add files

README.md

@@ -0,0 +1,48 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: eval_microsoft-deberta-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. -->
+
+# eval_microsoft-deberta-large
+
+This model is a fine-tuned version of [microsoft_deberta-large_squad/checkpoint-14000](https://huggingface.co/microsoft_deberta-large_squad/checkpoint-14000) on the squad 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: 3e-05
+- train_batch_size: 12
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0.0
+
+### Framework versions
+
+- Transformers 4.14.1
+- Pytorch 1.9.0
+- Datasets 1.16.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,5 @@
+{
+    "eval_exact_match": 87.89025543992432,
+    "eval_f1": 93.8755152147345,
+    "eval_samples": 10788
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "microsoft/deberta-large",
+  "architectures": [
+    "DebertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.14.1",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,5 @@
+{
+    "eval_exact_match": 87.89025543992432,
+    "eval_f1": 93.8755152147345,
+    "eval_samples": 10788
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0183e6a88fdc9807efac1477257af57f93535ef4d9d9cf2964ae7c277ddeb9e
+size 1620825459

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "vocab_type": "gpt2", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/deberta-large", "tokenizer_class": "DebertaTokenizer"}

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.897018970189702,
+  "global_step": 14000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.932249322493225e-05,
+      "loss": 1.2027,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.86449864498645e-05,
+      "loss": 0.9342,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.7967479674796748e-05,
+      "loss": 0.8946,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.7289972899729e-05,
+      "loss": 0.8385,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.6612466124661247e-05,
+      "loss": 0.8886,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.59349593495935e-05,
+      "loss": 0.8402,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.5257452574525747e-05,
+      "loss": 0.8194,
+      "step": 3500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.4579945799457998e-05,
+      "loss": 0.8212,
+      "step": 4000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.3902439024390246e-05,
+      "loss": 0.8091,
+      "step": 4500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.3224932249322494e-05,
+      "loss": 0.8132,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.2547425474254745e-05,
+      "loss": 0.8147,
+      "step": 5500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.186991869918699e-05,
+      "loss": 0.7896,
+      "step": 6000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.119241192411924e-05,
+      "loss": 0.789,
+      "step": 6500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.051490514905149e-05,
+      "loss": 0.7633,
+      "step": 7000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.983739837398374e-05,
+      "loss": 0.7146,
+      "step": 7500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.915989159891599e-05,
+      "loss": 0.5437,
+      "step": 8000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.8482384823848237e-05,
+      "loss": 0.5602,
+      "step": 8500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 0.5229,
+      "step": 9000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.7127371273712736e-05,
+      "loss": 0.5459,
+      "step": 9500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.6449864498644987e-05,
+      "loss": 0.5575,
+      "step": 10000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.5772357723577235e-05,
+      "loss": 0.5722,
+      "step": 10500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.5094850948509487e-05,
+      "loss": 0.5476,
+      "step": 11000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.4417344173441735e-05,
+      "loss": 0.5541,
+      "step": 11500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.3739837398373984e-05,
+      "loss": 0.5298,
+      "step": 12000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.3062330623306234e-05,
+      "loss": 0.5409,
+      "step": 12500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.2384823848238483e-05,
+      "loss": 0.5411,
+      "step": 13000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1707317073170733e-05,
+      "loss": 0.5214,
+      "step": 13500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1029810298102981e-05,
+      "loss": 0.5251,
+      "step": 14000
+    }
+  ],
+  "max_steps": 22140,
+  "num_train_epochs": 3,
+  "total_flos": 1.3649092771917312e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0140c9b640ab2aabcdf79912c154a0768fa347bf89cba19df008dccf8b2bce6a
+size 2927