Hugging Face's logo

viditsorg
/
finetuneMt5English

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Trained with AutoTrain
Inference Endpoints
Model card Files Metrics Community
viditraj860 commited on
Commit
f029e81
•
1 Parent(s): 84d3c79

Upload folder using huggingface_hub

Browse files
Files changed (25) hide show
  1. .gitattributes +2 -0
  2. README.md +35 -0
  3. checkpoint-2400/config.json +37 -0
  4. checkpoint-2400/generation_config.json +11 -0
  5. checkpoint-2400/model.safetensors +3 -0
  6. checkpoint-2400/optimizer.pt +3 -0
  7. checkpoint-2400/rng_state.pth +3 -0
  8. checkpoint-2400/scheduler.pt +3 -0
  9. checkpoint-2400/special_tokens_map.json +23 -0
  10. checkpoint-2400/spiece.model +3 -0
  11. checkpoint-2400/tokenizer.json +3 -0
  12. checkpoint-2400/tokenizer_config.json +38 -0
  13. checkpoint-2400/trainer_state.json +778 -0
  14. checkpoint-2400/training_args.bin +3 -0
  15. config.json +37 -0
  16. generation_config.json +11 -0
  17. model.safetensors +3 -0
  18. runs/Dec14_08-39-45_r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf/events.out.tfevents.1702543186.r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf.87.0 +3 -0
  19. runs/Dec14_08-39-45_r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf/events.out.tfevents.1702545989.r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf.87.1 +3 -0
  20. special_tokens_map.json +23 -0
  21. spiece.model +3 -0
  22. tokenizer.json +3 -0
  23. tokenizer_config.json +38 -0
  24. training_args.bin +3 -0
  25. training_params.json +1 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text2text-generation
6
+ widget:
7
+ - text: "I love AutoTrain"
8
+ datasets:
9
+ - viditsorg/autotrain-data-p70w-m3ok-fcks
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Seq2Seq
15
+
16
+ ## Validation Metrics
17
+ loss: 3.213425874710083
18
+
19
+ rouge1: 27.3285
20
+
21
+ rouge2: 8.8456
22
+
23
+ rougeL: 16.8011
24
+
25
+ rougeLsum: 24.6941
26
+
27
+ gen_len: 82.945
28
+
29
+ runtime: 353.4203
30
+
31
+ samples_per_second: 0.566
32
+
33
+ steps_per_second: 0.141
34
+
35
+ : 3.0
checkpoint-2400/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "length_penalty": 0.6,
20
+ "max_length": 84,
21
+ "model_type": "mt5",
22
+ "no_repeat_ngram_size": 2,
23
+ "num_beams": 4,
24
+ "num_decoder_layers": 12,
25
+ "num_heads": 12,
26
+ "num_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "relative_attention_max_distance": 128,
30
+ "relative_attention_num_buckets": 32,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "T5Tokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.35.2",
35
+ "use_cache": false,
36
+ "vocab_size": 250112
37
+ }
checkpoint-2400/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "length_penalty": 0.6,
5
+ "max_length": 84,
6
+ "no_repeat_ngram_size": 2,
7
+ "num_beams": 4,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.35.2",
