update model

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: 0314_i6dh_mobilebert_int8vs_lr7e-05
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# 0314_i6dh_mobilebert_int8vs_lr7e-05
+
+This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v1](https://huggingface.co/csarron/mobilebert-uncased-squad-v1) on the squad dataset.
+
+The model has 12 blocks, and is quantized. The embeddings are also quantized.
+
+```json
+    {
+      "epoch": 15.0,
+      "eval_exact_match": 83.68968779564806,
+      "eval_f1": 90.37926101768134,
+      "step": 41500
+    }
+  ```
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 7e-05
+- train_batch_size: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- num_epochs: 15.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 1.13.1+cu116
+- Datasets 2.8.0
+- Tokenizers 0.13.2

mobilebert-base-qat-vs.json

@@ -0,0 +1,29 @@
+{
+    "algorithm": "quantization",
+    "preset": "mixed",
+    "overflow_fix": "disable",
+    "initializer": {
+        "range": {
+            "num_init_samples": 128,
+            "type": "percentile",
+            "params": {
+                "min_percentile": 0.01,
+                "max_percentile": 99.99
+            }
+        },
+        "batchnorm_adaptation": {
+            "num_bn_adaptation_samples": 16
+        }
+    },
+    "scope_overrides": {
+        "activations": {
+            "{re}.*matmul_0": {
+                "mode": "symmetric"
+            }
+        }
+    },
+    "ignored_scopes": [
+        "{re}.*__add___[0-1]",
+        "{re}.*__truediv__*",
+    ],
+}

openvino_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57e41a489719ef6d7699ecc9cf7c13746c86bce7fab55df530046324d4a886a
-size 14913176
+oid sha256:6672e949ad1cdcf3e17f101ed252e6f47197b2ecb1b9f642c3e7ce5d17f9a792
+size 14913204

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d24bb9b436cbacc94e1dd6fe398005dcb36756c0affc935b1f0ed715be7dbb7
+oid sha256:9437ce84764871c8d1474484ecd1583954f64a38986ce3f35336e3790ffbd885
 size 59190159