Upload 13 files

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: mit
+base_model: agentlans/deberta-v3-xsmall-zyda-2
+tags:
+- generated_from_trainer
+model-index:
+- name: deberta-v3-xsmall-zyda-2-sentiment
+  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-xsmall-zyda-2-sentiment
+
+This model is a fine-tuned version of [agentlans/deberta-v3-xsmall-zyda-2](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0493
+- Mse: 0.0493
+
+## 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: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mse    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0627        | 1.0   | 3143 | 0.0665          | 0.0665 |
+| 0.0411        | 2.0   | 6286 | 0.0493          | 0.0493 |
+| 0.0321        | 3.0   | 9429 | 0.0524          | 0.0524 |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.04927213117480278,
+    "eval_mse": 0.049272132016595305,
+    "eval_runtime": 10.4326,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 958.536,
+    "eval_steps_per_second": 119.817,
+    "total_flos": 9935679003367680.0,
+    "train_loss": 0.05866297316179509,
+    "train_runtime": 1207.603,
+    "train_samples": 201105,
+    "train_samples_per_second": 499.597,
+    "train_steps_per_second": 7.808
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "agentlans/deberta-v3-xsmall-zyda-2",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "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": "4.46.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.04927213117480278,
+    "eval_mse": 0.049272132016595305,
+    "eval_runtime": 10.4326,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 958.536,
+    "eval_steps_per_second": 119.817
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64bb0296f7b370ce35b0666cd7f26fb0bb06c64245a16e871885925e52a90f49
+size 283345892

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,62 @@
+{
+  "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]",
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9935679003367680.0,
+    "train_loss": 0.05866297316179509,
+    "train_runtime": 1207.603,
+    "train_samples": 201105,
+    "train_samples_per_second": 499.597,
+    "train_steps_per_second": 7.808
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.04927213117480278,
+  "best_model_checkpoint": "deberta-v3-xsmall-zyda-2-sentiment/checkpoint-6286",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9429,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1590836780146357,
+      "grad_norm": 1.8468247652053833,
+      "learning_rate": 4.7348605366422736e-05,
+      "loss": 0.2115,
+      "step": 500
+    },
+    {
+      "epoch": 0.3181673560292714,
+      "grad_norm": 1.7370903491973877,
+      "learning_rate": 4.4697210732845476e-05,
+      "loss": 0.101,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4772510340439071,
+      "grad_norm": 1.7206146717071533,
+      "learning_rate": 4.2045816099268216e-05,
+      "loss": 0.0846,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6363347120585428,
+      "grad_norm": 1.1373802423477173,
+      "learning_rate": 3.9394421465690956e-05,
+      "loss": 0.0748,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7954183900731785,
+      "grad_norm": 0.9603880047798157,
+      "learning_rate": 3.674302683211369e-05,
+      "loss": 0.0691,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9545020680878142,
+      "grad_norm": 1.0165342092514038,
+      "learning_rate": 3.409163219853643e-05,
+      "loss": 0.0627,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.06652908027172089,
+      "eval_mse": 0.06652908171153529,
+      "eval_runtime": 10.5244,
+      "eval_samples_per_second": 950.17,
+      "eval_steps_per_second": 118.771,
+      "step": 3143
+    },
+    {
+      "epoch": 1.1135857461024499,
+      "grad_norm": 0.9926055073738098,
+      "learning_rate": 3.144023756495917e-05,
+      "loss": 0.0522,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2726694241170855,
+      "grad_norm": 1.247205376625061,
+      "learning_rate": 2.878884293138191e-05,
+      "loss": 0.0485,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4317531021317214,
+      "grad_norm": 1.7589031457901,
+      "learning_rate": 2.6137448297804644e-05,
+      "loss": 0.0463,
+      "step": 4500
+    },
+    {
+      "epoch": 1.590836780146357,
+      "grad_norm": 0.7484694719314575,
+      "learning_rate": 2.3486053664227384e-05,
+      "loss": 0.0443,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7499204581609926,
+      "grad_norm": 1.5068027973175049,
+      "learning_rate": 2.083465903065012e-05,
+      "loss": 0.0421,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9090041361756285,
+      "grad_norm": 0.832625150680542,
+      "learning_rate": 1.818326439707286e-05,
+      "loss": 0.0411,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.04927213117480278,
+      "eval_mse": 0.049272132016595305,
+      "eval_runtime": 11.3101,
+      "eval_samples_per_second": 884.162,
+      "eval_steps_per_second": 110.52,
+      "step": 6286
+    },
+    {
+      "epoch": 2.068087814190264,
+      "grad_norm": 0.6708300709724426,
+      "learning_rate": 1.5531869763495598e-05,
+      "loss": 0.0387,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2271714922048997,
+      "grad_norm": 0.6490187644958496,
+      "learning_rate": 1.2880475129918337e-05,
+      "loss": 0.0337,
+      "step": 7000
+    },
+    {
+      "epoch": 2.3862551702195356,
+      "grad_norm": 0.7127770185470581,
+      "learning_rate": 1.0229080496341075e-05,
+      "loss": 0.0324,
+      "step": 7500
+    },
+    {
+      "epoch": 2.545338848234171,
+      "grad_norm": 0.6604452133178711,
+      "learning_rate": 7.5776858627638146e-06,
+      "loss": 0.0326,
+      "step": 8000
+    },
+    {
+      "epoch": 2.704422526248807,
+      "grad_norm": 0.5042712092399597,
+      "learning_rate": 4.926291229186552e-06,
+      "loss": 0.0323,
+      "step": 8500
+    },
+    {
+      "epoch": 2.8635062042634427,
+      "grad_norm": 0.573316752910614,
+      "learning_rate": 2.2748965956092908e-06,
+      "loss": 0.0321,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.05235280096530914,
+      "eval_mse": 0.05235280389813637,
+      "eval_runtime": 10.3984,
+      "eval_samples_per_second": 961.689,
+      "eval_steps_per_second": 120.211,
+      "step": 9429
+    },
+    {
+      "epoch": 3.0,
+      "step": 9429,
+      "total_flos": 9935679003367680.0,
+      "train_loss": 0.05866297316179509,
+      "train_runtime": 1207.603,
+      "train_samples_per_second": 499.597,
+      "train_steps_per_second": 7.808
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9429,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9935679003367680.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3b335a637ee1abd3e5da0d4f9e8ac74f5cd424a9c44c9efbe15e454133d934
+size 5368