+ "learning_rate": 0.00042991228070175444,
98
+ "loss": 0.9231,
99
+ "step": 1100
100
+ },
101
+ {
102
+ "epoch": 1.0,
103
+ "grad_norm": 0.1454974114894867,
104
+ "learning_rate": 0.000421140350877193,
105
+ "loss": 0.8752,
106
+ "step": 1200
107
+ },
108
+ {
109
+ "epoch": 1.0833333333333333,
110
+ "grad_norm": 0.14425410330295563,
111
+ "learning_rate": 0.0004123684210526316,
112
+ "loss": 0.8895,
113
+ "step": 1300
114
+ },
115
+ {
116
+ "epoch": 1.1666666666666667,
117
+ "grad_norm": 0.09587734937667847,
118
+ "learning_rate": 0.0004035964912280702,
119
+ "loss": 0.837,
120
+ "step": 1400
121
+ },
122
+ {
123
+ "epoch": 1.25,
124
+ "grad_norm": 0.13110461831092834,
125
+ "learning_rate": 0.00039482456140350875,
126
+ "loss": 0.8488,
127
+ "step": 1500
128
+ },
129
+ {
130
+ "epoch": 1.3333333333333333,
131
+ "grad_norm": 0.1459980010986328,
132
+ "learning_rate": 0.00038605263157894735,
133
+ "loss": 0.8795,
134
+ "step": 1600
135
+ },
136
+ {
137
+ "epoch": 1.4166666666666667,
138
+ "grad_norm": 0.09983498603105545,
139
+ "learning_rate": 0.00037728070175438596,
140
+ "loss": 0.8449,
141
+ "step": 1700
142
+ },
143
+ {
144
+ "epoch": 1.5,
145
+ "grad_norm": 0.13172173500061035,
146
+ "learning_rate": 0.00036850877192982456,
147
+ "loss": 0.8977,
148
+ "step": 1800
149
+ },
150
+ {
151
+ "epoch": 1.5833333333333335,
152
+ "grad_norm": 0.10697636008262634,
153
+ "learning_rate": 0.00035973684210526317,
154
+ "loss": 0.9018,
155
+ "step": 1900
156
+ },
157
+ {
158
+ "epoch": 1.6666666666666665,
159
+ "grad_norm": 0.15373478829860687,
160
+ "learning_rate": 0.00035096491228070177,
161
+ "loss": 0.8847,
162
+ "step": 2000
163
+ },
164
+ {
165
+ "epoch": 1.6666666666666665,
166
+ "eval_loss": 0.7850176095962524,
167
+ "eval_rouge1": 0.3881,
168
+ "eval_rouge2": 0.1563,
169
+ "eval_rougeL": 0.2745,
170
+ "eval_rougeLsum": 0.2746,
171
+ "eval_runtime": 1411.9277,
172
+ "eval_samples_per_second": 0.85,
173
+ "eval_steps_per_second": 0.212,
174
+ "step": 2000
175
+ },
176
+ {
177
+ "epoch": 1.75,
178
+ "grad_norm": 0.14189960062503815,
179
+ "learning_rate": 0.0003421929824561403,
180
+ "loss": 0.8162,
181
+ "step": 2100
182
+ },
183
+ {
184
+ "epoch": 1.8333333333333335,
185
+ "grad_norm": 0.11188172549009323,
186
+ "learning_rate": 0.000333421052631579,
187
+ "loss": 0.8098,
188
+ "step": 2200
189
+ },
190
+ {
191
+ "epoch": 1.9166666666666665,
192
+ "grad_norm": 0.12888970971107483,
193
+ "learning_rate": 0.0003246491228070175,
194
+ "loss": 0.914,
195
+ "step": 2300
196
+ },
197
+ {
198
+ "epoch": 2.0,
199
+ "grad_norm": 0.15828001499176025,
200
+ "learning_rate": 0.00031587719298245613,
201
+ "loss": 0.8815,
202
+ "step": 2400
203
+ },
204
+ {
205
+ "epoch": 2.0833333333333335,
206
+ "grad_norm": 0.12439479678869247,
207
