Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a93aad74494e1da199a78d40cddc05b035544f04f6b1f54ae0d9518920ecda
+oid sha256:e0fef1db67ac977720c047d252588fd18bef0cb290d28e1d9d058df5c23bc9b4
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64fd34cf15527c9242ff55f7d79a57537a489b3a707e638c23d25fe290d76ef3
+oid sha256:1a081813ee762e60a4e3208448a1b83529283fad9ecea44e13ab242ba0ee3455
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2be089e58af285b82a77df44ed8dc14c9f419db076cc74bf8b10029313b041
+oid sha256:e30e6ed91bf92efee6b0b2958ad13a151734e9702f0b270a999e923840ecdad3
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0867207050323486,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.0864734649658203,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 10.332,
       "eval_steps_per_second": 1.296,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 0.9422,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.0864734649658203,
+      "eval_runtime": 186.4609,
+      "eval_samples_per_second": 10.351,
+      "eval_steps_per_second": 1.298,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.837764184871977e+17,
+  "total_flos": 1.9793785004539085e+17,
   "trial_name": null,
   "trial_params": null
 }