Upload with huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-large_lemon_10k_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. -->
+
+# roberta-large_lemon_10k_3_p3
+
+This model is a fine-tuned version of [model_saves/roberta-large_lemon_10k_3_p2](https://huggingface.co/model_saves/roberta-large_lemon_10k_3_p2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4616
+- Accuracy: 0.9394
+
+## 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 | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| No log        | 1.0   | 268  | 0.9393   | 0.4460          |
+| No log        | 2.0   | 536  | 0.9394   | 0.4616          |
+| No log        | 3.0   | 804  | 0.9382   | 0.5016          |
+| 0.2628        | 4.0   | 1072 | 0.9389   | 0.5514          |
+| 0.2628        | 5.0   | 1340 | 0.9377   | 0.6032          |
+| 0.2628        | 6.0   | 1608 | 0.6419   | 0.9375          |
+| 0.2628        | 7.0   | 1876 | 0.7208   | 0.9377          |
+| 0.1093        | 8.0   | 2144 | 0.7791   | 0.9376          |
+
+
+### 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": 0.9394112188195306,
+    "eval_loss": 0.46163710951805115,
+    "eval_runtime": 3.4597,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1266.598,
+    "eval_steps_per_second": 10.117,
+    "train_loss": 0.039562054534456624,
+    "train_runtime": 261.1202,
+    "train_samples": 34304,
+    "train_samples_per_second": 1970.587,
+    "train_steps_per_second": 15.395
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.9394112188195306,
+    "eval_loss": 0.46163710951805115,
+    "eval_runtime": 3.4597,
+    "eval_samples": 4382,
+    "eval_samples_per_second": 1266.598,
+    "eval_steps_per_second": 10.117
+}

inference_tweak_params.json

@@ -0,0 +1 @@
+{"min_error_probability": 0.72, "additional_confidence": 0.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963c1a6c40c2dd20028ee184a14d5398820339d2e38eb844866d69058d17ea6f
+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_lemon_10k_3_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": 0.039562054534456624,
+    "train_runtime": 261.1202,
+    "train_samples": 34304,
+    "train_samples_per_second": 1970.587,
+    "train_steps_per_second": 15.395
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": 0.9394112188195306,
+  "best_model_checkpoint": "model_saves/roberta-large_lemon_10k_3_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": 0.9393497243931618,
+      "eval_loss": 0.4459913671016693,
+      "eval_runtime": 3.4398,
+      "eval_samples_per_second": 1273.909,
+      "eval_steps_per_second": 10.175,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9394112188195306,
+      "eval_loss": 0.46163710951805115,
+      "eval_runtime": 3.4301,
+      "eval_samples_per_second": 1277.515,
+      "eval_steps_per_second": 10.204,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.938237234316126,
+      "eval_loss": 0.5016078352928162,
+      "eval_runtime": 3.4314,
+      "eval_samples_per_second": 1277.037,
+      "eval_steps_per_second": 10.2,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1e-05,
+      "loss": 0.2628,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9388969017989915,
+      "eval_loss": 0.5514333248138428,
+      "eval_runtime": 4.6434,
+      "eval_samples_per_second": 943.704,
+      "eval_steps_per_second": 7.538,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9377396885027784,
+      "eval_loss": 0.6031810641288757,
+      "eval_runtime": 3.437,
+      "eval_samples_per_second": 1274.931,
+      "eval_steps_per_second": 10.183,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9375440244188776,
+      "eval_loss": 0.6418653130531311,
+      "eval_runtime": 3.5192,
+      "eval_samples_per_second": 1245.154,
+      "eval_steps_per_second": 9.945,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9377396885027784,
+      "eval_loss": 0.7208025455474854,
+      "eval_runtime": 3.4571,
+      "eval_samples_per_second": 1267.546,
+      "eval_steps_per_second": 10.124,
+      "step": 1876
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 1e-05,
+      "loss": 0.1093,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9376390612596295,
+      "eval_loss": 0.7791202068328857,
+      "eval_runtime": 3.4736,
+      "eval_samples_per_second": 1261.504,
+      "eval_steps_per_second": 10.076,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "step": 2144,
+      "total_flos": 2.8204045344702464e+16,
+      "train_loss": 0.039562054534456624,
+      "train_runtime": 261.1202,
+      "train_samples_per_second": 1970.587,
+      "train_steps_per_second": 15.395
+    }
+  ],
+  "max_steps": 4020,
+  "num_train_epochs": 15,
+  "total_flos": 2.8204045344702464e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccec45cc27155e48ace2512bd065291b344f3081f3d2740d61556725a66ec249
+size 3439