asdf

.gitattributes

@@ -25,3 +25,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,54 @@
 ---
 license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: splinter-base-squad2_3
+  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. -->
+
+# splinter-base-squad2_3
+
+This model is a fine-tuned version of [tau/splinter-base-qass](https://huggingface.co/tau/splinter-base-qass) on the squad_v2 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: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.20.0.dev0
+- Pytorch 1.11.0a0+17540c5
+- Datasets 2.2.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 1.0,
+    "eval_HasAns_exact": 78.34008097165992,
+    "eval_HasAns_f1": 84.67679499790667,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 79.47855340622371,
+    "eval_NoAns_f1": 79.47855340622371,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 78.9101322327971,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 82.07395272867763,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 78.9101322327971,
+    "eval_f1": 82.07395272867774,
+    "eval_samples": 12208,
+    "eval_total": 11873,
+    "train_loss": 1.0508381767365316,
+    "train_runtime": 1311.9498,
+    "train_samples": 132131,
+    "train_samples_per_second": 100.713,
+    "train_steps_per_second": 1.574
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "tau/splinter-base-qass",
+  "architectures": [
+    "SplinterForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initialize_new_qass": true,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "splinter",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "question_token_id": 104,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c2f8ffcdc41d518e6b87ffd4c3c38ef11ca00dd494a0ddcdceb74083801e03
+size 50101493

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 1.0,
+    "eval_HasAns_exact": 78.34008097165992,
+    "eval_HasAns_f1": 84.67679499790667,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 79.47855340622371,
+    "eval_NoAns_f1": 79.47855340622371,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 78.9101322327971,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 82.07395272867763,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 78.9101322327971,
+    "eval_f1": 82.07395272867774,
+    "eval_samples": 12208,
+    "eval_total": 11873
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a05958ffed4a3bdbad5686226b88c000ca3e20ae0ae6168340e199e34ae5808
+size 445147921

runs/Jun03_21-55-50_b6dcb14562f6/1654293371.494883/events.out.tfevents.1654293371.b6dcb14562f6.19259.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4677ee5a616a544fb2546b69dd0f57fb4c0b9d82a06abfa9acf4efd0442f20
+size 5220

runs/Jun03_21-55-50_b6dcb14562f6/events.out.tfevents.1654293371.b6dcb14562f6.19259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb30a7a226236f17365aa1a48949fbda0d8a53c96167146d28de3f771705426d
+size 6202

runs/Jun03_21-55-50_b6dcb14562f6/events.out.tfevents.1654294772.b6dcb14562f6.19259.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fb4b80eb32b6c3960099e6b2dc6d9b359540506302d3d3b024fc8b5bfd6c23
+size 785

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "[QUESTION]"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "[QUESTION]"
+  ],
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "tau/splinter-base-qass",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/.cache/huggingface/transformers/4abdf987baedc3cc34df313a86725615a89b36b3b69631703c5c99fd165fcb6b.5f8d8adb4106c43ee43d2bbbdf22053095b63cf98e866c0164335424931f338c",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "SplinterTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.0508381767365316,
+    "train_runtime": 1311.9498,
+    "train_samples": 132131,
+    "train_samples_per_second": 100.713,
+    "train_steps_per_second": 1.574
+}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 2065,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.527845036319613e-05,
+      "loss": 1.6102,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.043583535108959e-05,
+      "loss": 1.0235,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.559322033898305e-05,
+      "loss": 0.9512,
+      "step": 600
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.0750605326876516e-05,
+      "loss": 0.9026,
+      "step": 800
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.5907990314769975e-05,
+      "loss": 0.873,
+      "step": 1000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.106537530266344e-05,
+      "loss": 1.253,
+      "step": 1200
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.6222760290556903e-05,
+      "loss": 0.8331,
+      "step": 1400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.1380145278450363e-05,
+      "loss": 1.5833,
+      "step": 1600
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.537530266343826e-06,
+      "loss": 0.7863,
+      "step": 1800
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6949152542372882e-06,
+      "loss": 0.7779,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_HasAns_exact": 78.34008097165992,
+      "eval_HasAns_f1": 84.67679499790667,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 79.47855340622371,
+      "eval_NoAns_f1": 79.47855340622371,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 78.9101322327971,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 82.07395272867763,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 78.9101322327971,
+      "eval_f1": 82.07395272867774,
+      "eval_total": 11873,
+      "step": 2065
+    },
+    {
+      "epoch": 1.0,
+      "step": 2065,
+      "total_flos": 2.697374883446784e+16,
+      "train_loss": 1.0508381767365316,
+      "train_runtime": 1311.9498,
+      "train_samples_per_second": 100.713,
+      "train_steps_per_second": 1.574
+    }
+  ],
+  "max_steps": 2065,
+  "num_train_epochs": 1,
+  "total_flos": 2.697374883446784e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3e4760362e8fd809f12f5619051a2bae958d58481a2f28aec87f08c1a674e8
+size 3247