Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: albert/albert-base-v2
+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 [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.2715
+- eval_accuracy: 0.8925
+- eval_runtime: 44.3585
+- eval_samples_per_second: 563.589
+- eval_steps_per_second: 2.209
+- 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": 0.89252,
+    "eval_loss": 0.27154749631881714,
+    "eval_runtime": 44.3585,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 563.589,
+    "eval_steps_per_second": 2.209,
+    "train_loss": 0.17865913017936375,
+    "train_runtime": 809.0649,
+    "train_samples": 25000,
+    "train_samples_per_second": 308.999,
+    "train_steps_per_second": 9.665
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "albert/albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "finetuning_task": "text-classification",
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.84076,
+    "eval_loss": 0.3598438799381256,
+    "eval_runtime": 47.5688,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 525.554,
+    "eval_steps_per_second": 2.06
+}

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6021f8f7ab84bd43c0be2a382ed39e21f2b4fdcc2bfb2416e667f25ce4862757
+size 200128

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6021f8f7ab84bd43c0be2a382ed39e21f2b4fdcc2bfb2416e667f25ce4862757
+size 200128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988e034eca9cbad6949247ece24d157a98ad9984c2aaa81387a3bb8232a098dd
+size 200128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d9a12ee5162981368fc98cef77071a44e16ed19b3b58efbf0636b403d60cd5
+size 46753425

runs/Apr21_19-06-37_clu/events.out.tfevents.1713726476.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3695dfd634f3c66cc7e4af307d1c0936a2640d72935d1c4eef75a787fafd85b0
+size 814

runs/Mar18_17-10-35_clu/1710781866.5679219/events.out.tfevents.1710781866.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0a5e4653e9b5b0e9f9114ff296052fbf2e0857aed44389bd99c048bec951e9
+size 5639

runs/Mar18_17-10-35_clu/events.out.tfevents.1710781866.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff745329f3196826b4248078cdb7606c7076c381b5b5a53d3fc2836c93139a0
+size 9051

runs/Mar18_17-10-35_clu/events.out.tfevents.1710782695.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ada75ba0e6715f0367d77b06e10471ffd06883d8c142ca1ed8b9d2d2314f7a
+size 363

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

test_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.84076,
+    "eval_loss": 0.3598438799381256,
+    "eval_runtime": 44.4368,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 562.597,
+    "eval_steps_per_second": 2.205
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.89252,
+    "eval_loss": 0.27154749631881714,
+    "eval_runtime": 44.3585,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 563.589,
+    "eval_steps_per_second": 2.209
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.84072,
+  "best_model_checkpoint": "checkpoint/albert-base-v2/imdb_42/checkpoint-1564",
+  "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": 0.8094,
+      "eval_loss": 0.39343979954719543,
+      "eval_runtime": 19.8571,
+      "eval_samples_per_second": 1258.993,
+      "eval_steps_per_second": 4.935,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.5098,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.84072,
+      "eval_loss": 0.3598405718803406,
+      "eval_runtime": 19.9131,
+      "eval_samples_per_second": 1255.458,
+      "eval_steps_per_second": 4.921,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.3335,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.83936,
+      "eval_loss": 0.4151993691921234,
+      "eval_runtime": 19.8841,
+      "eval_samples_per_second": 1257.285,
+      "eval_steps_per_second": 4.929,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.2248,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.82468,
+      "eval_loss": 0.44072645902633667,
+      "eval_runtime": 19.8311,
+      "eval_samples_per_second": 1260.645,
+      "eval_steps_per_second": 4.942,
+      "step": 3128
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.82064,
+      "eval_loss": 0.6104266047477722,
+      "eval_runtime": 19.826,
+      "eval_samples_per_second": 1260.968,
+      "eval_steps_per_second": 4.943,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.1481,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.78312,
+      "eval_loss": 0.9157971143722534,
+      "eval_runtime": 19.8594,
+      "eval_samples_per_second": 1258.849,
+      "eval_steps_per_second": 4.935,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0904,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.81568,
+      "eval_loss": 0.8991187214851379,
+      "eval_runtime": 19.845,
+      "eval_samples_per_second": 1259.764,
+      "eval_steps_per_second": 4.938,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0532,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.82364,
+      "eval_loss": 1.0848387479782104,
+      "eval_runtime": 19.903,
+      "eval_samples_per_second": 1256.093,
+      "eval_steps_per_second": 4.924,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.026,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8226,
+      "eval_loss": 1.1122615337371826,
+      "eval_runtime": 19.8109,
+      "eval_samples_per_second": 1261.933,
+      "eval_steps_per_second": 4.947,
+      "step": 7038
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.81924,
+      "eval_loss": 1.2039557695388794,
+      "eval_runtime": 19.8508,
+      "eval_samples_per_second": 1259.396,
+      "eval_steps_per_second": 4.937,
+      "step": 7820
+    },
+    {
+      "epoch": 10.0,
+      "step": 7820,
+      "total_flos": 1493631360000000.0,
+      "train_loss": 0.17865913017936375,
+      "train_runtime": 809.0649,
+      "train_samples_per_second": 308.999,
+      "train_steps_per_second": 9.665
+    }
+  ],
+  "max_steps": 7820,
+  "num_train_epochs": 10,
+  "total_flos": 1493631360000000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2eddc05289366c5a87139ea57137ff681dec15447838a56b273b059e273576d
+size 3631