gpol13 commited on
Commit
63e7d6d
·
verified ·
1 Parent(s): e8def0e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Salesforce/codet5-base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Salesforce/codet5-base",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q",
27
+ "v"
28
+ ],
29
+ "task_type": "SEQ_2_SEQ_LM",
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884a0093414b70010b5acdaf807bd6ab9909f018212a33265462924174feaab6
3
+ size 3558888
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb54def89b3cf1bc1d93ca6509fb50712e03f9a61571e286faf81bee0e5ff5f
3
+ size 7198906
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791f3776dbab55e844e0dc36b717af30310258ed41342da9d1ca07b772bdaa11
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37326798aa680a8e4350ddf21cb6c35d99c6dcd5c03a9af7c8fa1d1a772c157d
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,753 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<extra_id_99>",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<extra_id_98>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<extra_id_97>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<extra_id_96>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<extra_id_95>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<extra_id_94>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<extra_id_93>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<extra_id_92>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<extra_id_90>",
68
+ "lstrip": true,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<extra_id_89>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<extra_id_88>",
82
+ "lstrip": true,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<extra_id_87>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<extra_id_86>",
96
+ "lstrip": true,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<extra_id_85>",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<extra_id_84>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<extra_id_83>",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<extra_id_82>",
124
+ "lstrip": true,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<extra_id_81>",
131
+ "lstrip": true,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<extra_id_80>",
138
+ "lstrip": true,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<extra_id_79>",
145
+ "lstrip": true,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<extra_id_78>",
152
+ "lstrip": true,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<extra_id_77>",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<extra_id_76>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<extra_id_75>",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<extra_id_74>",
180
+ "lstrip": true,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<extra_id_73>",
187
+ "lstrip": true,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<extra_id_72>",
194
+ "lstrip": true,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<extra_id_71>",
201
+ "lstrip": true,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<extra_id_70>",
208
+ "lstrip": true,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<extra_id_69>",
215
+ "lstrip": true,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<extra_id_68>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<extra_id_67>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<extra_id_66>",
236
+ "lstrip": true,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<extra_id_65>",
243
+ "lstrip": true,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<extra_id_64>",
250
+ "lstrip": true,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<extra_id_63>",
257
+ "lstrip": true,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<extra_id_62>",
264
+ "lstrip": true,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<extra_id_61>",
271
+ "lstrip": true,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<extra_id_60>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<extra_id_59>",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<extra_id_58>",
292
+ "lstrip": true,
293
+ "normalized": true,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<extra_id_57>",
299
+ "lstrip": true,
300
+ "normalized": true,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<extra_id_56>",
306
+ "lstrip": true,
307
+ "normalized": true,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<extra_id_55>",
313
+ "lstrip": true,
314
+ "normalized": true,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<extra_id_54>",
320
+ "lstrip": true,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<extra_id_53>",
327
+ "lstrip": true,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<extra_id_52>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<extra_id_51>",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<extra_id_50>",
348
+ "lstrip": true,
349
+ "normalized": true,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<extra_id_49>",
355
+ "lstrip": true,
356
+ "normalized": true,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<extra_id_48>",
362
+ "lstrip": true,
363
