Hugging Face's logo

Mahalingam
/
DistilBart-Med-Summary

Summarization
Transformers
PyTorch
English
bart
text2text-generation
sagemaker
Inference Endpoints
Model card Files Community
Mahalingam commited on
Commit
50f566c
•
1 Parent(s): 20e22a7

Upload 12 files

Browse files
Files changed (12) hide show
  1. README.md +210 -0
  2. all_results.json +22 -0
  3. config.json +76 -0
  4. eval_results.json +11 -0
  5. merges.txt +0 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +1 -0
  8. tokenizer_config.json +1 -0
  9. train_results.json +14 -0
  10. trainer_state.json +23 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ tags:
5
+ - sagemaker
6
+ - bart
7
+ - summarization
8
+ datasets:
9
+ - samsum
10
+ widget:
11
+ - text: "Jeff: Can I train a \U0001F917 Transformers model on Amazon SageMaker? \n\
12
+ Philipp: Sure you can use the new Hugging Face Deep Learning Container. \nJeff:\
13
+ \ ok.\nJeff: and how can I get started? \nJeff: where can I find documentation?\
14
+ \ \nPhilipp: ok, ok you can find everything here. https://huggingface.co/blog/the-partnership-amazon-sagemaker-and-hugging-face "
15
+ model-index:
16
+ - name: philschmid/distilbart-cnn-12-6-samsum
17
+ results:
18
+ - task:
19
+ type: summarization
20
+ name: Summarization
21
+ dataset:
22
+ name: samsum
23
+ type: samsum
24
+ config: samsum
25
+ split: test
26
+ metrics:
27
+ - type: rouge
28
+ value: 41.0895
29
+ name: ROUGE-1
30
+ verified: true
31
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTBlZmQzZDFmNzY5YTBjMTI3ZjRkNDk4NTI3YzQxOGY4MjlkMTU4ZGJkZWE4YjQ4ZDFhOTIxM2M1YWEyMDQ4MCIsInZlcnNpb24iOjF9.Nw7idRmEmjS-c91HthjVGw6YxttVA_tRB2QRkGwVSVABR3_BY84HvwLOZVstc6a9gUHopMj_W9SRfa_6xTWcBA
32
+ - type: rouge
33
+ value: 20.7459
34
+ name: ROUGE-2
35
+ verified: true
36
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjRhN2E4ZDNiNWNkY2RkNjMxMjhiYjcxYjc4OWM4NWQ5MDNjZDMwOGIwNWI2NWJiYzljMzc0NzY1ZDBmMTRmZCIsInZlcnNpb24iOjF9.nYxNimi33AW0T8T1JhqFUukxe4W4niXj4UzLRTuc40NeZveDTSpPS8QzR4rF1gK-r2irqIX5FrvG4dwQHrESBA
37
+ - type: rouge
38
+ value: 31.5952
39
+ name: ROUGE-L
40
+ verified: true
41
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjYzYTRjOTU1MDVhN2ZlOGE3YTIxMjk1NDBiY2E2ZWI1MDA5ZTJkOTQ4MzgxNThkOGU4OTUzODU0YWE1OTQ5MiIsInZlcnNpb24iOjF9.G2EtxIlJ86AcNx2bqw2nu1UbdczQ-anl1c02EopQyC81BEcEAbnY-liPvHXLjPVQvP97GGGjqTDLZYjYJ71hDQ
42
+ - type: rouge
43
+ value: 38.3389
44
+ name: ROUGE-LSUM
45
+ verified: true
46
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWExZmM2YWI1MDU0ZjE1YWY1NDNiY2E4YTkwZjA5MTE0YmM1NzI4YTc1YjI0MWFmZDlkYTBlZjVlMDk2ZGQxZSIsInZlcnNpb24iOjF9.jjBghJ66Gj_95AdDpWG2TR_MnuUtj8Fzc0M3KS9vqsM0iqtlu9khY8lXrFpMaIeDxVBYKltMMFdZWH8mVv2wCg
