Add model and its dependencies

.gitattributes

@@ -9,6 +9,7 @@
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- ''
+metrics:
+- accuracy
+model-index:
+- name: SEED0042
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: MNLI
+      type: ''
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8879266428935303
+---
+
+<!-- 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. -->
+
+# SEED0042
+
+This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the MNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4265
+- Accuracy: 0.8879
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: not_parallel
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3762        | 1.0   | 12272 | 0.3312          | 0.8794   |
+| 0.2542        | 2.0   | 24544 | 0.3467          | 0.8843   |
+| 0.1503        | 3.0   | 36816 | 0.4265          | 0.8879   |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.10.0+cu113
+- Datasets 2.1.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.28156463129009596,
+    "train_runtime": 4491.1198,
+    "train_samples": 392702,
+    "train_samples_per_second": 262.319,
+    "train_steps_per_second": 8.198,
+    "validation-m_accuracy": 0.8879266428935303,
+    "validation-m_loss": 0.42651689052581787,
+    "validation-m_runtime": 14.8496,
+    "validation-m_samples": 9815,
+    "validation-m_samples_per_second": 660.96,
+    "validation-m_steps_per_second": 20.674,
+    "validation-mm_accuracy": 0.8861879576891782,
+    "validation-mm_loss": 0.4235312342643738,
+    "validation-mm_runtime": 15.3329,
+    "validation-mm_samples": 9832,
+    "validation-mm_samples_per_second": 641.234,
+    "validation-mm_steps_per_second": 20.087
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "finetuning_task": "mnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d364f7a223d8531b6dc4290ff32d0bec39122ce22b8487bd5dd375e01fe3d48c
+size 438024493

run_arguments.json

@@ -0,0 +1,24 @@
+{
+    "model_name_or_path": "google/electra-base-discriminator",
+    "task_name": "mnli",
+    "output_dir": "./output/electra/mnli/0001/SEED0042/",
+    "learning_rate": 3e-05,
+    "num_train_epochs": 3,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "seed": 42,
+    "warmup_steps": 2000,
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": true,
+    "pad_to_max_length": false,
+    "max_seq_length": 128,
+    "report_to": [],
+    "save_strategy": "epoch",
+    "evaluation_strategy": "epoch",
+    "logging_steps": 2500,
+    "use_fast_tokenizer": true,
+    "group_by_length": true,
+    "save_training_dynamics": true,
+    "save_training_dynamics_after_epoch": true
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-base-discriminator", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.28156463129009596,
+    "train_runtime": 4491.1198,
+    "train_samples": 392702,
+    "train_samples_per_second": 262.319,
+    "train_steps_per_second": 8.198
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 36816,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.9569163602941176e-05,
+      "loss": 0.6153,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.741498161764706e-05,
+      "loss": 0.4236,
+      "step": 5000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.5260799632352943e-05,
+      "loss": 0.391,
+      "step": 7500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.3106617647058826e-05,
+      "loss": 0.3762,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8793683138053999,
+      "eval_loss": 0.331181138753891,
+      "eval_runtime": 14.8457,
+      "eval_samples_per_second": 661.136,
+      "eval_steps_per_second": 20.679,
+      "step": 12272
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.0952435661764706e-05,
+      "loss": 0.3551,
+      "step": 12500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.879825367647059e-05,
+      "loss": 0.2603,
+      "step": 15000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.6644071691176472e-05,
+      "loss": 0.2538,
+      "step": 17500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.4489889705882352e-05,
+      "loss": 0.2529,
+      "step": 20000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.2335707720588235e-05,
+      "loss": 0.2542,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8842587875700458,
+      "eval_loss": 0.3466881811618805,
+      "eval_runtime": 14.8408,
+      "eval_samples_per_second": 661.35,
+      "eval_steps_per_second": 20.686,
+      "step": 24544
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.0181525735294117e-05,
+      "loss": 0.2337,
+      "step": 25000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.02734375e-06,
+      "loss": 0.1582,
+      "step": 27500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.873161764705882e-06,
+      "loss": 0.1561,
+      "step": 30000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.7189797794117646e-06,
+      "loss": 0.1564,
+      "step": 32500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.5647977941176472e-06,
+      "loss": 0.1503,
+      "step": 35000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8879266428935303,
+      "eval_loss": 0.42651689052581787,
+      "eval_runtime": 14.833,
+      "eval_samples_per_second": 661.699,
+      "eval_steps_per_second": 20.697,
+      "step": 36816
+    },
+    {
+      "epoch": 3.0,
+      "step": 36816,
+      "total_flos": 2.486132475548778e+16,
+      "train_loss": 0.28156463129009596,
+      "train_runtime": 4491.1198,
+      "train_samples_per_second": 262.319,
+      "train_steps_per_second": 8.198
+    }
+  ],
+  "max_steps": 36816,
+  "num_train_epochs": 3,
+  "total_flos": 2.486132475548778e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8adcde99b618c0e55f2ec26910886c1404cd7c1eb7a866a6078447d02c9881
+size 3119

