Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+model-index:
+- name: imdb_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. -->
+
+# imdb_42
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0095
+- eval_accuracy: 0.9987
+- eval_runtime: 48.9862
+- eval_samples_per_second: 510.348
+- eval_steps_per_second: 2.001
+- step: 0
+
+## 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: 32
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.99872,
+    "eval_loss": 0.009523958899080753,
+    "eval_runtime": 48.9862,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 510.348,
+    "eval_steps_per_second": 2.001,
+    "train_loss": 0.07955141689466394,
+    "train_runtime": 1147.935,
+    "train_samples": 25000,
+    "train_samples_per_second": 217.782,
+    "train_steps_per_second": 6.812
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "single_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.9136,
+    "eval_loss": 0.5574674010276794,
+    "eval_runtime": 52.5651,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 475.601,
+    "eval_steps_per_second": 1.864
+}

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e920968a87e67adc67049321999648e769ebf0914f219dc8461b8719228512a
+size 200128

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e920968a87e67adc67049321999648e769ebf0914f219dc8461b8719228512a
+size 200128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7694a0547d2a89c7dabee974e24cf839c71185f137f4d4135ca41d04e4c9e935
+size 200128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f4a781653f5d302ad4678666b0172ccf7aefd4083e277c7a5704019f89d71a
+size 737766955

runs/Apr17_12-36-31_clu/events.out.tfevents.1713357481.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81bc94dcc447e5d9605e8c1101549239153f8e60915b4689bbc654d8665af826
+size 298

runs/Apr21_17-15-24_clu/events.out.tfevents.1713719787.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656fc93c666503d8c418237ff88fcad26b780f6fcb302527523df8b64e53b579
+size 814

runs/Mar18_14-37-33_clu/1710772688.37095/events.out.tfevents.1710772688.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24b23853cb1521ae8f74ce0c17feb16fdd15d843b6898875f5c779138aa691e
+size 5631

runs/Mar18_14-37-33_clu/events.out.tfevents.1710772688.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3724a9aaa1b3fba795d1b81aba935f73705619908dc0c2df0b2e90bca0e649ba
+size 9023

runs/Mar18_14-37-33_clu/events.out.tfevents.1710773859.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5add8644d5e4da2c1fdcd936f1bfd6a30439d46a02e6b6979aea4b3b7605a58f
+size 363

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

test_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.9136,
+    "eval_loss": 0.5574674010276794,
+    "eval_runtime": 49.0027,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 510.175,
+    "eval_steps_per_second": 2.0
+}

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 @@
+{
+    "eval_accuracy": 0.99872,
+    "eval_loss": 0.009523958899080753,
+    "eval_runtime": 48.9862,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 510.348,
+    "eval_steps_per_second": 2.001
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.9136,
+  "best_model_checkpoint": "checkpoint/deberta-base/imdb_42/checkpoint-6256",
+  "epoch": 10.0,
+  "global_step": 7820,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.91168,
+      "eval_loss": 0.22001588344573975,
+      "eval_runtime": 22.3141,
+      "eval_samples_per_second": 1120.369,
+      "eval_steps_per_second": 4.392,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.2741,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.90984,
+      "eval_loss": 0.23234927654266357,
+      "eval_runtime": 22.2845,
+      "eval_samples_per_second": 1121.854,
+      "eval_steps_per_second": 4.398,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.1524,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.91116,
+      "eval_loss": 0.31343552470207214,
+      "eval_runtime": 22.2601,
+      "eval_samples_per_second": 1123.083,
+      "eval_steps_per_second": 4.402,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.0863,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.91352,
+      "eval_loss": 0.36432042717933655,
+      "eval_runtime": 22.1164,
+      "eval_samples_per_second": 1130.384,
+      "eval_steps_per_second": 4.431,
+      "step": 3128
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.90884,
+      "eval_loss": 0.3902149498462677,
+      "eval_runtime": 22.2414,
+      "eval_samples_per_second": 1124.03,
+      "eval_steps_per_second": 4.406,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.046,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9102,
+      "eval_loss": 0.45257332921028137,
+      "eval_runtime": 22.1568,
+      "eval_samples_per_second": 1128.324,
+      "eval_steps_per_second": 4.423,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0244,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.91224,
+      "eval_loss": 0.5029028058052063,
+      "eval_runtime": 22.1112,
+      "eval_samples_per_second": 1130.65,
+      "eval_steps_per_second": 4.432,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.019,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9136,
+      "eval_loss": 0.5574696063995361,
+      "eval_runtime": 22.1411,
+      "eval_samples_per_second": 1129.122,
+      "eval_steps_per_second": 4.426,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0114,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.91356,
+      "eval_loss": 0.5506225228309631,
+      "eval_runtime": 22.2458,
+      "eval_samples_per_second": 1123.808,
+      "eval_steps_per_second": 4.405,
+      "step": 7038
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.91312,
+      "eval_loss": 0.559421956539154,
+      "eval_runtime": 22.097,
+      "eval_samples_per_second": 1131.374,
+      "eval_steps_per_second": 4.435,
+      "step": 7820
+    },
+    {
+      "epoch": 10.0,
+      "step": 7820,
+      "total_flos": 1.6444735872e+16,
+      "train_loss": 0.07955141689466394,
+      "train_runtime": 1147.935,
+      "train_samples_per_second": 217.782,
+      "train_steps_per_second": 6.812
+    }
+  ],
+  "max_steps": 7820,
+  "num_train_epochs": 10,
+  "total_flos": 1.6444735872e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0281b25f752f418d3ef28b56395ea4c47f253624c2921ce32e22c95ed1a7acf4
+size 3631