+ "normalized": true,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<extra_id_47>",
369
+ "lstrip": true,
370
+ "normalized": true,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<extra_id_46>",
376
+ "lstrip": true,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<extra_id_45>",
383
+ "lstrip": true,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<extra_id_43>",
397
+ "lstrip": true,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<extra_id_42>",
404
+ "lstrip": true,
405
+ "normalized": true,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<extra_id_41>",
411
+ "lstrip": true,
412
+ "normalized": true,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<extra_id_40>",
418
+ "lstrip": true,
419
+ "normalized": true,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<extra_id_39>",
425
+ "lstrip": true,
426
+ "normalized": true,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<extra_id_38>",
432
+ "lstrip": true,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<extra_id_37>",
439
+ "lstrip": true,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<extra_id_36>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<extra_id_35>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<extra_id_34>",
460
+ "lstrip": true,
461
+ "normalized": true,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<extra_id_33>",
467
+ "lstrip": true,
468
+ "normalized": true,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<extra_id_32>",
474
+ "lstrip": true,
475
+ "normalized": true,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<extra_id_31>",
481
+ "lstrip": true,
482
+ "normalized": true,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<extra_id_30>",
488
+ "lstrip": true,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<extra_id_29>",
495
+ "lstrip": true,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<extra_id_28>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<extra_id_27>",
509
+ "lstrip": true,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<extra_id_26>",
516
+ "lstrip": true,
517
+ "normalized": true,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<extra_id_25>",
523
+ "lstrip": true,
524
+ "normalized": true,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<extra_id_24>",
530
+ "lstrip": true,
531
+ "normalized": true,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<extra_id_23>",
537
+ "lstrip": true,
538
+ "normalized": true,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<extra_id_22>",
544
+ "lstrip": true,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<extra_id_21>",
551
+ "lstrip": true,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<extra_id_20>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<extra_id_19>",
565
+ "lstrip": true,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<extra_id_18>",
572
+ "lstrip": true,
573
+ "normalized": true,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<extra_id_17>",
579
+ "lstrip": true,
580
+ "normalized": true,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<extra_id_16>",
586
+ "lstrip": true,
587
+ "normalized": true,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<extra_id_15>",
593
+ "lstrip": true,
594
+ "normalized": true,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<extra_id_14>",
600
+ "lstrip": true,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<extra_id_13>",
607
+ "lstrip": true,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<extra_id_12>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<extra_id_11>",
621
+ "lstrip": true,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<extra_id_10>",
628
+ "lstrip": true,
629
+ "normalized": true,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<extra_id_9>",
635
+ "lstrip": true,
636
+ "normalized": true,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "<extra_id_8>",
642
+ "lstrip": true,
643
+ "normalized": true,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<extra_id_7>",
649
+ "lstrip": true,
650
+ "normalized": true,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "<extra_id_6>",
656
+ "lstrip": true,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<extra_id_5>",
663
+ "lstrip": true,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "<extra_id_4>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<extra_id_3>",
677
+ "lstrip": true,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<extra_id_2>",
684
+ "lstrip": true,
685
+ "normalized": true,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<extra_id_1>",
691
+ "lstrip": true,
692
+ "normalized": true,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<extra_id_0>",
698
+ "lstrip": true,
699
+ "normalized": true,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ }
703
+ ],
704
+ "bos_token": {
705
+ "content": "<s>",
706
+ "lstrip": false,
707
+ "normalized": true,
708
+ "rstrip": false,
709
+ "single_word": false
710
+ },
711
+ "cls_token": {
712
+ "content": "<s>",
713
+ "lstrip": false,
714
+ "normalized": true,
715
+ "rstrip": false,
716
+ "single_word": false
717
+ },
718
+ "eos_token": {
719
