viditraj860 commited on
Commit
e76e68f
1 Parent(s): 746ec17

Upload folder using huggingface_hub

Browse files
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-kkyz-xs7p-9nss
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Seq2Seq
15
+
16
+ ## Validation Metrics
17
+ loss: 2.2772634029388428
18
+
19
+ rouge1: 39.2994
20
+
21
+ rouge2: 16.9505
22
+
23
+ rougeL: 24.9144
24
+
25
+ rougeLsum: 36.4135
26
+
27
+ gen_len: 141.54
28
+
29
+ runtime: 805.5411
30
+
31
+ samples_per_second: 0.248
32
+
33
+ steps_per_second: 0.062
34
+
35
+ : 3.0
checkpoint-1600/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.36.1",
68
+ "use_cache": false,
69
+ "vocab_size": 50265
70
+ }
checkpoint-1600/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 0,
7
+ "forced_eos_token_id": 2,
8
+ "length_penalty": 2.0,
9
+ "max_length": 142,
10
+ "min_length": 56,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 4,
13
+ "pad_token_id": 1,
14
+ "transformers_version": "4.36.1",
15
+ "use_cache": false
16
+ }
checkpoint-1600/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99fbefb7029b05c29708341b504ab94571b7d4733249e8ba977b0b5fddf21fa
3
+ size 1625426996
checkpoint-1600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef28390419d39b143d67fee5d0f9d6f128c875fd7d3ee73727cd1a83652301d
3
+ size 3250759951
checkpoint-1600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f872c38122dafd8177deae0dbcb308e16480793074563a7040f1b7cb086aefe3
3
+ size 14244
checkpoint-1600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2570e6bf79384fc32260d59a8d174249e1a51467ac1807ca2443a610d2a4e9
3
+ size 1064
checkpoint-1600/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-1600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
checkpoint-1600/trainer_state.json ADDED
@@ -0,0 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.2772634029388428,
3
+ "best_model_checkpoint": "/tmp/model/checkpoint-1600",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1600,
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": 3.958333333333333e-06,
14
+ "loss": 3.8721,
15
+ "step": 20
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 8.125000000000001e-06,
20
+ "loss": 3.3675,
21
+ "step": 40
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 1.2291666666666666e-05,
26
+ "loss": 3.5553,
27
+ "step": 60
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.6458333333333335e-05,
32
+ "loss": 3.2187,
33
+ "step": 80
34
+ },
35
+ {
36
+ "epoch": 0.12,
37
+ "learning_rate": 2.0625e-05,
38
+ "loss": 3.3576,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "learning_rate": 2.479166666666667e-05,
44
+ "loss": 3.2111,
45
+ "step": 120
46
+ },
47
+ {
48
+ "epoch": 0.17,
49
+ "learning_rate": 2.8958333333333337e-05,
50
+ "loss": 3.1881,
51
+ "step": 140
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "learning_rate": 3.3125e-05,
56
+ "loss": 3.0568,
57
+ "step": 160
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "learning_rate": 3.708333333333334e-05,
62
+ "loss": 3.1593,
63
+ "step": 180
64
+ },
65
+ {
66
+ "epoch": 0.25,
67
+ "learning_rate": 4.125e-05,
