Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0698bceed7cb5683561305da34c0da90d4fb42c982fed50846670487d1bcd90a
+oid sha256:1fd6665b3fca8307b4a850466143a7febba5378fb87299f6c228b334280a8be8
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd8391942631a3988f0c74ed7670346d5b0bab996fe790aad94ae67fb5cf736
+oid sha256:80609acf10ab518787737b5f6a0c39d203f2316a6b68a05cf35e2f798c8eeddb
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4a977350df40c9b5afb65eb8e48a767be847c486a19a831f37b3267caf5f9f
+oid sha256:20c40dab02973b1cc46cf9629cd02e8f44b9b493929030f20bf23390e0e7e4d8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.136294960975647,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 1.1321903467178345,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.4666666666666668,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 10.878,
       "eval_steps_per_second": 1.364,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 0.9393,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 1.1321903467178345,
+      "eval_runtime": 177.2509,
+      "eval_samples_per_second": 10.889,
+      "eval_steps_per_second": 1.365,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.474685431062528e+16,
+  "total_flos": 8.219848108179456e+16,
   "trial_name": null,
   "trial_params": null
 }