Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: safetune
+  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. -->
+
+# safetune
+
+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: 1.1197
+- Mse: 1.1197
+
+## 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    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 2.2203        | 0.05  | 50   | 1.8289          | 1.8289 |
+| 1.8997        | 0.1   | 100  | 1.7516          | 1.7516 |
+| 1.4082        | 0.15  | 150  | 1.3950          | 1.3950 |
+| 1.5899        | 0.2   | 200  | 1.9590          | 1.9590 |
+| 1.3633        | 0.25  | 250  | 1.3316          | 1.3316 |
+| 1.3758        | 0.29  | 300  | 1.2860          | 1.2860 |
+| 1.3339        | 0.34  | 350  | 1.2694          | 1.2694 |
+| 1.2831        | 0.39  | 400  | 1.3048          | 1.3048 |
+| 1.2928        | 0.44  | 450  | 1.2395          | 1.2395 |
+| 1.2506        | 0.49  | 500  | 1.4315          | 1.4315 |
+| 1.204         | 0.54  | 550  | 1.1596          | 1.1596 |
+| 1.1749        | 0.59  | 600  | 1.1995          | 1.1995 |
+| 1.134         | 0.64  | 650  | 1.3782          | 1.3782 |
+| 1.3097        | 0.69  | 700  | 1.1867          | 1.1867 |
+| 1.29          | 0.74  | 750  | 1.2024          | 1.2024 |
+| 1.1575        | 0.78  | 800  | 1.1197          | 1.1197 |
+| 1.2148        | 0.83  | 850  | 1.1944          | 1.1944 |
+| 1.1597        | 0.88  | 900  | 1.2023          | 1.2023 |
+| 1.1422        | 0.93  | 950  | 1.1546          | 1.1546 |
+| 1.0734        | 0.98  | 1000 | 1.2593          | 1.2593 |
+
+
+### 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": 1.1196767091751099,
+    "eval_mse": 1.1196766412049022,
+    "eval_runtime": 226.7848,
+    "eval_samples": 3624,
+    "eval_samples_per_second": 15.98,
+    "eval_steps_per_second": 3.995,
+    "train_loss": 1.3573072581342673,
+    "train_runtime": 8104.8878,
+    "train_samples": 32615,
+    "train_samples_per_second": 4.024,
+    "train_steps_per_second": 0.126
+}

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": 1.1196767091751099,
+    "eval_mse": 1.1196766412049022,
+    "eval_runtime": 226.7848,
+    "eval_samples": 3624,
+    "eval_samples_per_second": 15.98,
+    "eval_steps_per_second": 3.995
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e44a76c4c31d7fa6cb34832257dda071b62a784cbecbf73e35dc09979403a8
+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": 1.3573072581342673,
+    "train_runtime": 8104.8878,
+    "train_samples": 32615,
+    "train_samples_per_second": 4.024,
+    "train_steps_per_second": 0.126
+}

