Upload 4 files

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1034.4726613658097,
+    "train_runtime": 1395.2083,
+    "train_samples": 3845,
+    "train_samples_per_second": 13.779,
+    "train_steps_per_second": 0.864
+}

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.149377593360996,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1205,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,13 +67,34 @@
       "learning_rate": 0.0002,
       "loss": 159.076,
       "step": 1000
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 0.0002,
+      "loss": 149.862,
+      "step": 1100
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 0.0002,
+      "loss": 121.4963,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "step": 1205,
+      "total_flos": 3.9380753570781855e+18,
+      "train_loss": 1034.4726613658097,
+      "train_runtime": 1395.2083,
+      "train_samples_per_second": 13.779,
+      "train_steps_per_second": 0.864
     }
   ],
   "logging_steps": 100,
   "max_steps": 1205,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 3.294404741029474e+18,
+  "total_flos": 3.9380753570781855e+18,
   "trial_name": null,
   "trial_params": null
 }

vocab.json

@@ -0,0 +1,39 @@
+{
+  " ": 6,
+  "</s>": 36,
+  "<pad>": 32,
+  "<s>": 35,
+  "<unk>": 34,
+  "a": 25,
+  "b": 5,
+  "d": 22,
+  "e": 21,
+  "f": 23,
+  "g": 10,
+  "h": 4,
+  "i": 11,
+  "j": 1,
+  "k": 15,
+  "l": 28,
+  "m": 31,
+  "n": 30,
+  "o": 14,
+  "p": 27,
+  "q": 17,
+  "s": 8,
+  "t": 3,
+  "u": 16,
+  "w": 29,
+  "x": 9,
+  "y": 26,
+  "z": 7,
+  "|": 33,
+  "ü": 2,
+  "č": 19,
+  "ŋ": 13,
+  "š": 20,
+  "ǰ": 0,
+  "ə": 24,
+  "ɣ": 12,
+  "∼": 18
+}