Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b335c2194cfd60f04249bd76b98ff04e290c73fca51af64a2a4a00e83ac4f287
+oid sha256:6d197d13e95ecedd3c92b1e419c3fa639e69b2ecef35f4f8d11c8ec3bb217933
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38abb10ea643512c32adf3660f5d0e32ba9305747bc71ca5eeed89f7410e969
+oid sha256:e2af8bdd562181e23a67fb1ef60be680f5a27f3597b4e6c92be7550df3e56b3a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347cad9f3bce277eed003720972c437ba21dbbd4b008635e9d49d0ca58e0dcb4
+oid sha256:b44a40a272b348c4ca9b50ab67314e7f3e02ed0a63f0e65a984b9a85dda18fc1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478733a125645f7571e11a00dfec746713e56b183a03f33534a6b81d3808d636
+oid sha256:3e2a7616f99506ce2115c2b51a0c8d6af99dd5ac2b72ef98b701eba7ab661118
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5617916584014893,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 1.5464540719985962,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 1.6029143897996359,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,13 +301,27 @@
       "eval_samples_per_second": 42.924,
       "eval_steps_per_second": 5.371,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.5299,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5464540719985962,
+      "eval_runtime": 143.5449,
+      "eval_samples_per_second": 43.708,
+      "eval_steps_per_second": 5.469,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2505986444644352e+17,
+  "total_flos": 1.3101343701897216e+17,
   "trial_name": null,
   "trial_params": null
 }