Upload with huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-v3-large_lemon_5k_3_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_5k_3_p3
+
+This model is a fine-tuned version of [model_saves/deberta-v3-large_lemon_5k_3_p2](https://huggingface.co/model_saves/deberta-v3-large_lemon_5k_3_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4203
+- 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: 62
+- 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  | 0.4128          | 0.9414   |
+| No log        | 2.0   | 536  | 0.4203          | 0.9416   |
+| No log        | 3.0   | 804  | 0.4517          | 0.9403   |
+| 0.2959        | 4.0   | 1072 | 0.4774          | 0.9404   |
+| 0.2959        | 5.0   | 1340 | 0.5193          | 0.9390   |
+
+
+### 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": 5.0,
+    "eval_accuracy": 0.9416026565592192,
+    "eval_loss": 0.4202573299407959,
+    "eval_runtime": 4.5706,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 958.739,
+    "eval_steps_per_second": 7.658,
+    "train_loss": 0.2665206225950327,
+    "train_runtime": 588.505,
+    "train_samples": 34304,
+    "train_samples_per_second": 874.351,
+    "train_steps_per_second": 6.831
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9416026565592192,
+    "eval_loss": 0.4202573299407959,
+    "eval_runtime": 4.5706,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 958.739,
+    "eval_steps_per_second": 7.658
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.64, "additional_confidence": 0.3}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb75d179865224c36417612be753d90def643ff7b50762f313e77c361c79113a
+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_5k_3_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": 5.0,
+    "train_loss": 0.2665206225950327,
+    "train_runtime": 588.505,
+    "train_samples": 34304,
+    "train_samples_per_second": 874.351,
+    "train_steps_per_second": 6.831
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.9416026565592192,
+  "best_model_checkpoint": "model_saves/deberta-v3-large_lemon_5k_3_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": 0.9414349444873042,
+      "eval_loss": 0.4127908945083618,
+      "eval_runtime": 4.5287,
+      "eval_samples_per_second": 967.6,
+      "eval_steps_per_second": 7.728,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9416026565592192,
+      "eval_loss": 0.4202573299407959,
+      "eval_runtime": 4.5397,
+      "eval_samples_per_second": 965.258,
+      "eval_steps_per_second": 7.71,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9402833215934883,
+      "eval_loss": 0.4516950249671936,
+      "eval_runtime": 4.5372,
+      "eval_samples_per_second": 965.786,
+      "eval_steps_per_second": 7.714,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2959,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9403615872270487,
+      "eval_loss": 0.4774470329284668,
+      "eval_runtime": 4.525,
+      "eval_samples_per_second": 968.402,
+      "eval_steps_per_second": 7.735,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9390198906517291,
+      "eval_loss": 0.5193233489990234,
+      "eval_runtime": 4.5347,
+      "eval_samples_per_second": 966.321,
+      "eval_steps_per_second": 7.718,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "step": 1340,
+      "total_flos": 1.694981597167616e+16,
+      "train_loss": 0.2665206225950327,
+      "train_runtime": 588.505,
+      "train_samples_per_second": 874.351,
+      "train_steps_per_second": 6.831
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 1.694981597167616e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d124a2218e890d0309f00e738f9676309cf55379453e4c3b7525225503652bcd
+size 3439