Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376b5eddbde07923e78c8d3161769842db2a582947a1c1c862f0d652245ffb1d
+oid sha256:9f4bb689bd65373ef6717dc634345f6cc7c0c2626a9a5a94183aae7778d8c17f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c96ba56c1327aa7721235dc72edfeaf5d7bf11f2d9bcbff8e2f326610b9b39
+oid sha256:34dd07745789cd80f6a5b25be9100fc1110ebc44c2ab224f9dc2b548036856c9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eda86b469533e86a34682e0068384ac45b349522c1991400b8806ee812a1bf1
+oid sha256:028655e510a909aa7d6085e69d23b85f281b9fdd6d7a66b5175d2c3d8b80ca35
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4164679050445557,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.4017506837844849,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5333333333333333,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 12.903,
       "eval_steps_per_second": 1.618,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.1691,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.4017506837844849,
+      "eval_runtime": 112.3429,
+      "eval_samples_per_second": 12.916,
+      "eval_steps_per_second": 1.62,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.909463700824064e+16,
+  "total_flos": 2.549292795076608e+16,
   "trial_name": null,
   "trial_params": null
 }