Training in progress, step 22196, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "indobenchmark/indogpt",
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tokenizer_class": "IndoNLGTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 40008
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.40.2"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b21f92c5404e47ca68173c72e07deb02dcfa76c6312bfb3d05f725b4f679cbf
+size 466289280

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f5d7d432340dbfdef4cab0f95469e56a22e08486a799d3fbd65e9e98a71d44
+size 932672442

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e449fc9f9384966e985a4bf6c53028dd32ac5ab84734989ccd4f8a7db41222b
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb43267f42c0224bd01b14a0c31ba8171c7255d3fa2f54496a7fc6309c899172
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.10000045053365712,
+  "eval_steps": 500,
+  "global_step": 22196,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010001847187994179,
+      "grad_norm": 8.891203880310059,
+      "learning_rate": 9.89998152812006e-06,
+      "loss": 3.7466,
+      "step": 2220
+    },
+    {
+      "epoch": 0.020003694375988357,
+      "grad_norm": 9.095343589782715,
+      "learning_rate": 9.799963056240118e-06,
+      "loss": 3.8874,
+      "step": 4440
+    },
+    {
+      "epoch": 0.030005541563982538,
+      "grad_norm": 10.57905387878418,
+      "learning_rate": 9.699944584360175e-06,
+      "loss": 3.865,
+      "step": 6660
+    },
+    {
+      "epoch": 0.040007388751976715,
+      "grad_norm": 4.935700416564941,
+      "learning_rate": 9.599926112480233e-06,
+      "loss": 3.8441,
+      "step": 8880
+    },
+    {
+      "epoch": 0.0500092359399709,
+      "grad_norm": 8.008011817932129,
+      "learning_rate": 9.499907640600292e-06,
+      "loss": 3.8126,
+      "step": 11100
+    },
+    {
+      "epoch": 0.060011083127965076,
+      "grad_norm": 6.469420909881592,
+      "learning_rate": 9.39988916872035e-06,
+      "loss": 3.8078,
+      "step": 13320
+    },
+    {
+      "epoch": 0.07001293031595926,
+      "grad_norm": 7.097398281097412,
+      "learning_rate": 9.29987069684041e-06,
+      "loss": 3.8054,
+      "step": 15540
+    },
+    {
+      "epoch": 0.08001477750395343,
+      "grad_norm": 5.952394485473633,
+      "learning_rate": 9.199852224960467e-06,
+      "loss": 3.802,
+      "step": 17760
+    },
+    {
+      "epoch": 0.09001662469194761,
+      "grad_norm": 4.3405280113220215,
+      "learning_rate": 9.099833753080524e-06,
+      "loss": 3.7729,
+      "step": 19980
+    }
+  ],
+  "logging_steps": 2220,
+  "max_steps": 221959,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 22196,
+  "total_flos": 5202695881728000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc904bdbb5ea6bf89d8de9a3fba06afee811e2edd34c9927b4008ec65155662
+size 5176