Upload with huggingface_hub

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+predict_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,53 @@
 ---
-license: unknown
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- cuad
+model-index:
+- name: electra-large
+  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. -->
+
+# electra-large
+
+This model is a fine-tuned version of [google/electra-large-discriminator](https://huggingface.co/google/electra-large-discriminator) on the cuad dataset.
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.4
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 6.0,
+    "predict_samples": 200910,
+    "test_HasAns_exact": 73.47266881028939,
+    "test_HasAns_f1": 84.84782944132844,
+    "test_HasAns_total": 1244,
+    "test_NoAns_exact": 77.19537100068074,
+    "test_NoAns_f1": 77.19537100068074,
+    "test_NoAns_total": 2938,
+    "test_best_exact": 76.42276422764228,
+    "test_best_exact_thresh": 0.0,
+    "test_best_f1": 79.78743515239424,
+    "test_best_f1_thresh": 0.0,
+    "test_exact": 76.0879961740794,
+    "test_f1": 79.4717120576309,
+    "test_runtime": 4793.2495,
+    "test_samples_per_second": 41.915,
+    "test_steps_per_second": 1.31,
+    "test_total": 4182,
+    "train_loss": 0.6195740632728837,
+    "train_runtime": 17430.5797,
+    "train_samples": 38499,
+    "train_samples_per_second": 13.252,
+    "train_steps_per_second": 1.657
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "google/electra-large-discriminator",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d50b495008e7b39dcd181811de67446208cf53004cf12287c97082c9fefa6bd
+size 45512922

predict_results.json

@@ -0,0 +1,19 @@
+{
+    "predict_samples": 200910,
+    "test_HasAns_exact": 73.47266881028939,
+    "test_HasAns_f1": 84.84782944132844,
+    "test_HasAns_total": 1244,
+    "test_NoAns_exact": 77.19537100068074,
+    "test_NoAns_f1": 77.19537100068074,
+    "test_NoAns_total": 2938,
+    "test_best_exact": 76.42276422764228,
+    "test_best_exact_thresh": 0.0,
+    "test_best_f1": 79.78743515239424,
+    "test_best_f1_thresh": 0.0,
+    "test_exact": 76.0879961740794,
+    "test_f1": 79.4717120576309,
+    "test_runtime": 4793.2495,
+    "test_samples_per_second": 41.915,
+    "test_steps_per_second": 1.31,
+    "test_total": 4182
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:803eb15fb2b4e00b67a3ccf1d4a68ed4a2e18049b88f717dc7bcbb6d816ccb5e
+size 1336516717

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]",
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6195740632728837,
+    "train_runtime": 17430.5797,
+    "train_samples": 38499,
+    "train_samples_per_second": 13.252,
+    "train_steps_per_second": 1.657
+}

trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 28878,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.826857815638203e-06,
+      "loss": 2.1589,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.653715631276405e-06,
+      "loss": 1.0548,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.480573446914607e-06,
+      "loss": 0.9587,
+      "step": 1500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.30743126255281e-06,
+      "loss": 1.1204,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.13428907819101e-06,
+      "loss": 0.9001,
+      "step": 2500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.961146893829214e-06,
+      "loss": 0.8905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.788004709467416e-06,
+      "loss": 0.8545,
+      "step": 3500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.614862525105618e-06,
+      "loss": 0.8632,
+      "step": 4000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.44172034074382e-06,
+      "loss": 0.8803,
+      "step": 4500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 8.268578156382022e-06,
+      "loss": 0.839,
+      "step": 5000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.095435972020224e-06,
+      "loss": 0.6965,
+      "step": 5500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 7.922293787658426e-06,
+      "loss": 0.6787,
+      "step": 6000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 7.749151603296628e-06,
+      "loss": 0.7203,
+      "step": 6500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.57600941893483e-06,
+      "loss": 0.7132,
+      "step": 7000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 7.4028672345730324e-06,
+      "loss": 0.6652,
+      "step": 7500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.2297250502112335e-06,
+      "loss": 0.6635,
+      "step": 8000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.056582865849436e-06,
+      "loss": 0.7138,
+      "step": 8500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.883440681487638e-06,
+      "loss": 0.6751,
+      "step": 9000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.71029849712584e-06,
+      "loss": 0.6525,
+      "step": 9500
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 6.537156312764042e-06,
+      "loss": 0.5809,
+      "step": 10000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 6.364014128402245e-06,
+      "loss": 0.5739,
+      "step": 10500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 6.190871944040446e-06,
+      "loss": 0.6014,
+      "step": 11000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 6.017729759678649e-06,
+      "loss": 0.6231,
+      "step": 11500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.84458757531685e-06,
+      "loss": 0.5746,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 5.671445390955053e-06,
+      "loss": 0.5799,
+      "step": 12500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.4983032065932554e-06,
+      "loss": 0.5977,
+      "step": 13000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 5.3251610222314565e-06,
+      "loss": 0.5458,
+      "step": 13500
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.152018837869659e-06,
+      "loss": 0.6165,
+      "step": 14000
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 4.978876653507861e-06,
+      "loss": 0.5616,
+      "step": 14500
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.805734469146063e-06,
+      "loss": 0.4902,
+      "step": 15000
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 4.632592284784265e-06,
+      "loss": 0.5228,
+      "step": 15500
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 4.459450100422467e-06,
+      "loss": 0.4979,
+      "step": 16000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 4.28630791606067e-06,
+      "loss": 0.5242,
+      "step": 16500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 4.113165731698872e-06,
+      "loss": 0.505,
+      "step": 17000
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 3.940023547337074e-06,
+      "loss": 0.4984,
+      "step": 17500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 3.7668813629752753e-06,
+      "loss": 0.493,
+      "step": 18000
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.593739178613478e-06,
+      "loss": 0.5153,
+      "step": 18500
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 3.42059699425168e-06,
+      "loss": 0.5,
+      "step": 19000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 3.247454809889882e-06,
+      "loss": 0.4652,
+      "step": 19500
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 3.0743126255280843e-06,
+      "loss": 0.4498,
+      "step": 20000
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.9011704411662862e-06,
+      "loss": 0.4487,
+      "step": 20500
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 2.728028256804488e-06,
+      "loss": 0.471,
+      "step": 21000
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 2.55488607244269e-06,
+      "loss": 0.4626,
+      "step": 21500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 2.381743888080892e-06,
+      "loss": 0.4714,
+      "step": 22000
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 2.2086017037190944e-06,
+      "loss": 0.458,
+      "step": 22500
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 2.0354595193572963e-06,
+      "loss": 0.4456,
+      "step": 23000
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 1.8623173349954985e-06,
+      "loss": 0.4446,
+      "step": 23500
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 1.6891751506337006e-06,
+      "loss": 0.4782,
+      "step": 24000
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 1.5160329662719026e-06,
+      "loss": 0.4174,
+      "step": 24500
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 1.3428907819101047e-06,
+      "loss": 0.4142,
+      "step": 25000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 1.1697485975483069e-06,
+      "loss": 0.4207,
+      "step": 25500
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 9.966064131865088e-07,
+      "loss": 0.4371,
+      "step": 26000
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 8.23464228824711e-07,
+      "loss": 0.4323,
+      "step": 26500
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 6.50322044462913e-07,
+      "loss": 0.3975,
+      "step": 27000
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 4.77179860101115e-07,
+      "loss": 0.4127,
+      "step": 27500
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 3.0403767573931714e-07,
+      "loss": 0.4299,
+      "step": 28000
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 1.3089549137751924e-07,
+      "loss": 0.4015,
+      "step": 28500
+    },
+    {
+      "epoch": 6.0,
+      "step": 28878,
+      "total_flos": 2.1452574293961523e+17,
+      "train_loss": 0.6195740632728837,
+      "train_runtime": 17430.5797,
+      "train_samples_per_second": 13.252,
+      "train_steps_per_second": 1.657
+    }
+  ],
+  "max_steps": 28878,
+  "num_train_epochs": 6,
+  "total_flos": 2.1452574293961523e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af660fe06a6411360999d369f4b11c2e24e168c126479b79658ea9e753474a87
+size 3579