47
+ - type: loss
48
+ value: 1.4566329717636108
49
+ name: loss
50
+ verified: true
51
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDAyYjFmNzRlYzkyNmUxMWM5YWYxNjgwZGQ1ZDc1Njg0MzU1ZjM4MjI5MTJlODRiNDdiNGRjYTkzZGUxNGMyZiIsInZlcnNpb24iOjF9.2eH5b7DlPeVQ_zFGlvKyRvqrc7yyT8vcf3koJGKGysV00vCQew8sOmFEmDegiBka8gq3UL987Dd2yZCU3b64Cw
52
+ - type: gen_len
53
+ value: 59.6032
54
+ name: gen_len
55
+ verified: true
56
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTFkOTlmMjFlODIxZWExZmQyMTQyNDYyY2RmNjY3YmM1NDFlNTI3OTRhZjU0MDQxNGY2NGQ4ZWY2OWFmNDliMyIsInZlcnNpb24iOjF9.K9qwFg3Flnu2-1H-WI9adj7yoBuJ3zBBDyda5BxRpJ1D4L_alLpCweqrVGuynOPl9PAWPuHo7bAG1y2zZNmmDw
57
+ - task:
58
+ type: summarization
59
+ name: Summarization
60
+ dataset:
61
+ name: xsum
62
+ type: xsum
63
+ config: default
64
+ split: test
65
+ metrics:
66
+ - type: rouge
67
+ value: 21.1644
68
+ name: ROUGE-1
69
+ verified: true
70
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzVjNWI1MWJmOTAzMDYxNjlkYzg4NjM3MzczMDJiYjNjYTg3NjYzNjQ3YTczYzg5MGU2NDcxOWQwZjdlODU4YSIsInZlcnNpb24iOjF9.CqB-ANpnx0GvwhsjeCzLB_RxaKqbnhc_980RG8fqDb2hNTk4LvDhqdDfkLFQMj8kvW4nQLLDSNUENQ7Uni9kCA
71
+ - type: rouge
72
+ value: 4.0659
73
+ name: ROUGE-2
74
+ verified: true
75
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjgzYTc5Y2VjZTliNmEwYTZjNTViODdjYTg2MGMyZTFkMjgyMjk0OGIzZjg1ODgzZDJmOTMwNmU4MzdlNTI2OCIsInZlcnNpb24iOjF9.1AfPtrpJ38Khz5vfRsN4Jwb3J_PdycddRH9DJtEccqmEz9BzDo-AO7Ts94sfVlYfSf3srplLHDcd_XFCwQtlBg
76
+ - type: rouge
77
+ value: 13.9414
78
+ name: ROUGE-L
79
+ verified: true
80
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODZlZTM2OTM5NzVlNDBjYjc2NDdhNmIxNDZhNGVjOTk4YzIzZmEwYzEwZmQ2ZmNmMjIzNzYwMzkxMjU1ODcxMCIsInZlcnNpb24iOjF9.vvp5PKmEp-Hyt46zgsvzjGOO8wrV0cDG68Z0VPqW2WfY5Sp3k3krEcKLATdQAQjfy96gKCCkQpBFefpjYWcmDA
81
+ - type: rouge
82
+ value: 17.0718
83
+ name: ROUGE-LSUM
84
+ verified: true
85
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWEyN2QyOWFhMjAzZTk4NjU5ODU5YjgxMjczNzc1MTM5OTY1OTVjZDMwZDhjODFlZTVmODNkYzFhOTc5NzZhYiIsInZlcnNpb24iOjF9.PwJT3EYTV3KifWaySiwSTxGyBWTB8bHMuaXG3AyRvWkY2xju1BSaBjPGCcfmlZs1yJwghOH7N4dBW5yJBEp5DA
86
+ - type: loss
87
+ value: 3.002755880355835
88
+ name: loss
89
+ verified: true
90
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGY0NjgzOGExZWZmNWI3ZTA1ZjRlYTU2OTZkYzk5NDdmOGVmNDdkNWU5YjViMWQyNGE2MTNkODhkZmQ1ZGE2OSIsInZlcnNpb24iOjF9.pWru9Nhl0aZThHz0qveOHmxTOCrZjHu9ySt5wI9MnGQ5ZEpxfufjpI196EMMn-KSSxAl-s7wHygtGC9_WtC1BQ
