init from Shigure

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# output
+
+This model is a fine-tuned version of [rinna/japanese-gpt2-small](https://huggingface.co/rinna/japanese-gpt2-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1545
+- Accuracy: 0.4936
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.1
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.4935946905386634,
+    "eval_loss": 3.154482126235962,
+    "eval_runtime": 1.862,
+    "eval_samples": 19,
+    "eval_samples_per_second": 10.204,
+    "eval_steps_per_second": 10.204,
+    "perplexity": 23.440894523264475,
+    "train_loss": 2.6836741773388053,
+    "train_runtime": 266.2205,
+    "train_samples": 79,
+    "train_samples_per_second": 2.967,
+    "train_steps_per_second": 2.967
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "rinna/japanese-gpt2-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.4935946905386634,
+    "eval_loss": 3.154482126235962,
+    "eval_runtime": 1.862,
+    "eval_samples": 19,
+    "eval_samples_per_second": 10.204,
+    "eval_steps_per_second": 10.204,
+    "perplexity": 23.440894523264475
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd6b2ec4e9ba7f042406e542e57ebea55475f5830447fcd96b500ad34c13ad5
+size 454312509

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
+size 805634

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "rinna/japanese-gpt2-small",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/yokoda/.cache/huggingface/hub/models--rinna--japanese-gpt2-small/snapshots/d35a68cf1fea74b71708ce898b351471b5c698ce/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 2.6836741773388053,
+    "train_runtime": 266.2205,
+    "train_samples": 79,
+    "train_samples_per_second": 2.967,
+    "train_steps_per_second": 2.967
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.33,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 3.0356,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "step": 790,
+      "total_flos": 412841410560000.0,
+      "train_loss": 2.6836741773388053,
+      "train_runtime": 266.2205,
+      "train_samples_per_second": 2.967,
+      "train_steps_per_second": 2.967
+    }
+  ],
+  "max_steps": 790,
+  "num_train_epochs": 10,
+  "total_flos": 412841410560000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f042ac9b4c029615fa4e25ef729378e9cce6e15dfb0132bd13265b13f80d1cb8
+size 3387