+ "content": "</s>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false
724
+ },
725
+ "mask_token": {
726
+ "content": "<mask>",
727
+ "lstrip": true,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "<pad>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "sep_token": {
740
+ "content": "</s>",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ },
746
+ "unk_token": {
747
+ "content": "<unk>",
748
+ "lstrip": false,
749
+ "normalized": true,
750
+ "rstrip": false,
751
+ "single_word": false
752
+ }
753
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,960 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
+ "lstrip": true,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<extra_id_99>",
847
+ "<extra_id_98>",
848
+ "<extra_id_97>",
849
+ "<extra_id_96>",
850
+ "<extra_id_95>",
851
+ "<extra_id_94>",
852
+ "<extra_id_93>",
853
+ "<extra_id_92>",
854
+ "<extra_id_91>",
855
+ "<extra_id_90>",
856
+ "<extra_id_89>",
857
+ "<extra_id_88>",
858
+ "<extra_id_87>",
859
+ "<extra_id_86>",
860
+ "<extra_id_85>",
861
+ "<extra_id_84>",
862
+ "<extra_id_83>",
863
+ "<extra_id_82>",
864
+ "<extra_id_81>",
865
+ "<extra_id_80>",
866
+ "<extra_id_79>",
867
+ "<extra_id_78>",
868
+ "<extra_id_77>",
869
+ "<extra_id_76>",
870
+ "<extra_id_75>",
871
+ "<extra_id_74>",
872
+ "<extra_id_73>",
873
+ "<extra_id_72>",
874
+ "<extra_id_71>",
875
+ "<extra_id_70>",
876
+ "<extra_id_69>",
877
+ "<extra_id_68>",
878
+ "<extra_id_67>",
879
+ "<extra_id_66>",
880
+ "<extra_id_65>",
881
+ "<extra_id_64>",
882
+ "<extra_id_63>",
883
+ "<extra_id_62>",
884
+ "<extra_id_61>",
885
+ "<extra_id_60>",
886
+ "<extra_id_59>",
887
+ "<extra_id_58>",
888
+ "<extra_id_57>",
889
+ "<extra_id_56>",
890
+ "<extra_id_55>",
891
+ "<extra_id_54>",
892
+ "<extra_id_53>",
893
+ "<extra_id_52>",
894
+ "<extra_id_51>",
895
+ "<extra_id_50>",
896
+ "<extra_id_49>",
897
+ "<extra_id_48>",
898
+ "<extra_id_47>",
899
+ "<extra_id_46>",
900
+ "<extra_id_45>",
901
+ "<extra_id_44>",
902
+ "<extra_id_43>",
903
+ "<extra_id_42>",
904
+ "<extra_id_41>",
905
+ "<extra_id_40>",
906
+ "<extra_id_39>",
907
+ "<extra_id_38>",
908
+ "<extra_id_37>",
909
+ "<extra_id_36>",
910
+ "<extra_id_35>",
911
+ "<extra_id_34>",
912
+ "<extra_id_33>",
913
+ "<extra_id_32>",
914
+ "<extra_id_31>",
915
+ "<extra_id_30>",
916
+ "<extra_id_29>",
917
+ "<extra_id_28>",
918
+ "<extra_id_27>",
919
+ "<extra_id_26>",
920
+ "<extra_id_25>",
921
+ "<extra_id_24>",
922
+ "<extra_id_23>",
923
+ "<extra_id_22>",
924
+ "<extra_id_21>",
925
+ "<extra_id_20>",
926
+ "<extra_id_19>",
927
+ "<extra_id_18>",
928
+ "<extra_id_17>",
929
+ "<extra_id_16>",
930
+ "<extra_id_15>",
931
+ "<extra_id_14>",
932
+ "<extra_id_13>",
933
+ "<extra_id_12>",
934
+ "<extra_id_11>",
935
+ "<extra_id_10>",
936
+ "<extra_id_9>",
937
+ "<extra_id_8>",
938
+ "<extra_id_7>",
939
+ "<extra_id_6>",
940
+ "<extra_id_5>",
941
+ "<extra_id_4>",
942
+ "<extra_id_3>",
943
+ "<extra_id_2>",
944
+ "<extra_id_1>",
945
+ "<extra_id_0>"
946
+ ],
947
+ "bos_token": "<s>",
948
+ "clean_up_tokenization_spaces": false,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "extra_special_tokens": {},
953
+ "mask_token": "<mask>",
954
+ "model_max_length": 512,
955
+ "pad_token": "<pad>",
956
+ "sep_token": "</s>",
957
+ "tokenizer_class": "RobertaTokenizer",
958
+ "trim_offsets": true,
959
+ "unk_token": "<unk>"
960
+ }
trainer_state.json ADDED
@@ -0,0 +1,1086 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7075,
3
+ "best_metric": 0.957730518736978,
4
+ "best_model_checkpoint": "/kaggle/working/sparse_lora/checkpoint-7075",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 7075,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0353356890459364,
14
+ "grad_norm": 87870.6484375,
15
+ "learning_rate": 4.9653710247349825e-05,
16
+ "loss": 4.5998,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.0706713780918728,
21
+ "grad_norm": 671269.4375,
22
+ "learning_rate": 4.930035335689046e-05,
23
+ "loss": 3.6646,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.10600706713780919,
28
+ "grad_norm": 103706.0,
29
+ "learning_rate": 4.89469964664311e-05,
30
+ "loss": 3.0394,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.1413427561837456,
35
+ "grad_norm": 60311.45703125,
36
+ "learning_rate": 4.859363957597173e-05,
37
+ "loss": 2.1607,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.17667844522968199,
42
+ "grad_norm": 56506.35546875,
43
+ "learning_rate": 4.8240282685512374e-05,
44
+ "loss": 2.0396,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.21201413427561838,
49
+ "grad_norm": 64563.61328125,
50
+ "learning_rate": 4.788692579505301e-05,
51
+ "loss": 1.8784,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.24734982332155478,
56
+ "grad_norm": 84701.9765625,
57
+ "learning_rate": 4.753356890459364e-05,
58
+ "loss": 1.823,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.2826855123674912,
63
+ "grad_norm": 80899.9765625,
64
+ "learning_rate": 4.718021201413428e-05,
65
+ "loss": 1.825,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.31802120141342755,
70
+ "grad_norm": 83637.8671875,
71
+ "learning_rate": 4.682685512367491e-05,
