Training in progress, step 740000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26fc7d85d9f02e6a64dd6a80217974cd29a1b0b54ea54e9b185baad200d5cbf
+oid sha256:c0b6142827a79f5d4b326c8ef95883604994380c09564cc48d7c1a0eecc0ae0c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d2617dcaf424c89a4b688e6f4da6209c2c4f8b6273e0866be4b1e433d0bac8
+oid sha256:23b5410b91904505f995b54f8dbaf35031127f48559f667a312bfe26edbdc46c
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88df4274470d41979d3cdbe4a25129230446986c8181439f49998ce0a51f2de
+oid sha256:d16bcb150fb723167f32e28532d305d9b788035b9c1c04eefc4171601b8a86cf
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be607f7560436df027ef62ca453f5afb8d7770ec356ed4a4ec23eedf6a0db7f4
+oid sha256:f68eb57082d644a52febc0af19784501f7d94576defdbcf673807dd01942a834
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29def8111a742b9412e55fb093f94afe63bb7e770d7ed5d28292a3cdbf42c223
+oid sha256:93e011812af607ddca2f8883a544e1029094dd30ea8f434fd3b69dea782324c8
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb6393653f317c7043e9a8b3debb3d85fe1b374103dd2a08137b8029e1480248
+oid sha256:8ac4fa903420068a2c49e97bb4ec5079f04b5e57b740f4f724d3e2eb49716420
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cdcd8f948ae7991b3b8cef0a5275b9e2e19dc1c57b631487377d234a0e9f31
+oid sha256:5d9f0f128872a454b4739c6d1bc039a16d454358b055fa818e1343bc269f4881
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.147250599355598,
-  "global_step": 730000,
+  "epoch": 11.299952662360468,
+  "global_step": 740000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5408,11 +5408,85 @@
       "eval_samples_per_second": 1264.795,
       "eval_steps_per_second": 20.237,
       "step": 730000
+    },
+    {
+      "epoch": 11.16,
+      "learning_rate": 3.591759627988353e-05,
+      "loss": 0.242,
+      "step": 731000
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 3.573801973101913e-05,
+      "loss": 0.2418,
+      "step": 732000
+    },
+    {
+      "epoch": 11.19,
+      "learning_rate": 3.5558927224079534e-05,
+      "loss": 0.2418,
+      "step": 733000
+    },
+    {
+      "epoch": 11.21,
+      "learning_rate": 3.5380320717591716e-05,
+      "loss": 0.2419,
+      "step": 734000
+    },
+    {
+      "epoch": 11.22,
+      "learning_rate": 3.5202202164767836e-05,
+      "loss": 0.2418,
+      "step": 735000
+    },
+    {
+      "epoch": 11.22,
+      "eval_runtime": 0.8971,
+      "eval_samples_per_second": 1114.723,
+      "eval_steps_per_second": 17.836,
+      "step": 735000
+    },
+    {
+      "epoch": 11.24,
+      "learning_rate": 3.5024573513483864e-05,
+      "loss": 0.2415,
+      "step": 736000
+    },
+    {
+      "epoch": 11.25,
+      "learning_rate": 3.484743670625822e-05,
+      "loss": 0.2414,
+      "step": 737000
+    },
+    {
+      "epoch": 11.27,
+      "learning_rate": 3.467079368023068e-05,
+      "loss": 0.2413,
+      "step": 738000
+    },
+    {
+      "epoch": 11.28,
+      "learning_rate": 3.449464636714107e-05,
+      "loss": 0.2415,
+      "step": 739000
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 3.431899669330819e-05,
+      "loss": 0.2414,
+      "step": 740000
+    },
+    {
+      "epoch": 11.3,
+      "eval_runtime": 0.7754,
+      "eval_samples_per_second": 1289.598,
+      "eval_steps_per_second": 20.634,
+      "step": 740000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.117311827465705e+22,
+  "total_flos": 5.187412088496052e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d2617dcaf424c89a4b688e6f4da6209c2c4f8b6273e0866be4b1e433d0bac8
+oid sha256:23b5410b91904505f995b54f8dbaf35031127f48559f667a312bfe26edbdc46c
 size 449471589