Training in progress, step 3300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c520e6990555b5a48a809c7cf7dde58597a96b50cf950d3e2902cf9f6a4b0e0a
+oid sha256:da28292dbab156be574052e9c26257747e679cfc1b0e0720913591b1b49fc241
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9395488ce2d250359a34bfc91ffac18bc16f87773bb093c94728bfa8f3ef91e
+oid sha256:401d3e8d8488fc10c9973811c5925cc26bab06dac22f6c35c8fb876ead2fea97
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084132876d83624f29d3863ed0c0b0e930fe3b7a99f53b6167286f214214e720
+oid sha256:b4776aa4ae2f79df395fd23658707cbcd26ae09b7f65f95efe553922891ee4cd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
+oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3147220611572266,
-  "best_model_checkpoint": "./outputs/checkpoint-3200",
-  "epoch": 2.3315118397085612,
+  "best_metric": 1.3015214204788208,
+  "best_model_checkpoint": "./outputs/checkpoint-3300",
+  "epoch": 2.4043715846994536,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,13 +455,27 @@
       "eval_samples_per_second": 43.683,
       "eval_steps_per_second": 5.466,
       "step": 3200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.2811,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.3015214204788208,
+      "eval_runtime": 143.5355,
+      "eval_samples_per_second": 43.71,
+      "eval_steps_per_second": 5.469,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.9074327262757683e+17,
+  "total_flos": 1.967030879005655e+17,
   "trial_name": null,
   "trial_params": null
 }