Upload with huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-large_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-large_spell_5k_1_p3
+
+This model is a fine-tuned version of [model_saves/deberta-large_spell_5k_1_p2](https://huggingface.co/model_saves/deberta-large_spell_5k_1_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4427
+- Accuracy: 0.9413
+
+## 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  | 0.4156          | 0.9408   |
+| No log        | 2.0   | 536  | 0.4427          | 0.9413   |
+| No log        | 3.0   | 804  | 0.4710          | 0.9407   |
+| 0.2543        | 4.0   | 1072 | 0.5293          | 0.9397   |
+| 0.2543        | 5.0   | 1340 | 0.5923          | 0.9391   |
+
+
+### 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 +1,3 @@
+{
+  "$START": 50265
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9413231364393609,
+    "eval_loss": 0.4426611661911011,
+    "eval_runtime": 4.6524,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 941.878,
+    "eval_steps_per_second": 7.523,
+    "train_loss": 0.22194259700490468,
+    "train_runtime": 572.4463,
+    "train_samples": 34304,
+    "train_samples_per_second": 898.879,
+    "train_steps_per_second": 7.022
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9413231364393609,
+    "eval_loss": 0.4426611661911011,
+    "eval_runtime": 4.6524,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 941.878,
+    "eval_steps_per_second": 7.523
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.66, "additional_confidence": 0.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93bf09d2ea2977fe584634043662e1fe07eae1bdf40d480ce93fe4bacef5ee66
+size 1641311087

special_tokens_map.json

@@ -0,0 +1,54 @@
+{
+  "additional_special_tokens": [
+    "$START"
+  ],
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,68 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": true,
+  "add_special_tokens": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "model_saves/deberta-large_spell_5k_1_p2",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "vocab_type": "gpt2"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.22194259700490468,
+    "train_runtime": 572.4463,
+    "train_samples": 34304,
+    "train_samples_per_second": 898.879,
+    "train_steps_per_second": 7.022
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.9413231364393609,
+  "best_model_checkpoint": "model_saves/deberta-large_spell_5k_1_p3/checkpoint-536",
+  "epoch": 5.0,
+  "global_step": 1340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9407696866020416,
+      "eval_loss": 0.41556528210639954,
+      "eval_runtime": 4.6348,
+      "eval_samples_per_second": 945.458,
+      "eval_steps_per_second": 7.552,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9413231364393609,
+      "eval_loss": 0.4426611661911011,
+      "eval_runtime": 4.6378,
+      "eval_samples_per_second": 944.852,
+      "eval_steps_per_second": 7.547,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9406522881517012,
+      "eval_loss": 0.47103145718574524,
+      "eval_runtime": 4.6337,
+      "eval_samples_per_second": 945.689,
+      "eval_steps_per_second": 7.553,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2543,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9397242813537718,
+      "eval_loss": 0.5292877554893494,
+      "eval_runtime": 4.6416,
+      "eval_samples_per_second": 944.076,
+      "eval_steps_per_second": 7.541,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9391428795044667,
+      "eval_loss": 0.5923100709915161,
+      "eval_runtime": 4.6379,
+      "eval_samples_per_second": 944.827,
+      "eval_steps_per_second": 7.547,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "step": 1340,
+      "total_flos": 2.0108696705040384e+16,
+      "train_loss": 0.22194259700490468,
+      "train_runtime": 572.4463,
+      "train_samples_per_second": 898.879,
+      "train_steps_per_second": 7.022
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 2.0108696705040384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27386c0d2951d732827d40bbacaa46837bb98b32771debba1984ca6532f2275c
+size 3439