+ "learning_rate": 0.00030710526315789473,
208
+ "loss": 0.8685,
209
+ "step": 2500
210
+ },
211
+ {
212
+ "epoch": 2.1666666666666665,
213
+ "grad_norm": 0.12364527583122253,
214
+ "learning_rate": 0.00029833333333333334,
215
+ "loss": 0.8185,
216
+ "step": 2600
217
+ },
218
+ {
219
+ "epoch": 2.25,
220
+ "grad_norm": 7.694972038269043,
221
+ "learning_rate": 0.0002895614035087719,
222
+ "loss": 0.8721,
223
+ "step": 2700
224
+ },
225
+ {
226
+ "epoch": 2.3333333333333335,
227
+ "grad_norm": 0.17389440536499023,
228
+ "learning_rate": 0.00028078947368421055,
229
+ "loss": 0.9235,
230
+ "step": 2800
231
+ },
232
+ {
233
+ "epoch": 2.4166666666666665,
234
+ "grad_norm": 0.13395565748214722,
235
+ "learning_rate": 0.0002720175438596491,
236
+ "loss": 0.8668,
237
+ "step": 2900
238
+ },
239
+ {
240
+ "epoch": 2.5,
241
+ "grad_norm": 0.11639299243688583,
242
+ "learning_rate": 0.00026324561403508775,
243
+ "loss": 0.8637,
244
+ "step": 3000
245
+ },
246
+ {
247
+ "epoch": 2.5,
248
+ "eval_loss": 0.7873790860176086,
249
+ "eval_rouge1": 0.3909,
250
+ "eval_rouge2": 0.1587,
251
+ "eval_rougeL": 0.2753,
252
+ "eval_rougeLsum": 0.2752,
253
+ "eval_runtime": 1346.5604,
254
+ "eval_samples_per_second": 0.891,
255
+ "eval_steps_per_second": 0.223,
256
+ "step": 3000
257
+ },
258
+ {
259
+ "epoch": 2.5833333333333335,
260
+ "grad_norm": 0.2207750380039215,
261
+ "learning_rate": 0.0002544736842105263,
262
+ "loss": 0.8495,
263
+ "step": 3100
264
+ },
265
+ {
266
+ "epoch": 2.6666666666666665,
267
+ "grad_norm": 0.14125679433345795,
268
+ "learning_rate": 0.0002457017543859649,
269
+ "loss": 0.8236,
270
+ "step": 3200
271
+ },
272
+ {
273
+ "epoch": 2.75,
274
+ "grad_norm": 0.16702750325202942,
275
+ "learning_rate": 0.0002369298245614035,
276
+ "loss": 0.8369,
277
+ "step": 3300
278
+ },
279
+ {
280
+ "epoch": 2.8333333333333335,
281
+ "grad_norm": 0.17848503589630127,
282
+ "learning_rate": 0.00022815789473684212,
283
+ "loss": 0.8555,
284
+ "step": 3400
285
+ },
286
+ {
287
+ "epoch": 2.9166666666666665,
288
+ "grad_norm": 0.17648929357528687,
289
+ "learning_rate": 0.00021938596491228072,
290
+ "loss": 0.8519,
291
+ "step": 3500
292
+ },
293
+ {
294
+ "epoch": 3.0,
295
+ "grad_norm": 0.1409672498703003,
296
+ "learning_rate": 0.00021061403508771932,
297
+ "loss": 0.9162,
298
+ "step": 3600
299
+ },
300
+ {
301
+ "epoch": 3.0833333333333335,
302
+ "grad_norm": 0.18376924097537994,
303
+ "learning_rate": 0.0002018421052631579,
304
+ "loss": 0.8468,
305
+ "step": 3700
306
+ },
307
+ {
308
+ "epoch": 3.1666666666666665,
309
+ "grad_norm": 0.20083250105381012,
310
+ "learning_rate": 0.0001930701754385965,
311
+ "loss": 0.8802,
312
+ "step": 3800
313
+ },
314
+ {
315
+ "epoch": 3.25,
316
+ "grad_norm": 0.18047745525836945,
317
