Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.9454582333564758,
+    "eval_matthews_correlation": 0.49369621090355154,
+    "eval_runtime": 5.2476,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 198.757,
+    "eval_steps_per_second": 24.964,
+    "train_loss": 0.28432635905137704,
+    "train_runtime": 1347.9437,
+    "train_samples": 8551,
+    "train_samples_per_second": 63.437,
+    "train_steps_per_second": 1.988
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "finetuning_task": "cola",
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "single_label_classification",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "transformers_version": "4.9.0.dev0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.9454582333564758,
+    "eval_matthews_correlation": 0.49369621090355154,
+    "eval_runtime": 5.2476,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 198.757,
+    "eval_steps_per_second": 24.964
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d96c74b5a27df7359cdb7dfb40334013c206218ca08cd4bdafc10d505dd5930
+size 469316829

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "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}, "additional_special_tokens": ["<eop>", "<eod>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "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"}, "additional_special_tokens": ["<eop>", "<eod>"], "special_tokens_map_file": null, "name_or_path": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.28432635905137704,
+    "train_runtime": 1347.9437,
+    "train_samples": 8551,
+    "train_samples_per_second": 63.437,
+    "train_steps_per_second": 1.988
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.49369621090355154,
+  "best_model_checkpoint": "./xlnet-base-cased/fine_tuned_models/checkpoint-1876",
+  "epoch": 10.0,
+  "global_step": 2680,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 0.6214,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8445629477500916,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 5.2858,
+      "eval_samples_per_second": 197.321,
+      "eval_steps_per_second": 24.783,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.5559,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.807519257068634,
+      "eval_matthews_correlation": 0.21580374087877008,
+      "eval_runtime": 5.302,
+      "eval_samples_per_second": 196.72,
+      "eval_steps_per_second": 24.708,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.4284,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6560272574424744,
+      "eval_matthews_correlation": 0.4538429410217894,
+      "eval_runtime": 5.3043,
+      "eval_samples_per_second": 196.635,
+      "eval_steps_per_second": 24.697,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3259,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7219155430793762,
+      "eval_matthews_correlation": 0.4369166632963792,
+      "eval_runtime": 5.3104,
+      "eval_samples_per_second": 196.406,
+      "eval_steps_per_second": 24.668,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.248,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.856024980545044,
+      "eval_matthews_correlation": 0.43655986862605256,
+      "eval_runtime": 5.2976,
+      "eval_samples_per_second": 196.881,
+      "eval_steps_per_second": 24.728,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.1894,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.9414917826652527,
+      "eval_matthews_correlation": 0.45061623518481686,
+      "eval_runtime": 5.2949,
+      "eval_samples_per_second": 196.983,
+      "eval_steps_per_second": 24.741,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1492,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.9454582333564758,
+      "eval_matthews_correlation": 0.49369621090355154,
+      "eval_runtime": 5.2965,
+      "eval_samples_per_second": 196.921,
+      "eval_steps_per_second": 24.733,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.1223,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.105307936668396,
+      "eval_matthews_correlation": 0.4859069062313801,
+      "eval_runtime": 5.2949,
+      "eval_samples_per_second": 196.982,
+      "eval_steps_per_second": 24.741,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.1115,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.2678706645965576,
+      "eval_matthews_correlation": 0.4829638975063273,
+      "eval_runtime": 5.3057,
+      "eval_samples_per_second": 196.58,
+      "eval_steps_per_second": 24.69,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0913,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2386504411697388,
+      "eval_matthews_correlation": 0.4787316411367127,
+      "eval_runtime": 5.3037,
+      "eval_samples_per_second": 196.655,
+      "eval_steps_per_second": 24.7,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3851987691901440.0,
+      "train_loss": 0.28432635905137704,
+      "train_runtime": 1347.9437,
+      "train_samples_per_second": 63.437,
+      "train_steps_per_second": 1.988
+    }
+  ],
+  "max_steps": 2680,
+  "num_train_epochs": 10,
+  "total_flos": 3851987691901440.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b82614e6d2f664ac0183a6f78236503134d41497608ec3bdb5f6cff910cd1b
+size 2671