commit files to HF hub

README.md

@@ -0,0 +1,96 @@
+
+---
+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 
+---
+
+## `distilbart-cnn-12-6-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)
+
+## Result
+
+### Hyperparameters
+```json
+{
+    "dataset_name": "samsum",
+    "do_eval": true,
+    "do_train": true,
+    "fp16": true,
+    "learning_rate": 5e-05,
+    "model_name_or_path": "sshleifer/distilbart-cnn-12-6",
+    "num_train_epochs": 3,
+    "output_dir": "/opt/ml/model",
+    "per_device_eval_batch_size": 8,
+    "per_device_train_batch_size": 8,
+    "seed": 7
+}
+```
+
+### Training
+
+| key | value |
+| --- | ----- |
+| epoch | 3.0 |
+| init_mem_cpu_alloc_delta | 180338 |
+| init_mem_cpu_peaked_delta | 18282 |
+| init_mem_gpu_alloc_delta | 1222242816 |
+| init_mem_gpu_peaked_delta | 0 |
+| train_mem_cpu_alloc_delta | 6971403 |
+| train_mem_cpu_peaked_delta | 640733 |
+| train_mem_gpu_alloc_delta | 4910897664 |
+| train_mem_gpu_peaked_delta | 23331969536 |
+| train_runtime | 155.2034 |
+| train_samples | 14732 |
+| train_samples_per_second | 2.242 |
+
+### Evaluation
+
+| key | value |
+| --- | ----- |
+| epoch | 3.0 |
+| eval_loss | 1.4209576845169067 |
+| eval_mem_cpu_alloc_delta | 868003 |
+| eval_mem_cpu_peaked_delta | 18250 |
+| eval_mem_gpu_alloc_delta | 0 |
+| eval_mem_gpu_peaked_delta | 328244736 |
+| eval_runtime | 0.6088 |
+| eval_samples | 818 |
+| eval_samples_per_second | 1343.647 |
+
+
+## Usage
+```python
+from transformers import pipeline
+summarizer = pipeline("summarization", model="philschmid/distilbart-cnn-12-6-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)
+```

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.4209576845169067,
+    "eval_mem_cpu_alloc_delta": 868003,
+    "eval_mem_cpu_peaked_delta": 18250,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 328244736,
+    "eval_runtime": 0.6088,
+    "eval_samples": 818,
+    "eval_samples_per_second": 1343.647,
+    "init_mem_cpu_alloc_delta": 180338,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 1222242816,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 6971403,
+    "train_mem_cpu_peaked_delta": 640733,
+    "train_mem_gpu_alloc_delta": 4910897664,
+    "train_mem_gpu_peaked_delta": 23331969536,
+    "train_runtime": 155.2034,
+    "train_samples": 14732,
+    "train_samples_per_second": 2.242
+}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "sshleifer/distilbart-cnn-12-6",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "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": 6,
+  "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,
+  "extra_pos_embeddings": 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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "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 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.4209576845169067,
+    "eval_mem_cpu_alloc_delta": 868003,
+    "eval_mem_cpu_peaked_delta": 18250,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 328244736,
+    "eval_runtime": 0.6088,
+    "eval_samples": 818,
+    "eval_samples_per_second": 1343.647
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67abec0e716c8fc11e87bb3f759ce59f2b77b7cff98d73a71a9127bf6d2825f1
+size 1222383347

special_tokens_map.json

@@ -0,0 +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

@@ -0,0 +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

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 180338,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 1222242816,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 6971403,
+    "train_mem_cpu_peaked_delta": 640733,
+    "train_mem_gpu_alloc_delta": 4910897664,
+    "train_mem_gpu_peaked_delta": 23331969536,
+    "train_runtime": 155.2034,
+    "train_samples": 14732,
+    "train_samples_per_second": 2.242
+}

trainer_state.json

@@ -0,0 +1,23 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 348,
+      "total_flos": 3.256941561040077e+16,
+      "train_runtime": 155.2034,
+      "train_samples_per_second": 2.242
+    }
+  ],
+  "max_steps": 348,
+  "num_train_epochs": 3,
+  "total_flos": 3.256941561040077e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445bcdc5aceb3f3e7eb6bf5074c748abcba6917e3b5045d97705cd824089e224
+size 2351