+ "learning_rate": 0.0001842982456140351,
318
+ "loss": 0.8162,
319
+ "step": 3900
320
+ },
321
+ {
322
+ "epoch": 3.3333333333333335,
323
+ "grad_norm": 0.16132934391498566,
324
+ "learning_rate": 0.0001755263157894737,
325
+ "loss": 0.8417,
326
+ "step": 4000
327
+ },
328
+ {
329
+ "epoch": 3.3333333333333335,
330
+ "eval_loss": 0.7860187888145447,
331
+ "eval_rouge1": 0.392,
332
+ "eval_rouge2": 0.1608,
333
+ "eval_rougeL": 0.2756,
334
+ "eval_rougeLsum": 0.2756,
335
+ "eval_runtime": 1399.5278,
336
+ "eval_samples_per_second": 0.857,
337
+ "eval_steps_per_second": 0.214,
338
+ "step": 4000
339
+ },
340
+ {
341
+ "epoch": 3.4166666666666665,
342
+ "grad_norm": 0.2105809897184372,
343
+ "learning_rate": 0.0001667543859649123,
344
+ "loss": 0.8855,
345
+ "step": 4100
346
+ },
347
+ {
348
+ "epoch": 3.5,
349
+ "grad_norm": 0.18433880805969238,
350
+ "learning_rate": 0.0001579824561403509,
351
+ "loss": 0.8405,
352
+ "step": 4200
353
+ },
354
+ {
355
+ "epoch": 3.5833333333333335,
356
+ "grad_norm": 0.13414153456687927,
357
+ "learning_rate": 0.00014921052631578947,
358
+ "loss": 0.8356,
359
+ "step": 4300
360
+ },
361
+ {
362
+ "epoch": 3.6666666666666665,
363
+ "grad_norm": 0.12219959497451782,
364
+ "learning_rate": 0.00014043859649122805,
365
+ "loss": 0.8142,
366
+ "step": 4400
367
+ },
368
+ {
369
+ "epoch": 3.75,
370
+ "grad_norm": 0.15552708506584167,
371
+ "learning_rate": 0.00013166666666666665,
372
+ "loss": 0.8198,
373
+ "step": 4500
374
+ },
375
+ {
376
+ "epoch": 3.8333333333333335,
377
+ "grad_norm": 0.15773844718933105,
378
+ "learning_rate": 0.00012289473684210525,
379
+ "loss": 0.8432,
380
+ "step": 4600
381
+ },
382
+ {
383
+ "epoch": 3.9166666666666665,
384
+ "grad_norm": 0.19309180974960327,
385
+ "learning_rate": 0.00011412280701754386,
386
+ "loss": 0.8577,
387
+ "step": 4700
388
+ },
389
+ {
390
+ "epoch": 4.0,
391
+ "grad_norm": 0.14865143597126007,
392
+ "learning_rate": 0.00010535087719298246,
393
+ "loss": 0.8575,
394
+ "step": 4800
395
+ },
396
+ {
397
+ "epoch": 4.083333333333333,
398
+ "grad_norm": 0.15284916758537292,
399
+ "learning_rate": 9.657894736842105e-05,
400
+ "loss": 0.8227,
401
+ "step": 4900
402
+ },
403
+ {
404
+ "epoch": 4.166666666666667,
405
+ "grad_norm": 0.22305266559123993,
406
+ "learning_rate": 8.780701754385966e-05,
407
+ "loss": 0.833,
408
+ "step": 5000
409
+ },
410
+ {
411
+ "epoch": 4.166666666666667,
412
+ "eval_loss": 0.7827907204627991,
413
+ "eval_rouge1": 0.391,
414
+ "eval_rouge2": 0.1599,
415
+ "eval_rougeL": 0.2764,
416
+ "eval_rougeLsum": 0.2764,
417
+ "eval_runtime": 1349.7759,
418
+ "eval_samples_per_second": 0.889,
419
+ "eval_steps_per_second": 0.222,
420
+ "step": 5000
421
+ },
422
+ {
423
+ "epoch": 4.25,
424
+ "grad_norm": 0.21298357844352722,
425
