Add model and its dependencies

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "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,
+  "finetuning_task": "mnli",
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96db18d6b91e03115853372caa2b59a49db9ce10ebc92df07748aab783484052
+size 46758609

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": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8472745797249108,
+  "best_model_checkpoint": "./outputs/albert-base-uncased/fine_tuned_models/checkpoint-9204",
+  "epoch": 5.0,
+  "global_step": 15340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5673640167364017e-05,
+      "loss": 0.5338,
+      "step": 3068
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8337238920020377,
+      "eval_loss": 0.42842260003089905,
+      "eval_runtime": 32.4611,
+      "eval_samples_per_second": 302.362,
+      "eval_steps_per_second": 37.799,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.9255230125523012e-05,
+      "loss": 0.3616,
+      "step": 6136
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8427916454406521,
+      "eval_loss": 0.41475561261177063,
+      "eval_runtime": 32.3849,
+      "eval_samples_per_second": 303.074,
+      "eval_steps_per_second": 37.888,
+      "step": 6136
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.2836820083682009e-05,
+      "loss": 0.258,
+      "step": 9204
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8472745797249108,
+      "eval_loss": 0.4169335663318634,
+      "eval_runtime": 32.3875,
+      "eval_samples_per_second": 303.049,
+      "eval_steps_per_second": 37.885,
+      "step": 9204
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.418410041841004e-06,
+      "loss": 0.1629,
+      "step": 12272
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8429954151808456,
+      "eval_loss": 0.514365017414093,
+      "eval_runtime": 32.4249,
+      "eval_samples_per_second": 302.7,
+      "eval_steps_per_second": 37.841,
+      "step": 12272
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0872,
+      "step": 15340
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8393275598573612,
+      "eval_loss": 0.6480396389961243,
+      "eval_runtime": 32.4279,
+      "eval_samples_per_second": 302.671,
+      "eval_steps_per_second": 37.838,
+      "step": 15340
+    },
+    {
+      "epoch": 5.0,
+      "step": 15340,
+      "total_flos": 1.762203942713088e+16,
+      "train_loss": 0.2806968082194223,
+      "train_runtime": 15169.7185,
+      "train_samples_per_second": 129.436,
+      "train_steps_per_second": 1.011
+    }
+  ],
+  "max_steps": 15340,
+  "num_train_epochs": 5,
+  "total_flos": 1.762203942713088e+16,
+  "trial_name": null,
+  "trial_params": null
+}