Next training iteration (90k)

added_tokens.json

@@ -1 +1 @@
-{"END_SELFPROMO_TOKEN": 32115, "LONG_WORD_TOKEN": 32106, "END_INTERACTION_TOKEN": 32117, "EXTRACT_SEGMENTS: ": 32100, "BETWEEN_SEGMENTS_TOKEN": 32118, "PROFANITY_TOKEN": 32110, "NUMBER_PERCENTAGE_TOKEN": 32103, "[Laughter]": 32109, "SHORT_HYPHENATED_TOKEN": 32105, "[Music]": 32107, "[Applause]": 32108, "END_SPONSOR_TOKEN": 32113, "NO_SEGMENT_TOKEN": 32111, "HYPHENATED_URL_TOKEN": 32102, "START_SPONSOR_TOKEN": 32112, "URL_TOKEN": 32101, "START_SELFPROMO_TOKEN": 32114, "START_INTERACTION_TOKEN": 32116, "NUMBER_TOKEN": 32104}
+{"SHORT_HYPHENATED_TOKEN": 32105, "END_SPONSOR_TOKEN": 32113, "EXTRACT_SEGMENTS: ": 32100, "[Music]": 32107, "NUMBER_PERCENTAGE_TOKEN": 32103, "LONG_WORD_TOKEN": 32106, "HYPHENATED_URL_TOKEN": 32102, "START_INTERACTION_TOKEN": 32116, "URL_TOKEN": 32101, "END_INTERACTION_TOKEN": 32117, "END_SELFPROMO_TOKEN": 32115, "NUMBER_TOKEN": 32104, "NO_SEGMENT_TOKEN": 32111, "PROFANITY_TOKEN": 32110, "BETWEEN_SEGMENTS_TOKEN": 32118, "START_SELFPROMO_TOKEN": 32114, "[Laughter]": 32109, "[Applause]": 32108, "START_SPONSOR_TOKEN": 32112}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e73df4acf596669fc8bbc5025e78d667d77045e11a809f1f2e7f6638f868a82
+oid sha256:71bb817c2eb93b2299b2db3e9a4fdf54230ad4f8af14493ca0539096676da785
 size 990383053

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ebddd8d23b9d2745ef5ee1df068df17974bd5cfbdcfb208e5eeb559e7e4a61
+oid sha256:5f5898f076f1662c347f647ca9305dacb1097aa523e328bb84cc7c4a92dda75a
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863bc83c7e2bc3df963dc3b7cd76697e4379b39112e53c3aacbeab9768904dc4
+oid sha256:c2e5c883e4333a69700fe4d098d3261cf9eac2c32334388c85d05b1fa6f3a483
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08060226008737285,
-  "global_step": 45000,
+  "epoch": 0.1612045201747457,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -68,11 +68,65 @@
       "learning_rate": 4.596988699563136e-05,
       "loss": 0.1129,
       "step": 45000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.5522096661812623e-05,
+      "loss": 0.1115,
+      "step": 50000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5074306327993884e-05,
+      "loss": 0.1072,
+      "step": 55000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.4626515994175145e-05,
+      "loss": 0.1079,
+      "step": 60000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.4178725660356406e-05,
+      "loss": 0.3569,
+      "step": 65000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.3730935326537667e-05,
+      "loss": 0.1283,
+      "step": 70000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.3283144992718934e-05,
+      "loss": 0.1039,
+      "step": 75000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.2835354658900195e-05,
+      "loss": 0.0956,
+      "step": 80000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.2387564325081456e-05,
+      "loss": 0.0989,
+      "step": 85000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.1939773991262716e-05,
+      "loss": 0.0966,
+      "step": 90000
     }
   ],
   "max_steps": 558297,
   "num_train_epochs": 1,
-  "total_flos": 4.439552157522432e+16,
+  "total_flos": 8.885642742554112e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88579f56375596872ffe40e72d85e293c40c8fa8ed74b8701b8ecc7002ec505
+oid sha256:da11e8af50c38dbf9430e2d7bbfab617719d848605add5ab7ec3aa4da77adca5
 size 3119