10
+ "use_cache": false
11
+ }
checkpoint-2400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948c23793b8023651647c4d5acaee78f4ee11feabfd8c5d02656008a878c6cf1
3
+ size 2329638768
checkpoint-2400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae653abc997d833f8b8196e68c4b144630aadaa60be8d99ba356df0a96ee3fc
3
+ size 4659448110
checkpoint-2400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817747d55f491ad65bf3459be0b901786eeca7bba2bd33343e165c54c8b41129
3
+ size 14244
checkpoint-2400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e148d8aa9ee6fba677da24cd9589db9b2fa7bbfa9dbd694102b5142f294d6b
3
+ size 1064
checkpoint-2400/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-2400/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
checkpoint-2400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73bed1ba1559b646793e05a5fef8052ea2e2a8366680454c386ff6371317210
3
+ size 16330559
checkpoint-2400/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<pad>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }
checkpoint-2400/trainer_state.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.213425874710083,
3
+ "best_model_checkpoint": "/tmp/model/checkpoint-2400",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 4.166666666666667e-06,
14
+ "loss": 5.741,
15
+ "step": 20
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 8.333333333333334e-06,
20
+ "loss": 5.0717,
21
+ "step": 40
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 1.25e-05,
26
+ "loss": 4.6499,
27
+ "step": 60
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.6666666666666667e-05,
32
+ "loss": 4.5674,
33
+ "step": 80
34
+ },
35
+ {
36
+ "epoch": 0.12,
37
+ "learning_rate": 2.0833333333333336e-05,
38
+ "loss": 4.41,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "learning_rate": 2.5e-05,
44
+ "loss": 4.3577,
45
+ "step": 120
46
+ },
47
+ {
48
+ "epoch": 0.17,
49
+ "learning_rate": 2.916666666666667e-05,
50
+ "loss": 4.4615,
51
+ "step": 140
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "learning_rate": 3.3333333333333335e-05,
56
+ "loss": 4.3785,
57
+ "step": 160
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "learning_rate": 3.7500000000000003e-05,
62
+ "loss": 4.3647,
63
+ "step": 180
64
+ },
65
+ {
66
+ "epoch": 0.25,
67
+ "learning_rate": 4.166666666666667e-05,
68
+ "loss": 4.2084,
69
+ "step": 200
70
+ },
71
+ {
72
+ "epoch": 0.28,
73
+ "learning_rate": 4.5833333333333334e-05,
74
+ "loss": 4.0819,
75
+ "step": 220
76
+ },
77
+ {
78
+ "epoch": 0.3,
79
+ "learning_rate": 5e-05,
80
+ "loss": 4.1261,
81
+ "step": 240
82
+ },
83
+ {
84
+ "epoch": 0.33,
85
+ "learning_rate": 4.9537037037037035e-05,
86
+ "loss": 4.4005,
87
+ "step": 260
88
+ },
89
+ {
90
+ "epoch": 0.35,
91
+ "learning_rate": 4.9074074074074075e-05,
92
+ "loss": 4.539,
93
+ "step": 280
94
+ },
95
+ {
96
+ "epoch": 0.38,