72
+ "loss": 1.6937,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.35335689045936397,
77
+ "grad_norm": 172655.1875,
78
+ "learning_rate": 4.647349823321555e-05,
79
+ "loss": 1.6309,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.38869257950530034,
84
+ "grad_norm": 212648.234375,
85
+ "learning_rate": 4.612014134275618e-05,
86
+ "loss": 1.5667,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.42402826855123676,
91
+ "grad_norm": 85414.8125,
92
+ "learning_rate": 4.5766784452296823e-05,
93
+ "loss": 1.5433,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.45936395759717313,
98
+ "grad_norm": 84665.4296875,
99
+ "learning_rate": 4.541342756183746e-05,
100
+ "loss": 1.5225,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.49469964664310956,
105
+ "grad_norm": 87850.546875,
106
+ "learning_rate": 4.50600706713781e-05,
107
+ "loss": 1.4696,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.5300353356890459,
112
+ "grad_norm": 105920.03125,
113
+ "learning_rate": 4.470671378091873e-05,
114
+ "loss": 1.5046,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.5653710247349824,
119
+ "grad_norm": 128489.2734375,
120
+ "learning_rate": 4.435335689045937e-05,
121
+ "loss": 1.4268,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.6007067137809188,
126
+ "grad_norm": 126656.5390625,
127
+ "learning_rate": 4.4000000000000006e-05,
128
+ "loss": 1.3749,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.6360424028268551,
133
+ "grad_norm": 90037.234375,
134
+ "learning_rate": 4.364664310954063e-05,
135
+ "loss": 1.4043,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.6713780918727915,
140
+ "grad_norm": 123195.953125,
141
+ "learning_rate": 4.329328621908127e-05,
142
+ "loss": 1.3655,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.7067137809187279,
147
+ "grad_norm": 106699.8984375,
148
+ "learning_rate": 4.293992932862191e-05,
149
+ "loss": 1.3125,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.7420494699646644,
154
+ "grad_norm": 141920.890625,
155
+ "learning_rate": 4.258657243816255e-05,
156
+ "loss": 1.2784,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.7773851590106007,
161
+ "grad_norm": 155978.375,
162
+ "learning_rate": 4.223321554770318e-05,
163
+ "loss": 1.307,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.8127208480565371,
168
+ "grad_norm": 151003.53125,
169
+ "learning_rate": 4.187985865724382e-05,
170
+ "loss": 1.2263,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.8480565371024735,
175
+ "grad_norm": 122458.796875,
176
+ "learning_rate": 4.1526501766784455e-05,
177
+ "loss": 1.1795,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.8833922261484098,
182
+ "grad_norm": 137286.90625,
183
+ "learning_rate": 4.1173144876325096e-05,
184
+ "loss": 1.2285,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.9187279151943463,
189
+ "grad_norm": 112117.640625,
190
+ "learning_rate": 4.081978798586573e-05,
191
+ "loss": 1.2263,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.9540636042402827,
196
+ "grad_norm": 127897.46875,
197
+ "learning_rate": 4.0466431095406356e-05,
198
+ "loss": 1.1636,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.9893992932862191,
203
+ "grad_norm": 121189.921875,
204
+ "learning_rate": 4.0113074204947e-05,
205
+ "loss": 1.1762,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 1.0,
210
+ "eval_bertscore_f1": 0.9435882283983255,
211
+ "eval_bleu": 0.34081729524428495,
212
+ "eval_loss": 0.8283334970474243,
213
+ "eval_meteor": 0.5505336031382576,
214
+ "eval_rouge1": 0.741807000391657,
215
+ "eval_rouge2": 0.561792451504467,
216
+ "eval_runtime": 458.3629,
217
+ "eval_samples_per_second": 14.102,
218
+ "eval_steps_per_second": 0.881,
219
+ "step": 1415
220
+ },
221
+ {
222
+ "epoch": 1.0247349823321554,
223
+ "grad_norm": 128025.5703125,
224
+ "learning_rate": 3.975971731448763e-05,
225
+ "loss": 1.1689,
226
+ "step": 1450
227
+ },
228
+ {
229
+ "epoch": 1.0600706713780919,
230
+ "grad_norm": 117022.6953125,
231
+ "learning_rate": 3.940636042402827e-05,
232
+ "loss": 1.1721,
233
+ "step": 1500
234
+ },
235
+ {
236
+ "epoch": 1.0954063604240283,
237
+ "grad_norm": 127291.71875,
238
+ "learning_rate": 3.9053003533568905e-05,
239
+ "loss": 1.1144,
240
+ "step": 1550
241
+ },
242
+ {
243
+ "epoch": 1.1307420494699647,
244
+ "grad_norm": 432520.5,
245
+ "learning_rate": 3.8699646643109545e-05,
246
+ "loss": 1.1173,
247
+ "step": 1600
248
+ },
249
+ {
250
+ "epoch": 1.1660777385159011,
251
+ "grad_norm": 133514.078125,
252
+ "learning_rate": 3.834628975265018e-05,
253
+ "loss": 1.1349,
254
+ "step": 1650
255
+ },
256
+ {
257
+ "epoch": 1.2014134275618376,
258
+ "grad_norm": 196108.515625,
259
+ "learning_rate": 3.799293286219082e-05,
260
+ "loss": 1.1105,
261
+ "step": 1700
262
+ },
263
+ {
264
+ "epoch": 1.2367491166077738,
265
+ "grad_norm": 141071.890625,
266
+ "learning_rate": 3.763957597173145e-05,
267
+ "loss": 1.0843,
268
+ "step": 1750
269
+ },
270
+ {
271
+ "epoch": 1.2720848056537102,
272
+ "grad_norm": 132118.53125,
273
+ "learning_rate": 3.728621908127209e-05,
274
+ "loss": 1.1424,
275
+ "step": 1800
276
+ },
277
+ {
278
