Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.855113685131073,
+    "eval_matthews_correlation": 0.512192712055601,
+    "eval_runtime": 5.216,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 199.961,
+    "eval_steps_per_second": 25.115,
+    "train_loss": 0.28002330011396265,
+    "train_runtime": 1315.8713,
+    "train_samples": 8551,
+    "train_samples_per_second": 64.984,
+    "train_steps_per_second": 2.037
+}

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": 0.855113685131073,
+    "eval_matthews_correlation": 0.512192712055601,
+    "eval_runtime": 5.216,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 199.961,
+    "eval_steps_per_second": 25.115
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4921164c62ed3412e9269fc27824777edc992525929bcf2b806371e67b14dab
+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": 0.28002330011396265,
+    "train_runtime": 1315.8713,
+    "train_samples": 8551,
+    "train_samples_per_second": 64.984,
+    "train_steps_per_second": 2.037
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.512192712055601,
+  "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": 0.6242,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6478146314620972,
+      "eval_matthews_correlation": 0.018148342420931135,
+      "eval_runtime": 5.3259,
+      "eval_samples_per_second": 195.835,
+      "eval_steps_per_second": 24.597,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.5475,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5800684690475464,
+      "eval_matthews_correlation": 0.3687428254676126,
+      "eval_runtime": 5.3218,
+      "eval_samples_per_second": 195.987,
+      "eval_steps_per_second": 24.616,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.4228,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.518549382686615,
+      "eval_matthews_correlation": 0.4729503605591106,
+      "eval_runtime": 5.3206,
+      "eval_samples_per_second": 196.031,
+      "eval_steps_per_second": 24.621,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3132,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7433116436004639,
+      "eval_matthews_correlation": 0.4456190824541546,
+      "eval_runtime": 5.2944,
+      "eval_samples_per_second": 197.001,
+      "eval_steps_per_second": 24.743,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.2426,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7162166833877563,
+      "eval_matthews_correlation": 0.4729503605591106,
+      "eval_runtime": 5.3233,
+      "eval_samples_per_second": 195.929,
+      "eval_steps_per_second": 24.609,
+      "step": 1340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.1892,
+      "step": 1608
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.7776421308517456,
+      "eval_matthews_correlation": 0.48239382723457414,
+      "eval_runtime": 5.3253,
+      "eval_samples_per_second": 195.858,
+      "eval_steps_per_second": 24.6,
+      "step": 1608
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1555,
+      "step": 1876
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.855113685131073,
+      "eval_matthews_correlation": 0.512192712055601,
+      "eval_runtime": 5.304,
+      "eval_samples_per_second": 196.642,
+      "eval_steps_per_second": 24.698,
+      "step": 1876
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.123,
+      "step": 2144
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.1328730583190918,
+      "eval_matthews_correlation": 0.47806047639386823,
+      "eval_runtime": 5.3251,
+      "eval_samples_per_second": 195.866,
+      "eval_steps_per_second": 24.601,
+      "step": 2144
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.096,
+      "step": 2412
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.1940616369247437,
+      "eval_matthews_correlation": 0.47687961708523924,
+      "eval_runtime": 5.3349,
+      "eval_samples_per_second": 195.504,
+      "eval_steps_per_second": 24.555,
+      "step": 2412
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0864,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.3239350318908691,
+      "eval_matthews_correlation": 0.45569507663230396,
+      "eval_runtime": 5.3171,
+      "eval_samples_per_second": 196.161,
+      "eval_steps_per_second": 24.638,
+      "step": 2680
+    },
+    {
+      "epoch": 10.0,
+      "step": 2680,
+      "total_flos": 3851987691901440.0,
+      "train_loss": 0.28002330011396265,
+      "train_runtime": 1315.8713,
+      "train_samples_per_second": 64.984,
+      "train_steps_per_second": 2.037
+    }
+  ],
+  "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 sha256:44f7961e2242dcdf213a66dd1f1a18f5bddd457418d572527cd158e93349a415
+size 2671