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:ff953f0fa73b96627f6fe8d04e227bf838ac7c98d5d71889beb7b410b93d185f
+oid sha256:601be6867d20b2c0173d032fa0906ae1a640ed66154293d554f582e9a2aa08db
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b6b781f56acfe75c55068d1f47755ab8ca67543bdf3926d521fbbcc1a41b882
+oid sha256:b1e9251f50ad678011925ca5532b4caf04fd62f0bb8b383660338a95fd107a50
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69702f8e1ff659b984f963bb890ddf81a9ac034534be37b04b97fff575a18b35
+oid sha256:af0a74da518cffe2c593216f7fa93fbcfcf6dd279608deff98a3bbfa8adf8b23
 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": 1.4535853862762451,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 1.438491940498352,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 1.6029143897996359,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,13 +301,27 @@
       "eval_samples_per_second": 43.721,
       "eval_steps_per_second": 5.47,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.4209,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.438491940498352,
+      "eval_runtime": 143.5083,
+      "eval_samples_per_second": 43.719,
+      "eval_steps_per_second": 5.47,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.25188037637931e+17,
+  "total_flos": 1.3114779429401395e+17,
   "trial_name": null,
   "trial_params": null
 }