add model gpt2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 4.20829439163208,
+    "eval_runtime": 0.3352,
+    "eval_samples": 2,
+    "eval_samples_per_second": 5.967,
+    "eval_steps_per_second": 2.984,
+    "perplexity": 67.24175384995638,
+    "train_loss": 3.8089685440063477,
+    "train_runtime": 55.2428,
+    "train_samples": 24,
+    "train_samples_per_second": 1.738,
+    "train_steps_per_second": 1.738
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "cahya/gpt2-small-indonesian-522M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 4.20829439163208,
+    "eval_runtime": 0.3352,
+    "eval_samples": 2,
+    "eval_samples_per_second": 5.967,
+    "eval_steps_per_second": 2.984,
+    "perplexity": 67.24175384995638
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a1bd0c533fe67aefe6285986f6dfb1e6d662954d4c85d88a7ff8f72ec28ee4
+size 510403817

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/57902062674d8ea91c522ec7c31f93f4b3947d525b682597edac4bc76b6d99c2.2b8bf81243d08385c806171bc7ced6d2a0dcc7f896ca637f4e777418f7f0cc3c", "name_or_path": "cahya/gpt2-small-indonesian-522M", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 3.8089685440063477,
+    "train_runtime": 55.2428,
+    "train_samples": 24,
+    "train_samples_per_second": 1.738,
+    "train_steps_per_second": 1.738
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.0,
+      "step": 96,
+      "total_flos": 25084035072000.0,
+      "train_loss": 3.8089685440063477,
+      "train_runtime": 55.2428,
+      "train_samples_per_second": 1.738,
+      "train_steps_per_second": 1.738
+    }
+  ],
+  "max_steps": 96,
+  "num_train_epochs": 4,
+  "total_flos": 25084035072000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6554eea579696a92ef4d78b8e2a78add162d04503f997fb6c93d22b22fb58aad
+size 2927