trainer_state.json

@@ -0,0 +1,445 @@
+{
+  "best_metric": 1.1196767091751099,
+  "best_model_checkpoint": "/data1/attanasiog/safetune/checkpoint-800",
+  "epoch": 0.9997547216090262,
+  "global_step": 1019,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 2.876,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-05,
+      "loss": 2.2203,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.828871488571167,
+      "eval_mse": 1.8288714481969155,
+      "eval_runtime": 227.9796,
+      "eval_samples_per_second": 15.896,
+      "eval_steps_per_second": 3.974,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2e-05,
+      "loss": 1.785,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 1.8997,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.751622200012207,
+      "eval_mse": 1.751622242974068,
+      "eval_runtime": 228.0631,
+      "eval_samples_per_second": 15.89,
+      "eval_steps_per_second": 3.973,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 1.3864,
+      "step": 125
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2e-05,
+      "loss": 1.4082,
+      "step": 150
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.395007848739624,
+      "eval_mse": 1.395007782705568,
+      "eval_runtime": 227.9405,
+      "eval_samples_per_second": 15.899,
+      "eval_steps_per_second": 3.975,
+      "step": 150
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2e-05,
+      "loss": 1.5694,
+      "step": 175
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2e-05,
+      "loss": 1.5899,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.9590266942977905,
+      "eval_mse": 1.9590266676369008,
+      "eval_runtime": 227.3633,
+      "eval_samples_per_second": 15.939,
+      "eval_steps_per_second": 3.985,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2e-05,
+      "loss": 1.4847,
+      "step": 225
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2e-05,
+      "loss": 1.3633,
+      "step": 250
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.3315744400024414,
+      "eval_mse": 1.3315745865311475,
+      "eval_runtime": 227.6165,
+      "eval_samples_per_second": 15.922,
+      "eval_steps_per_second": 3.98,
+      "step": 250
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2e-05,
+      "loss": 1.3815,
+      "step": 275
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2e-05,
+      "loss": 1.3758,
+      "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.2860150337219238,
+      "eval_mse": 1.2860150669160453,
+      "eval_runtime": 227.7122,
+      "eval_samples_per_second": 15.915,
+      "eval_steps_per_second": 3.979,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2e-05,
+      "loss": 1.224,
+      "step": 325
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2e-05,
+      "loss": 1.3339,
+      "step": 350
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 1.269413709640503,
+      "eval_mse": 1.2694137826567282,
+      "eval_runtime": 227.6275,
+      "eval_samples_per_second": 15.921,
+      "eval_steps_per_second": 3.98,
+      "step": 350
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2e-05,
+      "loss": 1.3231,
+      "step": 375
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2e-05,
+      "loss": 1.2831,
+      "step": 400
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.3048381805419922,
+      "eval_mse": 1.304838097239528,
+      "eval_runtime": 227.5334,
+      "eval_samples_per_second": 15.927,
+      "eval_steps_per_second": 3.982,
+      "step": 400
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2e-05,
+      "loss": 1.2382,
+      "step": 425
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2e-05,
+      "loss": 1.2928,
+      "step": 450
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.239485263824463,
+      "eval_mse": 1.2394852607350224,
+      "eval_runtime": 227.856,
+      "eval_samples_per_second": 15.905,
+      "eval_steps_per_second": 3.976,
+      "step": 450
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2e-05,
+      "loss": 1.1165,
+      "step": 475
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2e-05,
+      "loss": 1.2506,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.4315423965454102,
+      "eval_mse": 1.431542415078766,
+      "eval_runtime": 227.6843,
+      "eval_samples_per_second": 15.917,
+      "eval_steps_per_second": 3.979,
+      "step": 500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2e-05,
+      "loss": 1.3249,
+      "step": 525
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2e-05,
+      "loss": 1.204,
+      "step": 550
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 1.1596423387527466,
+      "eval_mse": 1.1596423544220553,
+      "eval_runtime": 228.0433,
+      "eval_samples_per_second": 15.892,
+      "eval_steps_per_second": 3.973,
+      "step": 550
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2e-05,
+      "loss": 1.1547,
+      "step": 575
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2e-05,
+      "loss": 1.1749,
+      "step": 600
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.199515461921692,
+      "eval_mse": 1.1995155261127237,
+      "eval_runtime": 227.6846,
+      "eval_samples_per_second": 15.917,
+      "eval_steps_per_second": 3.979,
+      "step": 600
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2e-05,
+      "loss": 1.1577,
+      "step": 625
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2e-05,
+      "loss": 1.134,
+      "step": 650
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.3781769275665283,
+      "eval_mse": 1.378176859542341,
+      "eval_runtime": 227.5773,
+      "eval_samples_per_second": 15.924,
+      "eval_steps_per_second": 3.981,
+      "step": 650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2e-05,
+      "loss": 1.1334,
+      "step": 675
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2e-05,
+      "loss": 1.3097,
+      "step": 700
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 1.1866751909255981,
+      "eval_mse": 1.1866752670053082,
+      "eval_runtime": 227.5406,
+      "eval_samples_per_second": 15.927,
+      "eval_steps_per_second": 3.982,
+      "step": 700
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2e-05,
+      "loss": 1.2474,
+      "step": 725
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2e-05,
+      "loss": 1.29,
+      "step": 750
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 1.2024071216583252,
+      "eval_mse": 1.2024071690881728,
+      "eval_runtime": 227.8015,
+      "eval_samples_per_second": 15.909,
+      "eval_steps_per_second": 3.977,
+      "step": 750
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2e-05,
+      "loss": 1.2337,
+      "step": 775
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2e-05,
+      "loss": 1.1575,
+      "step": 800
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.1196767091751099,
+      "eval_mse": 1.1196766412049022,
+      "eval_runtime": 227.7925,
+      "eval_samples_per_second": 15.909,
+      "eval_steps_per_second": 3.977,
+      "step": 800
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2e-05,
+      "loss": 1.2553,
+      "step": 825
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2e-05,
+      "loss": 1.2148,
+      "step": 850
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 1.1944221258163452,
+      "eval_mse": 1.1944222031625475,
+      "eval_runtime": 226.9861,
+      "eval_samples_per_second": 15.966,
+      "eval_steps_per_second": 3.991,
+      "step": 850
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2e-05,
+      "loss": 1.211,
+      "step": 875
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2e-05,
+      "loss": 1.1597,
+      "step": 900
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 1.2022933959960938,
+      "eval_mse": 1.202293462029616,
+      "eval_runtime": 227.036,
+      "eval_samples_per_second": 15.962,
+      "eval_steps_per_second": 3.991,
+      "step": 900
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2e-05,
+      "loss": 1.193,
+      "step": 925
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2e-05,
+      "loss": 1.1422,
+      "step": 950
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.1545809507369995,
+      "eval_mse": 1.1545808871136407,
+      "eval_runtime": 226.9798,
+      "eval_samples_per_second": 15.966,
+      "eval_steps_per_second": 3.992,
+      "step": 950
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2e-05,
+      "loss": 1.1564,
+      "step": 975
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2e-05,
+      "loss": 1.0734,
+      "step": 1000
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.2593152523040771,
+      "eval_mse": 1.2593151942043517,
+      "eval_runtime": 226.9727,
+      "eval_samples_per_second": 15.967,
+      "eval_steps_per_second": 3.992,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "step": 1019,
+      "total_flos": 3.038852037112627e+16,
+      "train_loss": 1.3573072581342673,
+      "train_runtime": 8104.8878,
+      "train_samples_per_second": 4.024,
+      "train_steps_per_second": 0.126
+    }
+  ],
+  "max_steps": 1019,
+  "num_train_epochs": 1,
+  "total_flos": 3.038852037112627e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac71aeaaac7d8031aa311b04bdae80b2fa469f0c37a04831b1ef207f8c45639
+size 3963