+ "learning_rate": 7.903508771929825e-05,
426
+ "loss": 0.8483,
427
+ "step": 5100
428
+ },
429
+ {
430
+ "epoch": 4.333333333333333,
431
+ "grad_norm": 0.19737210869789124,
432
+ "learning_rate": 7.026315789473685e-05,
433
+ "loss": 0.7888,
434
+ "step": 5200
435
+ },
436
+ {
437
+ "epoch": 4.416666666666667,
438
+ "grad_norm": 0.21889951825141907,
439
+ "learning_rate": 6.149122807017544e-05,
440
+ "loss": 0.8418,
441
+ "step": 5300
442
+ },
443
+ {
444
+ "epoch": 4.5,
445
+ "grad_norm": 0.13705947995185852,
446
+ "learning_rate": 5.271929824561403e-05,
447
+ "loss": 0.8639,
448
+ "step": 5400
449
+ },
450
+ {
451
+ "epoch": 4.583333333333333,
452
+ "grad_norm": 0.17922119796276093,
453
+ "learning_rate": 4.394736842105263e-05,
454
+ "loss": 0.8368,
455
+ "step": 5500
456
+ },
457
+ {
458
+ "epoch": 4.666666666666667,
459
+ "grad_norm": 0.21064095199108124,
460
+ "learning_rate": 3.5175438596491226e-05,
461
+ "loss": 0.8273,
462
+ "step": 5600
463
+ },
464
+ {
465
+ "epoch": 4.75,
466
+ "grad_norm": 0.17207187414169312,
467
+ "learning_rate": 2.6403508771929826e-05,
468
+ "loss": 0.921,
469
+ "step": 5700
470
+ },
471
+ {
472
+ "epoch": 4.833333333333333,
473
+ "grad_norm": 0.19569571316242218,
474
+ "learning_rate": 1.7631578947368424e-05,
475
+ "loss": 0.7884,
476
+ "step": 5800
477
+ },
478
+ {
479
+ "epoch": 4.916666666666667,
480
+ "grad_norm": 0.17810054123401642,
481
+ "learning_rate": 8.859649122807017e-06,
482
+ "loss": 0.8292,
483
+ "step": 5900
484
+ },
485
+ {
486
+ "epoch": 5.0,
487
+ "grad_norm": 0.19543497264385223,
488
+ "learning_rate": 8.771929824561403e-08,
489
+ "loss": 0.8396,
490
+ "step": 6000
491
+ },
492
+ {
493
+ "epoch": 5.0,
494
+ "eval_loss": 0.7824317216873169,
495
+ "eval_rouge1": 0.3925,
496
+ "eval_rouge2": 0.1608,
497
+ "eval_rougeL": 0.2776,
498
+ "eval_rougeLsum": 0.2776,
499
+ "eval_runtime": 1367.3028,
500
+ "eval_samples_per_second": 0.878,
501
+ "eval_steps_per_second": 0.219,
502
+ "step": 6000
503
+ }
504
+ ],
505
+ "logging_steps": 100,
506
+ "max_steps": 6000,
507
+ "num_input_tokens_seen": 0,
508
+ "num_train_epochs": 5,
509
+ "save_steps": 1000,
510
+ "stateful_callbacks": {
511
+ "TrainerControl": {
512
+ "args": {
513
+ "should_epoch_stop": false,
514
+ "should_evaluate": false,
515
+ "should_log": false,
516
+ "should_save": true,
517
+ "should_training_stop": true
518
+ },
519
+ "attributes": {}
520
+ }
521
+ },
522
+ "total_flos": 3.3912029970432e+16,
523
+ "train_batch_size": 4,
524
+ "trial_name": null,
525
+ "trial_params": null
526
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c0610f8b16c32dc914093221e783b825c5f92071a740b8df2cf51fa686aaadd
3
- size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaaa261bee53153443eba88bc72df53913dc20042b154f56a05ffc8033635d65
3
+ size 5905