Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9431104886add9484e9a908263c404a811f2182da11c5c59ba22d999f155bd12
+oid sha256:1ff9162fbd145402974375e09dc12bab1aff0e8f70bc19a3f988845881883009
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c61a56239e70904df54c63aefaa5ca175622aefee4045a39933a01fffff9e0
+oid sha256:2b194c558949949d1f1dcd9ee90dd9469de8c9839f43676b19d73133bde27646
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44c27a4571e6eb1a7ee928ce7b6d2caa61e9848f87f288e6907748065a8b638
+oid sha256:2915f019b93087780b8c2fddccd9b297eeaba58311ffa4c3bfcb1370794510fa
 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": 1.441214680671692,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.4250988960266113,
+  "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": 12.727,
       "eval_steps_per_second": 1.596,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.1801,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.4250988960266113,
+      "eval_runtime": 151.7377,
+      "eval_samples_per_second": 12.719,
+      "eval_steps_per_second": 1.595,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.273189776703488e+16,
+  "total_flos": 1.913313634025472e+16,
   "trial_name": null,
   "trial_params": null
 }