Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.5387118458747864,
+    "eval_matthews_correlation": 0.5159673470694772,
+    "eval_runtime": 5.1252,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 203.503,
+    "eval_steps_per_second": 25.56,
+    "train_loss": 0.28853215957755474,
+    "train_runtime": 1321.6062,
+    "train_samples": 8551,
+    "train_samples_per_second": 64.702,
+    "train_steps_per_second": 2.028
+}

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": 0.5387118458747864,
+    "eval_matthews_correlation": 0.5159673470694772,
+    "eval_runtime": 5.1252,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 203.503,
+    "eval_steps_per_second": 25.56
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab301e25fd263f502060ff3f172e035929077b86a2b011d20585ddaf909a2395
+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": 0.28853215957755474,
+    "train_runtime": 1321.6062,
+    "train_samples": 8551,
+    "train_samples_per_second": 64.702,
+    "train_steps_per_second": 2.028
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.5159673470694772,
+  "best_model_checkpoint": "./xlnet-base-cased/fine_tuned_models/checkpoint-1072",
+  "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": 0.6209,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6063559651374817,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 5.3348,
+      "eval_samples_per_second": 195.508,
+      "eval_steps_per_second": 24.556,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.5596,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5895028114318848,
+      "eval_matthews_correlation": 0.33728969959232674,
+      "eval_runtime": 5.3138,
+      "eval_samples_per_second": 196.282,
+      "eval_steps_per_second": 24.653,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.4363,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6392635107040405,
+      "eval_matthews_correlation": 0.3799227380360581,
+      "eval_runtime": 5.2969,
+      "eval_samples_per_second": 196.909,
+      "eval_steps_per_second": 24.732,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3313,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5387118458747864,
+      "eval_matthews_correlation": 0.5159673470694772,
+      "eval_runtime": 5.2925,
+      "eval_samples_per_second": 197.072,
+      "eval_steps_per_second": 24.752,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.2597,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7145249843597412,
+      "eval_matthews_correlation": 0.48924710895559326,
+      "eval_runtime": 5.3082,
+      "eval_samples_per_second": 196.49,
+      "eval_steps_per_second": 24.679,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.1937,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.8948436379432678,
+      "eval_matthews_correlation": 0.4772761198584598,
+      "eval_runtime": 5.3286,
+      "eval_samples_per_second": 195.735,
+      "eval_steps_per_second": 24.584,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1567,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.9947971105575562,
+      "eval_matthews_correlation": 0.47467239745267154,
+      "eval_runtime": 5.3053,
+      "eval_samples_per_second": 196.596,
+      "eval_steps_per_second": 24.692,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.1292,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.9624822735786438,
+      "eval_matthews_correlation": 0.5089710686381267,
+      "eval_runtime": 5.3084,
+      "eval_samples_per_second": 196.481,
+      "eval_steps_per_second": 24.678,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.1037,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.052783489227295,
+      "eval_matthews_correlation": 0.507992911858168,
+      "eval_runtime": 5.3049,
+      "eval_samples_per_second": 196.61,
+      "eval_steps_per_second": 24.694,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0943,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.1543114185333252,
+      "eval_matthews_correlation": 0.5100509365200628,
+      "eval_runtime": 5.3208,
+      "eval_samples_per_second": 196.022,
+      "eval_steps_per_second": 24.62,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3851987691901440.0,
+      "train_loss": 0.28853215957755474,
+      "train_runtime": 1321.6062,
+      "train_samples_per_second": 64.702,
+      "train_steps_per_second": 2.028
+    }
+  ],
+  "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 sha256:4d767c514b94d8cdaf505cd5256dc8255dd7c9c364d95ddc0549ceb09084ca5b
+size 2671