68
+ "loss": 2.9964,
69
+ "step": 200
70
+ },
71
+ {
72
+ "epoch": 0.28,
73
+ "learning_rate": 4.541666666666667e-05,
74
+ "loss": 3.2086,
75
+ "step": 220
76
+ },
77
+ {
78
+ "epoch": 0.3,
79
+ "learning_rate": 4.958333333333334e-05,
80
+ "loss": 3.314,
81
+ "step": 240
82
+ },
83
+ {
84
+ "epoch": 0.33,
85
+ "learning_rate": 4.958333333333334e-05,
86
+ "loss": 3.1285,
87
+ "step": 260
88
+ },
89
+ {
90
+ "epoch": 0.35,
91
+ "learning_rate": 4.912037037037037e-05,
92
+ "loss": 2.8458,
93
+ "step": 280
94
+ },
95
+ {
96
+ "epoch": 0.38,
97
+ "learning_rate": 4.865740740740741e-05,
98
+ "loss": 2.6054,
99
+ "step": 300
100
+ },
101
+ {
102
+ "epoch": 0.4,
103
+ "learning_rate": 4.819444444444445e-05,
104
+ "loss": 3.1717,
105
+ "step": 320
106
+ },
107
+ {
108
+ "epoch": 0.42,
109
+ "learning_rate": 4.773148148148148e-05,
110
+ "loss": 3.2007,
111
+ "step": 340
112
+ },
113
+ {
114
+ "epoch": 0.45,
115
+ "learning_rate": 4.726851851851852e-05,
116
+ "loss": 3.0557,
117
+ "step": 360
118
+ },
119
+ {
120
+ "epoch": 0.47,
121
+ "learning_rate": 4.6805555555555556e-05,
122
+ "loss": 2.8199,
123
+ "step": 380
124
+ },
125
+ {
126
+ "epoch": 0.5,
127
+ "learning_rate": 4.6342592592592595e-05,
128
+ "loss": 2.8118,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.53,
133
+ "learning_rate": 4.590277777777778e-05,
134
+ "loss": 2.9147,
135
+ "step": 420
136
+ },
137
+ {
138
+ "epoch": 0.55,
139
+ "learning_rate": 4.543981481481482e-05,
140
+ "loss": 2.6742,
141
+ "step": 440
142
+ },
143
+ {
144
+ "epoch": 0.57,
145
+ "learning_rate": 4.497685185185185e-05,
146
+ "loss": 2.8732,
147
+ "step": 460
148
+ },
149
+ {
150
+ "epoch": 0.6,
151
+ "learning_rate": 4.4513888888888885e-05,
152
+ "loss": 2.6045,
153
+ "step": 480
154
+ },
155
+ {
156
+ "epoch": 0.62,
157
+ "learning_rate": 4.405092592592593e-05,
158
+ "loss": 2.7271,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.65,
163
+ "learning_rate": 4.3587962962962965e-05,
164
+ "loss": 2.5203,
165
+ "step": 520
166
+ },
167
+ {
168
+ "epoch": 0.68,
169
+ "learning_rate": 4.3125000000000005e-05,
170
+ "loss": 2.7714,
171
+ "step": 540
172
+ },
173
+ {
174
+ "epoch": 0.7,
175
+ "learning_rate": 4.266203703703704e-05,
176
+ "loss": 3.081,
177
+ "step": 560
178
+ },
179
+ {
180
+ "epoch": 0.72,
181
+ "learning_rate": 4.219907407407408e-05,
182
+ "loss": 2.6275,
183
+ "step": 580
184
+ },
185
+ {
186
+ "epoch": 0.75,
187
+ "learning_rate": 4.173611111111112e-05,
188
+ "loss": 2.8672,
189
+ "step": 600
190
+ },
191
+ {
192
+ "epoch": 0.78,
193
+ "learning_rate": 4.127314814814815e-05,
194
+ "loss": 2.6542,
195
+ "step": 620
196
+ },
197
+ {
198
+ "epoch": 0.8,
199
+ "learning_rate": 4.0810185185185184e-05,
200
+ "loss": 2.9697,
201
+ "step": 640
202
+ },
203
+ {
204
+ "epoch": 0.82,
205
+ "learning_rate": 4.0347222222222223e-05,
206
+ "loss": 2.8099,
207
+ "step": 660
208
+ },
209
+ {
210
+ "epoch": 0.85,
211
+ "learning_rate": 3.988425925925926e-05,
212
+ "loss": 2.6577,
213
+ "step": 680
214
+ },
215
+ {
216
+ "epoch": 0.88,
217
+ "learning_rate": 3.94212962962963e-05,