97
+ "learning_rate": 4.8611111111111115e-05,
98
+ "loss": 4.2227,
99
+ "step": 300
100
+ },
101
+ {
102
+ "epoch": 0.4,
103
+ "learning_rate": 4.814814814814815e-05,
104
+ "loss": 4.2553,
105
+ "step": 320
106
+ },
107
+ {
108
+ "epoch": 0.42,
109
+ "learning_rate": 4.768518518518519e-05,
110
+ "loss": 4.1659,
111
+ "step": 340
112
+ },
113
+ {
114
+ "epoch": 0.45,
115
+ "learning_rate": 4.722222222222222e-05,
116
+ "loss": 4.0688,
117
+ "step": 360
118
+ },
119
+ {
120
+ "epoch": 0.47,
121
+ "learning_rate": 4.675925925925926e-05,
122
+ "loss": 4.0632,
123
+ "step": 380
124
+ },
125
+ {
126
+ "epoch": 0.5,
127
+ "learning_rate": 4.62962962962963e-05,
128
+ "loss": 4.0898,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.53,
133
+ "learning_rate": 4.5833333333333334e-05,
134
+ "loss": 3.6001,
135
+ "step": 420
136
+ },
137
+ {
138
+ "epoch": 0.55,
139
+ "learning_rate": 4.5370370370370374e-05,
140
+ "loss": 4.3352,
141
+ "step": 440
142
+ },
143
+ {
144
+ "epoch": 0.57,
145
+ "learning_rate": 4.490740740740741e-05,
146
+ "loss": 4.1648,
147
+ "step": 460
148
+ },
149
+ {
150
+ "epoch": 0.6,
151
+ "learning_rate": 4.4444444444444447e-05,
152
+ "loss": 3.8782,
153
+ "step": 480
154
+ },
155
+ {
156
+ "epoch": 0.62,
157
+ "learning_rate": 4.3981481481481486e-05,
158
+ "loss": 3.7935,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.65,
163
+ "learning_rate": 4.351851851851852e-05,
164
+ "loss": 4.1225,
165
+ "step": 520
166
+ },
167
+ {
168
+ "epoch": 0.68,
169
+ "learning_rate": 4.305555555555556e-05,
170
+ "loss": 3.9524,
171
+ "step": 540
172
+ },
173
+ {
174
+ "epoch": 0.7,
175
+ "learning_rate": 4.259259259259259e-05,
176
+ "loss": 4.0101,
177
+ "step": 560
178
+ },
179
+ {
180
+ "epoch": 0.72,
181
+ "learning_rate": 4.212962962962963e-05,
182
+ "loss": 3.9894,
183
+ "step": 580
184
+ },
185
+ {
186
+ "epoch": 0.75,
187
+ "learning_rate": 4.166666666666667e-05,
188
+ "loss": 3.6272,
189
+ "step": 600
190
+ },
191
+ {
192
+ "epoch": 0.78,
193
+ "learning_rate": 4.1203703703703705e-05,
194
+ "loss": 4.1463,
195
+ "step": 620
196
+ },
197
+ {
198
+ "epoch": 0.8,
199
+ "learning_rate": 4.074074074074074e-05,
200
+ "loss": 3.78,
201
+ "step": 640
202
+ },
203
+ {
204
+ "epoch": 0.82,
205
+ "learning_rate": 4.027777777777778e-05,
206
+ "loss": 4.1798,
207
+ "step": 660
208
+ },
209
+ {
210
+ "epoch": 0.85,
211
+ "learning_rate": 3.981481481481482e-05,
212
+ "loss": 3.9722,
213
+ "step": 680
214
+ },
215
+ {
216
+ "epoch": 0.88,
217
+ "learning_rate": 3.935185185185186e-05,
218
+ "loss": 3.7356,
219
+ "step": 700
220
+ },
221
+ {
222
+ "epoch": 0.9,
223
+ "learning_rate": 3.888888888888889e-05,
224
+ "loss": 4.01,
225
+ "step": 720
226
+ },
227
+ {
228
+ "epoch": 0.93,
229
+ "learning_rate": 3.8425925925925924e-05,
230
+ "loss": 3.78,
231
+ "step": 740
232
+ },
233
+ {
234
+ "epoch": 0.95,
235
