Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b697653fb1fadb3338a18ba8ca2e508da3603eebebb92cd2d4d0a19bf2b728f
+oid sha256:ccc347408e59845427b20f810ffc1c63dbc130f1591e6d8f133efee96fe70a1b
 size 66690264

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741805ded654520994730dcf337a922e9f9e0b80f29b4d60e7af05b2ee502050
+oid sha256:40f6c9550eac9c1f2df8f2467b0df11d0fe7a0e27b333e206fc3fb0217a4bdb3
 size 133393631

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ac6cc9f96cb23f38dad14b3c8b94857940a2c54443bb178825363cab7260c0
+oid sha256:2aecb175b401aad5342b976c594fc9d9720fb1d1217dbf6aec48e9deb3a15dd1
 size 13990

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2375bb704062abe009d16c81c5208b4a77486ea2b7e1b6be5a4f624a4401587f
+oid sha256:e301ebd8064bb9799d23981baab716db6ee7302f5ba2efc70a2dd3be85fbcb46
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1000,
   "best_metric": 9.911575317382812,
   "best_model_checkpoint": "./models/v-001/checkpoint-1000",
-  "epoch": 61.32608695652174,
+  "epoch": 64.55434782608695,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -844,6 +844,50 @@
       "eval_samples_per_second": 8.227,
       "eval_steps_per_second": 0.518,
       "step": 1900
+    },
+    {
+      "epoch": 61.97826086956522,
+      "grad_norm": 0.8085272312164307,
+      "learning_rate": 8.236784546933718e-07,
+      "loss": 3.697,
+      "step": 1920
+    },
+    {
+      "epoch": 62.619565217391305,
+      "grad_norm": 0.7857375741004944,
+      "learning_rate": 4.676975846132692e-07,
+      "loss": 3.6836,
+      "step": 1940
+    },
+    {
+      "epoch": 63.26086956521739,
+      "grad_norm": 0.7917608618736267,
+      "learning_rate": 2.1146817970871258e-07,
+      "loss": 3.6163,
+      "step": 1960
+    },
+    {
+      "epoch": 63.91304347826087,
+      "grad_norm": 0.7354781031608582,
+      "learning_rate": 5.550625190150483e-08,
+      "loss": 3.6652,
+      "step": 1980
+    },
+    {
+      "epoch": 64.55434782608695,
+      "grad_norm": 0.7902089357376099,
+      "learning_rate": 1.2588775841204658e-10,
+      "loss": 3.6326,
+      "step": 2000
+    },
+    {
+      "epoch": 64.55434782608695,
+      "eval_accuracy": 0.0008273447429635729,
+      "eval_loss": 10.191176414489746,
+      "eval_runtime": 37.3382,
+      "eval_samples_per_second": 8.088,
+      "eval_steps_per_second": 0.509,
+      "step": 2000
     }
   ],
   "logging_steps": 20,
@@ -858,12 +902,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2479524451392000.0,
+  "total_flos": 2610102966336000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null