Hugging Face's logo

norBARA
/
IA

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
norBARA commited on
Commit
5ed833f
·
1 Parent(s): 4a772bd

C

Browse files
Files changed (22) hide show
  1. README.md +48 -0
  2. checkpoint-70215/config.json +61 -0
  3. checkpoint-70215/generation_config.json +6 -0
  4. checkpoint-70215/optimizer.pt +3 -0
  5. checkpoint-70215/pytorch_model.bin +3 -0
  6. checkpoint-70215/rng_state.pth +3 -0
  7. checkpoint-70215/scheduler.pt +3 -0
  8. checkpoint-70215/trainer_state.json +895 -0
  9. checkpoint-70215/training_args.bin +3 -0
  10. checkpoint-93620/config.json +61 -0
  11. checkpoint-93620/generation_config.json +6 -0
  12. checkpoint-93620/optimizer.pt +3 -0
  13. checkpoint-93620/pytorch_model.bin +3 -0
  14. checkpoint-93620/rng_state.pth +3 -0
  15. checkpoint-93620/scheduler.pt +3 -0
  16. checkpoint-93620/trainer_state.json +1190 -0
  17. checkpoint-93620/training_args.bin +3 -0
  18. logs/events.out.tfevents.1691051711.f1837383dfd0.2726.0 +3 -0
  19. logs/events.out.tfevents.1691068757.f1837383dfd0.2726.1 +3 -0
  20. special_tokens_map.json +107 -0
  21. tokenizer.json +0 -0
  22. tokenizer_config.json +112 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/flan-t5-small
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: IA
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # IA
15
+
16
+ This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 4
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.31.0
46
+ - Pytorch 2.0.1+cu118
47
+ - Datasets 2.14.2
48
+ - Tokenizers 0.13.3
checkpoint-70215/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.31.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-70215/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.31.0"
6
+ }
checkpoint-70215/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981a70e351717de4bc99b89850fe6de3e53ec0b49fe5fc582e676a062a6f1ed2
3
+ size 615802245
checkpoint-70215/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56bc5978ee26aa9fb09e06f22425780d636b77caebfc793e9551897cc5e6e0b
3
+ size 307910149
checkpoint-70215/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16a8e86482536b523f171b3ac8b14cb8494f722188d7bf4858bac595d6bf909
3
+ size 14575
checkpoint-70215/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac154dd458d4a57c7000512f637bdf8c80e0f1403c9e84330d296a9d3ee92ad4
3
+ size 627
checkpoint-70215/trainer_state.json ADDED
@@ -0,0 +1,895 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9058317542076111,
3
+ "best_model_checkpoint": "norBARA/IA/checkpoint-70215",
4
+ "epoch": 3.0,
5
+ "global_step": 70215,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.973296304208503e-05,
13
+ "loss": 4.0843,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.946592608417005e-05,
19
+ "loss": 3.5105,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.9198889126255076e-05,
25
+ "loss": 3.2948,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 4.89318521683401e-05,
31
+ "loss": 3.1137,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 4.8664815210425125e-05,
37
+ "loss": 2.9855,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 4.839777825251015e-05,
43
+ "loss": 2.9086,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 4.8130741294595174e-05,
49
+ "loss": 2.8061,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 4.78637043366802e-05,
55
+ "loss": 2.7305,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.19,
60
+ "learning_rate": 4.7596667378765224e-05,
61
+ "loss": 2.6679,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.21,
66
+ "learning_rate": 4.732963042085025e-05,
67
+ "loss": 2.616,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.23,
72
+ "learning_rate": 4.706259346293527e-05,
73
+ "loss": 2.5824,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 4.67955565050203e-05,
79
+ "loss": 2.5671,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.28,
84
+ "learning_rate": 4.652851954710532e-05,
85
+ "loss": 2.4818,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "learning_rate": 4.6261482589190346e-05,
91
+ "loss": 2.4255,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.32,
96
+ "learning_rate": 4.599444563127537e-05,
97
+ "loss": 2.4096,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.34,
102
+ "learning_rate": 4.5727408673360395e-05,
103
+ "loss": 2.3959,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.36,
108
+ "learning_rate": 4.546037171544542e-05,
109
+ "loss": 2.3399,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.38,
114
+ "learning_rate": 4.5193334757530445e-05,
115
+ "loss": 2.3288,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.41,
120
+ "learning_rate": 4.492629779961547e-05,
121
+ "loss": 2.2737,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.43,
126
+ "learning_rate": 4.4659260841700494e-05,
127
+ "loss": 2.2641,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "learning_rate": 4.439222388378552e-05,
133
+ "loss": 2.2556,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.47,
138
+ "learning_rate": 4.412518692587054e-05,
139
+ "loss": 2.2102,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.49,
144
+ "learning_rate": 4.385814996795557e-05,
145
+ "loss": 2.157,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.51,
150
+ "learning_rate": 4.359111301004059e-05,
151
+ "loss": 2.1435,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.53,
156
+ "learning_rate": 4.3324076052125617e-05,
157
+ "loss": 2.1125,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.56,
162
+ "learning_rate": 4.305703909421064e-05,
163
+ "loss": 2.0885,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.58,
168
+ "learning_rate": 4.2790002136295666e-05,
169
+ "loss": 2.0974,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "learning_rate": 4.252296517838069e-05,
175
+ "loss": 2.0545,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.62,
180
+ "learning_rate": 4.2255928220465715e-05,
181
+ "loss": 2.0123,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.64,
186
+ "learning_rate": 4.198889126255074e-05,
