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:d84bca271ca6da822aedb10315d06a0a63330433b969ac9d3cb454e6d1ca9639
+oid sha256:170d38a3031043f578e3b839939f2683259b2380e857825a026efb81cc2c70b7
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bd310f40aa55ba02a368992a8a260dd02d3246ac3446f890ab4935a8b31bb4
+oid sha256:174bad07f996f8ce51402077ec5f8697b1d354cda45c255a62542fc8d12013b2
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c06d15ff9b633b68ebbf688949ae28d38f1d004fd46f5c3de3aeed397a80edf
+oid sha256:f1c38a299f8b760e39f4034c705149f355ecb058b3be5ffa99a3d42cc8272c92
 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": 0.9311172366142273,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 0.9276091456413269,
+  "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": 2.112,
       "eval_steps_per_second": 0.265,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.7487,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.9276091456413269,
+      "eval_runtime": 916.7039,
+      "eval_samples_per_second": 2.105,
+      "eval_steps_per_second": 0.264,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.4402852955938816e+17,
+  "total_flos": 5.6988624815579136e+17,
   "trial_name": null,
   "trial_params": null
 }