218
+ "loss": 2.7843,
219
+ "step": 700
220
+ },
221
+ {
222
+ "epoch": 0.9,
223
+ "learning_rate": 3.8958333333333336e-05,
224
+ "loss": 2.7663,
225
+ "step": 720
226
+ },
227
+ {
228
+ "epoch": 0.93,
229
+ "learning_rate": 3.849537037037037e-05,
230
+ "loss": 2.6443,
231
+ "step": 740
232
+ },
233
+ {
234
+ "epoch": 0.95,
235
+ "learning_rate": 3.803240740740741e-05,
236
+ "loss": 2.6549,
237
+ "step": 760
238
+ },
239
+ {
240
+ "epoch": 0.97,
241
+ "learning_rate": 3.756944444444445e-05,
242
+ "loss": 2.4063,
243
+ "step": 780
244
+ },
245
+ {
246
+ "epoch": 1.0,
247
+ "learning_rate": 3.710648148148148e-05,
248
+ "loss": 2.5605,
249
+ "step": 800
250
+ },
251
+ {
252
+ "epoch": 1.0,
253
+ "eval_gen_len": 141.655,
254
+ "eval_loss": 2.4260785579681396,
255
+ "eval_rouge1": 36.8904,
256
+ "eval_rouge2": 14.0444,
257
+ "eval_rougeL": 22.5839,
258
+ "eval_rougeLsum": 33.8603,
259
+ "eval_runtime": 806.3061,
260
+ "eval_samples_per_second": 0.248,
261
+ "eval_steps_per_second": 0.062,
262
+ "step": 800
263
+ },
264
+ {
265
+ "epoch": 1.02,
266
+ "learning_rate": 3.664351851851852e-05,
267
+ "loss": 2.3288,
268
+ "step": 820
269
+ },
270
+ {
271
+ "epoch": 1.05,
272
+ "learning_rate": 3.6180555555555555e-05,
273
+ "loss": 2.0535,
274
+ "step": 840
275
+ },
276
+ {
277
+ "epoch": 1.07,
278
+ "learning_rate": 3.5717592592592595e-05,
279
+ "loss": 2.0489,
280
+ "step": 860
281
+ },
282
+ {
283
+ "epoch": 1.1,
284
+ "learning_rate": 3.5254629629629635e-05,
285
+ "loss": 1.9129,
286
+ "step": 880
287
+ },
288
+ {
289
+ "epoch": 1.12,
290
+ "learning_rate": 3.479166666666667e-05,
291
+ "loss": 2.3016,
292
+ "step": 900
293
+ },
294
+ {
295
+ "epoch": 1.15,
296
+ "learning_rate": 3.432870370370371e-05,
297
+ "loss": 2.1098,
298
+ "step": 920
299
+ },
300
+ {
301
+ "epoch": 1.18,
302
+ "learning_rate": 3.386574074074074e-05,
303
+ "loss": 2.0364,
304
+ "step": 940
305
+ },
306
+ {
307
+ "epoch": 1.2,
308
+ "learning_rate": 3.340277777777778e-05,
309
+ "loss": 1.8088,
310
+ "step": 960
311
+ },
312
+ {
313
+ "epoch": 1.23,
314
+ "learning_rate": 3.293981481481482e-05,
315
+ "loss": 1.9104,
316
+ "step": 980
317
+ },
318
+ {
319
+ "epoch": 1.25,
320
+ "learning_rate": 3.247685185185185e-05,
321
+ "loss": 1.9855,
322
+ "step": 1000
323
+ },
324
+ {
325
+ "epoch": 1.27,
326
+ "learning_rate": 3.2013888888888886e-05,
327
+ "loss": 2.0865,
328
+ "step": 1020
329
+ },
330
+ {
331
+ "epoch": 1.3,
332
+ "learning_rate": 3.1550925925925926e-05,
333
+ "loss": 2.127,
334
+ "step": 1040
335
+ },
336
+ {
337
+ "epoch": 1.32,
338
+ "learning_rate": 3.1087962962962966e-05,
339
+ "loss": 2.1918,
340
+ "step": 1060
341
+ },
342
+ {
343
+ "epoch": 1.35,
344
+ "learning_rate": 3.0625000000000006e-05,
345
+ "loss": 1.9604,
346
+ "step": 1080
347
+ },
348
+ {
349
+ "epoch": 1.38,
350
+ "learning_rate": 3.016203703703704e-05,
351
+ "loss": 2.289,
352
+ "step": 1100
353
+ },
354
+ {
355
+ "epoch": 1.4,
356
+ "learning_rate": 2.9699074074074075e-05,
357
+ "loss": 1.6954,
358
+ "step": 1120
359
+ },
360
+ {
361
+ "epoch": 1.43,
362
+ "learning_rate": 2.9236111111111115e-05,
