Upload folder using huggingface_hub

.gitignore

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

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: deberta-v3-large-harmfulness
+  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. -->
+
+# deberta-v3-large-harmfulness
+
+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: 1.1439
+- Mse: 1.1439
+
+## 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: 4
+- 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: constant
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mse    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 2.1055        | 0.06  | 50   | 1.7626          | 1.7626 |
+| 1.6818        | 0.12  | 100  | 1.4659          | 1.4659 |
+| 1.4062        | 0.18  | 150  | 1.6323          | 1.6323 |
+| 1.4777        | 0.24  | 200  | 1.3776          | 1.3776 |
+| 1.4106        | 0.3   | 250  | 1.3044          | 1.3044 |
+| 1.2702        | 0.37  | 300  | 1.3792          | 1.3792 |
+| 1.4448        | 0.43  | 350  | 1.3048          | 1.3048 |
+| 1.3582        | 0.49  | 400  | 1.2485          | 1.2485 |
+| 1.2357        | 0.55  | 450  | 1.3709          | 1.3709 |
+| 1.1075        | 0.61  | 500  | 1.2538          | 1.2538 |
+| 1.2406        | 0.67  | 550  | 1.1996          | 1.1996 |
+| 1.2309        | 0.73  | 600  | 1.2671          | 1.2671 |
+| 1.194         | 0.79  | 650  | 1.4326          | 1.4326 |
+| 1.2135        | 0.85  | 700  | 1.1763          | 1.1763 |
+| 1.2196        | 0.91  | 750  | 1.1439          | 1.1439 |
+| 1.1983        | 0.97  | 800  | 1.1711          | 1.1711 |
+
+
+### Framework versions
+
+- Transformers 4.30.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.13.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.1438716650009155,
+    "eval_mse": 1.1438715909390142,
+    "eval_runtime": 188.9837,
+    "eval_samples": 2920,
+    "eval_samples_per_second": 15.451,
+    "eval_steps_per_second": 3.863,
+    "train_loss": 1.4025647422428107,
+    "train_runtime": 6674.4502,
+    "train_samples": 26279,
+    "train_samples_per_second": 3.937,
+    "train_steps_per_second": 0.123
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "text-classification",
+  "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_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "regression",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.1438716650009155,
+    "eval_mse": 1.1438715909390142,
+    "eval_runtime": 188.9837,
+    "eval_samples": 2920,
+    "eval_samples_per_second": 15.451,
+    "eval_steps_per_second": 3.863
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a55995538b508d371b6a0d36f0c011a9eeec83bb4cf1b9ebd967d58f65b921
+size 1740392185

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "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 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.4025647422428107,
+    "train_runtime": 6674.4502,
+    "train_samples": 26279,
+    "train_samples_per_second": 3.937,
+    "train_steps_per_second": 0.123
+}