+ "learning_rate": 3.7962962962962964e-05,
236
+ "loss": 3.6708,
237
+ "step": 760
238
+ },
239
+ {
240
+ "epoch": 0.97,
241
+ "learning_rate": 3.7500000000000003e-05,
242
+ "loss": 3.817,
243
+ "step": 780
244
+ },
245
+ {
246
+ "epoch": 1.0,
247
+ "learning_rate": 3.7037037037037037e-05,
248
+ "loss": 3.69,
249
+ "step": 800
250
+ },
251
+ {
252
+ "epoch": 1.0,
253
+ "eval_gen_len": 82.86,
254
+ "eval_loss": 3.467059373855591,
255
+ "eval_rouge1": 26.488,
256
+ "eval_rouge2": 7.7701,
257
+ "eval_rougeL": 15.7699,
258
+ "eval_rougeLsum": 23.5892,
259
+ "eval_runtime": 353.8993,
260
+ "eval_samples_per_second": 0.565,
261
+ "eval_steps_per_second": 0.141,
262
+ "step": 800
263
+ },
264
+ {
265
+ "epoch": 1.02,
266
+ "learning_rate": 3.6574074074074076e-05,
267
+ "loss": 3.5478,
268
+ "step": 820
269
+ },
270
+ {
271
+ "epoch": 1.05,
272
+ "learning_rate": 3.611111111111111e-05,
273
+ "loss": 3.7204,
274
+ "step": 840
275
+ },
276
+ {
277
+ "epoch": 1.07,
278
+ "learning_rate": 3.564814814814815e-05,
279
+ "loss": 3.6043,
280
+ "step": 860
281
+ },
282
+ {
283
+ "epoch": 1.1,
284
+ "learning_rate": 3.518518518518519e-05,
285
+ "loss": 3.6187,
286
+ "step": 880
287
+ },
288
+ {
289
+ "epoch": 1.12,
290
+ "learning_rate": 3.472222222222222e-05,
291
+ "loss": 3.556,
292
+ "step": 900
293
+ },
294
+ {
295
+ "epoch": 1.15,
296
+ "learning_rate": 3.425925925925926e-05,
297
+ "loss": 3.6192,
298
+ "step": 920
299
+ },
300
+ {
301
+ "epoch": 1.18,
302
+ "learning_rate": 3.3796296296296295e-05,
303
+ "loss": 3.693,
304
+ "step": 940
305
+ },
306
+ {
307
+ "epoch": 1.2,
308
+ "learning_rate": 3.3333333333333335e-05,
309
+ "loss": 3.7153,
310
+ "step": 960
311
+ },
312
+ {
313
+ "epoch": 1.23,
314
+ "learning_rate": 3.2870370370370375e-05,
315
+ "loss": 3.8134,
316
+ "step": 980
317
+ },
318
+ {
319
+ "epoch": 1.25,
320
+ "learning_rate": 3.240740740740741e-05,
321
+ "loss": 3.5188,
322
+ "step": 1000
323
+ },
324
+ {
325
+ "epoch": 1.27,
326
+ "learning_rate": 3.194444444444444e-05,
327
+ "loss": 3.4658,
328
+ "step": 1020
329
+ },
330
+ {
331
+ "epoch": 1.3,
332
+ "learning_rate": 3.148148148148148e-05,
333
+ "loss": 3.834,
334
+ "step": 1040
335
+ },
336
+ {
337
+ "epoch": 1.32,
338
+ "learning_rate": 3.101851851851852e-05,
339
+ "loss": 3.9915,
340
+ "step": 1060
341
+ },
342
+ {
343
+ "epoch": 1.35,
344
+ "learning_rate": 3.055555555555556e-05,
345
+ "loss": 3.3837,
346
+ "step": 1080
347
+ },
348
+ {
349
+ "epoch": 1.38,
350
+ "learning_rate": 3.0092592592592593e-05,
351
+ "loss": 3.4688,
352
+ "step": 1100
353
+ },
354
+ {
355
+ "epoch": 1.4,
356
+ "learning_rate": 2.962962962962963e-05,
357
+ "loss": 3.8257,
358
+ "step": 1120
359
+ },
360
+ {
361
+ "epoch": 1.43,
362
+ "learning_rate": 2.916666666666667e-05,
363
+ "loss": 3.7379,
364
+ "step": 1140
365
+ },
366
+ {
367
+ "epoch": 1.45,
368
+ "learning_rate": 2.8703703703703706e-05,
