Model save

README.md

@@ -0,0 +1,53 @@
+---
+base_model: gokuls/HBERTv1_L12_H768_A12_ffn_1
+tags:
+- generated_from_trainer
+model-index:
+- name: HBERTv1_48_L12_H768_A12_ffn_1_KD
+  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. -->
+
+# HBERTv1_48_L12_H768_A12_ffn_1_KD
+
+This model is a fine-tuned version of [gokuls/HBERTv1_L12_H768_A12_ffn_1](https://huggingface.co/gokuls/HBERTv1_L12_H768_A12_ffn_1) on an unknown dataset.
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 10
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10000
+- num_epochs: 100
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.14.0a0+410ce96
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "gokuls/HBERTv1_L12_H768_A12_ffn_1",
+  "activation": "relu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.05,
+  "dim": 768,
+  "dropout": 0.05,
+  "hidden_dim": 768,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "hybridbert",
+  "n_heads": 12,
+  "n_layers": 12,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.1,
+  "sinusoidal_pos_embds": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1700267479.serv-9219.1465078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5687975781f9dee79a1cdf8ba5df222f95c8e8c06a2ef37ef46fcfd02a9190
+size 4147

logs/events.out.tfevents.1700267954.serv-9219.1473212.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf972ba7cc920ae3304c054c880d533be22c97e31f0c89dafba1e7843891c0c
+size 4147

logs/events.out.tfevents.1700268483.serv-9207.684889.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849b76994e0e0448c9ff4860f02c766a7238f500af8d377e12439e05325e1689
+size 4145

logs/events.out.tfevents.1700269264.serv-9219.1486330.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78ef1b7810e470dc31924f5af4ba6010fadd9535e5e5bd08ca64d58fe88ce8a
+size 4145

logs/events.out.tfevents.1700269296.serv-9219.1487261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df0876e3103cc534e4ff18519f1f0bd50920cdff39e82ebb1408816f9c508f3
+size 4145

logs/events.out.tfevents.1700269444.serv-9219.1487974.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e23916e6f885d7492c2a2cb4194b102387487e1c259df382e1f59a301dc0afd
+size 4145

logs/events.out.tfevents.1700269538.serv-9219.1489822.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f5afb6a8aff9e5cdcc42ac682934ddd89fc0073199a6c98dc3d2798ff3536f
+size 4145

logs/events.out.tfevents.1700270101.serv-9207.687883.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885c46c2b2a59fe26f6da79120fe2097a4e2c41e50a5142e4591765e42059fd3
+size 18809

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1a70569bb7b812b0094dce584ca63d50d33d2ccc236929c9852d66de124300
+size 404832560

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70370d7daa440c99422b0538fee1cf082253f48c9d50ad78f29ca563b8a35e8f
+size 5243