Upload with huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-large_spell_5k_2_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_2_p3
+
+This model is a fine-tuned version of [model_saves/deberta-large_spell_5k_2_p2](https://huggingface.co/model_saves/deberta-large_spell_5k_2_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4141
+- Accuracy: 0.9416
+
+## 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: 52
+- 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  | 0.4141          | 0.9416   |
+| No log        | 2.0   | 536  | 0.4367          | 0.9412   |
+| No log        | 3.0   | 804  | 0.4807          | 0.9400   |
+| 0.255         | 4.0   | 1072 | 0.5355          | 0.9398   |
+
+
+### 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": 4.0,
+    "eval_accuracy": 0.9415858853520276,
+    "eval_loss": 0.4140821695327759,
+    "eval_runtime": 4.6545,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 941.454,
+    "eval_steps_per_second": 7.52,
+    "train_loss": 0.2488155276028078,
+    "train_runtime": 461.8978,
+    "train_samples": 34304,
+    "train_samples_per_second": 1114.013,
+    "train_steps_per_second": 8.703
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9415858853520276,
+    "eval_loss": 0.4140821695327759,
+    "eval_runtime": 4.6545,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 941.454,
+    "eval_steps_per_second": 7.52
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.6, "additional_confidence": 0.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38688cb5791ba81c161fcc96078a25bd9040ce60d295ce2aaefed9d34447e604
+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_2_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": 4.0,
+    "train_loss": 0.2488155276028078,
+    "train_runtime": 461.8978,
+    "train_samples": 34304,
+    "train_samples_per_second": 1114.013,
+    "train_steps_per_second": 8.703
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.9415858853520276,
+  "best_model_checkpoint": "model_saves/deberta-large_spell_5k_2_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": 0.9415858853520276,
+      "eval_loss": 0.4140821695327759,
+      "eval_runtime": 4.6367,
+      "eval_samples_per_second": 945.078,
+      "eval_steps_per_second": 7.549,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9412113283914176,
+      "eval_loss": 0.43673956394195557,
+      "eval_runtime": 4.6514,
+      "eval_samples_per_second": 942.088,
+      "eval_steps_per_second": 7.525,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9400261630832187,
+      "eval_loss": 0.4806632399559021,
+      "eval_runtime": 4.6427,
+      "eval_samples_per_second": 943.853,
+      "eval_steps_per_second": 7.539,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.255,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9397745949753463,
+      "eval_loss": 0.5354779362678528,
+      "eval_runtime": 4.6445,
+      "eval_samples_per_second": 943.488,
+      "eval_steps_per_second": 7.536,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "step": 1072,
+      "total_flos": 1.6098442656874496e+16,
+      "train_loss": 0.2488155276028078,
+      "train_runtime": 461.8978,
+      "train_samples_per_second": 1114.013,
+      "train_steps_per_second": 8.703
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 1.6098442656874496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2ae009b7fe96297f6dbeab957fb318f1695d42d1b877899f15cc04d918081e
+size 3439