Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "albert-base-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": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734a6234631032d1fefce26311e712a34bf4e95b07b59b99ab4df05457753ac4
+size 88777619

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5070197a24554c1621ef88b2bc34a013a6601fcfd02bb9621083e92614f2dd
+size 44387257

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a8ea2268948301b867b05dd85905cf1e41748e55932b3508c99d5271631459
+size 1064

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 0.8657115697860718,
+  "best_model_checkpoint": "finetune_albert-base-v2/checkpoint-5476",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.879230581933285e-05,
+      "loss": 1.3985,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7574872169466766e-05,
+      "loss": 0.9829,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6357438519600684e-05,
+      "loss": 0.9236,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.51400048697346e-05,
+      "loss": 0.8908,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.392257121986852e-05,
+      "loss": 0.8725,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8976992964744568,
+      "eval_runtime": 127.703,
+      "eval_samples_per_second": 82.77,
+      "eval_steps_per_second": 0.65,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2705137570002435e-05,
+      "loss": 0.7766,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.1487703920136353e-05,
+      "loss": 0.6966,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.027027027027027e-05,
+      "loss": 0.6786,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.052836620404189e-06,
+      "loss": 0.6796,
+      "step": 4500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 0.694,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8657115697860718,
+      "eval_runtime": 127.2976,
+      "eval_samples_per_second": 83.034,
+      "eval_steps_per_second": 0.652,
+      "step": 5476
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8214,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2901778606365696.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4393d37b2b7df989c3e37405ad5b342c6344469137c6ad6e37ec9cbf8623f42c
+size 4536