+ "epoch": 1.3074204946996466,
279
+ "grad_norm": 160950.84375,
280
+ "learning_rate": 3.693286219081272e-05,
281
+ "loss": 1.1462,
282
+ "step": 1850
283
+ },
284
+ {
285
+ "epoch": 1.342756183745583,
286
+ "grad_norm": 128804.078125,
287
+ "learning_rate": 3.6579505300353355e-05,
288
+ "loss": 1.0572,
289
+ "step": 1900
290
+ },
291
+ {
292
+ "epoch": 1.3780918727915195,
293
+ "grad_norm": 157611.953125,
294
+ "learning_rate": 3.6226148409893995e-05,
295
+ "loss": 1.0987,
296
+ "step": 1950
297
+ },
298
+ {
299
+ "epoch": 1.4134275618374559,
300
+ "grad_norm": 141798.90625,
301
+ "learning_rate": 3.587279151943463e-05,
302
+ "loss": 1.0541,
303
+ "step": 2000
304
+ },
305
+ {
306
+ "epoch": 1.4487632508833923,
307
+ "grad_norm": 171915.71875,
308
+ "learning_rate": 3.551943462897527e-05,
309
+ "loss": 1.0487,
310
+ "step": 2050
311
+ },
312
+ {
313
+ "epoch": 1.4840989399293285,
314
+ "grad_norm": 127521.7109375,
315
+ "learning_rate": 3.51660777385159e-05,
316
+ "loss": 0.9808,
317
+ "step": 2100
318
+ },
319
+ {
320
+ "epoch": 1.5194346289752652,
321
+ "grad_norm": 144515.828125,
322
+ "learning_rate": 3.4812720848056544e-05,
323
+ "loss": 0.9844,
324
+ "step": 2150
325
+ },
326
+ {
327
+ "epoch": 1.5547703180212014,
328
+ "grad_norm": 135642.578125,
329
+ "learning_rate": 3.445936395759717e-05,
330
+ "loss": 0.9523,
331
+ "step": 2200
332
+ },
333
+ {
334
+ "epoch": 1.5901060070671378,
335
+ "grad_norm": 211087.34375,
336
+ "learning_rate": 3.410600706713781e-05,
337
+ "loss": 0.9904,
338
+ "step": 2250
339
+ },
340
+ {
341
+ "epoch": 1.6254416961130742,
342
+ "grad_norm": 157448.421875,
343
+ "learning_rate": 3.3752650176678445e-05,
344
+ "loss": 1.0143,
345
+ "step": 2300
346
+ },
347
+ {
348
+ "epoch": 1.6607773851590106,
349
+ "grad_norm": 185968.609375,
350
+ "learning_rate": 3.3399293286219085e-05,
351
+ "loss": 1.0191,
352
+ "step": 2350
353
+ },
354
+ {
355
+ "epoch": 1.696113074204947,
356
+ "grad_norm": 138438.078125,
357
+ "learning_rate": 3.304593639575972e-05,
358
+ "loss": 1.0524,
359
+ "step": 2400
360
+ },
361
+ {
362
+ "epoch": 1.7314487632508833,
363
+ "grad_norm": 151158.640625,
364
+ "learning_rate": 3.269257950530035e-05,
365
+ "loss": 0.9748,
366
+ "step": 2450
367
+ },
368
+ {
369
+ "epoch": 1.76678445229682,
370
+ "grad_norm": 146153.25,
371
+ "learning_rate": 3.233922261484099e-05,
372
+ "loss": 0.9595,
373
+ "step": 2500
374
+ },
375
+ {
376
+ "epoch": 1.802120141342756,
377
+ "grad_norm": 145571.171875,
378
+ "learning_rate": 3.198586572438163e-05,
379
+ "loss": 0.9884,
380
+ "step": 2550
381
+ },
382
+ {
383
+ "epoch": 1.8374558303886925,
384
+ "grad_norm": 200024.28125,
385
+ "learning_rate": 3.163250883392227e-05,
386
+ "loss": 0.9961,
387
+ "step": 2600
388
+ },
389
+ {
390
+ "epoch": 1.872791519434629,
391
+ "grad_norm": 1255579.375,
392
+ "learning_rate": 3.1279151943462894e-05,
393
+ "loss": 0.9381,
394
+ "step": 2650
395
+ },
396
+ {
397
+ "epoch": 1.9081272084805654,
398
+ "grad_norm": 191306.1875,
399
+ "learning_rate": 3.0925795053003535e-05,
400
+ "loss": 0.9179,
401
+ "step": 2700
402
+ },
403
+ {
404
+ "epoch": 1.9434628975265018,
405
+ "grad_norm": 139976.265625,
406
+ "learning_rate": 3.057243816254417e-05,
407
+ "loss": 0.9741,
408
+ "step": 2750
409
+ },
410
+ {
411
+ "epoch": 1.978798586572438,
412
+ "grad_norm": 254590.484375,
413
+ "learning_rate": 3.021908127208481e-05,
414
+ "loss": 0.97,
415
+ "step": 2800
416
+ },
417
+ {
418
+ "epoch": 2.0,
419
+ "eval_bertscore_f1": 0.9522204981784862,
420
+ "eval_bleu": 0.4391766527339286,
421
+ "eval_loss": 0.6113855838775635,
422
+ "eval_meteor": 0.6141492660226205,
423
+ "eval_rouge1": 0.7802485332799334,
424
+ "eval_rouge2": 0.6456575876833133,
425
+ "eval_runtime": 442.4344,
426
+ "eval_samples_per_second": 14.61,
427
+ "eval_steps_per_second": 0.913,
428
+ "step": 2830
429
+ },
430
+ {
431
+ "epoch": 2.0141342756183747,
432
+ "grad_norm": 251050.734375,
433
+ "learning_rate": 2.9865724381625443e-05,
434
+ "loss": 0.9362,
435
+ "step": 2850
436
+ },
437
+ {
438
+ "epoch": 2.049469964664311,
439
+ "grad_norm": 165134.1875,
440
+ "learning_rate": 2.9512367491166083e-05,
441
+ "loss": 0.9642,
442
+ "step": 2900
443
+ },
444
+ {
445
+ "epoch": 2.0848056537102475,
446
+ "grad_norm": 167977.453125,
447
+ "learning_rate": 2.9159010600706717e-05,
448
+ "loss": 0.899,
449
+ "step": 2950
450
+ },
451
+ {
452
+ "epoch": 2.1201413427561837,
453
+ "grad_norm": 137508.921875,
454
+ "learning_rate": 2.8805653710247347e-05,
455
+ "loss": 0.8828,
456
+ "step": 3000
457
+ },
458
+ {
459
+ "epoch": 2.1554770318021204,
460
+ "grad_norm": 155117.59375,
461
+ "learning_rate": 2.8452296819787988e-05,
462
+ "loss": 0.8958,
463
+ "step": 3050
464
+ },
465
+ {
466
+ "epoch": 2.1908127208480566,
467
+ "grad_norm": 155701.109375,
468
+ "learning_rate": 2.809893992932862e-05,
469
+ "loss": 0.9106,
470
+ "step": 3100
471
+ },
472
+ {
473
+ "epoch": 2.2261484098939928,
474
+ "grad_norm": 148495.125,
475
+ "learning_rate": 2.7745583038869262e-05,
476
+ "loss": 0.9755,
477
+ "step": 3150
478
+ },
479
+ {
480
+ "epoch": 2.2614840989399294,
481
+ "grad_norm": 179815.203125,
