Upload with huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-v3-large_lemon-spell_5k_1_p3
+  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. -->
+
+# deberta-v3-large_lemon-spell_5k_1_p3
+
+This model is a fine-tuned version of [model_saves/deberta-v3-large_lemon-spell_5k_1_p2](https://huggingface.co/model_saves/deberta-v3-large_lemon-spell_5k_1_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4106
+- Accuracy: 0.9421
+
+## 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: 128
+- eval_batch_size: 128
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- num_epochs: 15.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 268  | 0.4106          | 0.9421   |
+| No log        | 2.0   | 536  | 0.4260          | 0.9418   |
+| No log        | 3.0   | 804  | 0.4570          | 0.9414   |
+| 0.2933        | 4.0   | 1072 | 0.4891          | 0.9402   |
+
+
+### Framework versions
+
+- Transformers 4.21.0.dev0
+- Pytorch 1.11.0+cu113
+- Datasets 2.3.2
+- Tokenizers 0.12.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "$START": 128001,
+  "[MASK]": 128000
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.942105792774964,
+    "eval_loss": 0.4105583429336548,
+    "eval_runtime": 4.5075,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 972.162,
+    "eval_steps_per_second": 7.765,
+    "train_loss": 0.28773752077301934,
+    "train_runtime": 464.8739,
+    "train_samples": 34304,
+    "train_samples_per_second": 1106.881,
+    "train_steps_per_second": 8.648
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.942105792774964,
+    "eval_loss": 0.4105583429336548,
+    "eval_runtime": 4.5075,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 972.162,
+    "eval_steps_per_second": 7.765
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.6, "additional_confidence": 0.36}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfd0192f9a9578d056dda61e253bf799fd704f050c0cf3d41939624c6ce5623
+size 1756303275

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": [
+    "$START"
+  ],
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": true,
+  "add_special_tokens": false,
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "name_or_path": "model_saves/deberta-v3-large_lemon-spell_5k_1_p2",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.28773752077301934,
+    "train_runtime": 464.8739,
+    "train_samples": 34304,
+    "train_samples_per_second": 1106.881,
+    "train_steps_per_second": 8.648
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.942105792774964,
+  "best_model_checkpoint": "model_saves/deberta-v3-large_lemon-spell_5k_1_p3/checkpoint-268",
+  "epoch": 4.0,
+  "global_step": 1072,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.942105792774964,
+      "eval_loss": 0.4105583429336548,
+      "eval_runtime": 4.5175,
+      "eval_samples_per_second": 969.997,
+      "eval_steps_per_second": 7.748,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9417703686311341,
+      "eval_loss": 0.4260367155075073,
+      "eval_runtime": 4.5375,
+      "eval_samples_per_second": 965.739,
+      "eval_steps_per_second": 7.714,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9413846308657298,
+      "eval_loss": 0.4569767713546753,
+      "eval_runtime": 4.5148,
+      "eval_samples_per_second": 970.583,
+      "eval_steps_per_second": 7.752,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2933,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9402218271671194,
+      "eval_loss": 0.48914003372192383,
+      "eval_runtime": 4.5137,
+      "eval_samples_per_second": 970.819,
+      "eval_steps_per_second": 7.754,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "step": 1072,
+      "total_flos": 1.3559663664562176e+16,
+      "train_loss": 0.28773752077301934,
+      "train_runtime": 464.8739,
+      "train_samples_per_second": 1106.881,
+      "train_steps_per_second": 8.648
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 1.3559663664562176e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49026044c22ef67ce2c73b76b26fead7263fc7c32aa5fe947949202903bfa3d6
+size 3503