First model version

added_tokens.json

@@ -0,0 +1 @@
+{"<|user|>": 50258, "<|pad|>": 50257, "<|system|>": 50259}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 50260
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac370124fe5154f34ff45b451d3f0d68168483f87e18f4ae9133f1ec3955e405
+size 510410601

runs/version_0/events.out.tfevents.1641082396.ACSDEV-DEV6.9336.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b93c9402aca233d4456a0cc9f4472f8fb5115075d079d904e877728e946c28
+size 72725

runs/version_0/hparams.yaml

@@ -0,0 +1,74 @@
+accelerator: null
+accumulate_grad_batches: null
+adam_epsilon: 1.0e-08
+amp_backend: native
+amp_level: null
+auto_lr_find: false
+auto_scale_batch_size: false
+auto_select_gpus: false
+base_modelpath: microsoft/DialoGPT-small
+batch_size: 4
+benchmark: false
+check_val_every_n_epoch: 1
+checkpoint_callback: null
+checkpoint_save_top_k: 5
+checkpoint_save_weights_only: true
+datasetpath: ..\data/dstc8-schema-guided-dialogue
+default_root_dir: null
+detect_anomaly: false
+deterministic: false
+devices: null
+early_stopping_patience: 8
+enable_checkpointing: true
+enable_model_summary: true
+enable_progress_bar: true
+fast_dev_run: false
+flush_logs_every_n_steps: null
+gpus: 1
+gradient_clip_algorithm: null
+gradient_clip_val: 1.0
+ipus: null
+learning_rate: 5.0e-05
+limit_predict_batches: 1.0
+limit_test_batches: 1.0
+limit_train_batches: 1.0
+limit_val_batches: 1.0
+log_every_n_steps: 50
+log_gpu_memory: null
+logger: true
+max_epochs: 10
+max_sequence_length: 512
+max_steps: -1
+max_time: null
+min_epochs: null
+min_steps: null
+move_metrics_to_cpu: false
+multiple_trainloader_mode: max_size_cycle
+num_nodes: 1
+num_processes: 1
+num_sanity_val_steps: 2
+overfit_batches: 0.0
+overwrite_prepared_data: false
+plugins: null
+precision: 32
+prepare_data_per_node: null
+process_position: 0
+profiler: null
+progress_bar_refresh_rate: null
+random_state: null
+reload_dataloaders_every_epoch: false
+reload_dataloaders_every_n_epochs: 0
+replace_sampler_ddp: true
+resume_from_checkpoint: null
+stochastic_weight_avg: false
+strategy: null
+sync_batchnorm: false
+terminate_on_nan: null
+tpu_cores: null
+track_grad_norm: -1
+val_check_interval: 0.25
+val_split: 0.1
+warmup_steps: 0
+weight_decay: 0.0
+weights_save_path: null
+weights_summary: top

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|pad|>", "additional_special_tokens": ["<|user|>", "<|system|>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}