philschmid HF staff commited on
Commit
3456945
1 Parent(s): c0060c5

commit files to HF hub

Browse files
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ language: en
4
+ tags:
5
+ - sagemaker
6
+ - bart
7
+ - summarization
8
+ license: apache-2.0
9
+ datasets:
10
+ - samsum
11
+ ---
12
+
13
+ ## bart-base-samsum
14
+ This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
15
+
16
+ For more information look at:
17
+ - [🤗 Transformers Documentation: Amazon SageMaker](https://huggingface.co/transformers/sagemaker.html)
18
+ - [Example Notebooks](https://github.com/huggingface/notebooks/tree/master/sagemaker)
19
+ - [Amazon SageMaker documentation for Hugging Face](https://docs.aws.amazon.com/sagemaker/latest/dg/hugging-face.html)
20
+ - [Python SDK SageMaker documentation for Hugging Face](https://sagemaker.readthedocs.io/en/stable/frameworks/huggingface/index.html)
21
+ - [Deep Learning Container](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#huggingface-training-containers)
22
+
23
+ ## Result
24
+ | key | value |
25
+ | --- | ----- |
26
+ | key | value |
27
+ | key | value |
28
+
29
+ ## Usage
30
+ ```python
31
+ from transformers import pipeline
32
+ summarizer = pipeline("summarization", model="philschmid/bart-base-samsum")
33
+
34
+ conversation = '''Jeff: Can I train a 🤗 Transformers model on Amazon SageMaker?
35
+ Philipp: Sure you can use the new Hugging Face Deep Learning Container.
36
+ Jeff: ok.
37
+ Jeff: and how can I get started?
38
+ Jeff: where can I find documentation?
39
+ Philipp: ok, ok you can find everything here. https://huggingface.co/blog/the-partnership-amazon-sagemaker-and-hugging-face
40
+ '''
41
+ nlp(conversation)
42
+ ```
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.5356481075286865,
4
+ "eval_mem_cpu_alloc_delta": 659047,
5
+ "eval_mem_cpu_peaked_delta": 18254,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 300285440,
8
+ "eval_runtime": 0.3116,
9
+ "eval_samples": 818,
10
+ "eval_samples_per_second": 2625.337,
11
+ "init_mem_cpu_alloc_delta": 180190,
12
+ "init_mem_cpu_peaked_delta": 18282,
13
+ "init_mem_gpu_alloc_delta": 558658048,
14
+ "init_mem_gpu_peaked_delta": 0,
15
+ "train_mem_cpu_alloc_delta": 6658519,
16
+ "train_mem_cpu_peaked_delta": 642937,
17
+ "train_mem_gpu_alloc_delta": 2267624448,
18
+ "train_mem_gpu_peaked_delta": 10355728896,
19
+ "train_runtime": 98.4931,
20
+ "train_samples": 14732,
21
+ "train_samples_per_second": 3.533
22
+ }
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "transformers_version": "4.4.2",
71
+ "use_cache": true,
72
+ "vocab_size": 50265
73
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.5356481075286865,
4
+ "eval_mem_cpu_alloc_delta": 659047,
5
+ "eval_mem_cpu_peaked_delta": 18254,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 300285440,
8
+ "eval_runtime": 0.3116,
9
+ "eval_samples": 818,
10
+ "eval_samples_per_second": 2625.337
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:f0c3f3be2e895993ca702b159f601e72a41087cb39704f40b85131491ad2216f
3
+ size 557985683
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 180190,
4
+ "init_mem_cpu_peaked_delta": 18282,
5
+ "init_mem_gpu_alloc_delta": 558658048,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 6658519,
8
+ "train_mem_cpu_peaked_delta": 642937,
9
+ "train_mem_gpu_alloc_delta": 2267624448,
10
+ "train_mem_gpu_peaked_delta": 10355728896,
11
+ "train_runtime": 98.4931,
12
+ "train_samples": 14732,
13
+ "train_samples_per_second": 3.533
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": 1.486313161228288e+16,
14
+ "train_runtime": 98.4931,
15
+ "train_samples_per_second": 3.533
16
+ }
17
+ ],
18
+ "max_steps": 348,
19
+ "num_train_epochs": 3,
20
+ "total_flos": 1.486313161228288e+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 sha256:7ce1e4b47d7e2bf2d0c8b8757cb9b372beec5d3906ba7d3437ae751ffd3c50ab
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff