add files

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: albert-large-v2_squad
+  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. -->
+
+# albert-large-v2_squad
+
+This model is a fine-tuned version of [albert-large-v2](https://huggingface.co/albert-large-v2) 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: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.14.1
+- Pytorch 1.9.0
+- Datasets 1.16.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 84.80605487228004,
+    "eval_f1": 91.80638438705844,
+    "eval_samples": 10808,
+    "train_loss": 0.7116935651942137,
+    "train_runtime": 6289.4873,
+    "train_samples": 88638,
+    "train_samples_per_second": 42.279,
+    "train_steps_per_second": 2.643
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "albert-large-v2",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "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,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 16,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.14.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 84.80605487228004,
+    "eval_f1": 91.80638438705844,
+    "eval_samples": 10808
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d3d9fb6f230a0ec03ee2c7e0ed21ab15f72d2f085a5c330a8668850b34163a
+size 66559895

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-large-v2", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7116935651942137,
+    "train_runtime": 6289.4873,
+    "train_samples": 88638,
+    "train_samples_per_second": 42.279,
+    "train_steps_per_second": 2.643
+}

trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 16620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.909747292418773e-05,
+      "loss": 1.4778,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.819494584837545e-05,
+      "loss": 1.0642,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.729241877256318e-05,
+      "loss": 1.0343,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.6389891696750903e-05,
+      "loss": 0.9568,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.548736462093863e-05,
+      "loss": 0.9389,
+      "step": 2500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.4584837545126353e-05,
+      "loss": 0.9047,
+      "step": 3000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.368231046931408e-05,
+      "loss": 0.9038,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.2779783393501805e-05,
+      "loss": 0.8988,
+      "step": 4000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1877256317689534e-05,
+      "loss": 0.8782,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0974729241877255e-05,
+      "loss": 0.8583,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.0072202166064983e-05,
+      "loss": 0.8542,
+      "step": 5500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.9169675090252708e-05,
+      "loss": 0.7334,
+      "step": 6000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.8267148014440436e-05,
+      "loss": 0.6949,
+      "step": 6500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7364620938628157e-05,
+      "loss": 0.678,
+      "step": 7000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.6462093862815885e-05,
+      "loss": 0.6878,
+      "step": 7500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.555956678700361e-05,
+      "loss": 0.6572,
+      "step": 8000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.4657039711191336e-05,
+      "loss": 0.6853,
+      "step": 8500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.3754512635379063e-05,
+      "loss": 0.6952,
+      "step": 9000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.2851985559566788e-05,
+      "loss": 0.6528,
+      "step": 9500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1949458483754514e-05,
+      "loss": 0.6509,
+      "step": 10000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1046931407942239e-05,
+      "loss": 0.695,
+      "step": 10500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0144404332129965e-05,
+      "loss": 0.6447,
+      "step": 11000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.24187725631769e-06,
+      "loss": 0.5355,
+      "step": 11500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 8.339350180505416e-06,
+      "loss": 0.496,
+      "step": 12000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 7.436823104693141e-06,
+      "loss": 0.4818,
+      "step": 12500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 6.534296028880867e-06,
+      "loss": 0.4734,
+      "step": 13000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.631768953068592e-06,
+      "loss": 0.4942,
+      "step": 13500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.729241877256318e-06,
+      "loss": 0.4771,
+      "step": 14000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.826714801444043e-06,
+      "loss": 0.4741,
+      "step": 14500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.924187725631769e-06,
+      "loss": 0.47,
+      "step": 15000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.0216606498194946e-06,
+      "loss": 0.4697,
+      "step": 15500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.1191335740072204e-06,
+      "loss": 0.4626,
+      "step": 16000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.1660649819494586e-07,
+      "loss": 0.4665,
+      "step": 16500
+    },
+    {
+      "epoch": 3.0,
+      "step": 16620,
+      "total_flos": 7799619875705856.0,
+      "train_loss": 0.7116935651942137,
+      "train_runtime": 6289.4873,
+      "train_samples_per_second": 42.279,
+      "train_steps_per_second": 2.643
+    }
+  ],
+  "max_steps": 16620,
+  "num_train_epochs": 3,
+  "total_flos": 7799619875705856.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5375640803ec6a06010ba28a5d2233dd0f720ff2eecea2f00ea6a9f0599554ff
+size 2927