Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b987300ed3bf1eabefdcf46c561f7da4872cca39645cb9d5b662921dee7e38
+oid sha256:376b5eddbde07923e78c8d3161769842db2a582947a1c1c862f0d652245ffb1d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9662648e8ff68edf557966408fa4f52086bc2cd000e7752c95a7844a5c294d8
+oid sha256:92c96ba56c1327aa7721235dc72edfeaf5d7bf11f2d9bcbff8e2f326610b9b39
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a459123c36ae0df8f68f5770d79b0ab359abbfdd421de1deab88f1fca75f214
+oid sha256:9eda86b469533e86a34682e0068384ac45b349522c1991400b8806ee812a1bf1
 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": 1.4343539476394653,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.4164679050445557,
+  "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": 12.886,
       "eval_steps_per_second": 1.616,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.1774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.4164679050445557,
+      "eval_runtime": 112.4536,
+      "eval_samples_per_second": 12.903,
+      "eval_steps_per_second": 1.618,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.272610076000256e+16,
+  "total_flos": 1.909463700824064e+16,
   "trial_name": null,
   "trial_params": null
 }