ravil99 commited on
Commit
569878e
1 Parent(s): a7c7ad4

Trained model

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 40478,
3
+ "<eos>": 40479,
4
+ "<pad>": 40482,
5
+ "<speaker1>": 40480,
6
+ "<speaker2>": 40481
7
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/gpt_personachat",
3
+ "afn": "gelu",
4
+ "architectures": [
5
+ "OpenAIGPTDoubleHeadsModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "embd_pdrop": 0.1,
9
+ "id2label": {
10
+ "0": "LABEL_0"
11
+ },
12
+ "initializer_range": 0.02,
13
+ "label2id": {
14
+ "LABEL_0": 0
15
+ },
16
+ "layer_norm_epsilon": 1e-05,
17
+ "model_type": "openai-gpt",
18
+ "n_ctx": 512,
19
+ "n_embd": 768,
20
+ "n_head": 12,
21
+ "n_layer": 12,
22
+ "n_positions": 512,
23
+ "n_special": 5,
24
+ "predict_special_tokens": true,
25
+ "resid_pdrop": 0.1,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.21.0",
33
+ "vocab_size": 40483
34
+ }
eval_results.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ f1_score = 1.0
2
+ language_model_loss = 2.7865337851821192
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_args.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f21184910087402a06e76de07441673515245cc1e7f4df568c15301c681861a
3
+ size 478798251
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<speaker1>",
4
+ "<speaker2>"
5
+ ],
6
+ "bos_token": "<bos>",
7
+ "eos_token": "<eos>",
8
+ "pad_token": "<pad>",
9
+ "unk_token": "<unk>"
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "name_or_path": "models/gpt_personachat",
3
+ "special_tokens_map_file": null,
4
+ "tokenizer_class": "OpenAIGPTTokenizer",
5
+ "unk_token": "<unk>"
6
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff