Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+base_model: FacebookAI/roberta-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 [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0110
+- eval_accuracy: 0.9985
+- eval_runtime: 53.5598
+- eval_samples_per_second: 466.768
+- eval_steps_per_second: 1.83
+- 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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.99852,
+    "eval_loss": 0.010997462086379528,
+    "eval_runtime": 53.5598,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 466.768,
+    "eval_steps_per_second": 1.83,
+    "train_loss": 0.09933292054764145,
+    "train_runtime": 786.2572,
+    "train_samples": 25000,
+    "train_samples_per_second": 317.962,
+    "train_steps_per_second": 9.946
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.90452,
+    "eval_loss": 0.5969864726066589,
+    "eval_runtime": 58.5801,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 426.766,
+    "eval_steps_per_second": 1.673
+}

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eaff8b93755060313577ea8fe208f1ab23b1d4b5cd805696bfc82f9acd968eb
+size 200128

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eaff8b93755060313577ea8fe208f1ab23b1d4b5cd805696bfc82f9acd968eb
+size 200128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f160dd906fa7e7f76652c228f3b14a569f926afae19079c8f8b058514b1911
+size 200128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc68c463572fed1e3d80d95207cef3d4bf34ac2081126230528e55268a612168
+size 498660333

runs/Apr17_12-17-05_clu/events.out.tfevents.1713356299.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659ceceacff6eaa1b2e232b979f39b12c61318664ca1c3a58d645b19fad16e26
+size 298

runs/Apr21_15-20-00_clu/events.out.tfevents.1713712904.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa54ea778593112b3a835580c9b11c348c91d97d84dbde2e6c3a47e02b367214
+size 814

runs/Apr21_16-02-15_clu/events.out.tfevents.1713715403.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6efe41cdacd466b2fcb060477fad2da955a4dd6e1932d88cbae4eea10ff918a
+size 814

runs/Mar18_08-01-48_clu/1710748936.2625425/events.out.tfevents.1710748936.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d74ec6401cb427b481e27da67a7bb81ede0fd0fc734923bdfa7590ddb2001c
+size 5631

runs/Mar18_08-01-48_clu/events.out.tfevents.1710748936.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ec6e3243e8a7f77f6cc06c6676a7f1c79e70d873de039dc5bb607da825dde3
+size 8893

runs/Mar18_08-01-48_clu/events.out.tfevents.1710749738.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7af0114695f29d96fa3eb77cda277b31e3bcc5f56ab763558d397aea9f718c
+size 363

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.90452,
+    "eval_loss": 0.5969864726066589,
+    "eval_runtime": 54.749,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 456.629,
+    "eval_steps_per_second": 1.79
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.99852,
+    "eval_loss": 0.010997462086379528,
+    "eval_runtime": 53.5598,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 466.768,
+    "eval_steps_per_second": 1.83
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.90448,
+  "best_model_checkpoint": "checkpoint/roberta-base/imdb_42/checkpoint-7820",
+  "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": 0.89504,
+      "eval_loss": 0.2561816871166229,
+      "eval_runtime": 15.2562,
+      "eval_samples_per_second": 1638.677,
+      "eval_steps_per_second": 6.424,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.31,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.88456,
+      "eval_loss": 0.27308961749076843,
+      "eval_runtime": 14.8397,
+      "eval_samples_per_second": 1684.673,
+      "eval_steps_per_second": 6.604,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.1868,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.88904,
+      "eval_loss": 0.3969782292842865,
+      "eval_runtime": 14.8251,
+      "eval_samples_per_second": 1686.329,
+      "eval_steps_per_second": 6.61,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.1164,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.89612,
+      "eval_loss": 0.41772395372390747,
+      "eval_runtime": 14.7947,
+      "eval_samples_per_second": 1689.796,
+      "eval_steps_per_second": 6.624,
+      "step": 3128
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.90036,
+      "eval_loss": 0.41006845235824585,
+      "eval_runtime": 14.7809,
+      "eval_samples_per_second": 1691.378,
+      "eval_steps_per_second": 6.63,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0645,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.90156,
+      "eval_loss": 0.4374634325504303,
+      "eval_runtime": 14.7992,
+      "eval_samples_per_second": 1689.277,
+      "eval_steps_per_second": 6.622,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.041,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.90168,
+      "eval_loss": 0.5321515202522278,
+      "eval_runtime": 14.7993,
+      "eval_samples_per_second": 1689.271,
+      "eval_steps_per_second": 6.622,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0283,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.90372,
+      "eval_loss": 0.5915437936782837,
+      "eval_runtime": 14.8252,
+      "eval_samples_per_second": 1686.323,
+      "eval_steps_per_second": 6.61,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0167,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.90312,
+      "eval_loss": 0.6018744707107544,
+      "eval_runtime": 14.825,
+      "eval_samples_per_second": 1686.339,
+      "eval_steps_per_second": 6.61,
+      "step": 7038
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.90448,
+      "eval_loss": 0.5969827175140381,
+      "eval_runtime": 14.9088,
+      "eval_samples_per_second": 1676.864,
+      "eval_steps_per_second": 6.573,
+      "step": 7820
+    },
+    {
+      "epoch": 10.0,
+      "step": 7820,
+      "total_flos": 1.644444096e+16,
+      "train_loss": 0.09933292054764145,
+      "train_runtime": 786.2572,
+      "train_samples_per_second": 317.962,
+      "train_steps_per_second": 9.946
+    }
+  ],
+  "max_steps": 7820,
+  "num_train_epochs": 10,
+  "total_flos": 1.644444096e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b37bcf2bbf5ac57bab5ceb03aa8fc57ede5ec04390d1bcdfff0bb7f50e3b5515
+size 3631