Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bd2bc512ee4b879274d0e429ac490ea9478616912b8b41ccfd3e8493782dad
+oid sha256:c7bf06c3dd60bace286de37675533cc4c41c87d98a8ac647b844f650fd7e2622
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9828766169c2931047bd8fe079bd413068f496b660f2b139e113165e26e24e7e
-size 25222277
+oid sha256:717ed77b4177d6e44d4e6e75bee25f8c57f6703a2170d3f3c75c5474370a884d
+size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85658496e06077f87b750aeb031c8edf46d72979c48ec879f8596b632cba3381
+oid sha256:8cfb045d2aace0aa6b48f6b2659a883d08eab7c39a2384b021a9dd36bdce66b0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1461560726165771,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.1315025091171265,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 10.361,
       "eval_steps_per_second": 1.299,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.9918,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.1315025091171265,
+      "eval_runtime": 186.4761,
+      "eval_samples_per_second": 10.35,
+      "eval_steps_per_second": 1.298,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.8242451495747584e+16,
+  "total_flos": 4.242711954033869e+16,
   "trial_name": null,
   "trial_params": null
 }