Training in progress, step 860000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e84ef55f585409a7eb44e502edc32a6f98749bb849f76b8b16d08a3dc37d8ae
+oid sha256:33c2dd3be5413f957dd0bc28a15d74ed06d6494592da1e0b0b7a9b5cff98543f
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a461e16ba87e1e69720d854eafd25f8ca62064d88d546c07f46eddd6113b782
+oid sha256:a71f43fa4af460f6d355ec42e55c1a209c0d00e00e1e71a83db48fda6386bd08
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac44739d68ab8d92ea75cbaa95e05b08c8692ab1a77edef6cb58ac613b56151
+oid sha256:3e95df6a4d037778eea05d14b6a856440647a0d0d1cd96b14fe0089db3d2ca05
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df68ed20ea8916573dab6835f47431337c9ff47e9296153749cafb56a0237a7
+oid sha256:3e461a2edfce20979aaf8643fc972588013ea8710a13005a233ed1e93cff795c
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f291c8b37b0aa8ca2df1a663842fb970bdeff54c0b2afea5e2500f1ec3c566
+oid sha256:1ce93d230c2b3e0029a85fd7329dfec40cd7b3ce89657776854f91684f3563c3
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21eb46d9347a0d809f89248620dfe17276a72e359d7ca7fa7d35b0bd105aa105
+oid sha256:4e389a444854e3a8498410c2bcb75d082ab0efa10fdcbb6bf4f0273b2bb86e5d
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351c206e5b3b4ed149381ec4e0dbf48f45d70d99336ae5535af82fc3c087c11c
+oid sha256:5700265db9033170469a10a97e864c396caa87c59262a13775cece6d18e13d0d
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa383878cd306edcfd23540112b984f51a1f84d02ae2848e2f7b0c8c85af935
+oid sha256:b0f1d070f7247d43e02284bd789b296fa89aaa5d91db9a24f1226ebc2a6cb000
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63948dedd46aa19ac12a8709dee2f12fa168b63bee773e75612f1919ff39b2f0
+oid sha256:8b4a68e81a6718c76544b602cd99c9a2dc4ab2f4f768d0dfcb99f521ee1fd60e
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec45b14f87f8f42299fc33d4fabbcc588674c41ff3399499af6ac36481288d5
+oid sha256:a84068892fd087eddda1aa0aa2f97caf64ae34a34d55297ff6867be4553c6f26
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208c2830fa39459dcf60f5b94c27151cbc48e3dc8fdf884186b8d5be230917b9
+oid sha256:31e18eaa468ae4a1684f551cb018df5d6a9cb8eadcd4fdd17b09a3c12ad301d8
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2391562567262697,
-  "global_step": 850000,
+  "epoch": 1.2590859447867921,
+  "global_step": 860000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10206,11 +10206,131 @@
       "learning_rate": 1.8436837415545772e-05,
       "loss": 0.2874,
       "step": 850000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.838183407087156e-05,
+      "loss": 0.2878,
+      "step": 850500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8326999187910095e-05,
+      "loss": 0.2872,
+      "step": 851000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8272332916577875e-05,
+      "loss": 0.2867,
+      "step": 851500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8217835406330415e-05,
+      "loss": 0.2874,
+      "step": 852000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.81635068061618e-05,
+      "loss": 0.2873,
+      "step": 852500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.810934726460436e-05,
+      "loss": 0.2875,
+      "step": 853000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.80553569297282e-05,
+      "loss": 0.2873,
+      "step": 853500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.800153594914084e-05,
+      "loss": 0.2875,
+      "step": 854000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7947884469986816e-05,
+      "loss": 0.2872,
+      "step": 854500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7894402638947176e-05,
+      "loss": 0.287,
+      "step": 855000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7841090602239237e-05,
+      "loss": 0.2872,
+      "step": 855500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.778794850561604e-05,
+      "loss": 0.2871,
+      "step": 856000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7734976494366073e-05,
+      "loss": 0.2873,
+      "step": 856500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7682174713312805e-05,
+      "loss": 0.2871,
+      "step": 857000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7629543306814255e-05,
+      "loss": 0.2875,
+      "step": 857500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.75770824187627e-05,
+      "loss": 0.287,
+      "step": 858000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7524792192584186e-05,
+      "loss": 0.2865,
+      "step": 858500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.747267277123821e-05,
+      "loss": 0.2867,
+      "step": 859000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.74207242972173e-05,
+      "loss": 0.2862,
+      "step": 859500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7368946912546556e-05,
+      "loss": 0.2878,
+      "step": 860000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 5.746589779150674e+22,
+  "total_flos": 5.8141983412238066e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a461e16ba87e1e69720d854eafd25f8ca62064d88d546c07f46eddd6113b782
+oid sha256:a71f43fa4af460f6d355ec42e55c1a209c0d00e00e1e71a83db48fda6386bd08
 size 449450757