add model files

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: cuenb2-mnli-negnli
+  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. -->
+
+# cuenb2-mnli-negnli
+
+This model is a fine-tuned version of [randomcomb_mlm_ep5_mnli](https://huggingface.co/randomcomb_mlm_ep5_mnli) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7677
+- Accuracy: 0.8533
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.21.0.dev0
+- Pytorch 1.8.0
+- Datasets 1.18.3
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8533333539962769,
+    "eval_loss": 0.7676794528961182,
+    "eval_runtime": 1.7635,
+    "eval_samples": 300,
+    "eval_samples_per_second": 170.112,
+    "eval_steps_per_second": 21.547,
+    "train_loss": 0.3936085205078125,
+    "train_runtime": 149.7213,
+    "train_samples": 1200,
+    "train_samples_per_second": 40.074,
+    "train_steps_per_second": 5.009
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "randomcomb_mlm_ep5_mnli",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "CONTRADICTION",
+    "1": "ENTAILMENT",
+    "2": "NEUTRAL"
+  },
+  "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 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8533333539962769,
+    "eval_loss": 0.7676794528961182,
+    "eval_runtime": 1.7635,
+    "eval_samples": 300,
+    "eval_samples_per_second": 170.112,
+    "eval_steps_per_second": 21.547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9485425b070abc096224d00246a9e681cb9f938fa03bf1e71182e8aa75787b89
+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": 5.0,
+    "train_loss": 0.3936085205078125,
+    "train_runtime": 149.7213,
+    "train_samples": 1200,
+    "train_samples_per_second": 40.074,
+    "train_steps_per_second": 5.009
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.33,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.528,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 750,
+      "total_flos": 394670126592000.0,
+      "train_loss": 0.3936085205078125,
+      "train_runtime": 149.7213,
+      "train_samples_per_second": 40.074,
+      "train_steps_per_second": 5.009
+    }
+  ],
+  "max_steps": 750,
+  "num_train_epochs": 5,
+  "total_flos": 394670126592000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fbdfa7a2ecf6267bd1fd614b4ea02a69218e78b7fefec18c3a4a77e064fd8c
+size 3311