End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,14 @@
+{
+    "eval_accuracy": 0.8728476821192053,
+    "eval_accuracy_mm": 0.8697111472742066,
+    "eval_loss": 0.7486604452133179,
+    "eval_loss_mm": 0.7538695335388184,
+    "eval_runtime": 29.4914,
+    "eval_runtime_mm": 25.5655,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 332.809,
+    "eval_samples_per_second_mm": 384.581,
+    "eval_steps_per_second": 41.605,
+    "eval_steps_per_second_mm": 48.073
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./fine-tune/roberta-base/mnli/",
+  "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": 0,
+    "1": 1,
+    "2": 2
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 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": "4.20.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "eval_accuracy": 0.8728476821192053,
+    "eval_accuracy_mm": 0.8697111472742066,
+    "eval_loss": 0.7486604452133179,
+    "eval_loss_mm": 0.7538695335388184,
+    "eval_runtime": 29.4914,
+    "eval_runtime_mm": 25.5655,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 332.809,
+    "eval_samples_per_second_mm": 384.581,
+    "eval_steps_per_second": 41.605,
+    "eval_steps_per_second_mm": 48.073
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecff98a71ba79939f41ed5d37be50642ae4cafb5523f20000d5cb16be068fb3
+size 498663405

runs/Jun14_11-14-47_pikachu/events.out.tfevents.1655176635.pikachu.4076869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf3793d29e4a7d4dd70fa4e6710fc8d1a59712e692128de5c0a11af220d791b
+size 556

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": "./fine-tune/roberta-base/mnli/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f55682bda2646faee2ba7a4fd6bac0576e20f731bc97e057c6c64c2706b471a
+size 3311