369
+ "loss": 3.9015,
370
+ "step": 1160
371
+ },
372
+ {
373
+ "epoch": 1.48,
374
+ "learning_rate": 2.824074074074074e-05,
375
+ "loss": 3.7064,
376
+ "step": 1180
377
+ },
378
+ {
379
+ "epoch": 1.5,
380
+ "learning_rate": 2.777777777777778e-05,
381
+ "loss": 3.4937,
382
+ "step": 1200
383
+ },
384
+ {
385
+ "epoch": 1.52,
386
+ "learning_rate": 2.7314814814814816e-05,
387
+ "loss": 3.6392,
388
+ "step": 1220
389
+ },
390
+ {
391
+ "epoch": 1.55,
392
+ "learning_rate": 2.6851851851851855e-05,
393
+ "loss": 3.6589,
394
+ "step": 1240
395
+ },
396
+ {
397
+ "epoch": 1.57,
398
+ "learning_rate": 2.6388888888888892e-05,
399
+ "loss": 3.6652,
400
+ "step": 1260
401
+ },
402
+ {
403
+ "epoch": 1.6,
404
+ "learning_rate": 2.5925925925925925e-05,
405
+ "loss": 3.5664,
406
+ "step": 1280
407
+ },
408
+ {
409
+ "epoch": 1.62,
410
+ "learning_rate": 2.5462962962962965e-05,
411
+ "loss": 3.7538,
412
+ "step": 1300
413
+ },
414
+ {
415
+ "epoch": 1.65,
416
+ "learning_rate": 2.5e-05,
417
+ "loss": 3.5765,
418
+ "step": 1320
419
+ },
420
+ {
421
+ "epoch": 1.68,
422
+ "learning_rate": 2.4537037037037038e-05,
423
+ "loss": 3.5302,
424
+ "step": 1340
425
+ },
426
+ {
427
+ "epoch": 1.7,
428
+ "learning_rate": 2.4074074074074074e-05,
429
+ "loss": 3.3333,
430
+ "step": 1360
431
+ },
432
+ {
433
+ "epoch": 1.73,
434
+ "learning_rate": 2.361111111111111e-05,
435
+ "loss": 3.506,
436
+ "step": 1380
437
+ },
438
+ {
439
+ "epoch": 1.75,
440
+ "learning_rate": 2.314814814814815e-05,
441
+ "loss": 3.5008,
442
+ "step": 1400
443
+ },
444
+ {
445
+ "epoch": 1.77,
446
+ "learning_rate": 2.2685185185185187e-05,
447
+ "loss": 3.8955,
448
+ "step": 1420
449
+ },
450
+ {
451
+ "epoch": 1.8,
452
+ "learning_rate": 2.2222222222222223e-05,
453
+ "loss": 3.3469,
454
+ "step": 1440
455
+ },
456
+ {
457
+ "epoch": 1.82,
458
+ "learning_rate": 2.175925925925926e-05,
459
+ "loss": 3.5623,
460
+ "step": 1460
461
+ },
462
+ {
463
+ "epoch": 1.85,
464
+ "learning_rate": 2.1296296296296296e-05,
465
+ "loss": 3.8341,
466
+ "step": 1480
467
+ },
468
+ {
469
+ "epoch": 1.88,
470
+ "learning_rate": 2.0833333333333336e-05,
471
+ "loss": 3.5073,
472
+ "step": 1500
473
+ },
474
+ {
475
+ "epoch": 1.9,
476
+ "learning_rate": 2.037037037037037e-05,
477
+ "loss": 3.6144,
478
+ "step": 1520
479
+ },
480
+ {
481
+ "epoch": 1.93,
482
+ "learning_rate": 1.990740740740741e-05,
483
+ "loss": 3.7585,
484
+ "step": 1540
485
+ },
486
+ {
487
+ "epoch": 1.95,
488
+ "learning_rate": 1.9444444444444445e-05,
489
+ "loss": 3.541,
490
+ "step": 1560
491
+ },
492
+ {
493
+ "epoch": 1.98,
494
+ "learning_rate": 1.8981481481481482e-05,
495
+ "loss": 3.7732,
496
+ "step": 1580
497
+ },
498
+ {
499
+ "epoch": 2.0,
500
+ "learning_rate": 1.8518518518518518e-05,
501
+ "loss": 3.4184,
502
+ "step": 1600
503
+ },
504
+ {
505
+ "epoch": 2.0,
506
+ "eval_gen_len": 82.965,
507
