学習済モデル追加

output/all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.6957201957702637,
+    "eval_runtime": 73.5868,
+    "eval_samples": 239,
+    "eval_samples_per_second": 3.248,
+    "eval_steps_per_second": 3.248,
+    "perplexity": 14.816185465869992,
+    "train_loss": 3.2128273765744857,
+    "train_runtime": 716.7583,
+    "train_samples": 239,
+    "train_samples_per_second": 1.0,
+    "train_steps_per_second": 1.0
+}

output/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": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

output/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.6957201957702637,
+    "eval_runtime": 73.5868,
+    "eval_samples": 239,
+    "eval_samples_per_second": 3.248,
+    "eval_steps_per_second": 3.248,
+    "perplexity": 14.816185465869992
+}

output/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.31.0"
+}

output/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb96ba24ae90eb560b674aefc10ae265769cba5736b5a1de3357d256dc4e357
+size 1344607197

output/runs/Aug16_05-43-41_86c1fce1b5e8/events.out.tfevents.1692164661.86c1fce1b5e8.2960.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76385a728adf4b1980c94df443fc1da5bf7b2f8123856fe27bdb6425507e6ae2
+size 4808

output/runs/Aug16_05-43-41_86c1fce1b5e8/events.out.tfevents.1692165456.86c1fce1b5e8.2960.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236810a19c4372134abc36034e018fdb231e1b79dbfb875ec14d1b23b5058c08
+size 359

output/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>"
+}

output/spiece.model

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

output/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}

output/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.2128273765744857,
+    "train_runtime": 716.7583,
+    "train_samples": 239,
+    "train_samples_per_second": 1.0,
+    "train_steps_per_second": 1.0
+}

output/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 717,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.5132496513249652e-05,
+      "loss": 3.3543,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 717,
+      "total_flos": 1331756795953152.0,
+      "train_loss": 3.2128273765744857,
+      "train_runtime": 716.7583,
+      "train_samples_per_second": 1.0,
+      "train_steps_per_second": 1.0
+    }
+  ],
+  "max_steps": 717,
+  "num_train_epochs": 3,
+  "total_flos": 1331756795953152.0,
+  "trial_name": null,
+  "trial_params": null
+}

output/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba90a4ad394f5dc7339ae1da6b35e589e4bd5a377bd6c5a00742f463d9b3713a
+size 3963