Training in progress, step 9851, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb9560a8c2fe423ef88591ac0d75f94884fe5582f9b6b783282d22b1370fc23
+oid sha256:8b1eabd77d190b17654c8c986e9239c763f0de2696fc13757ebbfea99d1ab898
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07c0e371e8347d7031e7a77e1760ae234fe283d2998e8890cb9f2acf682bd6f
+oid sha256:3a27f1f4fa6a539ecd24c414a787a0da9924a806bc14762914d726d8c3fba45b
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02bf5604d96d55b809dd1552690250e2164168d4b80ec847e5101bd7d910b5f
+oid sha256:f846559439d6fa707e08e85521a12eee437c8cb62c3340d7028744e6838c14fa
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8a70b54b4c634942b08249f8cc6e6889c33d7c513637bc49b9d2b7a00426ce
+oid sha256:5a5356fffe7bb053301c50aaf04556d44d143af51d6846b85dda4a04030a9c1e
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7cd3679656ae98477cc816a6c7c865253dbb97497498a91f08c26ecf155e5b3
+oid sha256:b04e47ef60962624b2bf17f74185d606eb69ce81d5f67b919559d74716d67b80
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9136823938478719,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9851,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -645,6 +645,62 @@
       "learning_rate": 9.104509510579184e-06,
       "loss": 1.952,
       "step": 9000
+    },
+    {
+      "epoch": 0.9238344204461816,
+      "grad_norm": 6.028636932373047,
+      "learning_rate": 8.035905107929046e-06,
+      "loss": 1.957,
+      "step": 9100
+    },
+    {
+      "epoch": 0.9339864470444913,
+      "grad_norm": 5.458266735076904,
+      "learning_rate": 6.9673007052789065e-06,
+      "loss": 1.9445,
+      "step": 9200
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "grad_norm": 7.229398727416992,
+      "learning_rate": 5.898696302628767e-06,
+      "loss": 1.8976,
+      "step": 9300
+    },
+    {
+      "epoch": 0.9542905002411106,
+      "grad_norm": 5.801294803619385,
+      "learning_rate": 4.830091899978628e-06,
+      "loss": 1.9468,
+      "step": 9400
+    },
+    {
+      "epoch": 0.9644425268394203,
+      "grad_norm": 4.766051769256592,
+      "learning_rate": 3.7614874973284893e-06,
+      "loss": 1.8822,
+      "step": 9500
+    },
+    {
+      "epoch": 0.97459455343773,
+      "grad_norm": 5.5660200119018555,
+      "learning_rate": 2.69288309467835e-06,
+      "loss": 1.8705,
+      "step": 9600
+    },
+    {
+      "epoch": 0.9847465800360397,
+      "grad_norm": 7.402261734008789,
+      "learning_rate": 1.6242786920282113e-06,
+      "loss": 1.9297,
+      "step": 9700
+    },
+    {
+      "epoch": 0.9948986066343494,
+      "grad_norm": 8.760640144348145,
+      "learning_rate": 5.556742893780722e-07,
+      "loss": 1.8924,
+      "step": 9800
     }
   ],
   "logging_steps": 100,
@@ -659,12 +715,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4893769911505920.0,
+  "total_flos": 5355046335700656.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null