+ "eval_loss": 3.26387882232666,
508
+ "eval_rouge1": 27.1928,
509
+ "eval_rouge2": 8.9006,
510
+ "eval_rougeL": 16.9355,
511
+ "eval_rougeLsum": 24.6536,
512
+ "eval_runtime": 353.2482,
513
+ "eval_samples_per_second": 0.566,
514
+ "eval_steps_per_second": 0.142,
515
+ "step": 1600
516
+ },
517
+ {
518
+ "epoch": 2.02,
519
+ "learning_rate": 1.8055555555555555e-05,
520
+ "loss": 3.4078,
521
+ "step": 1620
522
+ },
523
+ {
524
+ "epoch": 2.05,
525
+ "learning_rate": 1.7592592592592595e-05,
526
+ "loss": 3.5058,
527
+ "step": 1640
528
+ },
529
+ {
530
+ "epoch": 2.08,
531
+ "learning_rate": 1.712962962962963e-05,
532
+ "loss": 3.4788,
533
+ "step": 1660
534
+ },
535
+ {
536
+ "epoch": 2.1,
537
+ "learning_rate": 1.6666666666666667e-05,
538
+ "loss": 3.3683,
539
+ "step": 1680
540
+ },
541
+ {
542
+ "epoch": 2.12,
543
+ "learning_rate": 1.6203703703703704e-05,
544
+ "loss": 3.6269,
545
+ "step": 1700
546
+ },
547
+ {
548
+ "epoch": 2.15,
549
+ "learning_rate": 1.574074074074074e-05,
550
+ "loss": 3.4723,
551
+ "step": 1720
552
+ },
553
+ {
554
+ "epoch": 2.17,
555
+ "learning_rate": 1.527777777777778e-05,
556
+ "loss": 3.5449,
557
+ "step": 1740
558
+ },
559
+ {
560
+ "epoch": 2.2,
561
+ "learning_rate": 1.4814814814814815e-05,
562
+ "loss": 3.5735,
563
+ "step": 1760
564
+ },
565
+ {
566
+ "epoch": 2.23,
567
+ "learning_rate": 1.4351851851851853e-05,
568
+ "loss": 3.6537,
569
+ "step": 1780
570
+ },
571
+ {
572
+ "epoch": 2.25,
573
+ "learning_rate": 1.388888888888889e-05,
574
+ "loss": 3.6652,
575
+ "step": 1800
576
+ },
577
+ {
578
+ "epoch": 2.27,
579
+ "learning_rate": 1.3425925925925928e-05,
580
+ "loss": 3.6673,
581
+ "step": 1820
582
+ },
583
+ {
584
+ "epoch": 2.3,
585
+ "learning_rate": 1.2962962962962962e-05,
586
+ "loss": 3.4442,
587
+ "step": 1840
588
+ },
589
+ {
590
+ "epoch": 2.33,
591
+ "learning_rate": 1.25e-05,
592
+ "loss": 3.2242,
593
+ "step": 1860
594
+ },
595
+ {
596
+ "epoch": 2.35,
597
+ "learning_rate": 1.2037037037037037e-05,
598
+ "loss": 3.4312,
599
+ "step": 1880
600
+ },
601
+ {
602
+ "epoch": 2.38,
603
+ "learning_rate": 1.1574074074074075e-05,
604
+ "loss": 3.2635,
605
+ "step": 1900
606
+ },
607
+ {
608
+ "epoch": 2.4,
609
+ "learning_rate": 1.1111111111111112e-05,
610
+ "loss": 3.2952,
611
+ "step": 1920
612
+ },
613
+ {
614
+ "epoch": 2.42,
615
+ "learning_rate": 1.0648148148148148e-05,
616
+ "loss": 3.3192,
617
+ "step": 1940
618
+ },
619
+ {
620
+ "epoch": 2.45,
621
+ "learning_rate": 1.0185185185185185e-05,
622
+ "loss": 3.6236,
623
+ "step": 1960
624
+ },
625
+ {
626
+ "epoch": 2.48,
627
+ "learning_rate": 9.722222222222223e-06,
628
+ "loss": 3.4545,
629
+ "step": 1980
630
+ },
631
+ {
632
+ "epoch": 2.5,
633
+ "learning_rate": 9.259259259259259e-06,
634
+ "loss": 3.2789,
635
+ "step": 2000
636
+ },
637
+ {
638
+ "epoch": 2.52,
639
+ "learning_rate": 8.796296296296297e-06,
640
+ "loss": 3.647,
641
+ "step": 2020
642
+ },
643
+ {
644
+ "epoch": 2.55,
645
+ "learning_rate": 8.333333333333334e-06,
646
+ "loss": 3.4436,
647
+ "step": 2040
648
+ },
649
+ {
650
+ "epoch": 2.58,
651
+ "learning_rate": 7.87037037037037e-06,
652
+ "loss": 3.4333,
653
+ "step": 2060
654
+ },
655
+ {
656
+ "epoch": 2.6,
657
+ "learning_rate": 7.4074074074074075e-06,
658
+ "loss": 3.5945,
659
+ "step": 2080
660
+ },
661
+ {
662
+ "epoch": 2.62,
663
+ "learning_rate": 6.944444444444445e-06,
664
+ "loss": 3.4041,
665
+ "step": 2100
666
+ },
667
+ {
668
+ "epoch": 2.65,
669
+ "learning_rate": 6.481481481481481e-06,
670
+ "loss": 3.2998,
671
+ "step": 2120
672
+ },
673
+ {
674
+ "epoch": 2.67,
675
+ "learning_rate": 6.0185185185185185e-06,
676
+ "loss": 3.2847,
677
+ "step": 2140
678
+ },
679
+ {
680
+ "epoch": 2.7,
681
+ "learning_rate": 5.555555555555556e-06,
682
+ "loss": 3.3913,
683
+ "step": 2160
684
+ },
685
+ {
686
+ "epoch": 2.73,
687
+ "learning_rate": 5.092592592592592e-06,
688
+ "loss": 3.2782,
689
+ "step": 2180
690
+ },
691
+ {
692
+ "epoch": 2.75,
693
+ "learning_rate": 4.6296296296296296e-06,
694
+ "loss": 3.5704,
695
+ "step": 2200
696
+ },
697
+ {
698
+ "epoch": 2.77,
699
+ "learning_rate": 4.166666666666667e-06,
700
+ "loss": 3.2631,
701
+ "step": 2220
702
+ },
703
+ {
704
+ "epoch": 2.8,
705
+ "learning_rate": 3.7037037037037037e-06,
706
+ "loss": 3.4875,
707
+ "step": 2240
708
+ },
709
+ {
710
+ "epoch": 2.83,
711
+ "learning_rate": 3.2407407407407406e-06,
712
+ "loss": 3.6455,
713
+ "step": 2260
714
+ },
715
+ {
716
+ "epoch": 2.85,
717
+ "learning_rate": 2.777777777777778e-06,
718
+ "loss": 3.2978,
719
+ "step": 2280
720
+ },
721
+ {
722
+ "epoch": 2.88,
723
+ "learning_rate": 2.3148148148148148e-06,
724
+ "loss": 3.7656,
725
+ "step": 2300
726
+ },
727
+ {
728
+ "epoch": 2.9,
729
+ "learning_rate": 1.8518518518518519e-06,
730
+ "loss": 3.1675,
731
+ "step": 2320
732
+ },
733
+ {
734
+ "epoch": 2.92,
735
+ "learning_rate": 1.388888888888889e-06,
736
+ "loss": 3.4532,
737
+ "step": 2340
738
+ },
739
+ {
740
+ "epoch": 2.95,
741
+ "learning_rate": 9.259259259259259e-07,
742
+ "loss": 3.4008,
743
+ "step": 2360
744
+ },
745
+ {
746
+ "epoch": 2.98,
747
+ "learning_rate": 4.6296296296296297e-07,
748
+ "loss": 3.6636,
749
+ "step": 2380
750
+ },
751
+ {
752
+ "epoch": 3.0,
753
+ "learning_rate": 0.0,
754
+ "loss": 3.2196,
755
+ "step": 2400
756
+ },
757
+ {
758
+ "epoch": 3.0,
759
+ "eval_gen_len": 82.945,
760
+ "eval_loss": 3.213425874710083,
761
+ "eval_rouge1": 27.3285,
762
+ "eval_rouge2": 8.8456,
763
+ "eval_rougeL": 16.8011,
764
+ "eval_rougeLsum": 24.6941,
765
+ "eval_runtime": 353.2997,
766
+ "eval_samples_per_second": 0.566,
767
+ "eval_steps_per_second": 0.142,
768
+ "step": 2400
769
+ }
770
+ ],
771
+ "logging_steps": 20,
772
+ "max_steps": 2400,
773
+ "num_train_epochs": 3,
774
+ "save_steps": 500,
