commit files to HF hub

README.md

@@ -0,0 +1,42 @@
+
+---
+language: en
+tags:
+- sagemaker
+- bart
+- summarization
+license: apache-2.0
+datasets:
+- samsum
+---
+
+## bart-base-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
+| key | value |
+| --- | ----- |
+| key | value |
+| key | value |
+
+## Usage
+```python
+from transformers import pipeline
+summarizer = pipeline("summarization", model="philschmid/bart-base-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": 1.5356481075286865,
+    "eval_mem_cpu_alloc_delta": 659047,
+    "eval_mem_cpu_peaked_delta": 18254,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 300285440,
+    "eval_runtime": 0.3116,
+    "eval_samples": 818,
+    "eval_samples_per_second": 2625.337,
+    "init_mem_cpu_alloc_delta": 180190,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 558658048,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 6658519,
+    "train_mem_cpu_peaked_delta": 642937,
+    "train_mem_gpu_alloc_delta": 2267624448,
+    "train_mem_gpu_peaked_delta": 10355728896,
+    "train_runtime": 98.4931,
+    "train_samples": 14732,
+    "train_samples_per_second": 3.533
+}

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "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
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.5356481075286865,
+    "eval_mem_cpu_alloc_delta": 659047,
+    "eval_mem_cpu_peaked_delta": 18254,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 300285440,
+    "eval_runtime": 0.3116,
+    "eval_samples": 818,
+    "eval_samples_per_second": 2625.337
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c3f3be2e895993ca702b159f601e72a41087cb39704f40b85131491ad2216f
+size 557985683

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}}

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-base"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 180190,
+    "init_mem_cpu_peaked_delta": 18282,
+    "init_mem_gpu_alloc_delta": 558658048,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 6658519,
+    "train_mem_cpu_peaked_delta": 642937,
+    "train_mem_gpu_alloc_delta": 2267624448,
+    "train_mem_gpu_peaked_delta": 10355728896,
+    "train_runtime": 98.4931,
+    "train_samples": 14732,
+    "train_samples_per_second": 3.533
+}

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": 1.486313161228288e+16,
+      "train_runtime": 98.4931,
+      "train_samples_per_second": 3.533
+    }
+  ],
+  "max_steps": 348,
+  "num_train_epochs": 3,
+  "total_flos": 1.486313161228288e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce1e4b47d7e2bf2d0c8b8757cb9b372beec5d3906ba7d3437ae751ffd3c50ab
+size 2351