187
+ "loss": 2.0299,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.66,
192
+ "learning_rate": 4.1721854304635764e-05,
193
+ "loss": 1.963,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.68,
198
+ "learning_rate": 4.145481734672079e-05,
199
+ "loss": 2.0054,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.7,
204
+ "learning_rate": 4.118778038880581e-05,
205
+ "loss": 2.0102,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.73,
210
+ "learning_rate": 4.092074343089084e-05,
211
+ "loss": 1.9359,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.75,
216
+ "learning_rate": 4.065370647297586e-05,
217
+ "loss": 1.9243,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.77,
222
+ "learning_rate": 4.038666951506089e-05,
223
+ "loss": 1.9235,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.79,
228
+ "learning_rate": 4.011963255714591e-05,
229
+ "loss": 1.8522,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.81,
234
+ "learning_rate": 3.9852595599230936e-05,
235
+ "loss": 1.8656,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.83,
240
+ "learning_rate": 3.958555864131596e-05,
241
+ "loss": 1.8714,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.85,
246
+ "learning_rate": 3.9318521683400985e-05,
247
+ "loss": 1.8386,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.88,
252
+ "learning_rate": 3.905148472548601e-05,
253
+ "loss": 1.8411,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.9,
258
+ "learning_rate": 3.8784447767571034e-05,
259
+ "loss": 1.8251,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.92,
264
+ "learning_rate": 3.851741080965606e-05,
265
+ "loss": 1.8082,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.94,
270
+ "learning_rate": 3.825037385174108e-05,
271
+ "loss": 1.7752,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.96,
276
+ "learning_rate": 3.798333689382611e-05,
277
+ "loss": 1.7992,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.98,
282
+ "learning_rate": 3.771629993591113e-05,
283
+ "loss": 1.7578,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.0,
288
+ "eval_gen_len": 10.30942106387524,
289
+ "eval_loss": 1.3722968101501465,
290
+ "eval_rouge1": 13.5957,
291
+ "eval_rouge2": 7.0766,
292
+ "eval_rougeL": 13.3911,
293
+ "eval_rougeLsum": 13.3971,
294
+ "eval_runtime": 1615.8665,
295
+ "eval_samples_per_second": 28.969,
296
+ "eval_steps_per_second": 3.622,
297
+ "step": 23405
298
+ },
299
+ {
300
+ "epoch": 1.0,
301
+ "learning_rate": 3.744926297799616e-05,
302
+ "loss": 1.7477,
303
+ "step": 23500
304
+ },
305
+ {
306
+ "epoch": 1.03,
307
+ "learning_rate": 3.718222602008118e-05,
308
+ "loss": 1.7099,
309
+ "step": 24000
310
+ },
311
+ {
312
+ "epoch": 1.05,
313
+ "learning_rate": 3.6915189062166206e-05,
314
+ "loss": 1.7081,
315
+ "step": 24500
316
+ },
317
+ {
318
+ "epoch": 1.07,
319
+ "learning_rate": 3.664815210425123e-05,
320
+ "loss": 1.7086,
321
+ "step": 25000
322
+ },
323
+ {
324
+ "epoch": 1.09,
325
+ "learning_rate": 3.6381115146336255e-05,
326
+ "loss": 1.6554,
327
+ "step": 25500
328
+ },
329
+ {
330
+ "epoch": 1.11,
331
+ "learning_rate": 3.611407818842128e-05,
332
+ "loss": 1.6971,
333
+ "step": 26000
334
+ },
335
+ {
336
+ "epoch": 1.13,
337
+ "learning_rate": 3.5847041230506304e-05,
338
+ "loss": 1.6616,
339
+ "step": 26500
340
+ },
341
+ {
342
+ "epoch": 1.15,
343
+ "learning_rate": 3.558000427259133e-05,
344
+ "loss": 1.6644,
345
+ "step": 27000
346
+ },
347
+ {
348
+ "epoch": 1.17,
349
+ "learning_rate": 3.5312967314676354e-05,
350
+ "loss": 1.6301,
351
+ "step": 27500
352
+ },
353
+ {
354
+ "epoch": 1.2,
355
+ "learning_rate": 3.504593035676138e-05,
356
+ "loss": 1.638,
357
+ "step": 28000
358
+ },
359
+ {
360
+ "epoch": 1.22,
361
+ "learning_rate": 3.47788933988464e-05,
362
+ "loss": 1.6436,
363
+ "step": 28500
364
+ },
365
+ {
366
+ "epoch": 1.24,
367
+ "learning_rate": 3.451185644093143e-05,
368
+ "loss": 1.6214,
369
+ "step": 29000
370
+ },
371
+ {
372
+ "epoch": 1.26,
373
+ "learning_rate": 3.424481948301645e-05,
374
+ "loss": 1.5978,
375
+ "step": 29500
376
+ },
377
+ {
378
+ "epoch": 1.28,
379
+ "learning_rate": 3.3977782525101476e-05,
380
+ "loss": 1.5972,
381
+ "step": 30000
382
+ },
383
+ {
384
+ "epoch": 1.3,
385
+ "learning_rate": 3.37107455671865e-05,
386
+ "loss": 1.6007,
387
+ "step": 30500
388
+ },
389
+ {
390
+ "epoch": 1.32,
391
+ "learning_rate": 3.3443708609271526e-05,
392
+ "loss": 1.5834,
393
+ "step": 31000
394
+ },
395
+ {
396
+ "epoch": 1.35,
397
+ "learning_rate": 3.317667165135655e-05,
398
+ "loss": 1.5915,
399
+ "step": 31500
400
+ },
401
+ {
402
+ "epoch": 1.37,
403
+ "learning_rate": 3.290963469344157e-05,
404
+ "loss": 1.5525,
405
+ "step": 32000
406
+ },
407
+ {
408
+ "epoch": 1.39,
409
+ "learning_rate": 3.26425977355266e-05,
410
+ "loss": 1.546,
411
+ "step": 32500
412
+ },
413
+ {
414
+ "epoch": 1.41,
415
+ "learning_rate": 3.2375560777611624e-05,
416
+ "loss": 1.5355,
417
+ "step": 33000
418
+ },
419
+ {
420
+ "epoch": 1.43,
421
+ "learning_rate": 3.210852381969665e-05,
422
+ "loss": 1.5136,
423
+ "step": 33500
424
+ },
425
+ {
426
+ "epoch": 1.45,
427
+ "learning_rate": 3.184148686178167e-05,
428
+ "loss": 1.5422,
429
+ "step": 34000
430
+ },
431
+ {
432
+ "epoch": 1.47,
433
+ "learning_rate": 3.15744499038667e-05,
434
+ "loss": 1.5073,
435
+ "step": 34500
436
+ },
437
+ {
438
+ "epoch": 1.5,
439
+ "learning_rate": 3.130741294595172e-05,
440
+ "loss": 1.4878,
441
+ "step": 35000
442
+ },
443
+ {
444
+ "epoch": 1.52,
445
+ "learning_rate": 3.104037598803675e-05,
446
+ "loss": 1.5078,
447
+ "step": 35500
448
+ },
449
+ {
450
+ "epoch": 1.54,
451
+ "learning_rate": 3.077333903012177e-05,
452
+ "loss": 1.5254,
453
+ "step": 36000
454
+ },
455
+ {
456
+ "epoch": 1.56,
457
+ "learning_rate": 3.0506302072206792e-05,
458
+ "loss": 1.4822,
459
+ "step": 36500
460
+ },
461
+ {
462
+ "epoch": 1.58,
463
+ "learning_rate": 3.023926511429182e-05,
464
+ "loss": 1.4692,
465
+ "step": 37000
466
+ },
467
+ {
468
+ "epoch": 1.6,
469
