Training in progress, step 730000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a4dbe9eca38a1792482b27bee5680ed76ff9b4fd9c693743e32db4ef9e8647
+oid sha256:1be007eb114cc618f1ceaa130909e92fd5731bc7aad8602b4ed98f81b57d25bf
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1af069a55aa141dcc761c0323c960402d5bdd923f0a54d0011b64f759ce573
+oid sha256:ea4c2b3e5d29d09f4a111c5075cde8ee07ba7f3b202fd9634b12a3a9c596859e
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66387fbbba596b80573df493f29c352b88c96c68303d4022fc8f1e14c19ee9e
+oid sha256:472c99e6947863db3f1c3d882d64923234eaab4acafbf699ca3ec4467c8ba935
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd40898eaf2bb8f0e6b4793242d3113eb1c145ed61a59dba0b51391b3bf76148
+oid sha256:cced04411b336cffec34790d9efd6c44e0f42ec0710b270ba40018e4d2110bd3
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33131db4d0dac1ab66ab66d875733bb83b9d53bdcdbb76cdb67e79eb395bffe
+oid sha256:3761d69b35d8301192dc513e1e8b4eb43934633a73f8a9567ed32e9ce5136e04
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4ac527158b6aa910da1978f5ab170d69172ed0e22a278e864ebd1fa5d08f7e
+oid sha256:cdb187bb03db539c4db87f036b94065ed1b4bc8ae6a103a3d335b3b87fb02788
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c41eb120388058e9e86dafd9920ba056d2f7de5234fa0df636e9377bd5cd58c
+oid sha256:1a234a61c6f373c55eead9dc4f863dd69f6b355d0e31c4f71324cdbe0628f412
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a27da1b3b783fed75c82831476e53d38ef818a90b5db4dbe8bd2147c26f1d00
+oid sha256:9a481c02af20ead0436feb53d8a01d57cdc94addc339ab22944f77b00d9318fa
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1301019ee94a4e73634cfb2e922704c945921ceecc63c3c74ee79aae0fb318
+oid sha256:ae53946121d7ea1cdb1ff678f657136fa4e5d4bad1a9f26aa0386c6bb047c44e
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15d3ae110e1b804d6f357797df2bd20ffa7af4cc5c48ef5f3805abb21eebf52
+oid sha256:64797a5397bc5a26908cb86c3611823652cf8c230fe6c26bd266a0f5beb30f2f
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2712ef8beaf45f8ea70ea16f7da83a9783b51ec4e90a9cb114e7f3a2c3044b7
+oid sha256:647e93cd3a2419679fdb9a7ca8861633886e70429797716b24c74206efebd08a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4393148861142095,
-  "global_step": 720000,
+  "epoch": 1.4593053706435737,
+  "global_step": 730000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8646,11 +8646,131 @@
       "learning_rate": 3.792431969018824e-05,
       "loss": 0.2951,
       "step": 720000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.783187692278245e-05,
+      "loss": 0.2952,
+      "step": 720500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.7739549441414945e-05,
+      "loss": 0.2951,
+      "step": 721000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.764733749850558e-05,
+      "loss": 0.2957,
+      "step": 721500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.755524134615825e-05,
+      "loss": 0.2955,
+      "step": 722000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.746326123616032e-05,
+      "loss": 0.2953,
+      "step": 722500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.7371397419981925e-05,
+      "loss": 0.2947,
+      "step": 723000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.7279650148775196e-05,
+      "loss": 0.2949,
+      "step": 723500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.7188019673373706e-05,
+      "loss": 0.2954,
+      "step": 724000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.709650624429166e-05,
+      "loss": 0.2949,
+      "step": 724500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.700511011172325e-05,
+      "loss": 0.2946,
+      "step": 725000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.691383152554207e-05,
+      "loss": 0.2953,
+      "step": 725500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.682267073530023e-05,
+      "loss": 0.295,
+      "step": 726000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.67316279902279e-05,
+      "loss": 0.2948,
+      "step": 726500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.664070353923245e-05,
+      "loss": 0.2949,
+      "step": 727000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.654989763089782e-05,
+      "loss": 0.295,
+      "step": 727500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.645921051348396e-05,
+      "loss": 0.2949,
+      "step": 728000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.6368642434925924e-05,
+      "loss": 0.2938,
+      "step": 728500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.627819364283345e-05,
+      "loss": 0.294,
+      "step": 729000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.6187864384490035e-05,
+      "loss": 0.2937,
+      "step": 729500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.6097654906852405e-05,
+      "loss": 0.2947,
+      "step": 730000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.86771334519035e+22,
+  "total_flos": 4.935320741341352e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1af069a55aa141dcc761c0323c960402d5bdd923f0a54d0011b64f759ce573
+oid sha256:ea4c2b3e5d29d09f4a111c5075cde8ee07ba7f3b202fd9634b12a3a9c596859e
 size 449450757