Upload with huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: electra-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. -->
+
+# electra-large_spell_10k_2_p3
+
+This model is a fine-tuned version of [model_saves/electra-large_spell_10k_2_p2](https://huggingface.co/model_saves/electra-large_spell_10k_2_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4425
+- Accuracy: 0.9397
+
+## 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  | 0.4425          | 0.9397   |
+| No log        | 2.0   | 536  | 0.4513          | 0.9394   |
+| No log        | 3.0   | 804  | 0.4718          | 0.9392   |
+| 0.3481        | 4.0   | 1072 | 0.4944          | 0.9377   |
+
+
+### 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": 30522
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9397242813537718,
+    "eval_loss": 0.44245752692222595,
+    "eval_runtime": 3.491,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1255.226,
+    "eval_steps_per_second": 10.026,
+    "train_loss": 0.34312588243342157,
+    "train_runtime": 322.8928,
+    "train_samples": 34304,
+    "train_samples_per_second": 1593.594,
+    "train_steps_per_second": 12.45
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9397242813537718,
+    "eval_loss": 0.44245752692222595,
+    "eval_runtime": 3.491,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1255.226,
+    "eval_steps_per_second": 10.026
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.58, "additional_confidence": 0.3}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8980446e5974020340add60fbd4e86b4933c099ff5d97b2e138d898df0719718
+size 1377528301

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "$START"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "add_special_tokens": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "model_saves/electra-large_spell_10k_2_p2",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.34312588243342157,
+    "train_runtime": 322.8928,
+    "train_samples": 34304,
+    "train_samples_per_second": 1593.594,
+    "train_steps_per_second": 12.45
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.9397242813537718,
+  "best_model_checkpoint": "model_saves/electra-large_spell_10k_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": 0.9397242813537718,
+      "eval_loss": 0.44245752692222595,
+      "eval_runtime": 3.4937,
+      "eval_samples_per_second": 1254.269,
+      "eval_steps_per_second": 10.018,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9393609051979561,
+      "eval_loss": 0.4512821435928345,
+      "eval_runtime": 3.4926,
+      "eval_samples_per_second": 1254.636,
+      "eval_steps_per_second": 10.021,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9392267355404242,
+      "eval_loss": 0.4718455374240875,
+      "eval_runtime": 3.5,
+      "eval_samples_per_second": 1251.986,
+      "eval_steps_per_second": 10.0,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.3481,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.937722917295587,
+      "eval_loss": 0.49437105655670166,
+      "eval_runtime": 3.4985,
+      "eval_samples_per_second": 1252.54,
+      "eval_steps_per_second": 10.004,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "step": 1072,
+      "total_flos": 1.4139683831283712e+16,
+      "train_loss": 0.34312588243342157,
+      "train_runtime": 322.8928,
+      "train_samples_per_second": 1593.594,
+      "train_steps_per_second": 12.45
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 1.4139683831283712e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fb05f9d63a30838f0f419d7da7671a24dfef70c8941b95339fbced22ee9410
+size 3439