Upload with huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-large_spell_10k_1_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_1_p3
+
+This model is a fine-tuned version of [model_saves/roberta-large_spell_10k_1_p2](https://huggingface.co/model_saves/roberta-large_spell_10k_1_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4478
+- Accuracy: 0.9400
+
+## 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: 42
+- 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  | 0.9394   | 0.4278          |
+| No log        | 2.0   | 536  | 0.9400   | 0.4478          |
+| No log        | 3.0   | 804  | 0.9385   | 0.4739          |
+| 0.2854        | 4.0   | 1072 | 0.9386   | 0.5202          |
+| 0.2854        | 5.0   | 1340 | 0.9399   | 0.5863          |
+| 0.2854        | 6.0   | 1608 | 0.6210   | 0.9392          |
+| 0.2854        | 7.0   | 1876 | 0.6682   | 0.9385          |
+| 0.1207        | 8.0   | 2144 | 0.7322   | 0.9382          |
+
+
+### 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": 8.0,
+    "eval_accuracy": 0.9400093918760273,
+    "eval_loss": 0.44778749346733093,
+    "eval_runtime": 3.4099,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1285.092,
+    "eval_steps_per_second": 10.264,
+    "train_loss": 0.04357551994608409,
+    "train_runtime": 253.8864,
+    "train_samples": 34304,
+    "train_samples_per_second": 2026.733,
+    "train_steps_per_second": 15.834
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.9400093918760273,
+    "eval_loss": 0.44778749346733093,
+    "eval_runtime": 3.4099,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1285.092,
+    "eval_steps_per_second": 10.264
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.66, "additional_confidence": 0.34}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5688ce2cea3d71503666370cf06d6c657f804b7d98432dd3318ae923de30de4c
+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_1_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": 8.0,
+    "train_loss": 0.04357551994608409,
+    "train_runtime": 253.8864,
+    "train_samples": 34304,
+    "train_samples_per_second": 2026.733,
+    "train_steps_per_second": 15.834
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": 0.9400093918760273,
+  "best_model_checkpoint": "model_saves/roberta-large_spell_10k_1_p3/checkpoint-536",
+  "epoch": 8.0,
+  "global_step": 2144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9394000380147363,
+      "eval_loss": 0.42779237031936646,
+      "eval_runtime": 3.428,
+      "eval_samples_per_second": 1278.298,
+      "eval_steps_per_second": 10.21,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9400093918760273,
+      "eval_loss": 0.44778749346733093,
+      "eval_runtime": 3.421,
+      "eval_samples_per_second": 1280.926,
+      "eval_steps_per_second": 10.231,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9385279352407786,
+      "eval_loss": 0.47391462326049805,
+      "eval_runtime": 3.4347,
+      "eval_samples_per_second": 1275.806,
+      "eval_steps_per_second": 10.19,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2854,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9385894296671474,
+      "eval_loss": 0.5202155113220215,
+      "eval_runtime": 3.4286,
+      "eval_samples_per_second": 1278.079,
+      "eval_steps_per_second": 10.208,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9398584510113038,
+      "eval_loss": 0.586251974105835,
+      "eval_runtime": 3.4236,
+      "eval_samples_per_second": 1279.933,
+      "eval_steps_per_second": 10.223,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9392379163452186,
+      "eval_loss": 0.6210373640060425,
+      "eval_runtime": 3.4049,
+      "eval_samples_per_second": 1286.985,
+      "eval_steps_per_second": 10.279,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9384999832287928,
+      "eval_loss": 0.6681624054908752,
+      "eval_runtime": 3.4013,
+      "eval_samples_per_second": 1288.333,
+      "eval_steps_per_second": 10.29,
+      "step": 1876
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 1e-05,
+      "loss": 0.1207,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9382092823041402,
+      "eval_loss": 0.7321578860282898,
+      "eval_runtime": 3.4179,
+      "eval_samples_per_second": 1282.092,
+      "eval_steps_per_second": 10.24,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "step": 2144,
+      "total_flos": 2.819055740256256e+16,
+      "train_loss": 0.04357551994608409,
+      "train_runtime": 253.8864,
+      "train_samples_per_second": 2026.733,
+      "train_steps_per_second": 15.834
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 2.819055740256256e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb493a0bf533230f9a35b466e87c40441358871cc2f0f3f053342f74c242e88
+size 3439