Upload 8 files

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "flax-community/gpt2-small-indonesian",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec8556458f5c680871a59ae4a95969e244944f27615f9d4ac01b484bd02056f
+oid sha256:a387b903013942d398fcbd058bf4d460d686b96cacced22bcec9850f1cee9158
 size 995641861

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d6b8260272051480772e7cb742e0fbcac1f84f6613c87e2dbbe863932b6238
+oid sha256:b305776192d9c7b02235267518eb48a56e77aeafffaa6041feca49d4bfb61c57
 size 497807197

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6162bb9db25c89c41e126a7a00a5d0695219447bff9b18d08731531620758440
+oid sha256:3e46ce4eb16240da9f3a8b3066acb6f59a234249ee2a3052f3323786da479838
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139d564a4ff8b0110bedb5670b2421665ae2dae7192939285858c6b23b9de487
+oid sha256:379fbb4843aa705c1a8ebf91edd4bc9efa24517c9b80a439967989d5fcb16ce9
 size 627

trainer_state.json

@@ -1,87 +1,201 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 3348,
+  "global_step": 8630,
   "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,
+      "epoch": 0.58,
+      "learning_rate": 9.710312862108923e-06,
+      "loss": 3.2151,
       "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
+      "eval_loss": 2.4692916870117188,
+      "eval_runtime": 45.2268,
+      "eval_samples_per_second": 40.883,
+      "eval_steps_per_second": 5.13,
+      "step": 863
     },
     {
-      "epoch": 1.19,
-      "learning_rate": 1.7013142174432496e-05,
-      "loss": 2.4595,
+      "epoch": 1.16,
+      "learning_rate": 9.420625724217845e-06,
+      "loss": 2.5031,
       "step": 1000
     },
     {
-      "epoch": 1.79,
-      "learning_rate": 1.5519713261648747e-05,
-      "loss": 2.3818,
+      "epoch": 1.74,
+      "learning_rate": 9.130938586326767e-06,
+      "loss": 2.3986,
       "step": 1500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 2.373106002807617,
-      "eval_runtime": 42.2281,
-      "eval_samples_per_second": 42.318,
-      "eval_steps_per_second": 5.305,
-      "step": 1674
+      "eval_loss": 2.3642208576202393,
+      "eval_runtime": 44.3366,
+      "eval_samples_per_second": 41.704,
+      "eval_steps_per_second": 5.233,
+      "step": 1726
     },
     {
-      "epoch": 2.39,
-      "learning_rate": 1.4026284348864996e-05,
-      "loss": 2.3449,
+      "epoch": 2.32,
+      "learning_rate": 8.84125144843569e-06,
+      "loss": 2.3399,
       "step": 2000
     },
     {
-      "epoch": 2.99,
-      "learning_rate": 1.2532855436081244e-05,
-      "loss": 2.3116,
+      "epoch": 2.9,
+      "learning_rate": 8.551564310544612e-06,
+      "loss": 2.3188,
       "step": 2500
     },
     {
       "epoch": 3.0,
-      "eval_loss": 2.333420515060425,
-      "eval_runtime": 42.4622,
-      "eval_samples_per_second": 42.084,
-      "eval_steps_per_second": 5.275,
-      "step": 2511
+      "eval_loss": 2.3149166107177734,
+      "eval_runtime": 44.9069,
+      "eval_samples_per_second": 41.174,
+      "eval_steps_per_second": 5.166,
+      "step": 2589
     },
     {
-      "epoch": 3.58,
-      "learning_rate": 1.1039426523297491e-05,
-      "loss": 2.2842,
+      "epoch": 3.48,
+      "learning_rate": 8.261877172653534e-06,
+      "loss": 2.2853,
       "step": 3000
     },
     {
       "epoch": 4.0,
-      "eval_loss": 2.3103713989257812,
-      "eval_runtime": 42.488,
-      "eval_samples_per_second": 42.059,
-      "eval_steps_per_second": 5.272,
-      "step": 3348
+      "eval_loss": 2.284034013748169,
+      "eval_runtime": 44.6174,
+      "eval_samples_per_second": 41.441,
+      "eval_steps_per_second": 5.2,
+      "step": 3452
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 7.972190034762456e-06,
+      "loss": 2.2634,
+      "step": 3500
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 7.68250289687138e-06,
+      "loss": 2.2415,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.2624311447143555,
+      "eval_runtime": 45.3808,
+      "eval_samples_per_second": 40.744,
+      "eval_steps_per_second": 5.112,
+      "step": 4315
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 7.392815758980302e-06,
+      "loss": 2.2406,
+      "step": 4500
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 7.103128621089225e-06,
+      "loss": 2.2182,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.2461531162261963,
+      "eval_runtime": 51.6238,
+      "eval_samples_per_second": 35.817,
+      "eval_steps_per_second": 4.494,
+      "step": 5178
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 6.813441483198147e-06,
+      "loss": 2.2067,
+      "step": 5500
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 6.523754345307068e-06,
+      "loss": 2.1992,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.2332844734191895,
+      "eval_runtime": 44.2392,
+      "eval_samples_per_second": 41.795,
+      "eval_steps_per_second": 5.244,
+      "step": 6041
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 6.234067207415992e-06,
+      "loss": 2.1873,
+      "step": 6500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.223007917404175,
+      "eval_runtime": 46.3144,
+      "eval_samples_per_second": 39.923,
+      "eval_steps_per_second": 5.009,
+      "step": 6904
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 5.944380069524913e-06,
+      "loss": 2.1861,
+      "step": 7000
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 5.654692931633836e-06,
+      "loss": 2.1706,
+      "step": 7500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.2148640155792236,
+      "eval_runtime": 44.5375,
+      "eval_samples_per_second": 41.516,
+      "eval_steps_per_second": 5.209,
+      "step": 7767
+    },
+    {
+      "epoch": 9.27,
+      "learning_rate": 5.365005793742758e-06,
+      "loss": 2.1684,
+      "step": 8000
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 5.0753186558516806e-06,
+      "loss": 2.1562,
+      "step": 8500
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.2083637714385986,
+      "eval_runtime": 45.5164,
+      "eval_samples_per_second": 40.623,
+      "eval_steps_per_second": 5.097,
+      "step": 8630
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6696,
-  "num_train_epochs": 8,
+  "max_steps": 17260,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 5243347206144000.0,
+  "total_flos": 1.352774172672e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473af4d249315b5a13e2c0ca57e02795d7dab4833b621f63e4ad450244c5026e
+oid sha256:b2f5178fa25426dad247073e5833a1fdc32d9a75338a2383aea842c695b18ef8
 size 4027