482
+ "learning_rate": 2.7392226148409892e-05,
483
+ "loss": 0.9842,
484
+ "step": 3200
485
+ },
486
+ {
487
+ "epoch": 2.2968197879858656,
488
+ "grad_norm": 193006.0625,
489
+ "learning_rate": 2.7038869257950533e-05,
490
+ "loss": 0.8794,
491
+ "step": 3250
492
+ },
493
+ {
494
+ "epoch": 2.3321554770318023,
495
+ "grad_norm": 181638.421875,
496
+ "learning_rate": 2.6685512367491167e-05,
497
+ "loss": 0.9415,
498
+ "step": 3300
499
+ },
500
+ {
501
+ "epoch": 2.3674911660777385,
502
+ "grad_norm": 172265.5,
503
+ "learning_rate": 2.6332155477031807e-05,
504
+ "loss": 0.9453,
505
+ "step": 3350
506
+ },
507
+ {
508
+ "epoch": 2.402826855123675,
509
+ "grad_norm": 142922.71875,
510
+ "learning_rate": 2.597879858657244e-05,
511
+ "loss": 0.8669,
512
+ "step": 3400
513
+ },
514
+ {
515
+ "epoch": 2.4381625441696113,
516
+ "grad_norm": 153024.515625,
517
+ "learning_rate": 2.562544169611307e-05,
518
+ "loss": 0.9168,
519
+ "step": 3450
520
+ },
521
+ {
522
+ "epoch": 2.4734982332155475,
523
+ "grad_norm": 325320.28125,
524
+ "learning_rate": 2.5272084805653712e-05,
525
+ "loss": 0.8523,
526
+ "step": 3500
527
+ },
528
+ {
529
+ "epoch": 2.508833922261484,
530
+ "grad_norm": 180908.15625,
531
+ "learning_rate": 2.491872791519435e-05,
532
+ "loss": 0.8853,
533
+ "step": 3550
534
+ },
535
+ {
536
+ "epoch": 2.5441696113074204,
537
+ "grad_norm": 171192.765625,
538
+ "learning_rate": 2.4565371024734986e-05,
539
+ "loss": 0.9041,
540
+ "step": 3600
541
+ },
542
+ {
543
+ "epoch": 2.579505300353357,
544
+ "grad_norm": 148674.578125,
545
+ "learning_rate": 2.421201413427562e-05,
546
+ "loss": 0.865,
547
+ "step": 3650
548
+ },
549
+ {
550
+ "epoch": 2.614840989399293,
551
+ "grad_norm": 189248.390625,
552
+ "learning_rate": 2.3858657243816253e-05,
553
+ "loss": 0.9255,
554
+ "step": 3700
555
+ },
556
+ {
557
+ "epoch": 2.65017667844523,
558
+ "grad_norm": 159843.796875,
559
+ "learning_rate": 2.350530035335689e-05,
560
+ "loss": 0.8886,
561
+ "step": 3750
562
+ },
563
+ {
564
+ "epoch": 2.685512367491166,
565
+ "grad_norm": 162496.359375,
566
+ "learning_rate": 2.3151943462897528e-05,
567
+ "loss": 0.8689,
568
+ "step": 3800
569
+ },
570
+ {
571
+ "epoch": 2.7208480565371023,
572
+ "grad_norm": 135053.5625,
573
+ "learning_rate": 2.2798586572438165e-05,
574
+ "loss": 0.8275,
575
+ "step": 3850
576
+ },
577
+ {
578
+ "epoch": 2.756183745583039,
579
+ "grad_norm": 249403.953125,
580
+ "learning_rate": 2.24452296819788e-05,
581
+ "loss": 0.8319,
582
+ "step": 3900
583
+ },
584
+ {
585
+ "epoch": 2.791519434628975,
586
+ "grad_norm": 181885.328125,
587
+ "learning_rate": 2.2091872791519436e-05,
588
+ "loss": 0.8719,
589
+ "step": 3950
590
+ },
591
+ {
592
+ "epoch": 2.8268551236749118,
593
+ "grad_norm": 156204.75,
594
+ "learning_rate": 2.1738515901060073e-05,
595
+ "loss": 0.8592,
596
+ "step": 4000
597
+ },
598
+ {
599
+ "epoch": 2.862190812720848,
600
+ "grad_norm": 159614.03125,
601
+ "learning_rate": 2.138515901060071e-05,
602
+ "loss": 0.8381,
603
+ "step": 4050
604
+ },
605
+ {
606
+ "epoch": 2.8975265017667846,
607
+ "grad_norm": 162379.78125,
608
+ "learning_rate": 2.1031802120141344e-05,
609
+ "loss": 0.8612,
610
+ "step": 4100
611
+ },
612
+ {
613
+ "epoch": 2.932862190812721,
614
+ "grad_norm": 149608.25,
615
+ "learning_rate": 2.067844522968198e-05,
616
+ "loss": 0.838,
617
+ "step": 4150
618
+ },
619
+ {
620
+ "epoch": 2.968197879858657,
621
+ "grad_norm": 145233.40625,
622
+ "learning_rate": 2.0325088339222618e-05,
623
+ "loss": 0.8411,
624
+ "step": 4200
625
+ },
626
+ {
627
+ "epoch": 3.0,
628
+ "eval_bertscore_f1": 0.955309976823628,
629
+ "eval_bleu": 0.47422911395097656,
630
+ "eval_loss": 0.5273156762123108,
631
+ "eval_meteor": 0.6439931966505934,
632
+ "eval_rouge1": 0.7960674625670938,
633
+ "eval_rouge2": 0.6807866947718111,
634
+ "eval_runtime": 440.5737,
635
+ "eval_samples_per_second": 14.672,
636
+ "eval_steps_per_second": 0.917,
637
+ "step": 4245
638
+ },
639
+ {
640
+ "epoch": 3.0035335689045937,
641
+ "grad_norm": 146904.109375,
642
+ "learning_rate": 1.997173144876325e-05,
643
+ "loss": 0.8212,
644
+ "step": 4250
645
+ },
646
+ {
647
+ "epoch": 3.03886925795053,
648
+ "grad_norm": 141972.140625,
649
+ "learning_rate": 1.9618374558303885e-05,
650
+ "loss": 0.8332,
651
+ "step": 4300
652
+ },
653
+ {
654
+ "epoch": 3.0742049469964665,
655
+ "grad_norm": 155438.34375,
656
+ "learning_rate": 1.9265017667844522e-05,
657
+ "loss": 0.8314,
658
+ "step": 4350
659
+ },
660
+ {
661
+ "epoch": 3.1095406360424027,
662
+ "grad_norm": 157805.5,
663
+ "learning_rate": 1.891166077738516e-05,
664
+ "loss": 0.8432,
665
+ "step": 4400
666
+ },
667
+ {
668
+ "epoch": 3.1448763250883394,
669
+ "grad_norm": 171890.296875,
670
+ "learning_rate": 1.8558303886925797e-05,
671
+ "loss": 0.8171,
672
+ "step": 4450
673
+ },
674
+ {
675
+ "epoch": 3.1802120141342756,
676
+ "grad_norm": 159529.09375,
677
+ "learning_rate": 1.8204946996466434e-05,
678
+ "loss": 0.8462,
679
+ "step": 4500
680
+ },
681
+ {
682
+ "epoch": 3.215547703180212,
683
+ "grad_norm": 291361.3125,
684
+ "learning_rate": 1.7851590106007067e-05,
685
+ "loss": 0.8525,
686
+ "step": 4550
687
+ },
688
+ {
689
+ "epoch": 3.2508833922261484,
690
+ "grad_norm": 146320.515625,
691
+ "learning_rate": 1.7498233215547705e-05,
692
+ "loss": 0.8691,
693
+ "step": 4600
694
+ },
695
+ {
696
+ "epoch": 3.2862190812720846,
697
+ "grad_norm": 142328.234375,
698
+ "learning_rate": 1.714487632508834e-05,
699
+ "loss": 0.8152,
700
+ "step": 4650
701
+ },
702
+ {
703
+ "epoch": 3.3215547703180213,
704
+ "grad_norm": 164441.828125,
705
+ "learning_rate": 1.679151943462898e-05,
706
+ "loss": 0.7897,
707
+ "step": 4700
708
+ },
709
+ {
710
+ "epoch": 3.3568904593639575,
711
+ "grad_norm": 181799.328125,
712
+ "learning_rate": 1.643816254416961e-05,
713
+ "loss": 0.89,
714
+ "step": 4750
715
+ },
716
+ {
717
+ "epoch": 3.392226148409894,
718
+ "grad_norm": 161868.921875,
719
+ "learning_rate": 1.6084805653710246e-05,
720
+ "loss": 0.8342,
721
+ "step": 4800
722
+ },
723
+ {
724
+ "epoch": 3.4275618374558303,
725
+ "grad_norm": 168403.046875,
726
+ "learning_rate": 1.5731448763250883e-05,
727
+ "loss": 0.7708,
728
+ "step": 4850
729
+ },
730
+ {
731
+ "epoch": 3.462897526501767,
732
+ "grad_norm": 180798.71875,
733
+ "learning_rate": 1.537809187279152e-05,
734
+ "loss": 0.8452,
735
+ "step": 4900
736
+ },
737
+ {
738
+ "epoch": 3.498233215547703,
739
+ "grad_norm": 194585.109375,
740
+ "learning_rate": 1.5024734982332156e-05,
741
+ "loss": 0.8543,
742
+ "step": 4950
743
+ },
744
+ {
745
+ "epoch": 3.53356890459364,
746
+ "grad_norm": 162353.515625,
747
+ "learning_rate": 1.4671378091872793e-05,
748
+ "loss": 0.7865,
749
+ "step": 5000
750
+ },
751
+ {
752
+ "epoch": 3.568904593639576,
753
+ "grad_norm": 161337.140625,
754
+ "learning_rate": 1.4318021201413428e-05,
755
+ "loss": 0.8459,
756
+ "step": 5050
757
+ },
758
+ {
759
+ "epoch": 3.604240282685512,
760
+ "grad_norm": 174313.953125,
761
+ "learning_rate": 1.3964664310954066e-05,
762
+ "loss": 0.8914,
763
+ "step": 5100
764
+ },
765
+ {
766
+ "epoch": 3.639575971731449,
767
+ "grad_norm": 163668.421875,
768
+ "learning_rate": 1.3611307420494701e-05,
769
+ "loss": 0.8457,
770
+ "step": 5150
771
+ },
772
+ {
773
+ "epoch": 3.674911660777385,
774
+ "grad_norm": 164355.765625,
775
+ "learning_rate": 1.3257950530035338e-05,
776
+ "loss": 0.8266,
777
+ "step": 5200
778
+ },
779
+ {
780
+ "epoch": 3.7102473498233217,
781
+ "grad_norm": 159919.046875,
782
+ "learning_rate": 1.2904593639575973e-05,
783
+ "loss": 0.7511,
784
+ "step": 5250
785
+ },
786
+ {
787
+ "epoch": 3.745583038869258,
788
+ "grad_norm": 131121.03125,
789
+ "learning_rate": 1.2551236749116607e-05,
790
+ "loss": 0.8333,
791
+ "step": 5300
792
+ },
793
+ {
794
+ "epoch": 3.7809187279151946,
795
+ "grad_norm": 160561.640625,
796
+ "learning_rate": 1.2197879858657244e-05,
797
+ "loss": 0.7992,
798
+ "step": 5350
799
+ },
800
+ {
801
+ "epoch": 3.8162544169611308,
802
+ "grad_norm": 200662.859375,
803
+ "learning_rate": 1.184452296819788e-05,
804
+ "loss": 0.8494,
805
+ "step": 5400
806
+ },
807
+ {
808
+ "epoch": 3.851590106007067,
809
+ "grad_norm": 158871.84375,
810
+ "learning_rate": 1.1491166077738517e-05,
811
+ "loss": 0.7689,
812
+ "step": 5450
813
+ },
814
+ {
815
+ "epoch": 3.8869257950530036,
816
+ "grad_norm": 233291.453125,
817
+ "learning_rate": 1.1137809187279152e-05,
818
+ "loss": 0.7717,
819
+ "step": 5500
820
+ },
821
+ {
822
+ "epoch": 3.92226148409894,
823
+ "grad_norm": 152039.84375,
824
+ "learning_rate": 1.078445229681979e-05,
825
+ "loss": 0.7991,
826
+ "step": 5550
827
+ },
828
+ {
829
+ "epoch": 3.9575971731448765,
830
+ "grad_norm": 174898.390625,
831
+ "learning_rate": 1.0431095406360425e-05,
832
+ "loss": 0.7713,
833
+ "step": 5600
834
+ },
835
+ {
836
+ "epoch": 3.9929328621908127,
837
+ "grad_norm": 185653.25,
838
+ "learning_rate": 1.0077738515901062e-05,
839
+ "loss": 0.8271,
840
+ "step": 5650
841
+ },
842
+ {
843
+ "epoch": 4.0,
844
+ "eval_bertscore_f1": 0.9574022400700072,
845
+ "eval_bleu": 0.49288907686192807,
846
+ "eval_loss": 0.4886058270931244,
847
+ "eval_meteor": 0.6607653874114606,
848
+ "eval_rouge1": 0.8043075620747033,
849
+ "eval_rouge2": 0.698973717724064,
850
+ "eval_runtime": 437.782,
851
+ "eval_samples_per_second": 14.765,
852
+ "eval_steps_per_second": 0.923,
853
+ "step": 5660
854
+ },
855
+ {
856
+ "epoch": 4.028268551236749,
857
+ "grad_norm": 189546.390625,
858
+ "learning_rate": 9.724381625441696e-06,
859
+ "loss": 0.8009,
860
+ "step": 5700
861
+ },
862
+ {
863
+ "epoch": 4.063604240282685,
864
+ "grad_norm": 179902.28125,
865
+ "learning_rate": 9.371024734982333e-06,
866
+ "loss": 0.7955,
867
+ "step": 5750
868
+ },
869
+ {
870
+ "epoch": 4.098939929328622,
871
+ "grad_norm": 134316.078125,
872
+ "learning_rate": 9.017667844522968e-06,
873
+ "loss": 0.8093,
874
+ "step": 5800
875
+ },
876
+ {
877
+ "epoch": 4.134275618374558,
878
+ "grad_norm": 113333.8203125,
879
+ "learning_rate": 8.664310954063605e-06,
880
+ "loss": 0.7959,
881
+ "step": 5850
882
+ },
883
+ {
884
+ "epoch": 4.169611307420495,
885
+ "grad_norm": 153999.46875,
886
+ "learning_rate": 8.31095406360424e-06,
887
+ "loss": 0.7883,
888
+ "step": 5900
889
+ },
890
+ {
891
+ "epoch": 4.204946996466431,
