Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-large
+tags:
+- generated_from_trainer
+metrics:
+- pearsonr
+- spearmanr
+model-index:
+- name: enc_cross_encoder__lr_7e-6__wd_0.1__trans_False__obj_mse__tri_None__s_42
+  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. -->
+
+# enc_cross_encoder__lr_7e-6__wd_0.1__trans_False__obj_mse__tri_None__s_42
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0917
+- Mse: 0.0917
+- Pearsonr: 0.4893
+- Spearmanr: 0.4924
+
+## 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: 7e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mse    | Pearsonr | Spearmanr |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:---------:|
+| No log        | 1.0   | 354  | 0.0982          | 0.0982 | 0.3975   | 0.4064    |
+| 0.1166        | 2.0   | 709  | 0.0880          | 0.0880 | 0.4867   | 0.4889    |
+| 0.0903        | 3.0   | 1062 | 0.0917          | 0.0917 | 0.4893   | 0.4924    |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.0.1
+- Datasets 2.19.1
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.09168503433465958,
+    "eval_mse": 0.09168502688407898,
+    "eval_pearsonr": 0.48928741659848096,
+    "eval_runtime": 16.8465,
+    "eval_samples": 2834,
+    "eval_samples_per_second": 168.225,
+    "eval_spearmanr": 0.4923729823700353,
+    "eval_steps_per_second": 21.073,
+    "train_loss": 0.10231328010559082,
+    "train_runtime": 760.799,
+    "train_samples": 11342,
+    "train_samples_per_second": 44.724,
+    "train_steps_per_second": 1.396
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "CrossEncoderForClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cache_dir": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_name_or_path": "microsoft/deberta-v3-large",
+  "model_revision": "main",
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "objective": "mse",
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pooler_type": "cls",
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transform": false,
+  "transformers_version": "4.37.2",
+  "triencoder_head": "None",
+  "type_vocab_size": 0,
+  "use_auth_token": false,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.09168503433465958,
+    "eval_mse": 0.09168502688407898,
+    "eval_pearsonr": 0.48928741659848096,
+    "eval_runtime": 16.8465,
+    "eval_samples": 2834,
+    "eval_samples_per_second": 168.225,
+    "eval_spearmanr": 0.4923729823700353,
+    "eval_steps_per_second": 21.073
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f875a6a62b9880d89b1f86157a77563c13432438b480a10bb0ae72f30d6add
+size 1740302700

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.09168503433465958,
+    "eval_mse": 0.09168502688407898,
+    "eval_pearsonr": 0.48928741659848096,
+    "eval_runtime": 16.8465,
+    "eval_samples": 2834,
+    "eval_samples_per_second": 168.225,
+    "eval_spearmanr": 0.4923729823700353,
+    "eval_steps_per_second": 21.073
+}

trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9957686882933707,
+  "eval_steps": 500,
+  "global_step": 1062,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.09817185997962952,
+      "eval_mse": 0.09817185997962952,
+      "eval_pearsonr": 0.39754295469203044,
+      "eval_runtime": 16.9607,
+      "eval_samples_per_second": 167.092,
+      "eval_spearmanr": 0.40639190714439083,
+      "eval_steps_per_second": 20.931,
+      "step": 354
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.119371727748691e-06,
+      "loss": 0.1166,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.08804947137832642,
+      "eval_mse": 0.08804947882890701,
+      "eval_pearsonr": 0.48670442010425546,
+      "eval_runtime": 16.8904,
+      "eval_samples_per_second": 167.788,
+      "eval_spearmanr": 0.48893639844454545,
+      "eval_steps_per_second": 21.018,
+      "step": 709
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 4.5445026178010473e-07,
+      "loss": 0.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.09168503433465958,
+      "eval_mse": 0.09168502688407898,
+      "eval_pearsonr": 0.48928741659848096,
+      "eval_runtime": 16.7916,
+      "eval_samples_per_second": 168.774,
+      "eval_spearmanr": 0.4923729823700353,
+      "eval_steps_per_second": 21.141,
+      "step": 1062
+    },
+    {
+      "epoch": 3.0,
+      "step": 1062,
+      "total_flos": 3498948102716928.0,
+      "train_loss": 0.10231328010559082,
+      "train_runtime": 760.799,
+      "train_samples_per_second": 44.724,
+      "train_steps_per_second": 1.396
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1062,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3498948102716928.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a88a741293877e35cd713b4bc437a6b7c20ebccab68a4ec55117c1136e100f2
+size 4411