Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13db8e2cd6952da31f9955c85e8e9a91d2097841ad65d7516eb0f5a5815a6d9
+size 1369786201

runs/Aug10_08-23-04_3d6e44caf36e/1660120464.8975794/events.out.tfevents.1660120464.3d6e44caf36e.444.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048f2f65438055f8ce1d73c1f74847d6c5d2096a3836a9c18713dc0819bf8eb4
+size 5364

runs/Aug10_08-23-04_3d6e44caf36e/events.out.tfevents.1660120464.3d6e44caf36e.444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb0167cef9079a859a233e072fde2e08fc2c6fc8c935eb8092dd9078ad812c5
+size 4208

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>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "[MASK]",
+  "name_or_path": "rinna/japanese-gpt2-medium",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--rinna--japanese-gpt2-medium/snapshots/f464b76739c884d8b0479a0a7705b7fa71c3fd5a/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d141a08ee9317cdfd02ce7302ce785a5cbb67a0d9851928e3a773c642418cb6
+size 3375