Model save

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: out
+  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. -->
+
+# out
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None 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: 5e-05
+- train_batch_size: 256
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.10.1
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.116673701227048,
+    "train_runtime": 309.01,
+    "train_samples": 30000,
+    "train_samples_per_second": 291.253,
+    "train_steps_per_second": 1.146
+}

args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84681b490574eec665dd628028717bdc85fbdb7ad3d54c8ed025f6816f1b69f3
+size 5652

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "QuantizedDistilBertForQuestionAnswering"
+  ],
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "vocab_size": 30522
+}

pruning_config.json

@@ -0,0 +1,26 @@
+{
+  "begin_pruning_step": 1400,
+  "end_pruning_step": 12000,
+  "explicit_prune": {},
+  "init_strategy": "uniform",
+  "initial_step": 0,
+  "not_to_prune": [
+    "qa_outputs",
+    "pooler",
+    "teacher"
+  ],
+  "policy_begin_step": 1400,
+  "policy_end_step": 10000,
+  "prune_layer_types": {
+    "Linear": {
+      "name": "weight"
+    }
+  },
+  "pruning_fn": "unstructured_magnitude",
+  "pruning_fn_default_kwargs": {
+    "target_sparsity": 0.85
+  },
+  "pruning_frequency": 100,
+  "scheduler": "iterative",
+  "weight_sparsity_map": {}
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ef050729f0931a1ab4b251d4ccc9bd10abefc57d7de8209769201e2e17232c
+size 265832945

raw_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f0839ac6d21be64cac0d009add03e24b92d8146d213fbb1f1473a3a4c3ea9e
+size 265864653

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 +1,56 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.116673701227048,
+    "train_runtime": 309.01,
+    "train_samples": 30000,
+    "train_samples_per_second": 291.253,
+    "train_steps_per_second": 1.146
+}

trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 354,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 354,
+      "total_flos": 8819084252160000.0,
+      "train_loss": 2.116673701227048,
+      "train_runtime": 309.01,
+      "train_samples_per_second": 291.253,
+      "train_steps_per_second": 1.146
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 354,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8819084252160000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed62376ecc90c8a01bbc2f29b3d92d6ab6a87975e9b65b07bf2310214f6493ce
+size 4664