Upload with huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-large_spell_5k_5_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. -->
+
+# roberta-large_spell_5k_5_p3
+
+This model is a fine-tuned version of [model_saves/roberta-large_spell_5k_5_p2](https://huggingface.co/model_saves/roberta-large_spell_5k_5_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4416
+- Accuracy: 0.9388
+
+## 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: 82
+- 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  | 0.4416          | 0.9388   |
+| No log        | 2.0   | 536  | 0.4567          | 0.9384   |
+| No log        | 3.0   | 804  | 0.5054          | 0.9386   |
+| 0.2675        | 4.0   | 1072 | 0.5354          | 0.9385   |
+
+
+### 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": 0.9388298169702255,
+    "eval_loss": 0.44159987568855286,
+    "eval_runtime": 3.3795,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1296.66,
+    "eval_steps_per_second": 10.357,
+    "train_loss": 0.2625667621840292,
+    "train_runtime": 318.2707,
+    "train_samples": 34304,
+    "train_samples_per_second": 1616.737,
+    "train_steps_per_second": 12.631
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9388298169702255,
+    "eval_loss": 0.44159987568855286,
+    "eval_runtime": 3.3795,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1296.66,
+    "eval_steps_per_second": 10.357
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.62, "additional_confidence": 0.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b967238d8662c10605cd40eceab5eafd90a4ae18da90cb3d885067f2b1875a
+size 1442098857

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "$START"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "add_special_tokens": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "model_saves/roberta-large_spell_5k_5_p2",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.2625667621840292,
+    "train_runtime": 318.2707,
+    "train_samples": 34304,
+    "train_samples_per_second": 1616.737,
+    "train_steps_per_second": 12.631
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.9388298169702255,
+  "best_model_checkpoint": "model_saves/roberta-large_spell_5k_5_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": 0.9388298169702255,
+      "eval_loss": 0.44159987568855286,
+      "eval_runtime": 3.3578,
+      "eval_samples_per_second": 1305.032,
+      "eval_steps_per_second": 10.424,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9383825847784524,
+      "eval_loss": 0.4566632807254791,
+      "eval_runtime": 3.3614,
+      "eval_samples_per_second": 1303.619,
+      "eval_steps_per_second": 10.412,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9385894296671474,
+      "eval_loss": 0.5054126381874084,
+      "eval_runtime": 3.365,
+      "eval_samples_per_second": 1302.238,
+      "eval_steps_per_second": 10.401,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2675,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9384943928263957,
+      "eval_loss": 0.5354475378990173,
+      "eval_runtime": 3.3723,
+      "eval_samples_per_second": 1299.394,
+      "eval_steps_per_second": 10.379,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "step": 1072,
+      "total_flos": 1.38598443646976e+16,
+      "train_loss": 0.2625667621840292,
+      "train_runtime": 318.2707,
+      "train_samples_per_second": 1616.737,
+      "train_steps_per_second": 12.631
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 1.38598443646976e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656559257ede07a7d067d7c492b4a36f64d138d49ccb9e6f7184774b31d5a685
+size 3439