Upload 8 files

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "flax-community/gpt2-small-indonesian",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "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": 0.0,
+  "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": "4.32.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.32.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec8556458f5c680871a59ae4a95969e244944f27615f9d4ac01b484bd02056f
+size 995641861

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf4ecd8a5b06187890c4066192de56ba0f136e5e1f7946399af28c3e64711db
+size 497807197

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa302b087d13df1585059f19c40718ddcbe9f202f5ca1867898c19a359f17e46
+size 627

trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 837,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.850657108721625e-05,
+      "loss": 2.9804,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4562251567840576,
+      "eval_runtime": 42.4632,
+      "eval_samples_per_second": 42.083,
+      "eval_steps_per_second": 5.275,
+      "step": 837
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6696,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1310836801536000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473af4d249315b5a13e2c0ca57e02795d7dab4833b621f63e4ad450244c5026e
+size 4027