End of training

config.json

@@ -63,42 +63,7 @@
     "50": "LABEL_50",
     "51": "LABEL_51",
     "52": "LABEL_52",
-    "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",
-    "75": "LABEL_75",
-    "76": "LABEL_76",
-    "77": "LABEL_77",
-    "78": "LABEL_78",
-    "79": "LABEL_79",
-    "80": "LABEL_80",
-    "81": "LABEL_81",
-    "82": "LABEL_82",
-    "83": "LABEL_83",
-    "84": "LABEL_84",
-    "85": "LABEL_85",
-    "86": "LABEL_86",
-    "87": "LABEL_87",
-    "88": "LABEL_88"
+    "53": "LABEL_53"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -153,44 +118,9 @@
     "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_75": 75,
-    "LABEL_76": 76,
-    "LABEL_77": 77,
-    "LABEL_78": 78,
-    "LABEL_79": 79,
     "LABEL_8": 8,
-    "LABEL_80": 80,
-    "LABEL_81": 81,
-    "LABEL_82": 82,
-    "LABEL_83": 83,
-    "LABEL_84": 84,
-    "LABEL_85": 85,
-    "LABEL_86": 86,
-    "LABEL_87": 87,
-    "LABEL_88": 88,
     "LABEL_9": 9
   },
   "layer_norm_eps": 1e-12,

logs/events.out.tfevents.1705981471.70e47a1f5afe.42.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f45493947e1d099fa617c89478315c8ca24f4a96bff6a29ec349377d035f830
+size 6624

logs/events.out.tfevents.1705981596.70e47a1f5afe.42.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a52d8b5735b82151db217365714e96e44f55139cb6f85cd578b826fd06a9ff
+size 6972

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbfecedd805a055d558e713fdab59dc3f5ce6a3cc40f43d3abc6ed1ac915a0b
-size 435863700
+oid sha256:15a258d9f93851cdd6ad47d4a89e6e843cd17df5266b4472832d1351b19749f8
+size 435756040

trainer_state.json

@@ -11,11 +11,11 @@
     {
       "epoch": 50.0,
       "step": 50,
-      "total_flos": 32636710679400.0,
-      "train_loss": 0.2473917007446289,
-      "train_runtime": 8.5287,
-      "train_samples_per_second": 52.763,
-      "train_steps_per_second": 5.863
+      "total_flos": 32856154788600.0,
+      "train_loss": 0.16719268798828124,
+      "train_runtime": 179.6035,
+      "train_samples_per_second": 2.506,
+      "train_steps_per_second": 0.278
     }
   ],
   "logging_steps": 750,
@@ -23,7 +23,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 32636710679400.0,
+  "total_flos": 32856154788600.0,
   "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 sha256:539f836c129844c7433ce90ce7a776a98d7e07cfa66853d433c5135b23816fc8
+oid sha256:8557c2036849cd866e8408772ea1bd305acc077f79dba43b158110308a074332
 size 4283