End of training

config.json

@@ -63,7 +63,28 @@
     "50": "LABEL_50",
     "51": "LABEL_51",
     "52": "LABEL_52",
-    "53": "LABEL_53"
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -118,8 +139,29 @@
     "LABEL_51": 51,
     "LABEL_52": 52,
     "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
     "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
     "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
     "LABEL_8": 8,
     "LABEL_9": 9
   },

logs/events.out.tfevents.1705982829.70e47a1f5afe.42.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b4310060813e68df5a607b976ee48195ea115ecf2f9d4202461c82ed9128c4
+size 7841

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6e0e7d5b29e13e5bc0ad5a1da2b27b9bb306b5ad38a6334d9657f5b0113d2c
-size 435756040
+oid sha256:69cbee484a05deb848b73eb4e78a97aa6ca7fa2fb97bbca3d868f9ca29cd79bf
+size 435820636

trainer_state.json

@@ -11,11 +11,11 @@
     {
       "epoch": 50.0,
       "step": 50,
-      "total_flos": 32856154788600.0,
-      "train_loss": 0.17393564224243163,
-      "train_runtime": 7.7992,
-      "train_samples_per_second": 57.698,
-      "train_steps_per_second": 6.411
+      "total_flos": 39756597592500.0,
+      "train_loss": 0.21248756408691405,
+      "train_runtime": 8.9613,
+      "train_samples_per_second": 50.216,
+      "train_steps_per_second": 5.58
     }
   ],
   "logging_steps": 750,
@@ -23,7 +23,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 32856154788600.0,
+  "total_flos": 39756597592500.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8557c2036849cd866e8408772ea1bd305acc077f79dba43b158110308a074332
+oid sha256:539f836c129844c7433ce90ce7a776a98d7e07cfa66853d433c5135b23816fc8
 size 4283