upload trained model

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9105504751205444,
+    "eval_loss": 0.5452536344528198,
+    "eval_runtime": 1.4363,
+    "eval_samples": 872,
+    "eval_samples_per_second": 607.136,
+    "train_runtime": 1978.9597,
+    "train_samples": 134698,
+    "train_samples_per_second": 5.318
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_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,
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9105504751205444,
+    "eval_loss": 0.5452536344528198,
+    "eval_runtime": 1.4363,
+    "eval_samples": 872,
+    "eval_samples_per_second": 607.136
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9d67fd1e48ef91403bbe74676be7a03207222e7474fe3c3cb84752026b8b4c
+size 46756715

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}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

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"}

train_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 5.0,
+    "train_runtime": 1978.9597,
+    "train_samples": 134698,
+    "train_samples_per_second": 5.318
+}

trainer_state.json

@@ -0,0 +1,149 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 10525,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9049881235154395e-05,
+      "loss": 0.3611,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.809976247030879e-05,
+      "loss": 0.2398,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7149643705463184e-05,
+      "loss": 0.2149,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6199524940617578e-05,
+      "loss": 0.1939,
+      "step": 2000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.5249406175771972e-05,
+      "loss": 0.1514,
+      "step": 2500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4299287410926367e-05,
+      "loss": 0.139,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.3349168646080762e-05,
+      "loss": 0.136,
+      "step": 3500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.2399049881235155e-05,
+      "loss": 0.1295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.144893111638955e-05,
+      "loss": 0.1054,
+      "step": 4500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0498812351543943e-05,
+      "loss": 0.0848,
+      "step": 5000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.548693586698338e-06,
+      "loss": 0.0881,
+      "step": 5500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 8.598574821852733e-06,
+      "loss": 0.087,
+      "step": 6000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.648456057007126e-06,
+      "loss": 0.0715,
+      "step": 6500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 6.698337292161521e-06,
+      "loss": 0.0534,
+      "step": 7000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 5.748218527315916e-06,
+      "loss": 0.0513,
+      "step": 7500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 4.798099762470309e-06,
+      "loss": 0.0528,
+      "step": 8000
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 3.8479809976247036e-06,
+      "loss": 0.0494,
+      "step": 8500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.897862232779098e-06,
+      "loss": 0.0283,
+      "step": 9000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.947743467933492e-06,
+      "loss": 0.0324,
+      "step": 9500
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 9.976247030878861e-07,
+      "loss": 0.0275,
+      "step": 10000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 4.750593824228029e-08,
+      "loss": 0.0308,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "step": 10525,
+      "total_flos": 14161246092288.0,
+      "train_runtime": 1978.9597,
+      "train_samples_per_second": 5.318
+    }
+  ],
+  "max_steps": 10525,
+  "num_train_epochs": 5,
+  "total_flos": 14161246092288.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8656ad9924b92bad18ebc35230ffc7a62547640414e60761fab0096d840c39
+size 2415