Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6372dd1fcac73a6d002b862e253a8f529a21bfb6505d426eb6490685b99079
+oid sha256:095cdc2206915b13c91737914986a8e276b6aa2aeb7f585f2e2299aaef863431
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4efb829900eca9ce90bdd07233b37b80c9ba4ef109e90b06c024612e54b339
+oid sha256:4c0918f01fc281fe650a7f34ce320b16f41041a3828360539c10b1d1b26b82b5
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e51a42ec5ffac256f3cd0ee0ccd7a6d3befe58914ad400c0cc707bc4a5ee283
+oid sha256:ed3753ab7977739b8eda494dd72defae5750f7283141b11a8f562160ba4c1a23
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642827d515e7c3d88d20c04224822701abbbc9250deb1d366045f974d08b8258
+oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b7199eafacf3aebfb36d08706c780a64bb0c6ec2f9e812edb49fb3334dca22
+oid sha256:178c6e38397a4175ef74b3ac48e86f590f2f5e0bc2e4d9b59014e014312512a2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.016366666666666,
+  "epoch": 12.018166666666666,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1058,6 +1058,76 @@
       "learning_rate": 2.6022695749334263e-05,
       "loss": 0.6486746215820313,
       "step": 7500
+    },
+    {
+      "epoch": 5.0088333333333335,
+      "grad_norm": 2.05151629447937,
+      "learning_rate": 2.5968368549352748e-05,
+      "loss": 0.6304220581054687,
+      "step": 7550
+    },
+    {
+      "epoch": 5.0105,
+      "grad_norm": 1.9714049100875854,
+      "learning_rate": 2.5913730366312535e-05,
+      "loss": 0.6141956710815429,
+      "step": 7600
+    },
+    {
+      "epoch": 5.012166666666666,
+      "grad_norm": 2.1039156913757324,
+      "learning_rate": 2.5858782749354603e-05,
+      "loss": 0.6495011901855469,
+      "step": 7650
+    },
+    {
+      "epoch": 5.013833333333333,
+      "grad_norm": 1.6918100118637085,
+      "learning_rate": 2.5803527256393243e-05,
+      "loss": 0.63647216796875,
+      "step": 7700
+    },
+    {
+      "epoch": 6.000633333333333,
+      "grad_norm": 1.6919469833374023,
+      "learning_rate": 2.5747965454071845e-05,
+      "loss": 0.671699447631836,
+      "step": 7750
+    },
+    {
+      "epoch": 6.0023,
+      "grad_norm": 1.7445021867752075,
+      "learning_rate": 2.569209891771852e-05,
+      "loss": 0.6194692611694336,
+      "step": 7800
+    },
+    {
+      "epoch": 6.003966666666667,
+      "grad_norm": 1.7923142910003662,
+      "learning_rate": 2.5635929231301407e-05,
+      "loss": 0.5799810409545898,
+      "step": 7850
+    },
+    {
+      "epoch": 6.005633333333333,
+      "grad_norm": 1.78199303150177,
+      "learning_rate": 2.5579457987383783e-05,
+      "loss": 0.577097282409668,
+      "step": 7900
+    },
+    {
+      "epoch": 6.0073,
+      "grad_norm": 1.3529242277145386,
+      "learning_rate": 2.5522686787078885e-05,
+      "loss": 0.5641065979003906,
+      "step": 7950
+    },
+    {
+      "epoch": 6.008966666666667,
+      "grad_norm": 1.547831416130066,
+      "learning_rate": 2.546561724000454e-05,
+      "loss": 0.5749254608154297,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1077,7 +1147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.69187376704045e+17,
+  "total_flos": 7.138017128514355e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null