Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2fca0462d584fde43c65c7b1a8433e500b640b3353fdaab1b986837aa1c57e
+oid sha256:1b886c2efef58451467ac8bcbd63c17273e6cfdca636ea55881dae47720aeb3c
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aaa6acb1fd5ef798f5bd201cfbbfc408fec3b2be83056659eda5ea3d1f866c1
+oid sha256:8df9e7c7ee5e1b40cf3b9bade9f9f9e81fdb6a6bea0f0cb164255b43c1a15fc1
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f905070f344ff5757d2e5f48fcda24ded17f953888429aa8e5791b2828fc54a
+oid sha256:8add635ab6b081112ff7d255bb9a21a69af8460dd1de7ddf6c5c5d319e909536
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9657241106033325,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 0.9637255072593689,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 2.9333333333333336,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 5.241,
       "eval_steps_per_second": 0.657,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.8358,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.9637255072593689,
+      "eval_runtime": 365.4459,
+      "eval_samples_per_second": 5.281,
+      "eval_steps_per_second": 0.662,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.936315915975148e+17,
+  "total_flos": 6.220289728654295e+17,
   "trial_name": null,
   "trial_params": null
 }