91
+ - type: gen_len
92
+ value: 71.2969
93
+ name: gen_len
94
+ verified: true
95
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q4ODZlZDY4YzE1MDEwNzJjNmNiYjI4NTU5NjRlNmY2NWNjYmUwNzcwZmY3NWVlZDA3NTMxY2Y2NWI1ODYwMCIsInZlcnNpb24iOjF9.0Y_lnTKQ5nmjnwAEju9T7xlLObWgwPLMOxlWDpjPBkDeW0bzHYqJcRADtFcvAhznJ3HktIV830QxjqkRYjZTDw
96
+ - task:
97
+ type: summarization
98
+ name: Summarization
99
+ dataset:
100
+ name: cnn_dailymail
101
+ type: cnn_dailymail
102
+ config: 3.0.0
103
+ split: test
104
+ metrics:
105
+ - type: rouge
106
+ value: 42.9764
107
+ name: ROUGE-1
108
+ verified: true
109
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzQ0NzAyNDM5YWIyZmY5OTUwNWZjNzRkYTliYWI0YzdmZTg5ZGVhZjJlMDBiZjg2YmE0ZjkxNzU4YjRkYTJjNCIsInZlcnNpb24iOjF9.dymlXdITNpMZpOaYvif-LcxaSRWKh8_RxV6mdBpuvlThPPi3-TwKCW20Fowor8H5RPsC0M1cfvNNzINCyApKCA
110
+ - type: rouge
111
+ value: 19.8711
112
+ name: ROUGE-2
113
+ verified: true
114
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTY5ZTI0OTEzNzI1NDRjYWE5MDk2NzVhZDEyNGEzNzU3OTE0NmJmYzhkMTU0MTI2MDVlOTdlNGU0OGI2MTdlNSIsInZlcnNpb24iOjF9.7xN2u4HjPL78CkkihB9I0befTn04IQqimvNlSHpc888arBm_qCtTGl7q7389ArpWUKEdkhvZ94BgB-Z_cXsqCg
115
+ - type: rouge
116
+ value: 29.5196
117
+ name: ROUGE-L
118
+ verified: true
119
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGY3YzRiYjljZWJhNGJiMTdhNDY5OTk0ODJhYWMxOGMwYjY4ZTBlNmQ0YTUxMzQ3YmZiNzg0ZDJiNTg4MzdiYyIsInZlcnNpb24iOjF9.Yj0ZaJelYcMJ-8SIon9x7GxRityWR3p0vcLNctTfcg6eCClalTQKBclCVgpDCO8WQyVxSz8EyCDb2qedRgF9CQ
120
+ - type: rouge
121
+ value: 39.959
122
+ name: ROUGE-LSUM
123
+ verified: true
124
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmI2MTE3NjQ2M2MwYjJmN2JmMTEwN2JkMDVhMWRiMDBiM2FlMzM5NjAxYWM1N2Q2MTA5MGRhZmI5ZDNjNzMwYSIsInZlcnNpb24iOjF9.A-2Ch4-M691OBAp4KmsYut10K3sF0fjw5ztutK_LTtn68Ne0x8w-u-7pEyjTuWJrJx4Q3Yb1eW3yeHPTnFI0DA
125
+ - type: loss
126
+ value: 3.014679193496704
127
+ name: loss
128
+ verified: true
129
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmNiNWZlOGZmOWZhNWZjNTg1ODIzMzY2ZGYxNzBiOWIxMWRiZTQ5MzM5NjRlYTQwMzRjOGI3YzNmZDhmYjQ3MCIsInZlcnNpb24iOjF9.BZkiJxZG0RdFzNgxgcS8U6_zPT1t7rvs-603cnC1tjMMYF3Lbae7rExRb-fVHN_ofZV_w5vl4uRLQ3OxZUY5Ag
130
+ - type: gen_len
131
+ value: 81.956
132
+ name: gen_len
133
+ verified: true
134
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTdhNGYxYWRlNTU0MzAxMWU1NzNmMTBjMmY3NzkzODAyYTMzZWYyZmNiMTViMzNmYTE0ZmFmNDdhMzQwMmJkNyIsInZlcnNpb24iOjF9.8lm84JtbCh-diuNQ01oXK6P8vV9CPyA8y-7D9o_OHb9Vk3pNEFM1jMSZVdEG9wFuMpWL3ARbXLadEPQB5HN8AQ
135
+ ---
136
+
137
+ ## `distilbart-cnn-12-6-samsum`
138
+
139
+ This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
140
+
141
+ For more information look at:
142
+ - [🤗 Transformers Documentation: Amazon SageMaker](https://huggingface.co/transformers/sagemaker.html)
143
+ - [Example Notebooks](https://github.com/huggingface/notebooks/tree/master/sagemaker)
144
+ - [Amazon SageMaker documentation for Hugging Face](https://docs.aws.amazon.com/sagemaker/latest/dg/hugging-face.html)
145
+ - [Python SDK SageMaker documentation for Hugging Face](https://sagemaker.readthedocs.io/en/stable/frameworks/huggingface/index.html)
146
+ - [Deep Learning Container](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#huggingface-training-containers)
147
+
148
+ ## Hyperparameters
149
+ ```json
150
+ {
151
+ "dataset_name": "samsum",
152
+ "do_eval": true,
153
+ "do_train": true,
154
+ "fp16": true,
155
+ "learning_rate": 5e-05,
156
+ "model_name_or_path": "sshleifer/distilbart-cnn-12-6",
157
+ "num_train_epochs": 3,
158
+ "output_dir": "/opt/ml/model",
159
+ "per_device_eval_batch_size": 8,
160
+ "per_device_train_batch_size": 8,
161
+ "seed": 7
162
+ }
163
+ ```
164
+
165
+ ## Train results
166
+
167
+ | key | value |
168
+ | --- | ----- |
169
+ | epoch | 3.0 |
170
+ | init_mem_cpu_alloc_delta | 180338 |
171
+ | init_mem_cpu_peaked_delta | 18282 |
172
+ | init_mem_gpu_alloc_delta | 1222242816 |
173
+ | init_mem_gpu_peaked_delta | 0 |
174
+ | train_mem_cpu_alloc_delta | 6971403 |
175
+ | train_mem_cpu_peaked_delta | 640733 |
176
+ | train_mem_gpu_alloc_delta | 4910897664 |
177
+ | train_mem_gpu_peaked_delta | 23331969536 |
178
+ | train_runtime | 155.2034 |
179
+ | train_samples | 14732 |
180
+ | train_samples_per_second | 2.242 |
181
+
182
+ ## Eval results
183
+
184
+ | key | value |
185
+ | --- | ----- |
186
+ | epoch | 3.0 |
187
+ | eval_loss | 1.4209576845169067 |
188
+ | eval_mem_cpu_alloc_delta | 868003 |
189
+ | eval_mem_cpu_peaked_delta | 18250 |
190
+ | eval_mem_gpu_alloc_delta | 0 |
191
+ | eval_mem_gpu_peaked_delta | 328244736 |
192
+ | eval_runtime | 0.6088 |
193
+ | eval_samples | 818 |
194
+ | eval_samples_per_second | 1343.647 |
195
+
196
+
197
+ ## Usage
198
+ ```python
199
+ from transformers import pipeline
200
+ summarizer = pipeline("summarization", model="philschmid/distilbart-cnn-12-6-samsum")
201
+
202
+ conversation = '''Jeff: Can I train a 🤗 Transformers model on Amazon SageMaker?
203
+ Philipp: Sure you can use the new Hugging Face Deep Learning Container.
204
+ Jeff: ok.
205
+ Jeff: and how can I get started?
206
+ Jeff: where can I find documentation?
207
+ Philipp: ok, ok you can find everything here. https://huggingface.co/blog/the-partnership-amazon-sagemaker-and-hugging-face
208
+ '''
209
+ nlp(conversation)
210
+ ```
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.4209576845169067,
4
+ "eval_mem_cpu_alloc_delta": 868003,
5
+ "eval_mem_cpu_peaked_delta": 18250,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 328244736,
8
+ "eval_runtime": 0.6088,
9
+ "eval_samples": 818,
10
+ "eval_samples_per_second": 1343.647,
11
+ "init_mem_cpu_alloc_delta": 180338,
12
+ "init_mem_cpu_peaked_delta": 18282,
13
+ "init_mem_gpu_alloc_delta": 1222242816,
14
+ "init_mem_gpu_peaked_delta": 0,
15
+ "train_mem_cpu_alloc_delta": 6971403,
16
+ "train_mem_cpu_peaked_delta": 640733,
17
+ "train_mem_gpu_alloc_delta": 4910897664,
18
+ "train_mem_gpu_peaked_delta": 23331969536,
19
+ "train_runtime": 155.2034,
20
+ "train_samples": 14732,
21
+ "train_samples_per_second": 2.242
22
+ }
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sshleifer/distilbart-cnn-12-6",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "BartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": true,
30
+ "forced_bos_token_id": 0,
31
+ "forced_eos_token_id": 2,
32
+ "gradient_checkpointing": false,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "length_penalty": 2.0,
46
+ "max_length": 142,
47
+ "max_position_embeddings": 1024,
48
+ "min_length": 56,
49
+ "model_type": "bart",
50
+ "no_repeat_ngram_size": 3,
51
+ "normalize_before": false,
52
+ "normalize_embedding": true,
53
+ "num_beams": 4,
54
+ "num_hidden_layers": 12,
55
+ "output_past": true,
56
+ "pad_token_id": 1,
57
+ "prefix": " ",
58
+ "replacing_rate": 0,
59
+ "scale_embedding": false,
60
+ "static_position_embeddings": false,
61
+ "student_decoder_layers": null,
62
+ "student_encoder_layers": null,
63
+ "task_specific_params": {
64
+ "summarization": {
65
+ "early_stopping": true,
66
+ "length_penalty": 2.0,
67
+ "max_length": 142,
68
+ "min_length": 56,
69
+ "no_repeat_ngram_size": 3,
70
+ "num_beams": 4
71
+ }
72
+ },
73
+ "transformers_version": "4.4.2",
74
+ "use_cache": true,
75
+ "vocab_size": 50264
76
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.4209576845169067,
4
+ "eval_mem_cpu_alloc_delta": 868003,
5
+ "eval_mem_cpu_peaked_delta": 18250,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 328244736,
8
+ "eval_runtime": 0.6088,
9
+ "eval_samples": 818,
10
+ "eval_samples_per_second": 1343.647
11
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67abec0e716c8fc11e87bb3f759ce59f2b77b7cff98d73a71a9127bf6d2825f1
3
+ size 1222383347
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "sshleifer/distilbart-cnn-12-6"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 180338,
4
+ "init_mem_cpu_peaked_delta": 18282,
5
+ "init_mem_gpu_alloc_delta": 1222242816,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 6971403,
8
+ "train_mem_cpu_peaked_delta": 640733,
9
+ "train_mem_gpu_alloc_delta": 4910897664,
10
+ "train_mem_gpu_peaked_delta": 23331969536,
11
+ "train_runtime": 155.2034,
12
+ "train_samples": 14732,
13
+ "train_samples_per_second": 2.242
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 348,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.0,
12
+ "step": 348,
13
+ "total_flos": 3.256941561040077e+16,
14
+ "train_runtime": 155.2034,
15
+ "train_samples_per_second": 2.242
16
+ }
17
+ ],
18
+ "max_steps": 348,
19
+ "num_train_epochs": 3,
20
+ "total_flos": 3.256941561040077e+16,
21
+ "trial_name": null,
22
+ "trial_params": null
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445bcdc5aceb3f3e7eb6bf5074c748abcba6917e3b5045d97705cd824089e224
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff