first commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 0.03293671831488609,
+    "eval_mem_cpu_alloc_delta": 85377,
+    "eval_mem_cpu_peaked_delta": 33067,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 569275904,
+    "eval_runtime": 4.0268,
+    "eval_samples": 23,
+    "eval_samples_per_second": 5.712,
+    "init_mem_cpu_alloc_delta": 1868923,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 1370738688,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 1.0334851364909519,
+    "train_mem_cpu_alloc_delta": 480835,
+    "train_mem_cpu_peaked_delta": 329934,
+    "train_mem_gpu_alloc_delta": 4036706816,
+    "train_mem_gpu_peaked_delta": 8663361536,
+    "train_runtime": 399.4076,
+    "train_samples": 23,
+    "train_samples_per_second": 1.728
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_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,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 0.03293671831488609,
+    "eval_mem_cpu_alloc_delta": 85377,
+    "eval_mem_cpu_peaked_delta": 33067,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 569275904,
+    "eval_runtime": 4.0268,
+    "eval_samples": 23,
+    "eval_samples_per_second": 5.712,
+    "perplexity": 1.0334851364909519
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12438c9ecb3f0be9106cde6cc82fb132611c13e2535515f2ad5b8285a9a3662
+size 1369800665

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, "tokenizer_class": "T5Tokenizer", "use_fast": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82", "tokenizer_file": null, "name_or_path": "rinna/japanese-gpt2-medium"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 30.0,
+    "init_mem_cpu_alloc_delta": 1868923,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 1370738688,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 480835,
+    "train_mem_cpu_peaked_delta": 329934,
+    "train_mem_gpu_alloc_delta": 4036706816,
+    "train_mem_gpu_peaked_delta": 8663361536,
+    "train_runtime": 399.4076,
+    "train_samples": 23,
+    "train_samples_per_second": 1.728
+}

trainer_state.json

@@ -0,0 +1,29 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "global_step": 690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 21.74,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 1.1133,
+      "step": 500
+    },
+    {
+      "epoch": 30.0,
+      "step": 690,
+      "total_flos": 1424967598080000.0,
+      "train_runtime": 399.4076,
+      "train_samples_per_second": 1.728
+    }
+  ],
+  "max_steps": 690,
+  "num_train_epochs": 30,
+  "total_flos": 1424967598080000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cb39dc91671c522f484e1862e34286b78345983173bb19730f50a974ad81f2
+size 2287