+ "learning_rate": 2.997222815637684e-05,
470
+ "loss": 1.4699,
471
+ "step": 37500
472
+ },
473
+ {
474
+ "epoch": 1.62,
475
+ "learning_rate": 2.970519119846187e-05,
476
+ "loss": 1.5252,
477
+ "step": 38000
478
+ },
479
+ {
480
+ "epoch": 1.64,
481
+ "learning_rate": 2.9438154240546894e-05,
482
+ "loss": 1.476,
483
+ "step": 38500
484
+ },
485
+ {
486
+ "epoch": 1.67,
487
+ "learning_rate": 2.9171117282631915e-05,
488
+ "loss": 1.4817,
489
+ "step": 39000
490
+ },
491
+ {
492
+ "epoch": 1.69,
493
+ "learning_rate": 2.8904080324716943e-05,
494
+ "loss": 1.4274,
495
+ "step": 39500
496
+ },
497
+ {
498
+ "epoch": 1.71,
499
+ "learning_rate": 2.8637043366801968e-05,
500
+ "loss": 1.4528,
501
+ "step": 40000
502
+ },
503
+ {
504
+ "epoch": 1.73,
505
+ "learning_rate": 2.837000640888699e-05,
506
+ "loss": 1.4375,
507
+ "step": 40500
508
+ },
509
+ {
510
+ "epoch": 1.75,
511
+ "learning_rate": 2.8102969450972017e-05,
512
+ "loss": 1.4036,
513
+ "step": 41000
514
+ },
515
+ {
516
+ "epoch": 1.77,
517
+ "learning_rate": 2.783593249305704e-05,
518
+ "loss": 1.38,
519
+ "step": 41500
520
+ },
521
+ {
522
+ "epoch": 1.79,
523
+ "learning_rate": 2.7568895535142063e-05,
524
+ "loss": 1.4489,
525
+ "step": 42000
526
+ },
527
+ {
528
+ "epoch": 1.82,
529
+ "learning_rate": 2.730185857722709e-05,
530
+ "loss": 1.3985,
531
+ "step": 42500
532
+ },
533
+ {
534
+ "epoch": 1.84,
535
+ "learning_rate": 2.7034821619312112e-05,
536
+ "loss": 1.4323,
537
+ "step": 43000
538
+ },
539
+ {
540
+ "epoch": 1.86,
541
+ "learning_rate": 2.676778466139714e-05,
542
+ "loss": 1.4051,
543
+ "step": 43500
544
+ },
545
+ {
546
+ "epoch": 1.88,
547
+ "learning_rate": 2.6500747703482164e-05,
548
+ "loss": 1.3908,
549
+ "step": 44000
550
+ },
551
+ {
552
+ "epoch": 1.9,
553
+ "learning_rate": 2.6233710745567186e-05,
554
+ "loss": 1.3892,
555
+ "step": 44500
556
+ },
557
+ {
558
+ "epoch": 1.92,
559
+ "learning_rate": 2.5966673787652213e-05,
560
+ "loss": 1.3936,
561
+ "step": 45000
562
+ },
563
+ {
564
+ "epoch": 1.94,
565
+ "learning_rate": 2.5699636829737238e-05,
566
+ "loss": 1.4004,
567
+ "step": 45500
568
+ },
569
+ {
570
+ "epoch": 1.97,
571
+ "learning_rate": 2.543259987182226e-05,
572
+ "loss": 1.3838,
573
+ "step": 46000
574
+ },
575
+ {
576
+ "epoch": 1.99,
577
+ "learning_rate": 2.5165562913907287e-05,
578
+ "loss": 1.3756,
579
+ "step": 46500
580
+ },
581
+ {
582
+ "epoch": 2.0,
583
+ "eval_gen_len": 10.362208929715873,
584
+ "eval_loss": 1.0369791984558105,
585
+ "eval_rouge1": 21.6305,
586
+ "eval_rouge2": 14.527,
587
+ "eval_rougeL": 21.4438,
588
+ "eval_rougeLsum": 21.4536,
589
+ "eval_runtime": 1661.185,
590
+ "eval_samples_per_second": 28.179,
591
+ "eval_steps_per_second": 3.523,
592
+ "step": 46810
593
+ },
594
+ {
595
+ "epoch": 2.01,
596
+ "learning_rate": 2.4898525955992312e-05,
597
+ "loss": 1.3742,
598
+ "step": 47000
599
+ },
600
+ {
601
+ "epoch": 2.03,
602
+ "learning_rate": 2.4631488998077333e-05,
603
+ "loss": 1.3323,
604
+ "step": 47500
605
+ },
606
+ {
607
+ "epoch": 2.05,
608
+ "learning_rate": 2.4364452040162358e-05,
609
+ "loss": 1.3481,
610
+ "step": 48000
611
+ },
612
+ {
613
+ "epoch": 2.07,
614
+ "learning_rate": 2.4097415082247385e-05,
615
+ "loss": 1.3529,
616
+ "step": 48500
617
+ },
618
+ {
619
+ "epoch": 2.09,
620
+ "learning_rate": 2.383037812433241e-05,
621
+ "loss": 1.3385,
622
+ "step": 49000
623
+ },
624
+ {
625
+ "epoch": 2.11,
626
+ "learning_rate": 2.356334116641743e-05,
627
+ "loss": 1.3378,
628
+ "step": 49500
629
+ },
630
+ {
631
+ "epoch": 2.14,
632
+ "learning_rate": 2.329630420850246e-05,
633
+ "loss": 1.3214,
634
+ "step": 50000
635
+ },
636
+ {
637
+ "epoch": 2.16,
638
+ "learning_rate": 2.3029267250587484e-05,
639
+ "loss": 1.3214,
640
+ "step": 50500
641
+ },
642
+ {
643
+ "epoch": 2.18,
644
+ "learning_rate": 2.2762230292672508e-05,
645
+ "loss": 1.3032,
646
+ "step": 51000
647
+ },
648
+ {
649
+ "epoch": 2.2,
650
+ "learning_rate": 2.249519333475753e-05,
651
+ "loss": 1.3152,
652
+ "step": 51500
653
+ },
654
+ {
655
+ "epoch": 2.22,
656
+ "learning_rate": 2.2228156376842557e-05,
657
+ "loss": 1.3169,
658
+ "step": 52000
659
+ },
660
+ {
661
+ "epoch": 2.24,
662
+ "learning_rate": 2.1961119418927582e-05,
663
+ "loss": 1.3132,
664
+ "step": 52500
665
+ },
666
+ {
667
+ "epoch": 2.26,
668
+ "learning_rate": 2.1694082461012603e-05,
669
+ "loss": 1.3171,
670
+ "step": 53000
671
+ },
672
+ {
673
+ "epoch": 2.29,
674
+ "learning_rate": 2.1427045503097628e-05,
675
+ "loss": 1.2979,
676
+ "step": 53500
677
+ },
678
+ {
679
+ "epoch": 2.31,
680
+ "learning_rate": 2.1160008545182656e-05,
681
+ "loss": 1.3013,
682
+ "step": 54000
683
+ },
684
+ {
685
+ "epoch": 2.33,
686
+ "learning_rate": 2.089297158726768e-05,
687
+ "loss": 1.3067,
688
+ "step": 54500
689
+ },
690
+ {
691
+ "epoch": 2.35,
692
+ "learning_rate": 2.06259346293527e-05,
693
+ "loss": 1.3199,
694
+ "step": 55000
695
+ },
696
+ {
697
+ "epoch": 2.37,
698
+ "learning_rate": 2.0358897671437726e-05,
699
+ "loss": 1.2876,
700
+ "step": 55500
701
+ },
702
+ {
703
+ "epoch": 2.39,
704
+ "learning_rate": 2.0091860713522754e-05,
705
+ "loss": 1.2876,
706
+ "step": 56000
707
+ },
708
+ {
709
+ "epoch": 2.41,
710
+ "learning_rate": 1.982482375560778e-05,
711
+ "loss": 1.2703,
712
+ "step": 56500
713
+ },
714
+ {
715
+ "epoch": 2.44,
716
+ "learning_rate": 1.95577867976928e-05,
717
+ "loss": 1.2641,
718
+ "step": 57000
719
+ },
720
+ {
721
+ "epoch": 2.46,
722
+ "learning_rate": 1.9290749839777828e-05,
723
+ "loss": 1.2976,
724
+ "step": 57500
725
+ },
726
+ {
727
+ "epoch": 2.48,
728
+ "learning_rate": 1.9023712881862852e-05,
729
+ "loss": 1.2577,
730
+ "step": 58000
731
+ },
732
+ {
733
+ "epoch": 2.5,
734
+ "learning_rate": 1.8756675923947873e-05,
735
+ "loss": 1.2925,
736
+ "step": 58500
737
+ },
738
+ {
739
+ "epoch": 2.52,
740
+ "learning_rate": 1.8489638966032898e-05,
741
+ "loss": 1.2686,
742
+ "step": 59000
743
+ },
744
+ {
745
+ "epoch": 2.54,
746
+ "learning_rate": 1.8222602008117926e-05,
747
+ "loss": 1.273,
748
+ "step": 59500
749
+ },
750
+ {
751
+ "epoch": 2.56,
752
+ "learning_rate": 1.795556505020295e-05,
753
+ "loss": 1.2604,
754
+ "step": 60000
755
+ },
756
+ {
757
+ "epoch": 2.58,
758
+ "learning_rate": 1.768852809228797e-05,
759
+ "loss": 1.265,
760
+ "step": 60500
761
+ },
762
+ {
763
+ "epoch": 2.61,
764
+ "learning_rate": 1.7421491134372996e-05,
765
+ "loss": 1.2653,
766
+ "step": 61000
767
+ },
768
+ {
769
+ "epoch": 2.63,
770
+ "learning_rate": 1.7154454176458024e-05,
771
+ "loss": 1.2241,
772
+ "step": 61500
773
+ },
774
+ {
775
+ "epoch": 2.65,
776
+ "learning_rate": 1.688741721854305e-05,
777
+ "loss": 1.233,
778
+ "step": 62000
779
+ },
780
+ {
781
+ "epoch": 2.67,
782
+ "learning_rate": 1.662038026062807e-05,
783
+ "loss": 1.2328,
784
+ "step": 62500
785
+ },
786
+ {
787
+ "epoch": 2.69,
788
+ "learning_rate": 1.6353343302713095e-05,
789
+ "loss": 1.2456,
790
+ "step": 63000
791
+ },
792
+ {
793
+ "epoch": 2.71,
794
+ "learning_rate": 1.6086306344798122e-05,
795
+ "loss": 1.2269,
796
+ "step": 63500
797
+ },
798
+ {
799
+ "epoch": 2.73,
800
+ "learning_rate": 1.5819269386883147e-05,
801
+ "loss": 1.2386,
802
+ "step": 64000
803
+ },
804
+ {
805
+ "epoch": 2.76,
806
+ "learning_rate": 1.5552232428968168e-05,
807
+ "loss": 1.2462,
808
+ "step": 64500
809
+ },
810
+ {
811
+ "epoch": 2.78,
812
+ "learning_rate": 1.5285195471053196e-05,
813
+ "loss": 1.2436,
814
+ "step": 65000
815
+ },
816
+ {
817
+ "epoch": 2.8,
818
+ "learning_rate": 1.5018158513138219e-05,
819
+ "loss": 1.2263,
820
+ "step": 65500
821
+ },
822
+ {
823
+ "epoch": 2.82,
824
+ "learning_rate": 1.4751121555223244e-05,
825
+ "loss": 1.2415,
826
+ "step": 66000
827
+ },
828
+ {
829
+ "epoch": 2.84,
830
+ "learning_rate": 1.4484084597308267e-05,
831
+ "loss": 1.256,
832
+ "step": 66500
833
+ },
834
+ {
835
+ "epoch": 2.86,
836
+ "learning_rate": 1.4217047639393294e-05,
837
+ "loss": 1.2272,
838
+ "step": 67000
839
+ },
840
+ {
841
+ "epoch": 2.88,
842
+ "learning_rate": 1.3950010681478317e-05,
843
+ "loss": 1.2169,
844
+ "step": 67500
845
+ },
846
+ {
847
+ "epoch": 2.91,
848
+ "learning_rate": 1.3682973723563342e-05,
849
+ "loss": 1.2149,
850
+ "step": 68000
851
+ },
852
+ {
853
+ "epoch": 2.93,
854
+ "learning_rate": 1.3415936765648365e-05,
855
+ "loss": 1.2085,
856
+ "step": 68500
857
+ },
858
+ {
859
+ "epoch": 2.95,
860
+ "learning_rate": 1.3148899807733393e-05,
861
+ "loss": 1.2077,
862
+ "step": 69000
863
+ },
864
+ {
865
+ "epoch": 2.97,
866
+ "learning_rate": 1.2881862849818416e-05,
867
+ "loss": 1.2123,
868
+ "step": 69500
869
+ },
870
+ {
871
+ "epoch": 2.99,
872
+ "learning_rate": 1.261482589190344e-05,
873
+ "loss": 1.2093,
874
+ "step": 70000
875
+ },
876
+ {
877
+ "epoch": 3.0,
878
+ "eval_gen_len": 9.954048280281992,
879
+ "eval_loss": 0.9058317542076111,
880
+ "eval_rouge1": 26.5379,
881
+ "eval_rouge2": 19.0017,
882
+ "eval_rougeL": 26.3586,
883
+ "eval_rougeLsum": 26.3719,
884
+ "eval_runtime": 1636.659,
885
+ "eval_samples_per_second": 28.601,
886
+ "eval_steps_per_second": 3.576,
887
+ "step": 70215
888
+ }
889
+ ],
890
+ "max_steps": 93620,
891
+ "num_train_epochs": 4,
892
+ "total_flos": 9789226340843520.0,
893
+ "trial_name": null,
894
+ "trial_params": null
895
+ }
checkpoint-70215/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b60b9e2fc63b431e182348795f85d6c9b1c879a51e45d10fb6ca306f20f4ce2
3
+ size 4091
checkpoint-93620/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.31.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-93620/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.31.0"
6
+ }
checkpoint-93620/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727f0321db100358e817820497d888d241be247f72f3764e51d00f5aa6aaa9b0
3
+ size 615802245
checkpoint-93620/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03da812f9002a089317447134719f1093383ade0914e05a13b21a88e68f3ef0c
3
+ size 307910149
checkpoint-93620/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb435582ce54ad19816fb0495b13d9e5b20d42277ea8426f8ec558d3e4eca59
3
+ size 14575
checkpoint-93620/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0041c9a8218f0baaacfcae29f59ec87f229df6ee83ca1908b025fc0058af10
3
+ size 627
checkpoint-93620/trainer_state.json ADDED
@@ -0,0 +1,1190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8677980303764343,
3
+ "best_model_checkpoint": "norBARA/IA/checkpoint-93620",
4
+ "epoch": 4.0,
5
+ "global_step": 93620,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.973296304208503e-05,
13
+ "loss": 4.0843,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.946592608417005e-05,
19
+ "loss": 3.5105,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.9198889126255076e-05,
25
+ "loss": 3.2948,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 4.89318521683401e-05,
31
+ "loss": 3.1137,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 4.8664815210425125e-05,
37
+ "loss": 2.9855,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 4.839777825251015e-05,
43
+ "loss": 2.9086,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 4.8130741294595174e-05,
49
+ "loss": 2.8061,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 4.78637043366802e-05,
55
+ "loss": 2.7305,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.19,
60
+ "learning_rate": 4.7596667378765224e-05,
61
+ "loss": 2.6679,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.21,
66
+ "learning_rate": 4.732963042085025e-05,
67
+ "loss": 2.616,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.23,
72
+ "learning_rate": 4.706259346293527e-05,
73
+ "loss": 2.5824,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 4.67955565050203e-05,
79
+ "loss": 2.5671,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.28,
84
+ "learning_rate": 4.652851954710532e-05,
85
+ "loss": 2.4818,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "learning_rate": 4.6261482589190346e-05,
91
+ "loss": 2.4255,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.32,
96
+ "learning_rate": 4.599444563127537e-05,
97
+ "loss": 2.4096,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.34,
102
+ "learning_rate": 4.5727408673360395e-05,
103
+ "loss": 2.3959,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.36,
108
+ "learning_rate": 4.546037171544542e-05,
109
+ "loss": 2.3399,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.38,
114
+ "learning_rate": 4.5193334757530445e-05,
115
+ "loss": 2.3288,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.41,
120
+ "learning_rate": 4.492629779961547e-05,
121
+ "loss": 2.2737,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.43,
126
+ "learning_rate": 4.4659260841700494e-05,
127
+ "loss": 2.2641,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "learning_rate": 4.439222388378552e-05,
133
+ "loss": 2.2556,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.47,
138
+ "learning_rate": 4.412518692587054e-05,
139
+ "loss": 2.2102,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.49,
144
+ "learning_rate": 4.385814996795557e-05,
145
+ "loss": 2.157,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.51,
150
+ "learning_rate": 4.359111301004059e-05,
151
+ "loss": 2.1435,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.53,
156
+ "learning_rate": 4.3324076052125617e-05,
157
+ "loss": 2.1125,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.56,
162
+ "learning_rate": 4.305703909421064e-05,
163
+ "loss": 2.0885,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.58,
168
+ "learning_rate": 4.2790002136295666e-05,
169
+ "loss": 2.0974,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "learning_rate": 4.252296517838069e-05,
175
+ "loss": 2.0545,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.62,
180
+ "learning_rate": 4.2255928220465715e-05,
181
+ "loss": 2.0123,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.64,
186
+ "learning_rate": 4.198889126255074e-05,
187
+ "loss": 2.0299,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.66,
192
+ "learning_rate": 4.1721854304635764e-05,
193
+ "loss": 1.963,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.68,
198
+ "learning_rate": 4.145481734672079e-05,
199
+ "loss": 2.0054,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.7,
204
+ "learning_rate": 4.118778038880581e-05,
205
+ "loss": 2.0102,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.73,
210
+ "learning_rate": 4.092074343089084e-05,
211
+ "loss": 1.9359,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.75,
216
+ "learning_rate": 4.065370647297586e-05,
217
+ "loss": 1.9243,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.77,
222
+ "learning_rate": 4.038666951506089e-05,
223
+ "loss": 1.9235,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.79,
228
+ "learning_rate": 4.011963255714591e-05,
229
+ "loss": 1.8522,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.81,
234
+ "learning_rate": 3.9852595599230936e-05,
235
+ "loss": 1.8656,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.83,
240
+ "learning_rate": 3.958555864131596e-05,
241
+ "loss": 1.8714,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.85,
246
+ "learning_rate": 3.9318521683400985e-05,
247
+ "loss": 1.8386,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.88,
252
+ "learning_rate": 3.905148472548601e-05,
253
+ "loss": 1.8411,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.9,
258
+ "learning_rate": 3.8784447767571034e-05,
259
+ "loss": 1.8251,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.92,
264
+ "learning_rate": 3.851741080965606e-05,
265
+ "loss": 1.8082,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.94,
270
+ "learning_rate": 3.825037385174108e-05,
271
+ "loss": 1.7752,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.96,
276
+ "learning_rate": 3.798333689382611e-05,
277
+ "loss": 1.7992,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.98,
282
+ "learning_rate": 3.771629993591113e-05,
283
+ "loss": 1.7578,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.0,
288
+ "eval_gen_len": 10.30942106387524,
289
+ "eval_loss": 1.3722968101501465,
290
+ "eval_rouge1": 13.5957,
291
+ "eval_rouge2": 7.0766,
292
+ "eval_rougeL": 13.3911,
293
+ "eval_rougeLsum": 13.3971,
294
+ "eval_runtime": 1615.8665,
295
+ "eval_samples_per_second": 28.969,
296
+ "eval_steps_per_second": 3.622,
297
+ "step": 23405
298
+ },
299
+ {
300
+ "epoch": 1.0,
301
+ "learning_rate": 3.744926297799616e-05,
302
+ "loss": 1.7477,
303
+ "step": 23500
304
+ },
305
+ {
306
+ "epoch": 1.03,
307
+ "learning_rate": 3.718222602008118e-05,
308
+ "loss": 1.7099,
309
+ "step": 24000
310
+ },
311
+ {
312
+ "epoch": 1.05,
313
+ "learning_rate": 3.6915189062166206e-05,
314
+ "loss": 1.7081,
315
+ "step": 24500
316
+ },
317
+ {
318
+ "epoch": 1.07,
319
+ "learning_rate": 3.664815210425123e-05,
320
+ "loss": 1.7086,
321
+ "step": 25000
322
+ },
323
+ {
324
+ "epoch": 1.09,
325
+ "learning_rate": 3.6381115146336255e-05,
326
+ "loss": 1.6554,
327
+ "step": 25500
328
+ },
329
+ {
330
+ "epoch": 1.11,
331
+ "learning_rate": 3.611407818842128e-05,
332
+ "loss": 1.6971,
333
+ "step": 26000
334
+ },
335
+ {
336
+ "epoch": 1.13,
337
+ "learning_rate": 3.5847041230506304e-05,
338
+ "loss": 1.6616,
339
+ "step": 26500
340
+ },
341
+ {
342
+ "epoch": 1.15,
343
+ "learning_rate": 3.558000427259133e-05,
344
+ "loss": 1.6644,
345
+ "step": 27000
346
+ },
347
+ {
348
+ "epoch": 1.17,
349
+ "learning_rate": 3.5312967314676354e-05,
350
+ "loss": 1.6301,
351
+ "step": 27500
352
+ },
353
+ {
354
+ "epoch": 1.2,
355
+ "learning_rate": 3.504593035676138e-05,
356
+ "loss": 1.638,
357
+ "step": 28000
358
+ },
359
+ {
360
+ "epoch": 1.22,
361
+ "learning_rate": 3.47788933988464e-05,
362
+ "loss": 1.6436,
363
+ "step": 28500
364
+ },
365
+ {
366
+ "epoch": 1.24,
367
+ "learning_rate": 3.451185644093143e-05,
368
+ "loss": 1.6214,
369
+ "step": 29000
370
+ },
371
+ {
372
+ "epoch": 1.26,
373
+ "learning_rate": 3.424481948301645e-05,
374
+ "loss": 1.5978,
375
+ "step": 29500
376
+ },
377
+ {
378
+ "epoch": 1.28,
379
+ "learning_rate": 3.3977782525101476e-05,
380
+ "loss": 1.5972,
381
+ "step": 30000
382
+ },
383
+ {
384
+ "epoch": 1.3,
385
+ "learning_rate": 3.37107455671865e-05,
386
+ "loss": 1.6007,
387
+ "step": 30500
388
+ },
389
+ {
390
+ "epoch": 1.32,
391
+ "learning_rate": 3.3443708609271526e-05,
392
+ "loss": 1.5834,
393
+ "step": 31000
394
+ },
395
+ {
396
+ "epoch": 1.35,
397
+ "learning_rate": 3.317667165135655e-05,
398
+ "loss": 1.5915,
399
+ "step": 31500
400
+ },
401
+ {
402
+ "epoch": 1.37,
403
+ "learning_rate": 3.290963469344157e-05,
404
+ "loss": 1.5525,
405
+ "step": 32000
406
+ },
407
+ {
408
+ "epoch": 1.39,
409
+ "learning_rate": 3.26425977355266e-05,
410
+ "loss": 1.546,
411
+ "step": 32500
412
+ },
413
+ {
414
+ "epoch": 1.41,
415
+ "learning_rate": 3.2375560777611624e-05,
416
+ "loss": 1.5355,
417
+ "step": 33000
418
+ },
419
+ {
420
+ "epoch": 1.43,
421
+ "learning_rate": 3.210852381969665e-05,
422
+ "loss": 1.5136,
423
+ "step": 33500
424
+ },
425
+ {
426
+ "epoch": 1.45,
427
+ "learning_rate": 3.184148686178167e-05,
428
+ "loss": 1.5422,
429
+ "step": 34000
430
+ },
431
+ {
432
+ "epoch": 1.47,
433
+ "learning_rate": 3.15744499038667e-05,
434
+ "loss": 1.5073,
435
+ "step": 34500
436
+ },
437
+ {
438
+ "epoch": 1.5,
439
+ "learning_rate": 3.130741294595172e-05,
440
+ "loss": 1.4878,
441
+ "step": 35000
442
+ },
443
+ {
444
+ "epoch": 1.52,
445
+ "learning_rate": 3.104037598803675e-05,
446
+ "loss": 1.5078,
447
+ "step": 35500
448
+ },
449
+ {
450
+ "epoch": 1.54,
451
+ "learning_rate": 3.077333903012177e-05,
452
+ "loss": 1.5254,
453
+ "step": 36000
454
+ },
455
+ {
456
+ "epoch": 1.56,
457
+ "learning_rate": 3.0506302072206792e-05,
458
+ "loss": 1.4822,
459
+ "step": 36500
460
+ },
461
+ {
462
+ "epoch": 1.58,
463
+ "learning_rate": 3.023926511429182e-05,
464
+ "loss": 1.4692,
465
+ "step": 37000
466
+ },
467
+ {
468
+ "epoch": 1.6,
469
+ "learning_rate": 2.997222815637684e-05,
470
+ "loss": 1.4699,
471
+ "step": 37500
472
+ },
473
+ {
474
+ "epoch": 1.62,
475
+ "learning_rate": 2.970519119846187e-05,
476
+ "loss": 1.5252,
477
+ "step": 38000
478
+ },
479
+ {
480
+ "epoch": 1.64,
481
+ "learning_rate": 2.9438154240546894e-05,
482
+ "loss": 1.476,
483
+ "step": 38500
484
+ },
485
+ {
486
+ "epoch": 1.67,
487
+ "learning_rate": 2.9171117282631915e-05,
488
+ "loss": 1.4817,
489
+ "step": 39000
490
+ },
491
+ {
492
+ "epoch": 1.69,
493
+ "learning_rate": 2.8904080324716943e-05,
494
+ "loss": 1.4274,
495
+ "step": 39500
496
+ },
497
+ {
498
+ "epoch": 1.71,
499
+ "learning_rate": 2.8637043366801968e-05,
500
+ "loss": 1.4528,
501
+ "step": 40000
502
+ },
503
+ {
504
+ "epoch": 1.73,
505
+ "learning_rate": 2.837000640888699e-05,
506
+ "loss": 1.4375,
507
+ "step": 40500
508
+ },
509
+ {
510
+ "epoch": 1.75,
511
+ "learning_rate": 2.8102969450972017e-05,
512
+ "loss": 1.4036,
513
+ "step": 41000
514
+ },
515
+ {
516
+ "epoch": 1.77,
517
+ "learning_rate": 2.783593249305704e-05,
518
+ "loss": 1.38,
519
+ "step": 41500
520
+ },
521
+ {
522
+ "epoch": 1.79,
523
+ "learning_rate": 2.7568895535142063e-05,
524
+ "loss": 1.4489,
525
+ "step": 42000
526
+ },
527
+ {
528
+ "epoch": 1.82,
529
+ "learning_rate": 2.730185857722709e-05,
530
+ "loss": 1.3985,
531
+ "step": 42500
532
+ },
533
+ {
534
+ "epoch": 1.84,
535
+ "learning_rate": 2.7034821619312112e-05,
536
+ "loss": 1.4323,
537
+ "step": 43000
538
+ },
539
+ {
540
+ "epoch": 1.86,
541
+ "learning_rate": 2.676778466139714e-05,
542
+ "loss": 1.4051,
543
+ "step": 43500
544
+ },
545
+ {
546
+ "epoch": 1.88,
547
+ "learning_rate": 2.6500747703482164e-05,
548
+ "loss": 1.3908,
549
+ "step": 44000
550
+ },
551
+ {
552
+ "epoch": 1.9,
553
+ "learning_rate": 2.6233710745567186e-05,
554
+ "loss": 1.3892,
555
+ "step": 44500
556
+ },
557
+ {
558
+ "epoch": 1.92,
559
+ "learning_rate": 2.5966673787652213e-05,
560
+ "loss": 1.3936,
561
+ "step": 45000
562
+ },
563
+ {
564
+ "epoch": 1.94,
565
+ "learning_rate": 2.5699636829737238e-05,
566
+ "loss": 1.4004,
567
+ "step": 45500
568
+ },
569
+ {
570
+ "epoch": 1.97,
571
+ "learning_rate": 2.543259987182226e-05,
572
+ "loss": 1.3838,
573
+ "step": 46000
574
+ },
575
+ {
576
+ "epoch": 1.99,
577
+ "learning_rate": 2.5165562913907287e-05,
578
+ "loss": 1.3756,
579
+ "step": 46500
580
+ },
581
+ {
582
+ "epoch": 2.0,
583
+ "eval_gen_len": 10.362208929715873,
584
+ "eval_loss": 1.0369791984558105,
585
+ "eval_rouge1": 21.6305,
586
+ "eval_rouge2": 14.527,
587
+ "eval_rougeL": 21.4438,
588
+ "eval_rougeLsum": 21.4536,
589
+ "eval_runtime": 1661.185,
590
+ "eval_samples_per_second": 28.179,
591
+ "eval_steps_per_second": 3.523,
592
+ "step": 46810
593
+ },
594
+ {
595
+ "epoch": 2.01,
596
+ "learning_rate": 2.4898525955992312e-05,
597
+ "loss": 1.3742,
598
+ "step": 47000
599
+ },
600
+ {
601
+ "epoch": 2.03,
602
+ "learning_rate": 2.4631488998077333e-05,
603
+ "loss": 1.3323,
604
+ "step": 47500
605
+ },
606
+ {
607
+ "epoch": 2.05,
608
+ "learning_rate": 2.4364452040162358e-05,
609
+ "loss": 1.3481,
610
+ "step": 48000
611
+ },
612
+ {
613
+ "epoch": 2.07,
614
+ "learning_rate": 2.4097415082247385e-05,
615
+ "loss": 1.3529,
616
+ "step": 48500
617
+ },
618
+ {
619
+ "epoch": 2.09,
620
+ "learning_rate": 2.383037812433241e-05,
621
+ "loss": 1.3385,
622
+ "step": 49000
623
+ },
624
+ {
625
+ "epoch": 2.11,
626
+ "learning_rate": 2.356334116641743e-05,
627
+ "loss": 1.3378,
628
+ "step": 49500
629
+ },
630
+ {
631
+ "epoch": 2.14,
632
+ "learning_rate": 2.329630420850246e-05,
633
+ "loss": 1.3214,
634
+ "step": 50000
635
+ },
636
+ {
637
+ "epoch": 2.16,
638
+ "learning_rate": 2.3029267250587484e-05,
639
+ "loss": 1.3214,
640
+ "step": 50500
641
+ },
642
+ {
643
+ "epoch": 2.18,
644
+ "learning_rate": 2.2762230292672508e-05,
645
+ "loss": 1.3032,
646
+ "step": 51000
647
+ },
648
+ {
649
+ "epoch": 2.2,
650
+ "learning_rate": 2.249519333475753e-05,
651
+ "loss": 1.3152,
652
+ "step": 51500
653
+ },
654
+ {
655
+ "epoch": 2.22,
656
+ "learning_rate": 2.2228156376842557e-05,
657
+ "loss": 1.3169,
658
+ "step": 52000
659
+ },
660
+ {
661
+ "epoch": 2.24,
662
+ "learning_rate": 2.1961119418927582e-05,
663
+ "loss": 1.3132,
664
+ "step": 52500
665
+ },
