Upload trainer_state.json

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012416190712689347,
+  "epoch": 0.010260970687827069,
   "eval_steps": 500,
   "global_step": 150,
   "is_hyper_param_search": false,
@@ -9,108 +9,108 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0008277460475126231,
-      "grad_norm": 0.6720314025878906,
-      "learning_rate": 0.00019448275862068965,
-      "loss": 2.806,
+      "epoch": 0.0006840647125218045,
+      "grad_norm": 0.6777583360671997,
+      "learning_rate": 0.0001931034482758621,
+      "loss": 2.5631,
       "step": 10
     },
     {
-      "epoch": 0.0016554920950252463,
-      "grad_norm": 0.7282748818397522,
-      "learning_rate": 0.00018068965517241382,
-      "loss": 2.4015,
+      "epoch": 0.001368129425043609,
+      "grad_norm": 0.529003918170929,
+      "learning_rate": 0.0001793103448275862,
+      "loss": 2.2202,
       "step": 20
     },
     {
-      "epoch": 0.0024832381425378696,
-      "grad_norm": 0.6224257349967957,
-      "learning_rate": 0.00016689655172413793,
-      "loss": 2.4062,
+      "epoch": 0.0020521941375654137,
+      "grad_norm": 0.6383516192436218,
+      "learning_rate": 0.00016551724137931035,
+      "loss": 2.2541,
       "step": 30
     },
     {
-      "epoch": 0.0033109841900504926,
-      "grad_norm": 0.6465514898300171,
-      "learning_rate": 0.00015310344827586207,
-      "loss": 2.3612,
+      "epoch": 0.002736258850087218,
+      "grad_norm": 0.547764778137207,
+      "learning_rate": 0.00015172413793103449,
+      "loss": 2.1831,
       "step": 40
     },
     {
-      "epoch": 0.004138730237563116,
-      "grad_norm": 0.5610107183456421,
+      "epoch": 0.003420323562609023,
+      "grad_norm": NaN,
       "learning_rate": 0.0001393103448275862,
-      "loss": 2.1203,
+      "loss": 2.2025,
       "step": 50
     },
     {
-      "epoch": 0.004966476285075739,
-      "grad_norm": 0.5969945192337036,
+      "epoch": 0.0041043882751308275,
+      "grad_norm": 0.6107162237167358,
       "learning_rate": 0.00012551724137931035,
-      "loss": 2.2384,
+      "loss": 2.1387,
       "step": 60
     },
     {
-      "epoch": 0.005794222332588362,
-      "grad_norm": 0.6113339066505432,
+      "epoch": 0.004788452987652632,
+      "grad_norm": 0.5852159261703491,
       "learning_rate": 0.00011172413793103449,
-      "loss": 2.3128,
+      "loss": 2.1362,
       "step": 70
     },
     {
-      "epoch": 0.006621968380100985,
-      "grad_norm": 0.8051493167877197,
+      "epoch": 0.005472517700174436,
+      "grad_norm": 0.587351381778717,
       "learning_rate": 9.793103448275862e-05,
-      "loss": 2.2082,
+      "loss": 2.1783,
       "step": 80
     },
     {
-      "epoch": 0.007449714427613608,
-      "grad_norm": 0.6741610169410706,
+      "epoch": 0.006156582412696241,
+      "grad_norm": 0.4379996657371521,
       "learning_rate": 8.413793103448277e-05,
-      "loss": 2.3156,
+      "loss": 2.0619,
       "step": 90
     },
     {
-      "epoch": 0.008277460475126232,
-      "grad_norm": 0.5629040598869324,
+      "epoch": 0.006840647125218046,
+      "grad_norm": 0.6348068714141846,
       "learning_rate": 7.03448275862069e-05,
-      "loss": 2.1989,
+      "loss": 2.1559,
       "step": 100
     },
     {
-      "epoch": 0.009105206522638855,
-      "grad_norm": 0.7672610282897949,
+      "epoch": 0.0075247118377398505,
+      "grad_norm": 0.5908586382865906,
       "learning_rate": 5.6551724137931037e-05,
-      "loss": 2.1749,
+      "loss": 2.0957,
       "step": 110
     },
     {
-      "epoch": 0.009932952570151478,
-      "grad_norm": 0.5322269201278687,
+      "epoch": 0.008208776550261655,
+      "grad_norm": 0.6663537621498108,
       "learning_rate": 4.275862068965518e-05,
-      "loss": 2.171,
+      "loss": 2.2033,
       "step": 120
     },
     {
-      "epoch": 0.010760698617664101,
-      "grad_norm": 0.7353241443634033,
+      "epoch": 0.008892841262783458,
+      "grad_norm": 0.5192745923995972,
       "learning_rate": 2.8965517241379313e-05,
-      "loss": 2.1584,
+      "loss": 2.0376,
       "step": 130
     },
     {
-      "epoch": 0.011588444665176724,
-      "grad_norm": 0.6774106025695801,
+      "epoch": 0.009576905975305264,
+      "grad_norm": 0.6954190731048584,
       "learning_rate": 1.5172413793103448e-05,
-      "loss": 2.2079,
+      "loss": 2.108,
       "step": 140
     },
     {
-      "epoch": 0.012416190712689347,
-      "grad_norm": 0.5964234471321106,
+      "epoch": 0.010260970687827069,
+      "grad_norm": 0.6196115016937256,
       "learning_rate": 1.3793103448275862e-06,
-      "loss": 2.1165,
+      "loss": 1.9693,
       "step": 150
     }
   ],
@@ -131,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.120470461579264e+16,
+  "total_flos": 5.164445885681664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null