775
+ "total_flos": 1.15108428644352e+16,
776
+ "trial_name": null,
777
+ "trial_params": null
778
+ }
checkpoint-2400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a83a8f612bb897a4d1984c9dc1dd1a76eedaa573de2a729564d7c0b32718c5
3
+ size 4792
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "length_penalty": 0.6,
20
+ "max_length": 84,
21
+ "model_type": "mt5",
22
+ "no_repeat_ngram_size": 2,
23
+ "num_beams": 4,
24
+ "num_decoder_layers": 12,
25
+ "num_heads": 12,
26
+ "num_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "relative_attention_max_distance": 128,
30
+ "relative_attention_num_buckets": 32,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "T5Tokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.35.2",
35
+ "use_cache": false,
36
+ "vocab_size": 250112
37
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "length_penalty": 0.6,
5
+ "max_length": 84,
6
+ "no_repeat_ngram_size": 2,
7
+ "num_beams": 4,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.35.2",
10
+ "use_cache": false
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948c23793b8023651647c4d5acaee78f4ee11feabfd8c5d02656008a878c6cf1
3
+ size 2329638768
runs/Dec14_08-39-45_r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf/events.out.tfevents.1702543186.r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf.87.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d908630070514547e36367362e2b9f659a3cb58fb218bcc22e2145e69df99e
3
+ size 25409
runs/Dec14_08-39-45_r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf/events.out.tfevents.1702545989.r-viditsorg-autotrain-p70w-m3ok-fcks-0-ogm33iyv-a93b6-6d6gf.87.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5abcbe8122d47d15fc3b1d9a2fabefd3a12ce6eac55476f0669dd59a82a4854
3
+ size 613
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73bed1ba1559b646793e05a5fef8052ea2e2a8366680454c386ff6371317210
3
+ size 16330559
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<pad>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a83a8f612bb897a4d1984c9dc1dd1a76eedaa573de2a729564d7c0b32718c5
3
+ size 4792
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"data_path": "viditsorg/autotrain-data-p70w-m3ok-fcks", "model": "csebuetnlp/mT5_multilingual_XLSum", "username": "viditsorg", "seed": 42, "train_split": "train", "valid_split": "validation", "project_name": "/tmp/model", "push_to_hub": true, "text_column": "autotrain_text", "target_column": "autotrain_label", "repo_id": "viditsorg/p70w-m3ok-fcks-0", "lr": 5e-05, "epochs": 3, "max_seq_length": 1024, "max_target_length": 256, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "logging_steps": -1, "evaluation_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "save_total_limit": 1, "save_strategy": "epoch", "use_peft": false, "use_int8": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "target_modules": []}