commit files to HF hub

README.md

@@ -0,0 +1,106 @@
+
+---
+language: en
+tags:
+- sagemaker
+- bart
+- summarization
+license: apache-2.0
+datasets:
+- samsum
+widget:
+- text: | 
+    Jeff: Can I train a 🤗 Transformers model on Amazon SageMaker? 
+    Philipp: Sure you can use the new Hugging Face Deep Learning Container. 
+    Jeff: ok.
+    Jeff: and how can I get started? 
+    Jeff: where can I find documentation? 
+    Philipp: ok, ok you can find everything here. https://huggingface.co/blog/the-partnership-amazon-sagemaker-and-hugging-face 
+model-index:
+- name: bart-large-cnn-samsum
+  results:
+  - task: 
+      name: Abstractive Text Summarization
+      type: abstractive-text-summarization
+    dataset:
+      name: SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization 
+      type: samsum
+    metrics:
+       - name: Validation ROGUE-1
+         type: rogue-1
+         value: 42.621
+       - name: Validation ROGUE-2
+         type: rogue-2
+         value: 21.9825
+       - name: Validation ROGUE-L
+         type: rogue-l
+         value: 33.034
+       - name: Test ROGUE-1
+         type: rogue-1
+         value: 41.3174
+       - name: Test ROGUE-2
+         type: rogue-2
+         value: 20.8716
+       - name: Test ROGUE-L
+         type: rogue-l
+         value: 32.1337
+---
+
+## `bart-large-cnn-samsum`
+
+This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
+
+For more information look at:
+- [🤗 Transformers Documentation: Amazon SageMaker](https://huggingface.co/transformers/sagemaker.html)
+- [Example Notebooks](https://github.com/huggingface/notebooks/tree/master/sagemaker)
+- [Amazon SageMaker documentation for Hugging Face](https://docs.aws.amazon.com/sagemaker/latest/dg/hugging-face.html)
+- [Python SDK SageMaker documentation for Hugging Face](https://sagemaker.readthedocs.io/en/stable/frameworks/huggingface/index.html)
+- [Deep Learning Container](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#huggingface-training-containers)
+
+## Hyperparameters
+```json
+{
+    "dataset_name": "samsum",
+    "do_eval": true,
+    "do_predict": true,
+    "do_train": true,
+    "fp16": true,
+    "learning_rate": 5e-05,
+    "model_name_or_path": "facebook/bart-large-cnn",
+    "num_train_epochs": 3,
+    "output_dir": "/opt/ml/model",
+    "per_device_eval_batch_size": 4,
+    "per_device_train_batch_size": 4,
+    "predict_with_generate": true,
+    "seed": 7
+}
+```
+
+## Usage
+```python
+from transformers import pipeline
+summarizer = pipeline("summarization", model="philschmid/bart-large-cnn-samsum")
+
+conversation = '''Jeff: Can I train a 🤗 Transformers model on Amazon SageMaker? 
+Philipp: Sure you can use the new Hugging Face Deep Learning Container. 
+Jeff: ok.
+Jeff: and how can I get started? 
+Jeff: where can I find documentation? 
+Philipp: ok, ok you can find everything here. https://huggingface.co/blog/the-partnership-amazon-sagemaker-and-hugging-face                                           
+'''
+nlp(conversation)
+```
+
+## Results
+
+| key | value |
+| --- | ----- |
+| eval_rouge1 | 42.621 |
+| eval_rouge2 | 21.9825 |
+| eval_rougeL | 33.034 |
+| eval_rougeLsum | 39.6783 |
+| test_rouge1 | 41.3174 |
+| test_rouge2 | 20.8716 |
+| test_rougeL | 32.1337 |
+| test_rougeLsum | 38.4149 |
+

all_results.json

@@ -0,0 +1,40 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 59.9829,
+    "eval_loss": 1.3891159296035767,
+    "eval_mem_cpu_alloc_delta": 78528783,
+    "eval_mem_cpu_peaked_delta": 2605953,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 980464128,
+    "eval_rouge1": 42.621,
+    "eval_rouge2": 21.9825,
+    "eval_rougeL": 33.034,
+    "eval_rougeLsum": 39.6783,
+    "eval_runtime": 29.301,
+    "eval_samples": 818,
+    "eval_samples_per_second": 27.917,
+    "init_mem_cpu_alloc_delta": 180674,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 1625362944,
+    "init_mem_gpu_peaked_delta": 0,
+    "test_gen_len": 60.0757,
+    "test_loss": 1.4224162101745605,
+    "test_mem_cpu_alloc_delta": 82666029,
+    "test_mem_cpu_peaked_delta": 2572070,
+    "test_mem_gpu_alloc_delta": 0,
+    "test_mem_gpu_peaked_delta": 1441433088,
+    "test_rouge1": 41.3174,
+    "test_rouge2": 20.8716,
+    "test_rougeL": 32.1337,
+    "test_rougeLsum": 38.4149,
+    "test_runtime": 34.32,
+    "test_samples": 819,
+    "test_samples_per_second": 23.864,
+    "train_mem_cpu_alloc_delta": 7544164,
+    "train_mem_cpu_peaked_delta": 413671172,
+    "train_mem_gpu_alloc_delta": 6524230144,
+    "train_mem_gpu_peaked_delta": 12734977024,
+    "train_runtime": 363.7124,
+    "train_samples": 14732,
+    "train_samples_per_second": 1.905
+}

checkpoint-500/config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 50264
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d163c581e7f6486c0ba6aca9ef9be464b53530dd99425929b2368b22c110bcb3
+size 3250644573

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccab95146195bc461505b4a62c73d7ed4d36a0d126fe880eb16d6c25b27754f0
+size 1625565295

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf91f1d266327835696d5fd0a7d3f49511ad7f615da29d5bfd68bb8ddf608a84
+size 559

checkpoint-500/special_tokens_map.json

@@ -0,0 +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}}

checkpoint-500/tokenizer_config.json

@@ -0,0 +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-large-cnn"}

checkpoint-500/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.1645021645021645,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3924963924963927e-05,
+      "loss": 1.2342,
+      "step": 500
+    }
+  ],
+  "max_steps": 693,
+  "num_train_epochs": 3,
+  "total_flos": 2.565976886136013e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089267ebad1d0e44144bf11503446d8f02d6ac1efd1d78d1084e457061548a66
+size 2351

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 50264
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 59.9829,
+    "eval_loss": 1.3891159296035767,
+    "eval_mem_cpu_alloc_delta": 78528783,
+    "eval_mem_cpu_peaked_delta": 2605953,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 980464128,
+    "eval_rouge1": 42.621,
+    "eval_rouge2": 21.9825,
+    "eval_rougeL": 33.034,
+    "eval_rougeLsum": 39.6783,
+    "eval_runtime": 29.301,
+    "eval_samples": 818,
+    "eval_samples_per_second": 27.917
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f453aa6edef4dba1893723b7313b57b06b60214442d308a8acc3baa9583dd7b
+size 1625565295

special_tokens_map.json

@@ -0,0 +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}}

test_results.json

@@ -0,0 +1,15 @@
+{
+    "test_gen_len": 60.0757,
+    "test_loss": 1.4224162101745605,
+    "test_mem_cpu_alloc_delta": 82666029,
+    "test_mem_cpu_peaked_delta": 2572070,
+    "test_mem_gpu_alloc_delta": 0,
+    "test_mem_gpu_peaked_delta": 1441433088,
+    "test_rouge1": 41.3174,
+    "test_rouge2": 20.8716,
+    "test_rougeL": 32.1337,
+    "test_rougeLsum": 38.4149,
+    "test_runtime": 34.32,
+    "test_samples": 819,
+    "test_samples_per_second": 23.864
+}

tokenizer_config.json

@@ -0,0 +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-large-cnn"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 180674,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 1625362944,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 7544164,
+    "train_mem_cpu_peaked_delta": 413671172,
+    "train_mem_gpu_alloc_delta": 6524230144,
+    "train_mem_gpu_peaked_delta": 12734977024,
+    "train_runtime": 363.7124,
+    "train_samples": 14732,
+    "train_samples_per_second": 1.905
+}

trainer_state.json

@@ -0,0 +1,29 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 693,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3924963924963927e-05,
+      "loss": 1.2342,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 693,
+      "total_flos": 3.5424926764630016e+16,
+      "train_runtime": 363.7124,
+      "train_samples_per_second": 1.905
+    }
+  ],
+  "max_steps": 693,
+  "num_train_epochs": 3,
+  "total_flos": 3.5424926764630016e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089267ebad1d0e44144bf11503446d8f02d6ac1efd1d78d1084e457061548a66
+size 2351