666
+ {
667
+ "epoch": 2.26,
668
+ "learning_rate": 2.1694082461012603e-05,
669
+ "loss": 1.3171,
670
+ "step": 53000
671
+ },
672
+ {
673
+ "epoch": 2.29,
674
+ "learning_rate": 2.1427045503097628e-05,
675
+ "loss": 1.2979,
676
+ "step": 53500
677
+ },
678
+ {
679
+ "epoch": 2.31,
680
+ "learning_rate": 2.1160008545182656e-05,
681
+ "loss": 1.3013,
682
+ "step": 54000
683
+ },
684
+ {
685
+ "epoch": 2.33,
686
+ "learning_rate": 2.089297158726768e-05,
687
+ "loss": 1.3067,
688
+ "step": 54500
689
+ },
690
+ {
691
+ "epoch": 2.35,
692
+ "learning_rate": 2.06259346293527e-05,
693
+ "loss": 1.3199,
694
+ "step": 55000
695
+ },
696
+ {
697
+ "epoch": 2.37,
698
+ "learning_rate": 2.0358897671437726e-05,
699
+ "loss": 1.2876,
700
+ "step": 55500
701
+ },
702
+ {
703
+ "epoch": 2.39,
704
+ "learning_rate": 2.0091860713522754e-05,
705
+ "loss": 1.2876,
706
+ "step": 56000
707
+ },
708
+ {
709
+ "epoch": 2.41,
710
+ "learning_rate": 1.982482375560778e-05,
711
+ "loss": 1.2703,
712
+ "step": 56500
713
+ },
714
+ {
715
+ "epoch": 2.44,
716
+ "learning_rate": 1.95577867976928e-05,
717
+ "loss": 1.2641,
718
+ "step": 57000
719
+ },
720
+ {
721
+ "epoch": 2.46,
722
+ "learning_rate": 1.9290749839777828e-05,
723
+ "loss": 1.2976,
724
+ "step": 57500
725
+ },
726
+ {
727
+ "epoch": 2.48,
728
+ "learning_rate": 1.9023712881862852e-05,
729
+ "loss": 1.2577,
730
+ "step": 58000
731
+ },
732
+ {
733
+ "epoch": 2.5,
734
+ "learning_rate": 1.8756675923947873e-05,
735
+ "loss": 1.2925,
736
+ "step": 58500
737
+ },
738
+ {
739
+ "epoch": 2.52,
740
+ "learning_rate": 1.8489638966032898e-05,
741
+ "loss": 1.2686,
742
+ "step": 59000
743
+ },
744
+ {
745
+ "epoch": 2.54,
746
+ "learning_rate": 1.8222602008117926e-05,
747
+ "loss": 1.273,
748
+ "step": 59500
749
+ },
750
+ {
751
+ "epoch": 2.56,
752
+ "learning_rate": 1.795556505020295e-05,
753
+ "loss": 1.2604,
754
+ "step": 60000
755
+ },
756
+ {
757
+ "epoch": 2.58,
758
+ "learning_rate": 1.768852809228797e-05,
759
+ "loss": 1.265,
760
+ "step": 60500
761
+ },
762
+ {
763
+ "epoch": 2.61,
764
+ "learning_rate": 1.7421491134372996e-05,
765
+ "loss": 1.2653,
766
+ "step": 61000
767
+ },
768
+ {
769
+ "epoch": 2.63,
770
+ "learning_rate": 1.7154454176458024e-05,
771
+ "loss": 1.2241,
772
+ "step": 61500
773
+ },
774
+ {
775
+ "epoch": 2.65,
776
+ "learning_rate": 1.688741721854305e-05,
777
+ "loss": 1.233,
778
+ "step": 62000
779
+ },
780
+ {
781
+ "epoch": 2.67,
782
+ "learning_rate": 1.662038026062807e-05,
783
+ "loss": 1.2328,
784
+ "step": 62500
785
+ },
786
+ {
787
+ "epoch": 2.69,
788
+ "learning_rate": 1.6353343302713095e-05,
789
+ "loss": 1.2456,
790
+ "step": 63000
791
+ },
792
+ {
793
+ "epoch": 2.71,
794
+ "learning_rate": 1.6086306344798122e-05,
795
+ "loss": 1.2269,
796
+ "step": 63500
797
+ },
798
+ {
799
+ "epoch": 2.73,
800
+ "learning_rate": 1.5819269386883147e-05,
801
+ "loss": 1.2386,
802
+ "step": 64000
803
+ },
804
+ {
805
+ "epoch": 2.76,
806
+ "learning_rate": 1.5552232428968168e-05,
807
+ "loss": 1.2462,
808
+ "step": 64500
809
+ },
810
+ {
811
+ "epoch": 2.78,
812
+ "learning_rate": 1.5285195471053196e-05,
813
+ "loss": 1.2436,
814
+ "step": 65000
815
+ },
816
+ {
817
+ "epoch": 2.8,
818
+ "learning_rate": 1.5018158513138219e-05,
819
+ "loss": 1.2263,
820
+ "step": 65500
821
+ },
822
+ {
823
+ "epoch": 2.82,
824
+ "learning_rate": 1.4751121555223244e-05,
825
+ "loss": 1.2415,
826
+ "step": 66000
827
+ },
828
+ {
829
+ "epoch": 2.84,
830
+ "learning_rate": 1.4484084597308267e-05,
831
+ "loss": 1.256,
832
+ "step": 66500
833
+ },
834
+ {
835
+ "epoch": 2.86,
836
+ "learning_rate": 1.4217047639393294e-05,
837
+ "loss": 1.2272,
838
+ "step": 67000
839
+ },
840
+ {
841
+ "epoch": 2.88,
842
+ "learning_rate": 1.3950010681478317e-05,
843
+ "loss": 1.2169,
844
+ "step": 67500
845
+ },
846
+ {
847
+ "epoch": 2.91,
848
+ "learning_rate": 1.3682973723563342e-05,
849
+ "loss": 1.2149,
850
+ "step": 68000
851
+ },
852
+ {
853
+ "epoch": 2.93,
854
+ "learning_rate": 1.3415936765648365e-05,
855
+ "loss": 1.2085,
856
+ "step": 68500
857
+ },
858
+ {
859
+ "epoch": 2.95,
860
+ "learning_rate": 1.3148899807733393e-05,
861
+ "loss": 1.2077,
862
+ "step": 69000
863
+ },
864
+ {
865
+ "epoch": 2.97,
866
+ "learning_rate": 1.2881862849818416e-05,
867
+ "loss": 1.2123,
868
+ "step": 69500
869
+ },
870
+ {
871
+ "epoch": 2.99,
872
+ "learning_rate": 1.261482589190344e-05,
873
+ "loss": 1.2093,
874
+ "step": 70000
875
+ },
876
+ {
877
+ "epoch": 3.0,
878
+ "eval_gen_len": 9.954048280281992,
879
+ "eval_loss": 0.9058317542076111,
880
+ "eval_rouge1": 26.5379,
881
+ "eval_rouge2": 19.0017,
882
+ "eval_rougeL": 26.3586,
883
+ "eval_rougeLsum": 26.3719,
884
+ "eval_runtime": 1636.659,
885
+ "eval_samples_per_second": 28.601,
886
+ "eval_steps_per_second": 3.576,
887
+ "step": 70215
888
+ },
889
+ {
890
+ "epoch": 3.01,
891
+ "learning_rate": 1.2347788933988465e-05,
892
+ "loss": 1.203,
893
+ "step": 70500
894
+ },
895
+ {
896
+ "epoch": 3.03,
897
+ "learning_rate": 1.208075197607349e-05,
898
+ "loss": 1.2175,
899
+ "step": 71000
900
+ },
901
+ {
902
+ "epoch": 3.05,
903
+ "learning_rate": 1.1813715018158514e-05,
904
+ "loss": 1.2061,
905
+ "step": 71500
906
+ },
907
+ {
908
+ "epoch": 3.08,
909
+ "learning_rate": 1.1546678060243538e-05,
910
+ "loss": 1.1981,
911
+ "step": 72000
912
+ },
913
+ {
914
+ "epoch": 3.1,
915
+ "learning_rate": 1.1279641102328563e-05,
916
+ "loss": 1.1797,
917
+ "step": 72500
918
+ },
919
+ {
920
+ "epoch": 3.12,
921
+ "learning_rate": 1.1012604144413588e-05,
922
+ "loss": 1.1568,
923
+ "step": 73000
924
+ },
925
+ {
926
+ "epoch": 3.14,
927
+ "learning_rate": 1.0745567186498612e-05,
928
+ "loss": 1.1953,
929
+ "step": 73500
930
+ },
931
+ {
932
+ "epoch": 3.16,
933
+ "learning_rate": 1.0478530228583637e-05,
934
+ "loss": 1.1627,
935
+ "step": 74000
936
+ },
937
+ {
938
+ "epoch": 3.18,
939
+ "learning_rate": 1.0211493270668661e-05,
940
+ "loss": 1.1778,
941
+ "step": 74500
942
+ },
943
+ {
944
+ "epoch": 3.2,
945
+ "learning_rate": 9.944456312753686e-06,