363
+ "loss": 2.2102,
364
+ "step": 1140
365
+ },
366
+ {
367
+ "epoch": 1.45,
368
+ "learning_rate": 2.8773148148148148e-05,
369
+ "loss": 2.287,
370
+ "step": 1160
371
+ },
372
+ {
373
+ "epoch": 1.48,
374
+ "learning_rate": 2.8310185185185185e-05,
375
+ "loss": 1.9731,
376
+ "step": 1180
377
+ },
378
+ {
379
+ "epoch": 1.5,
380
+ "learning_rate": 2.7847222222222224e-05,
381
+ "loss": 2.2276,
382
+ "step": 1200
383
+ },
384
+ {
385
+ "epoch": 1.52,
386
+ "learning_rate": 2.738425925925926e-05,
387
+ "loss": 1.8473,
388
+ "step": 1220
389
+ },
390
+ {
391
+ "epoch": 1.55,
392
+ "learning_rate": 2.69212962962963e-05,
393
+ "loss": 1.8407,
394
+ "step": 1240
395
+ },
396
+ {
397
+ "epoch": 1.57,
398
+ "learning_rate": 2.6458333333333334e-05,
399
+ "loss": 1.9851,
400
+ "step": 1260
401
+ },
402
+ {
403
+ "epoch": 1.6,
404
+ "learning_rate": 2.599537037037037e-05,
405
+ "loss": 2.2261,
406
+ "step": 1280
407
+ },
408
+ {
409
+ "epoch": 1.62,
410
+ "learning_rate": 2.553240740740741e-05,
411
+ "loss": 1.9708,
412
+ "step": 1300
413
+ },
414
+ {
415
+ "epoch": 1.65,
416
+ "learning_rate": 2.5069444444444447e-05,
417
+ "loss": 1.9759,
418
+ "step": 1320
419
+ },
420
+ {
421
+ "epoch": 1.68,
422
+ "learning_rate": 2.4606481481481483e-05,
423
+ "loss": 1.9717,
424
+ "step": 1340
425
+ },
426
+ {
427
+ "epoch": 1.7,
428
+ "learning_rate": 2.414351851851852e-05,
429
+ "loss": 1.8061,
430
+ "step": 1360
431
+ },
432
+ {
433
+ "epoch": 1.73,
434
+ "learning_rate": 2.3680555555555556e-05,
435
+ "loss": 1.7061,
436
+ "step": 1380
437
+ },
438
+ {
439
+ "epoch": 1.75,
440
+ "learning_rate": 2.3217592592592592e-05,
441
+ "loss": 2.0426,
442
+ "step": 1400
443
+ },
444
+ {
445
+ "epoch": 1.77,
446
+ "learning_rate": 2.2754629629629632e-05,
447
+ "loss": 2.0017,
448
+ "step": 1420
449
+ },
450
+ {
451
+ "epoch": 1.8,
452
+ "learning_rate": 2.229166666666667e-05,
453
+ "loss": 1.979,
454
+ "step": 1440
455
+ },
456
+ {
457
+ "epoch": 1.82,
458
+ "learning_rate": 2.1828703703703705e-05,
459
+ "loss": 1.9851,
460
+ "step": 1460
461
+ },
462
+ {
463
+ "epoch": 1.85,
464
+ "learning_rate": 2.136574074074074e-05,
465
+ "loss": 1.7156,
466
+ "step": 1480
467
+ },
468
+ {
469
+ "epoch": 1.88,
470
+ "learning_rate": 2.0902777777777778e-05,
471
+ "loss": 2.0078,
472
+ "step": 1500
473
+ },
474
+ {
475
+ "epoch": 1.9,
476
+ "learning_rate": 2.0439814814814814e-05,
477
+ "loss": 1.8058,
478
+ "step": 1520
479
+ },
480
+ {
481
+ "epoch": 1.93,
482
+ "learning_rate": 1.997685185185185e-05,
483
+ "loss": 2.3492,
484
+ "step": 1540
485
+ },
486
+ {
487
+ "epoch": 1.95,
488
+ "learning_rate": 1.951388888888889e-05,
489
+ "loss": 2.169,
490
+ "step": 1560
491
+ },
492
+ {
493
+ "epoch": 1.98,
494
+ "learning_rate": 1.9050925925925927e-05,
495
+ "loss": 1.9333,
496
+ "step": 1580
497
+ },
498
+ {
499
+ "epoch": 2.0,
500
+ "learning_rate": 1.8587962962962964e-05,
501
+ "loss": 2.0535,
502
+ "step": 1600
503
+ },
504
+ {
505
+ "epoch": 2.0,
506
+ "eval_gen_len": 141.54,
507
+ "eval_loss": 2.2772634029388428,
508
+ "eval_rouge1": 39.2994,
509
