Training in progress, step 720000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640777d4df17094532677050d169633ab25c6e5307fe7b26b1ef2480f2fa436c
+oid sha256:66a4dbe9eca38a1792482b27bee5680ed76ff9b4fd9c693743e32db4ef9e8647
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589beff1989fc9c0ae009d9c4e89cc81dea78aca3df050a942a083e247b0b3bb
+oid sha256:5c1af069a55aa141dcc761c0323c960402d5bdd923f0a54d0011b64f759ce573
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d73966766ab27f8d8b82049597603e5e27df9de3bfb4bc68f052966836974a7
+oid sha256:b66387fbbba596b80573df493f29c352b88c96c68303d4022fc8f1e14c19ee9e
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d01455789648693f3c874de11c7ed6063a3725328c7accf41053ba2de2ef602
+oid sha256:cd40898eaf2bb8f0e6b4793242d3113eb1c145ed61a59dba0b51391b3bf76148
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea50129c89a3bcb4d508277085bd760cf99e8e7596db26b1b0416ea6e662c44
+oid sha256:d33131db4d0dac1ab66ab66d875733bb83b9d53bdcdbb76cdb67e79eb395bffe
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ef7983f20d7466e22a66c14b4eb278bac441cabcddf12c2ab45c6a7ad45ccb
+oid sha256:4b4ac527158b6aa910da1978f5ab170d69172ed0e22a278e864ebd1fa5d08f7e
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7030fabf7b722e2752b51d9deb3cc7dac4745661c75fe5c48a022d295a9ffb0d
+oid sha256:9c41eb120388058e9e86dafd9920ba056d2f7de5234fa0df636e9377bd5cd58c
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8fd80ed1622a37fb8836b353462fe160453f93a1dbe072cd8bd1e37f25f658
+oid sha256:7a27da1b3b783fed75c82831476e53d38ef818a90b5db4dbe8bd2147c26f1d00
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9333397ba4ec25f889f96bb6104d7c6cf0bc5fd5c8036f75df959bdd43d52a66
+oid sha256:fc1301019ee94a4e73634cfb2e922704c945921ceecc63c3c74ee79aae0fb318
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58730a986e4ecbe1e49387372f3829be2d2d88e8ab521897bf3b764a726b44be
+oid sha256:f15d3ae110e1b804d6f357797df2bd20ffa7af4cc5c48ef5f3805abb21eebf52
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335855e99fe5c1eafe16f664b8e35342405853ed0ef1faa2892c2126df9feea5
+oid sha256:e2712ef8beaf45f8ea70ea16f7da83a9783b51ec4e90a9cb114e7f3a2c3044b7
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4193244015848456,
-  "global_step": 710000,
+  "epoch": 1.4393148861142095,
+  "global_step": 720000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8526,11 +8526,131 @@
       "learning_rate": 3.979699361219395e-05,
       "loss": 0.2956,
       "step": 710000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.9702298612493816e-05,
+      "loss": 0.2958,
+      "step": 710500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.960771378517049e-05,
+      "loss": 0.296,
+      "step": 711000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.951323938881533e-05,
+      "loss": 0.2953,
+      "step": 711500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.941887568171766e-05,
+      "loss": 0.2956,
+      "step": 712000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.9324622921864323e-05,
+      "loss": 0.2963,
+      "step": 712500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.923048136693873e-05,
+      "loss": 0.2951,
+      "step": 713000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.913645127432028e-05,
+      "loss": 0.2957,
+      "step": 713500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.904253290108369e-05,
+      "loss": 0.2953,
+      "step": 714000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.8948726503998176e-05,
+      "loss": 0.2954,
+      "step": 714500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.885503233952689e-05,
+      "loss": 0.2958,
+      "step": 715000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.876145066382606e-05,
+      "loss": 0.2948,
+      "step": 715500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.86679817327444e-05,
+      "loss": 0.2953,
+      "step": 716000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.857462580182245e-05,
+      "loss": 0.2952,
+      "step": 716500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.848138312629171e-05,
+      "loss": 0.2953,
+      "step": 717000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.838825396107415e-05,
+      "loss": 0.2962,
+      "step": 717500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.8295238560781317e-05,
+      "loss": 0.2957,
+      "step": 718000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.820233717971374e-05,
+      "loss": 0.2955,
+      "step": 718500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.810955007186029e-05,
+      "loss": 0.2953,
+      "step": 719000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.801687749089737e-05,
+      "loss": 0.295,
+      "step": 719500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.792431969018824e-05,
+      "loss": 0.2951,
+      "step": 720000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.800106373011031e+22,
+  "total_flos": 4.86771334519035e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589beff1989fc9c0ae009d9c4e89cc81dea78aca3df050a942a083e247b0b3bb
+oid sha256:5c1af069a55aa141dcc761c0323c960402d5bdd923f0a54d0011b64f759ce573
 size 449450757