training_dynamics/epoch0_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0be2f036cbb4178513f0ff285b3f6601e7db0e7b5b8548829b1a20196f3b4e
+size 3142315

training_dynamics/epoch0_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0936c7706f091548f99c6b4389bb2cbc74dd55a84514103a226d888d281c8e
+size 4713131

training_dynamics/epoch1_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ce5f11c72d3585d24e52b785731450ab9848b24fcda9d0775ec600d9f93cef
+size 3142315

training_dynamics/epoch1_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac68bdb3ef3c05d0f7606e165086fd99053ba4b8ab2b7ff144ad04c2bf8ebe49
+size 4713131

training_dynamics/epoch2_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186fc6c92cbcc1d0b06f118a198307d147c1457cc03e7d8de98940c3392eb642
+size 3142315

training_dynamics/epoch2_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1260ca59e5e4bcdb5dceb9fc7a6b983942e6b49a245c67f9f656b85e1a8b28da
+size 4713131

training_dynamics_after_epoch/epoch0_after_epoch_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4308434961105efbd84ef75e1b6483e64780826fb3de6753ee9e0dc72b90b58
+size 3142315

training_dynamics_after_epoch/epoch0_after_epoch_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c07d675f8cd7b86bbd0f46d5c0b5c7a50c06bf5a40a087be2851557b1b7c63
+size 4713131

training_dynamics_after_epoch/epoch1_after_epoch_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d932165e8f0194d4227579002c66c3449d7b5c8ae67aff1953aa573a9e299cea
+size 3142315

training_dynamics_after_epoch/epoch1_after_epoch_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4595a928776233486bcff287852dfe8a575c3720f144dcdbde17bc7d87cc1d
+size 4713131

training_dynamics_after_epoch/epoch2_after_epoch_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0419fb999d1098411d63bafb8a49fedb7e5d9a34df569b899b06a21ed984ad5
+size 3142315

training_dynamics_after_epoch/epoch2_after_epoch_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43227d08347e8c16bc16c3f206f4ef88ca29c4de7e6dd9432e27b117236ad7cd
+size 4713131

val-mm_sals.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79162199bed87a985b277148ab7a07345f485cd475ad02248c4f673d84b63f78
+size 10068096

validation-m_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "validation-m_accuracy": 0.8879266428935303,
+    "validation-m_loss": 0.42651689052581787,
+    "validation-m_runtime": 14.8496,
+    "validation-m_samples": 9815,
+    "validation-m_samples_per_second": 660.96,
+    "validation-m_steps_per_second": 20.674
+}

validation-mm_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "validation-mm_accuracy": 0.8861879576891782,
+    "validation-mm_loss": 0.4235312342643738,
+    "validation-mm_runtime": 15.3329,
+    "validation-mm_samples": 9832,
+    "validation-mm_samples_per_second": 641.234,
+    "validation-mm_steps_per_second": 20.087
+}