Upload model & training results

README.md

@@ -1,3 +1,46 @@
 ---
-license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: tim_expression_identify.2
+  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. -->
+
+# tim_expression_identify.2
+
+This model is a fine-tuned version of [/misc/projdata17/infofil/syang/work_dir/temporal/pretrain_temporal/log/time_expression/tim_expression_identify.2](https://huggingface.co//misc/projdata17/infofil/syang/work_dir/temporal/pretrain_temporal/log/time_expression/tim_expression_identify.2) on an unknown dataset.
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- Pytorch 1.12.1
+- Datasets 2.7.1.dev0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9948635162899911,
+    "eval_f1": 0.9283819628647215,
+    "eval_loss": 0.01901385374367237,
+    "eval_precision": 0.9067357512953368,
+    "eval_recall": 0.9510869565217391,
+    "eval_runtime": 1.8791,
+    "eval_samples": 112,
+    "eval_samples_per_second": 59.605,
+    "eval_steps_per_second": 7.451,
+    "predict_accuracy": 0.9436280563102001,
+    "predict_f1": 0.0,
+    "predict_loss": 0.3772517442703247,
+    "predict_precision": 0.0,
+    "predict_recall": 0.0,
+    "predict_runtime": 14.6577,
+    "predict_samples_per_second": 47.415,
+    "predict_steps_per_second": 0.205,
+    "train_loss": 0.03244630874149383,
+    "train_runtime": 120.6083,
+    "train_samples": 1007,
+    "train_samples_per_second": 25.048,
+    "train_steps_per_second": 3.134
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-TIME",
+    "1": "I-TIME",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-TIME": 0,
+    "I-TIME": 1,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9948635162899911,
+    "eval_f1": 0.9283819628647215,
+    "eval_loss": 0.01901385374367237,
+    "eval_precision": 0.9067357512953368,
+    "eval_recall": 0.9510869565217391,
+    "eval_runtime": 1.8791,
+    "eval_samples": 112,
+    "eval_samples_per_second": 59.605,
+    "eval_steps_per_second": 7.451
+}

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9436280563102001,
+    "predict_f1": 0.0,
+    "predict_loss": 0.3772517442703247,
+    "predict_precision": 0.0,
+    "predict_recall": 0.0,
+    "predict_runtime": 14.6577,
+    "predict_samples_per_second": 47.415,
+    "predict_steps_per_second": 0.205
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2fe8d376a6c22f7c59e578a9e6e540bd1e1f9a8cbecab9aaa9f60076c832b44
+size 1417392237

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": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-large",
+  "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": 0.03244630874149383,
+    "train_runtime": 120.6083,
+    "train_samples": 1007,
+    "train_samples_per_second": 25.048,
+    "train_steps_per_second": 3.134
+}