Upload 11 files

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: epoch_10_1
+  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. -->
+
+# epoch_10_1
+
+This model is a fine-tuned version of [rinna/japanese-gpt2-medium](https://huggingface.co/rinna/japanese-gpt2-medium) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2078
+- Accuracy: 0.7527
+
+## 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: 3
+- eval_batch_size: 3
+- 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 4.18.0.dev0
+- Pytorch 1.11.0+cu102
+- Datasets 2.0.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7527454204826329,
+    "eval_loss": 1.2078169584274292,
+    "eval_runtime": 282.4779,
+    "eval_samples": 2732,
+    "eval_samples_per_second": 9.672,
+    "eval_steps_per_second": 3.225,
+    "perplexity": 3.3461718411294057,
+    "train_loss": 1.7279373135446325,
+    "train_runtime": 6450.8845,
+    "train_samples": 2732,
+    "train_samples_per_second": 4.235,
+    "train_steps_per_second": 1.412
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "rinna/japanese-gpt2-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": 4096,
+  "n_layer": 24,
+  "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": "4.18.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7527454204826329,
+    "eval_loss": 1.2078169584274292,
+    "eval_runtime": 282.4779,
+    "eval_samples": 2732,
+    "eval_samples_per_second": 9.672,
+    "eval_steps_per_second": 3.225,
+    "perplexity": 3.3461718411294057
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdae8a559e03c6ce19615ef8fb5d6212a395fb1b5378c3ff75f10451d4728b2
+size 1369801817

special_tokens_map.json

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

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 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": true, "use_fast": false, "special_tokens_map_file": "/home/seich/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82", "name_or_path": "rinna/japanese-gpt2-medium", "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.7279373135446325,
+    "train_runtime": 6450.8845,
+    "train_samples": 2732,
+    "train_samples_per_second": 4.235,
+    "train_steps_per_second": 1.412
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 9110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.725576289791438e-05,
+      "loss": 2.4428,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.451152579582876e-05,
+      "loss": 2.2742,
+      "step": 1000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.176728869374314e-05,
+      "loss": 2.1079,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.902305159165752e-05,
+      "loss": 2.0447,
+      "step": 2000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.62788144895719e-05,
+      "loss": 1.9388,
+      "step": 2500
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 3.353457738748628e-05,
+      "loss": 1.8627,
+      "step": 3000
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.079034028540066e-05,
+      "loss": 1.805,
+      "step": 3500
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 2.8046103183315044e-05,
+      "loss": 1.7183,
+      "step": 4000
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 2.530186608122942e-05,
+      "loss": 1.6946,
+      "step": 4500
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 2.25576289791438e-05,
+      "loss": 1.5987,
+      "step": 5000
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 1.981339187705818e-05,
+      "loss": 1.5931,
+      "step": 5500
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 1.7069154774972558e-05,
+      "loss": 1.5127,
+      "step": 6000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 1.432491767288694e-05,
+      "loss": 1.5066,
+      "step": 6500
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 1.1580680570801318e-05,
+      "loss": 1.4534,
+      "step": 7000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 8.836443468715698e-06,
+      "loss": 1.4371,
+      "step": 7500
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 6.092206366630078e-06,
+      "loss": 1.4109,
+      "step": 8000
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 3.3479692645444565e-06,
+      "loss": 1.395,
+      "step": 8500
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 6.037321624588365e-07,
+      "loss": 1.3817,
+      "step": 9000
+    },
+    {
+      "epoch": 10.0,
+      "step": 9110,
+      "total_flos": 5.074420594900992e+16,
+      "train_loss": 1.7279373135446325,
+      "train_runtime": 6450.8845,
+      "train_samples_per_second": 4.235,
+      "train_steps_per_second": 1.412
+    }
+  ],
+  "max_steps": 9110,
+  "num_train_epochs": 10,
+  "total_flos": 5.074420594900992e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf8702d07bf20dfa11191146f1ad63e92f90f981a7a2b9396e3012cd35db0fb
+size 3055