trainer_state.json

@@ -0,0 +1,361 @@
+{
+  "best_metric": 1.1438716650009155,
+  "best_model_checkpoint": "/data1/attanasiog/safetune/models/checkpoint-750",
+  "epoch": 0.9996955859969558,
+  "global_step": 821,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 3.1406,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2e-05,
+      "loss": 2.1055,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.762616515159607,
+      "eval_mse": 1.7626165039521147,
+      "eval_runtime": 183.7464,
+      "eval_samples_per_second": 15.891,
+      "eval_steps_per_second": 3.973,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 1.7607,
+      "step": 75
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 1.6818,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4659080505371094,
+      "eval_mse": 1.4659080196895005,
+      "eval_runtime": 183.1621,
+      "eval_samples_per_second": 15.942,
+      "eval_steps_per_second": 3.986,
+      "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2e-05,
+      "loss": 1.5873,
+      "step": 125
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2e-05,
+      "loss": 1.4062,
+      "step": 150
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 1.6322834491729736,
+      "eval_mse": 1.632283383560956,
+      "eval_runtime": 183.308,
+      "eval_samples_per_second": 15.929,
+      "eval_steps_per_second": 3.982,
+      "step": 150
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2e-05,
+      "loss": 1.5638,
+      "step": 175
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2e-05,
+      "loss": 1.4777,
+      "step": 200
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 1.3775594234466553,
+      "eval_mse": 1.3775594118336603,
+      "eval_runtime": 183.7408,
+      "eval_samples_per_second": 15.892,
+      "eval_steps_per_second": 3.973,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2e-05,
+      "loss": 1.4016,
+      "step": 225
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2e-05,
+      "loss": 1.4106,
+      "step": 250
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 1.304379940032959,
+      "eval_mse": 1.3043799442360644,
+      "eval_runtime": 183.2767,
+      "eval_samples_per_second": 15.932,
+      "eval_steps_per_second": 3.983,
+      "step": 250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2e-05,
+      "loss": 1.3077,
+      "step": 275
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2e-05,
+      "loss": 1.2702,
+      "step": 300
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 1.3791648149490356,
+      "eval_mse": 1.3791648080316543,
+      "eval_runtime": 183.7482,
+      "eval_samples_per_second": 15.891,
+      "eval_steps_per_second": 3.973,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2e-05,
+      "loss": 1.3216,
+      "step": 325
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2e-05,
+      "loss": 1.4448,
+      "step": 350
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 1.3047657012939453,
+      "eval_mse": 1.3047656766562488,
+      "eval_runtime": 183.5141,
+      "eval_samples_per_second": 15.912,
+      "eval_steps_per_second": 3.978,
+      "step": 350
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2e-05,
+      "loss": 1.3344,
+      "step": 375
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2e-05,
+      "loss": 1.3582,
+      "step": 400
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.248475432395935,
+      "eval_mse": 1.248475439073647,
+      "eval_runtime": 183.4404,
+      "eval_samples_per_second": 15.918,
+      "eval_steps_per_second": 3.979,
+      "step": 400
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2e-05,
+      "loss": 1.1767,
+      "step": 425
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2e-05,
+      "loss": 1.2357,
+      "step": 450
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.3708600997924805,
+      "eval_mse": 1.3708599920592506,
+      "eval_runtime": 183.3578,
+      "eval_samples_per_second": 15.925,
+      "eval_steps_per_second": 3.981,
+      "step": 450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2e-05,
+      "loss": 1.3204,
+      "step": 475
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2e-05,
+      "loss": 1.1075,
+      "step": 500
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 1.2537685632705688,
+      "eval_mse": 1.2537685594483436,
+      "eval_runtime": 183.4476,
+      "eval_samples_per_second": 15.917,
+      "eval_steps_per_second": 3.979,
+      "step": 500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2e-05,
+      "loss": 1.4399,
+      "step": 525
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2e-05,
+      "loss": 1.2406,
+      "step": 550
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.19956636428833,
+      "eval_mse": 1.1995664079472905,
+      "eval_runtime": 183.4122,
+      "eval_samples_per_second": 15.92,
+      "eval_steps_per_second": 3.98,
+      "step": 550
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2e-05,
+      "loss": 1.1667,
+      "step": 575
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2e-05,
+      "loss": 1.2309,
+      "step": 600
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 1.2671302556991577,
+      "eval_mse": 1.2671302648346725,
+      "eval_runtime": 183.2517,
+      "eval_samples_per_second": 15.934,
+      "eval_steps_per_second": 3.984,
+      "step": 600
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2e-05,
+      "loss": 1.1541,
+      "step": 625
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2e-05,
+      "loss": 1.194,
+      "step": 650
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 1.4325885772705078,
+      "eval_mse": 1.4325886574488846,
+      "eval_runtime": 183.2552,
+      "eval_samples_per_second": 15.934,
+      "eval_steps_per_second": 3.984,
+      "step": 650
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2e-05,
+      "loss": 1.1926,
+      "step": 675
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2e-05,
+      "loss": 1.2135,
+      "step": 700
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.176251769065857,
+      "eval_mse": 1.1762518139201403,
+      "eval_runtime": 183.5032,
+      "eval_samples_per_second": 15.913,
+      "eval_steps_per_second": 3.978,
+      "step": 700
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2e-05,
+      "loss": 1.111,
+      "step": 725
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2e-05,
+      "loss": 1.2196,
+      "step": 750
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 1.1438716650009155,
+      "eval_mse": 1.1438715909390142,
+      "eval_runtime": 183.3716,
+      "eval_samples_per_second": 15.924,
+      "eval_steps_per_second": 3.981,
+      "step": 750
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2e-05,
+      "loss": 1.1891,
+      "step": 775
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2e-05,
+      "loss": 1.1983,
+      "step": 800
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 1.1710615158081055,
+      "eval_mse": 1.1710615362599224,
+      "eval_runtime": 183.5541,
+      "eval_samples_per_second": 15.908,
+      "eval_steps_per_second": 3.977,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "step": 821,
+      "total_flos": 2.448378334121165e+16,
+      "train_loss": 1.4025647422428107,
+      "train_runtime": 6674.4502,
+      "train_samples_per_second": 3.937,
+      "train_steps_per_second": 0.123
+    }
+  ],
+  "max_steps": 821,
+  "num_train_epochs": 1,
+  "total_flos": 2.448378334121165e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0852e3c764ae0e37900120f0010f656239481ac67a06ba842b587dd893bb1f2
+size 4027