Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73454161117257a6eadf951d72a89a7fbd44621ac88cc94b3925c5e99db69f97
+oid sha256:c520e6990555b5a48a809c7cf7dde58597a96b50cf950d3e2902cf9f6a4b0e0a
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883300515096f663a55a666a62892f0941b8d1f96d149713b704ce98c7bc0be6
+oid sha256:c9395488ce2d250359a34bfc91ffac18bc16f87773bb093c94728bfa8f3ef91e
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e42983a0941a5ea3ab8dd356cda0bea564cad32d8e894b126d9bb07e48e1e57
+oid sha256:084132876d83624f29d3863ed0c0b0e930fe3b7a99f53b6167286f214214e720
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
+oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3265715837478638,
-  "best_model_checkpoint": "./outputs/checkpoint-3100",
-  "epoch": 2.2586520947176685,
+  "best_metric": 1.3147220611572266,
+  "best_model_checkpoint": "./outputs/checkpoint-3200",
+  "epoch": 2.3315118397085612,
   "eval_steps": 100,
-  "global_step": 3100,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -441,13 +441,27 @@
       "eval_samples_per_second": 43.69,
       "eval_steps_per_second": 5.466,
       "step": 3100
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002,
+      "loss": 1.3005,
+      "step": 3200
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 1.3147220611572266,
+      "eval_runtime": 143.6246,
+      "eval_samples_per_second": 43.683,
+      "eval_steps_per_second": 5.466,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.847919861143716e+17,
+  "total_flos": 1.9074327262757683e+17,
   "trial_name": null,
   "trial_params": null
 }