commit from zz

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: test-mlm
+  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. -->
+
+# test-mlm
+
+This model is a fine-tuned version of [/root/autodl-tmp/nbme/deberta-v3-large](https://huggingface.co//root/autodl-tmp/nbme/deberta-v3-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5185
+- Accuracy: 0.6987
+
+## 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: 4
+- eval_batch_size: 8
+- 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 4.19.0.dev0
+- Pytorch 1.11.0
+- Datasets 2.1.0
+- Tokenizers 0.12.1

added_tokens.json

@@ -0,0 +1 @@
+{"[MASK]": 128000}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6986770866102621,
+    "eval_loss": 1.5184571743011475,
+    "eval_runtime": 50.0544,
+    "eval_samples": 794,
+    "eval_samples_per_second": 15.863,
+    "eval_steps_per_second": 1.998,
+    "perplexity": 4.565176487471998,
+    "train_loss": 1.5083582298156009,
+    "train_runtime": 7793.681,
+    "train_samples": 14828,
+    "train_samples_per_second": 5.708,
+    "train_steps_per_second": 1.427
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/root/autodl-tmp/nbme/deberta-v3-large",
+  "architectures": [
+    "NewDebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128001
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6986770866102621,
+    "eval_loss": 1.5184571743011475,
+    "eval_runtime": 50.0544,
+    "eval_samples": 794,
+    "eval_samples_per_second": 15.863,
+    "eval_steps_per_second": 1.998,
+    "perplexity": 4.565176487471998
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2f66fc7f71282ad9572e83c58abc6aa20f49951290f54bbc8c48b5b57654c7
+size 1740500457

special_tokens_map.json

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

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "vocab_type": "spm", "special_tokens_map_file": null, "name_or_path": "/root/autodl-tmp/nbme/deberta-v3-large", "sp_model_kwargs": {}, "tokenizer_class": "DebertaV2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5083582298156009,
+    "train_runtime": 7793.681,
+    "train_samples": 14828,
+    "train_samples_per_second": 5.708,
+    "train_steps_per_second": 1.427
+}

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 11121,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.100800287743908e-06,
+      "loss": 2.8188,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.201600575487818e-06,
+      "loss": 1.8053,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.3024008632317245e-06,
+      "loss": 1.5897,
+      "step": 3000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 6.403201150975632e-06,
+      "loss": 1.4814,
+      "step": 4000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.50400143871954e-06,
+      "loss": 1.3795,
+      "step": 5000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.604801726463448e-06,
+      "loss": 1.3396,
+      "step": 6000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.705602014207356e-06,
+      "loss": 1.2938,
+      "step": 7000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2.806402301951264e-06,
+      "loss": 1.2645,
+      "step": 8000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.9072025896951715e-06,
+      "loss": 1.2359,
+      "step": 9000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.0080028774390793e-06,
+      "loss": 1.2172,
+      "step": 10000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.0880316518298715e-07,
+      "loss": 1.205,
+      "step": 11000
+    },
+    {
+      "epoch": 3.0,
+      "step": 11121,
+      "total_flos": 4.147380631930061e+16,
+      "train_loss": 1.5083582298156009,
+      "train_runtime": 7793.681,
+      "train_samples_per_second": 5.708,
+      "train_steps_per_second": 1.427
+    }
+  ],
+  "max_steps": 11121,
+  "num_train_epochs": 3,
+  "total_flos": 4.147380631930061e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a21949356dc8e894e20a5e23cc4b9ad03bab37ed07c14be91035a352f0b7a0a
+size 3119