Upload with huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-large_spell_10k_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_10k_2_p3
+
+This model is a fine-tuned version of [model_saves/deberta-large_spell_10k_2_p2](https://huggingface.co/model_saves/deberta-large_spell_10k_2_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4234
+- Accuracy: 0.9418
+
+## 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 | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| No log        | 1.0   | 268  | 0.9418   | 0.4234          |
+| No log        | 2.0   | 536  | 0.9414   | 0.4422          |
+| No log        | 3.0   | 804  | 0.9410   | 0.4873          |
+| 0.2514        | 4.0   | 1072 | 0.9404   | 0.5362          |
+| 0.2514        | 5.0   | 1340 | 0.5959   | 0.9400          |
+| 0.2514        | 6.0   | 1608 | 0.6462   | 0.9387          |
+| 0.2514        | 7.0   | 1876 | 0.7177   | 0.9389          |
+
+
+### 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": 7.0,
+    "eval_accuracy": 0.9417647782287369,
+    "eval_loss": 0.42341962456703186,
+    "eval_runtime": 4.7205,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 928.289,
+    "eval_steps_per_second": 7.414,
+    "train_loss": 0.03849986062121036,
+    "train_runtime": 360.0465,
+    "train_samples": 34304,
+    "train_samples_per_second": 1429.149,
+    "train_steps_per_second": 11.165
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.9417647782287369,
+    "eval_loss": 0.42341962456703186,
+    "eval_runtime": 4.7205,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 928.289,
+    "eval_steps_per_second": 7.414
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.58, "additional_confidence": 0.2}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7860faccb17c0316ac51c2e058501620b8a3f379e2c246e6b66a944295b2dd4f
+size 1661811119

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_10k_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": 7.0,
+    "train_loss": 0.03849986062121036,
+    "train_runtime": 360.0465,
+    "train_samples": 34304,
+    "train_samples_per_second": 1429.149,
+    "train_steps_per_second": 11.165
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.9417647782287369,
+  "best_model_checkpoint": "model_saves/deberta-large_spell_10k_2_p3/checkpoint-268",
+  "epoch": 7.0,
+  "global_step": 1876,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9417647782287369,
+      "eval_loss": 0.42341962456703186,
+      "eval_runtime": 4.7165,
+      "eval_samples_per_second": 929.086,
+      "eval_steps_per_second": 7.421,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9413510884513467,
+      "eval_loss": 0.4421840310096741,
+      "eval_runtime": 4.7038,
+      "eval_samples_per_second": 931.593,
+      "eval_steps_per_second": 7.441,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9410156643075168,
+      "eval_loss": 0.4872588813304901,
+      "eval_runtime": 4.7049,
+      "eval_samples_per_second": 931.375,
+      "eval_steps_per_second": 7.439,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2514,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9403727680318429,
+      "eval_loss": 0.5361831784248352,
+      "eval_runtime": 4.6987,
+      "eval_samples_per_second": 932.608,
+      "eval_steps_per_second": 7.449,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.94000380147363,
+      "eval_loss": 0.5959360003471375,
+      "eval_runtime": 4.6891,
+      "eval_samples_per_second": 934.505,
+      "eval_steps_per_second": 7.464,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9387124185198851,
+      "eval_loss": 0.6461729407310486,
+      "eval_runtime": 4.6774,
+      "eval_samples_per_second": 936.845,
+      "eval_steps_per_second": 7.483,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9388857209941972,
+      "eval_loss": 0.7177152633666992,
+      "eval_runtime": 4.6912,
+      "eval_samples_per_second": 934.082,
+      "eval_steps_per_second": 7.461,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "step": 1876,
+      "total_flos": 2.8568658875777024e+16,
+      "train_loss": 0.03849986062121036,
+      "train_runtime": 360.0465,
+      "train_samples_per_second": 1429.149,
+      "train_steps_per_second": 11.165
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 2.8568658875777024e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf0d284c51f6e63683ee3b2ecdce663c8473a55ed0d8050160a9d3235dc4aaa
+size 3439