892
+ "grad_norm": 284284.375,
893
+ "learning_rate": 7.957597173144876e-06,
894
+ "loss": 0.7858,
895
+ "step": 5950
896
+ },
897
+ {
898
+ "epoch": 4.240282685512367,
899
+ "grad_norm": 139182.28125,
900
+ "learning_rate": 7.6042402826855124e-06,
901
+ "loss": 0.804,
902
+ "step": 6000
903
+ },
904
+ {
905
+ "epoch": 4.275618374558304,
906
+ "grad_norm": 169185.328125,
907
+ "learning_rate": 7.250883392226149e-06,
908
+ "loss": 0.7745,
909
+ "step": 6050
910
+ },
911
+ {
912
+ "epoch": 4.310954063604241,
913
+ "grad_norm": 200688.453125,
914
+ "learning_rate": 6.897526501766785e-06,
915
+ "loss": 0.7795,
916
+ "step": 6100
917
+ },
918
+ {
919
+ "epoch": 4.3462897526501765,
920
+ "grad_norm": 135357.96875,
921
+ "learning_rate": 6.544169611307421e-06,
922
+ "loss": 0.8412,
923
+ "step": 6150
924
+ },
925
+ {
926
+ "epoch": 4.381625441696113,
927
+ "grad_norm": 137914.25,
928
+ "learning_rate": 6.190812720848057e-06,
929
+ "loss": 0.811,
930
+ "step": 6200
931
+ },
932
+ {
933
+ "epoch": 4.41696113074205,
934
+ "grad_norm": 179002.140625,
935
+ "learning_rate": 5.837455830388693e-06,
936
+ "loss": 0.7859,
937
+ "step": 6250
938
+ },
939
+ {
940
+ "epoch": 4.4522968197879855,
941
+ "grad_norm": 139846.9375,
942
+ "learning_rate": 5.484098939929329e-06,
943
+ "loss": 0.801,
944
+ "step": 6300
945
+ },
946
+ {
947
+ "epoch": 4.487632508833922,
948
+ "grad_norm": 161350.671875,
949
+ "learning_rate": 5.1307420494699655e-06,
950
+ "loss": 0.8203,
951
+ "step": 6350
952
+ },
953
+ {
954
+ "epoch": 4.522968197879859,
955
+ "grad_norm": 153958.46875,
956
+ "learning_rate": 4.777385159010601e-06,
957
+ "loss": 0.7693,
958
+ "step": 6400
959
+ },
960
+ {
961
+ "epoch": 4.5583038869257955,
962
+ "grad_norm": 154714.984375,
963
+ "learning_rate": 4.424028268551237e-06,
964
+ "loss": 0.7808,
965
+ "step": 6450
966
+ },
967
+ {
968
+ "epoch": 4.593639575971731,
969
+ "grad_norm": 294880.1875,
970
+ "learning_rate": 4.070671378091873e-06,
971
+ "loss": 0.8194,
972
+ "step": 6500
973
+ },
974
+ {
975
+ "epoch": 4.628975265017668,
976
+ "grad_norm": 480907.34375,
977
+ "learning_rate": 3.717314487632509e-06,
978
+ "loss": 0.8096,
979
+ "step": 6550
980
+ },
981
+ {
982
+ "epoch": 4.6643109540636045,
983
+ "grad_norm": 319982.71875,
984
+ "learning_rate": 3.363957597173145e-06,
985
+ "loss": 0.7987,
986
+ "step": 6600
987
+ },
988
+ {
989
+ "epoch": 4.69964664310954,
990
+ "grad_norm": 188937.359375,
991
+ "learning_rate": 3.010600706713781e-06,
992
+ "loss": 0.8162,
993
+ "step": 6650
994
+ },
995
+ {
996
+ "epoch": 4.734982332155477,
997
+ "grad_norm": 166750.71875,
998
+ "learning_rate": 2.6572438162544172e-06,
999
+ "loss": 0.7726,
1000
+ "step": 6700
1001
+ },
1002
+ {
1003
+ "epoch": 4.770318021201414,
1004
+ "grad_norm": 179732.5625,
1005
+ "learning_rate": 2.303886925795053e-06,
1006
+ "loss": 0.7848,
1007
+ "step": 6750
1008
+ },
1009
+ {
1010
+ "epoch": 4.80565371024735,
1011
+ "grad_norm": 135768.640625,
1012
+ "learning_rate": 1.9505300353356893e-06,
1013
+ "loss": 0.8204,
1014
+ "step": 6800
1015
+ },
1016
+ {
1017
+ "epoch": 4.840989399293286,
1018
+ "grad_norm": 194958.0625,
1019
+ "learning_rate": 1.5971731448763252e-06,
1020
+ "loss": 0.8214,
1021
+ "step": 6850
1022
+ },
1023
+ {
1024
+ "epoch": 4.876325088339223,
1025
+ "grad_norm": 205979.40625,
1026
+ "learning_rate": 1.2438162544169612e-06,
1027
+ "loss": 0.7658,
1028
+ "step": 6900
1029
+ },
1030
+ {
1031
+ "epoch": 4.911660777385159,
1032
+ "grad_norm": 140958.078125,
1033
+ "learning_rate": 8.904593639575972e-07,
1034
+ "loss": 0.777,
1035
+ "step": 6950
1036
+ },
1037
+ {
1038
+ "epoch": 4.946996466431095,
1039
+ "grad_norm": 149027.953125,
1040
+ "learning_rate": 5.371024734982332e-07,
1041
+ "loss": 0.8286,
1042
+ "step": 7000
1043
+ },
1044
+ {
1045
+ "epoch": 4.982332155477032,
1046
+ "grad_norm": 161736.4375,
1047
+ "learning_rate": 1.8374558303886926e-07,
1048
+ "loss": 0.7922,
1049
+ "step": 7050
1050
+ },
1051
+ {
1052
+ "epoch": 5.0,
1053
+ "eval_bertscore_f1": 0.957730518736978,
1054
+ "eval_bleu": 0.49562010024897835,
1055
+ "eval_loss": 0.47903409600257874,
1056
+ "eval_meteor": 0.6644886697409358,
1057
+ "eval_rouge1": 0.8053692499714378,
1058
+ "eval_rouge2": 0.7018033389816531,
1059
+ "eval_runtime": 438.2906,
1060
+ "eval_samples_per_second": 14.748,
1061
+ "eval_steps_per_second": 0.922,
1062
+ "step": 7075
1063
+ }
1064
+ ],
1065
+ "logging_steps": 50,
1066
+ "max_steps": 7075,
1067
+ "num_input_tokens_seen": 0,
1068
+ "num_train_epochs": 5,
1069
+ "save_steps": 500,
1070
+ "stateful_callbacks": {
1071
+ "TrainerControl": {
1072
+ "args": {
1073
+ "should_epoch_stop": false,
1074
+ "should_evaluate": false,
1075
+ "should_log": false,
1076
+ "should_save": true,
1077
+ "should_training_stop": true
1078
+ },
1079
+ "attributes": {}
1080
+ }
1081
+ },
1082
+ "total_flos": 1.730048539557888e+16,
1083
+ "train_batch_size": 16,
1084
+ "trial_name": null,
1085
+ "trial_params": null
1086
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5603b8ad6e5c44098ff4d1375f09416bfc133ae607756a2e0d3c0084e202b93e
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff