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:b6d4fff8398a005291af4bcafd5071060d689832ee1e2e0d16ca43f7ddcefa34
+oid sha256:209a24c1da8a93ac16367365eec1fae0adaa3a62bfd35bbeaed228d1e940dcba
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e68c6f34dbbb9ee51991b9cc9eb88fc6a38115b951ae1314afef0e0449d853
+oid sha256:f90ff78eb336ca2a0d175b16a248ed1a5ba3c8c8e3686c58f7b1676d16c99c58
 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": 1.1354840993881226,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 1.1310428380966187,
+  "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": 10.873,
       "eval_steps_per_second": 1.363,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 0.9393,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 1.1310428380966187,
+      "eval_runtime": 177.407,
+      "eval_samples_per_second": 10.879,
+      "eval_steps_per_second": 1.364,
+      "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
 }