946
+ "loss": 1.172,
947
+ "step": 75000
948
+ },
949
+ {
950
+ "epoch": 3.23,
951
+ "learning_rate": 9.67741935483871e-06,
952
+ "loss": 1.1784,
953
+ "step": 75500
954
+ },
955
+ {
956
+ "epoch": 3.25,
957
+ "learning_rate": 9.410382396923735e-06,
958
+ "loss": 1.1874,
959
+ "step": 76000
960
+ },
961
+ {
962
+ "epoch": 3.27,
963
+ "learning_rate": 9.14334543900876e-06,
964
+ "loss": 1.1623,
965
+ "step": 76500
966
+ },
967
+ {
968
+ "epoch": 3.29,
969
+ "learning_rate": 8.876308481093784e-06,
970
+ "loss": 1.1969,
971
+ "step": 77000
972
+ },
973
+ {
974
+ "epoch": 3.31,
975
+ "learning_rate": 8.609271523178809e-06,
976
+ "loss": 1.1816,
977
+ "step": 77500
978
+ },
979
+ {
980
+ "epoch": 3.33,
981
+ "learning_rate": 8.342234565263833e-06,
982
+ "loss": 1.1534,
983
+ "step": 78000
984
+ },
985
+ {
986
+ "epoch": 3.35,
987
+ "learning_rate": 8.075197607348856e-06,
988
+ "loss": 1.1889,
989
+ "step": 78500
990
+ },
991
+ {
992
+ "epoch": 3.38,
993
+ "learning_rate": 7.808160649433882e-06,
994
+ "loss": 1.1786,
995
+ "step": 79000
996
+ },
997
+ {
998
+ "epoch": 3.4,
999
+ "learning_rate": 7.541123691518906e-06,
1000
+ "loss": 1.1621,
1001
+ "step": 79500
1002
+ },
1003
+ {
1004
+ "epoch": 3.42,
1005
+ "learning_rate": 7.2740867336039315e-06,
1006
+ "loss": 1.1692,
1007
+ "step": 80000
1008
+ },
1009
+ {
1010
+ "epoch": 3.44,
1011
+ "learning_rate": 7.007049775688956e-06,
1012
+ "loss": 1.1789,
1013
+ "step": 80500
1014
+ },
1015
+ {
1016
+ "epoch": 3.46,
1017
+ "learning_rate": 6.74001281777398e-06,
1018
+ "loss": 1.1925,
1019
+ "step": 81000
1020
+ },
1021
+ {
1022
+ "epoch": 3.48,
1023
+ "learning_rate": 6.472975859859005e-06,
1024
+ "loss": 1.1847,
1025
+ "step": 81500
1026
+ },
1027
+ {
1028
+ "epoch": 3.5,
1029
+ "learning_rate": 6.205938901944029e-06,
1030
+ "loss": 1.1495,
1031
+ "step": 82000
1032
+ },
1033
+ {
1034
+ "epoch": 3.52,
1035
+ "learning_rate": 5.9389019440290535e-06,
1036
+ "loss": 1.1631,
1037
+ "step": 82500
1038
+ },
1039
+ {
1040
+ "epoch": 3.55,
1041
+ "learning_rate": 5.671864986114078e-06,
1042
+ "loss": 1.2052,
1043
+ "step": 83000
1044
+ },
1045
+ {
1046
+ "epoch": 3.57,
1047
+ "learning_rate": 5.404828028199103e-06,
1048
+ "loss": 1.1773,
1049
+ "step": 83500
1050
+ },
1051
+ {
1052
+ "epoch": 3.59,
1053
+ "learning_rate": 5.137791070284127e-06,
1054
+ "loss": 1.1574,
1055
+ "step": 84000
1056
+ },
1057
+ {
1058
+ "epoch": 3.61,
1059
+ "learning_rate": 4.870754112369153e-06,
1060
+ "loss": 1.1516,
1061
+ "step": 84500
1062
+ },
1063
+ {
1064
+ "epoch": 3.63,
1065
+ "learning_rate": 4.603717154454177e-06,
1066
+ "loss": 1.1736,
1067
+ "step": 85000
1068
+ },
1069
+ {
1070
+ "epoch": 3.65,
1071
+ "learning_rate": 4.336680196539202e-06,
1072
+ "loss": 1.1511,
1073
+ "step": 85500
1074
+ },
1075
+ {
1076
+ "epoch": 3.67,
1077
+ "learning_rate": 4.069643238624226e-06,
1078
+ "loss": 1.1277,
1079
+ "step": 86000
1080
+ },
1081
+ {
1082
+ "epoch": 3.7,
1083
+ "learning_rate": 3.8026062807092505e-06,
1084
+ "loss": 1.1425,
1085
+ "step": 86500
1086
+ },
1087
+ {
1088
+ "epoch": 3.72,
1089
+ "learning_rate": 3.535569322794275e-06,
1090
+ "loss": 1.1848,
1091
+ "step": 87000
1092
+ },
1093
+ {
1094
+ "epoch": 3.74,
1095
+ "learning_rate": 3.2685323648792996e-06,
1096
+ "loss": 1.149,
1097
+ "step": 87500
1098
+ },
1099
+ {
1100
+ "epoch": 3.76,
1101
+ "learning_rate": 3.001495406964324e-06,
1102
+ "loss": 1.1535,
1103
+ "step": 88000
1104
+ },
1105
+ {
1106
+ "epoch": 3.78,
1107
+ "learning_rate": 2.7344584490493487e-06,
1108
+ "loss": 1.1594,
1109
+ "step": 88500
1110
+ },
1111
+ {
1112
+ "epoch": 3.8,
1113
+ "learning_rate": 2.467421491134373e-06,
1114
+ "loss": 1.1756,
1115
+ "step": 89000
1116
+ },
1117
+ {
1118
+ "epoch": 3.82,
1119
+ "learning_rate": 2.2003845332193975e-06,
1120
+ "loss": 1.1691,
1121
+ "step": 89500
1122
+ },
1123
+ {
1124
+ "epoch": 3.85,
1125
+ "learning_rate": 1.933347575304422e-06,
1126
+ "loss": 1.1526,
1127
+ "step": 90000
1128
+ },
1129
+ {
1130
+ "epoch": 3.87,
1131
+ "learning_rate": 1.666310617389447e-06,
1132
+ "loss": 1.1633,
1133
+ "step": 90500
1134
+ },
1135
+ {
1136
+ "epoch": 3.89,
1137
+ "learning_rate": 1.3992736594744714e-06,
1138
+ "loss": 1.1563,
1139
+ "step": 91000
1140
+ },
1141
+ {
1142
+ "epoch": 3.91,
1143
+ "learning_rate": 1.132236701559496e-06,
1144
+ "loss": 1.1448,
1145
+ "step": 91500
1146
+ },
1147
+ {
1148
+ "epoch": 3.93,
1149
+ "learning_rate": 8.651997436445205e-07,
1150
+ "loss": 1.1857,
1151
+ "step": 92000
1152
+ },
1153
+ {
1154
+ "epoch": 3.95,
1155
+ "learning_rate": 5.98162785729545e-07,
1156
+ "loss": 1.1477,
1157
+ "step": 92500
1158
+ },
1159
+ {
1160
+ "epoch": 3.97,
1161
+ "learning_rate": 3.3112582781456954e-07,
1162
+ "loss": 1.1724,
1163
+ "step": 93000
1164
+ },
1165
+ {
1166
+ "epoch": 3.99,
1167
+ "learning_rate": 6.408886989959411e-08,
1168
+ "loss": 1.1404,
1169
+ "step": 93500
1170
+ },
1171
+ {
1172
+ "epoch": 4.0,
1173
+ "eval_gen_len": 9.971416364024781,
1174
+ "eval_loss": 0.8677980303764343,
1175
+ "eval_rouge1": 28.2457,
1176
+ "eval_rouge2": 20.4786,
1177
+ "eval_rougeL": 28.0552,
1178
+ "eval_rougeLsum": 28.0753,
1179
+ "eval_runtime": 1600.8029,
1180
+ "eval_samples_per_second": 29.242,
1181
+ "eval_steps_per_second": 3.656,
1182
+ "step": 93620
1183
+ }
1184
+ ],
1185
+ "max_steps": 93620,
1186
+ "num_train_epochs": 4,
1187
+ "total_flos": 1.305230178779136e+16,
1188
+ "trial_name": null,
1189
+ "trial_params": null
1190
+ }
checkpoint-93620/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b60b9e2fc63b431e182348795f85d6c9b1c879a51e45d10fb6ca306f20f4ce2
3
+ size 4091
logs/events.out.tfevents.1691051711.f1837383dfd0.2726.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe41f454211f1c6e19ae1e8ea21bfa49de9a5391bdfc29602992082eb29e1e8
3
+ size 37338
logs/events.out.tfevents.1691068757.f1837383dfd0.2726.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f67670749993e26c6dc7e67a7cb9588bde8020da0a7e4c5d84ce50858e7db35
3
+ size 5042
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }