commit model from SageMaker

.gitattributes

@@ -6,3 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,22 @@
+
+---
+tags:
+- sagemaker
+datasets:
+- imdb
+---
+
+## distilbert-sagemaker-1609802168
+
+Trained from SageMaker HuggingFace extension.
+
+#### Eval
+
+| key | value |
+| --- | ----- |
+| eval_loss | 0.19187863171100616 |
+| eval_accuracy | 0.9259 |
+| eval_f1 | 0.9272173656811707 |
+| eval_precision | 0.9147286821705426 |
+| eval_recall | 0.9400517825134436 |
+| epoch | 1.0 |

checkpoint-500/config.json

@@ -0,0 +1,22 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "vocab_size": 30522
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7e15c38d718f7905016fc002143d3c45bc54a46298067e449f7b658c83d0b4
+size 535705407

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0afe657365814f9efd068c8336d9834b6fcdebb99269c31a6f0d20d7e3977ecd
+size 267863191

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c224e097cae2496cbff5b97adf82e72607747b4f37635cac15ec223484cf8e
+size 559

checkpoint-500/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.639386189258312,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.639386189258312,
+      "learning_rate": 5e-05,
+      "loss": 0.36648394775390625,
+      "step": 500
+    }
+  ],
+  "max_steps": 782,
+  "num_train_epochs": 1,
+  "total_flos": 3290972651520000,
+  "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:f244a3cc12a77ba8bef12bd3f384fd1a8817271993a03d5fd7bbfc7e9a7b7b98
+size 1839

config.json

@@ -0,0 +1,22 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "vocab_size": 30522
+}

eval_results.txt

@@ -0,0 +1,6 @@
+epoch = 1.0
+eval_accuracy = 0.9259
+eval_f1 = 0.9272173656811707
+eval_loss = 0.19187863171100616
+eval_precision = 0.9147286821705426
+eval_recall = 0.9400517825134436

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cabc2a8c9cc480dc918d02de1f660f81df78a701935534b49c8bfe58f1a3ea
+size 267863191

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f244a3cc12a77ba8bef12bd3f384fd1a8817271993a03d5fd7bbfc7e9a7b7b98
+size 1839