Upload 10 files

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "rinna/japanese-gpt2-xsmall",
+  "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": 512,
+  "n_head": 8,
+  "n_inner": 2304,
+  "n_layer": 6,
+  "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": "4.30.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f439b793219f0eed31e642828e7e4079914e8c5157ab640f9c13bd54cfe2a38e
+size 149616533

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b846d06040ac97933a3a457ec7e833e13e82f3e99b40760226e4b43ec03b3a2
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ecc15bf0106d7303694fd12832cd98ec044f076c8dc9e41a12ed1a949424cd
+size 627

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 +1,16 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": NaN,
+  "best_model_checkpoint": "output/checkpoint-500",
+  "epoch": 2.0833333333333335,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.527777777777778e-05,
+      "loss": 4.0735,
+      "step": 500
+    },
+    {
+      "epoch": 2.08,
+      "eval_loss": NaN,
+      "eval_runtime": 2.1474,
+      "eval_samples_per_second": 223.064,
+      "eval_steps_per_second": 111.765,
+      "step": 500
+    }
+  ],
+  "max_steps": 720,
+  "num_train_epochs": 3,
+  "total_flos": 12827512255488.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad53b97c6fce22e7a0cca64e1a5ddbff21a7cad0c4624a6d9929b7ffd3ca60a
+size 3899