first model version

README.md

@@ -0,0 +1,79 @@
+---
+language:
+- en
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: randomcomb_mlm_ep5_mnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8615744507729862
+---
+
+<!-- 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. -->
+
+# randomcomb_mlm_ep5_mnli
+
+This model is a fine-tuned version of [randomcomb_mlm_ep5](https://huggingface.co/randomcomb_mlm_ep5) on the GLUE MNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4416
+- Accuracy: 0.8616
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.5569        | 0.41  | 5000  | 0.4415          | 0.8273   |
+| 0.4598        | 0.81  | 10000 | 0.4234          | 0.8425   |
+| 0.3832        | 1.22  | 15000 | 0.4398          | 0.8475   |
+| 0.3314        | 1.63  | 20000 | 0.4137          | 0.8494   |
+| 0.3158        | 2.04  | 25000 | 0.4484          | 0.8527   |
+| 0.2294        | 2.44  | 30000 | 0.4471          | 0.8552   |
+| 0.2283        | 2.85  | 35000 | 0.4541          | 0.8557   |
+
+
+### Framework versions
+
+- Transformers 4.21.0.dev0
+- Pytorch 1.8.0
+- Datasets 1.18.3
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 3.0,
+    "epoch_mm": 3.0,
+    "eval_accuracy": 0.8577687213448802,
+    "eval_accuracy_mm": 0.8615744507729862,
+    "eval_loss": 0.45781588554382324,
+    "eval_loss_mm": 0.44157227873802185,
+    "eval_runtime": 64.4376,
+    "eval_runtime_mm": 64.8196,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 152.318,
+    "eval_samples_per_second_mm": 151.682,
+    "eval_steps_per_second": 9.529,
+    "eval_steps_per_second_mm": 9.488,
+    "train_loss": 0.35126533325938025,
+    "train_runtime": 16355.0125,
+    "train_samples": 392702,
+    "train_samples_per_second": 72.033,
+    "train_steps_per_second": 2.251
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "randomcomb_mlm_ep5",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 1,
+    "neutral": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "epoch_mm": 3.0,
+    "eval_accuracy": 0.8577687213448802,
+    "eval_accuracy_mm": 0.8615744507729862,
+    "eval_loss": 0.45781588554382324,
+    "eval_loss_mm": 0.44157227873802185,
+    "eval_runtime": 64.4376,
+    "eval_runtime_mm": 64.8196,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 152.318,
+    "eval_samples_per_second_mm": 151.682,
+    "eval_steps_per_second": 9.529,
+    "eval_steps_per_second_mm": 9.488
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4540b6ee84017a04850db2a4066e4785818500e812e76ce4df7cc623ceab97
+size 498668617

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "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": 3.0,
+    "train_loss": 0.35126533325938025,
+    "train_runtime": 16355.0125,
+    "train_samples": 392702,
+    "train_samples_per_second": 72.033,
+    "train_steps_per_second": 2.251
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 36816,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.592568448500652e-05,
+      "loss": 0.5569,
+      "step": 5000
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.8273051451859399,
+      "eval_loss": 0.4415350556373596,
+      "eval_runtime": 67.2256,
+      "eval_samples_per_second": 146.001,
+      "eval_steps_per_second": 9.133,
+      "step": 5000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.185136897001304e-05,
+      "loss": 0.4598,
+      "step": 10000
+    },
+    {
+      "epoch": 0.81,
+      "eval_accuracy": 0.8424859908303617,
+      "eval_loss": 0.4233930706977844,
+      "eval_runtime": 67.0843,
+      "eval_samples_per_second": 146.308,
+      "eval_steps_per_second": 9.153,
+      "step": 10000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7777053455019558e-05,
+      "loss": 0.3832,
+      "step": 15000
+    },
+    {
+      "epoch": 1.22,
+      "eval_accuracy": 0.8474783494651045,
+      "eval_loss": 0.4397834539413452,
+      "eval_runtime": 67.4964,
+      "eval_samples_per_second": 145.415,
+      "eval_steps_per_second": 9.097,
+      "step": 15000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.3702737940026075e-05,
+      "loss": 0.3314,
+      "step": 20000
+    },
+    {
+      "epoch": 1.63,
+      "eval_accuracy": 0.8494141619969434,
+      "eval_loss": 0.41370636224746704,
+      "eval_runtime": 64.9501,
+      "eval_samples_per_second": 151.116,
+      "eval_steps_per_second": 9.453,
+      "step": 20000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.628422425032594e-06,
+      "loss": 0.3158,
+      "step": 25000
+    },
+    {
+      "epoch": 2.04,
+      "eval_accuracy": 0.8526744778400408,
+      "eval_loss": 0.448415607213974,
+      "eval_runtime": 64.7745,
+      "eval_samples_per_second": 151.526,
+      "eval_steps_per_second": 9.479,
+      "step": 25000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.554106910039114e-06,
+      "loss": 0.2294,
+      "step": 30000
+    },
+    {
+      "epoch": 2.44,
+      "eval_accuracy": 0.8552215995924605,
+      "eval_loss": 0.4471375644207001,
+      "eval_runtime": 64.5567,
+      "eval_samples_per_second": 152.037,
+      "eval_steps_per_second": 9.511,
+      "step": 30000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.4797913950456324e-06,
+      "loss": 0.2283,
+      "step": 35000
+    },
+    {
+      "epoch": 2.85,
+      "eval_accuracy": 0.8557310239429444,
+      "eval_loss": 0.4541068375110626,
+      "eval_runtime": 64.9188,
+      "eval_samples_per_second": 151.189,
+      "eval_steps_per_second": 9.458,
+      "step": 35000
+    },
+    {
+      "epoch": 3.0,
+      "step": 36816,
+      "total_flos": 7.74938740264658e+16,
+      "train_loss": 0.35126533325938025,
+      "train_runtime": 16355.0125,
+      "train_samples_per_second": 72.033,
+      "train_steps_per_second": 2.251
+    }
+  ],
+  "max_steps": 36816,
+  "num_train_epochs": 3,
+  "total_flos": 7.74938740264658e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585da1d3235f77485f2ea4e9dd0a16ee3a4dd9efb0687943113aaffc9a753512
+size 3311