Upload with huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-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. -->
+
+# roberta-large_spell_10k_2_p3
+
+This model is a fine-tuned version of [model_saves/roberta-large_spell_10k_2_p2](https://huggingface.co/model_saves/roberta-large_spell_10k_2_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4256
+- Accuracy: 0.9409
+
+## 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  | 0.9409   | 0.4256          |
+| No log        | 2.0   | 536  | 0.9408   | 0.4378          |
+| No log        | 3.0   | 804  | 0.9401   | 0.4636          |
+| 0.3125        | 4.0   | 1072 | 0.9389   | 0.4978          |
+| 0.3125        | 5.0   | 1340 | 0.5485   | 0.9397          |
+| 0.3125        | 6.0   | 1608 | 0.5955   | 0.9387          |
+| 0.3125        | 7.0   | 1876 | 0.6463   | 0.9379          |
+
+
+### 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": 0.9409150370643679,
+    "eval_loss": 0.42563650012016296,
+    "eval_runtime": 3.4,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1288.831,
+    "eval_steps_per_second": 10.294,
+    "train_loss": 0.06808348861076176,
+    "train_runtime": 256.0914,
+    "train_samples": 34304,
+    "train_samples_per_second": 2009.283,
+    "train_steps_per_second": 15.698
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.9409150370643679,
+    "eval_loss": 0.42563650012016296,
+    "eval_runtime": 3.4,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1288.831,
+    "eval_steps_per_second": 10.294
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.54, "additional_confidence": 0.16}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a74a25fc68e651994f107ecf42262deb3b03b6700f7f0c2ae3d32cdead071b
+size 1462598889

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_10k_2_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": 7.0,
+    "train_loss": 0.06808348861076176,
+    "train_runtime": 256.0914,
+    "train_samples": 34304,
+    "train_samples_per_second": 2009.283,
+    "train_steps_per_second": 15.698
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.9409150370643679,
+  "best_model_checkpoint": "model_saves/roberta-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": 0.9409150370643679,
+      "eval_loss": 0.42563650012016296,
+      "eval_runtime": 3.411,
+      "eval_samples_per_second": 1284.661,
+      "eval_steps_per_second": 10.261,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9408311810284105,
+      "eval_loss": 0.4377546012401581,
+      "eval_runtime": 3.4157,
+      "eval_samples_per_second": 1282.899,
+      "eval_steps_per_second": 10.247,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9401267903263677,
+      "eval_loss": 0.4636364281177521,
+      "eval_runtime": 3.4059,
+      "eval_samples_per_second": 1286.575,
+      "eval_steps_per_second": 10.276,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.3125,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9389360346157717,
+      "eval_loss": 0.49778589606285095,
+      "eval_runtime": 3.4265,
+      "eval_samples_per_second": 1278.858,
+      "eval_steps_per_second": 10.215,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9396851485369917,
+      "eval_loss": 0.5484528541564941,
+      "eval_runtime": 3.4032,
+      "eval_samples_per_second": 1287.628,
+      "eval_steps_per_second": 10.285,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.938678876105502,
+      "eval_loss": 0.5954769253730774,
+      "eval_runtime": 3.4051,
+      "eval_samples_per_second": 1286.887,
+      "eval_steps_per_second": 10.279,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9379018101722962,
+      "eval_loss": 0.6462979316711426,
+      "eval_runtime": 3.4098,
+      "eval_samples_per_second": 1285.133,
+      "eval_steps_per_second": 10.265,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "step": 1876,
+      "total_flos": 2.4688986932903936e+16,
+      "train_loss": 0.06808348861076176,
+      "train_runtime": 256.0914,
+      "train_samples_per_second": 2009.283,
+      "train_steps_per_second": 15.698
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 2.4688986932903936e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c382bed615dc93b15b836eb9618971e7f7084bbda55f39dee6bffd4c9858887
+size 3439