+ "eval_rouge2": 16.9505,
510
+ "eval_rougeL": 24.9144,
511
+ "eval_rougeLsum": 36.4135,
512
+ "eval_runtime": 807.8602,
513
+ "eval_samples_per_second": 0.248,
514
+ "eval_steps_per_second": 0.062,
515
+ "step": 1600
516
+ }
517
+ ],
518
+ "logging_steps": 20,
519
+ "max_steps": 2400,
520
+ "num_input_tokens_seen": 0,
521
+ "num_train_epochs": 3,
522
+ "save_steps": 500,
523
+ "total_flos": 6931077737742336.0,
524
+ "train_batch_size": 2,
525
+ "trial_name": null,
526
+ "trial_params": null
527
+ }
checkpoint-1600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed37513683036541625e7f5514d8f35538f17a473665d9eda27b3decc4a8937d
3
+ size 4920
checkpoint-1600/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.36.1",
68
+ "use_cache": false,
69
+ "vocab_size": 50265
70
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 0,
7
+ "forced_eos_token_id": 2,
8
+ "length_penalty": 2.0,
9
+ "max_length": 142,
10
+ "min_length": 56,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 4,
13
+ "pad_token_id": 1,
14
+ "transformers_version": "4.36.1",
15
+ "use_cache": false
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99fbefb7029b05c29708341b504ab94571b7d4733249e8ba977b0b5fddf21fa
3
+ size 1625426996
runs/Dec14_15-01-50_r-viditsorg-autotrain-kkyz-xs7p-9nss-0-f2dzwefr-832b9-nrcmp/events.out.tfevents.1702566112.r-viditsorg-autotrain-kkyz-xs7p-9nss-0-f2dzwefr-832b9-nrcmp.47.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0ec52f65a4804ca876f711d4d812c1807855c1d0639a4dd96e611a822f91e9
3
+ size 26267
runs/Dec14_15-01-50_r-viditsorg-autotrain-kkyz-xs7p-9nss-0-f2dzwefr-832b9-nrcmp/events.out.tfevents.1702570458.r-viditsorg-autotrain-kkyz-xs7p-9nss-0-f2dzwefr-832b9-nrcmp.47.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c40c7462a7e5d88a08c48688bf12f38e55311ba1733f62942f3725b61232826
3
+ size 613
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed37513683036541625e7f5514d8f35538f17a473665d9eda27b3decc4a8937d
3
+ size 4920
training_params.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "viditsorg/autotrain-data-kkyz-xs7p-9nss",
3
+ "model": "facebook/bart-large-cnn",
4
+ "username": "viditsorg",
5
+ "seed": 42,
6
+ "train_split": "train",
7
+ "valid_split": "validation",
8
+ "project_name": "/tmp/model",
9
+ "push_to_hub": true,
10
+ "text_column": "autotrain_text",
11
+ "target_column": "autotrain_label",
12
+ "repo_id": "viditsorg/kkyz-xs7p-9nss-0",
13
+ "lr": 5e-05,
14
+ "epochs": 3,
15
+ "max_seq_length": 1024,
16
+ "max_target_length": 256,
17
+ "batch_size": 2,
18
+ "warmup_ratio": 0.1,
19
+ "gradient_accumulation": 1,
20
+ "optimizer": "adamw_torch",
21
+ "scheduler": "linear",
22
+ "weight_decay": 0.0,
23
+ "max_grad_norm": 1.0,
24
+ "logging_steps": -1,
25
+ "evaluation_strategy": "epoch",
26
+ "auto_find_batch_size": false,
27
+ "mixed_precision": "fp16",
28
+ "save_total_limit": 1,
29
+ "save_strategy": "epoch",
30
+ "peft": false,
31
+ "quantization": null,
32
+ "lora_r": 16,
33
+ "lora_alpha": 32,
34
+ "lora_dropout": 0.05,
35
+ "target_modules": []
36
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff