Trained model

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<bos>": 40478,
+  "<eos>": 40479,
+  "<pad>": 40482,
+  "<speaker1>": 40480,
+  "<speaker2>": 40481
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "models/gpt_personachat",
+  "afn": "gelu",
+  "architectures": [
+    "OpenAIGPTDoubleHeadsModel"
+  ],
+  "attn_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "openai-gpt",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 512,
+  "n_special": 5,
+  "predict_special_tokens": true,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0",
+  "vocab_size": 40483
+}

eval_results.txt

@@ -0,0 +1,2 @@
+f1_score = 1.0
+language_model_loss = 2.7865337851821192

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "models/gpt_personachat", "model_type": "gpt", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 14, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 244, "weight_decay": 0.0, "model_class": "ConvAIModel", "do_sample": true, "lm_coef": 2.0, "max_history": 1, "max_length": 30, "mc_coef": 1.0, "min_length": 1, "num_candidates": 1, "personality_permutations": 1, "temperature": 0.7, "top_k": 0, "top_p": 0.9}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f21184910087402a06e76de07441673515245cc1e7f4df568c15301c681861a
+size 478798251

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<speaker1>",
+    "<speaker2>"
+  ],
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+  "name_or_path": "models/gpt_personachat",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "OpenAIGPTTokenizer",
+  "unk_token": "<unk>"
+}