Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cb3af7f12d93b82e14f620097e75b7051c2f53f32b194f549347dc112ca906
+oid sha256:68d908b68e0276946898ab780e8afec1d1c8d6bc0154a09fe2a6360efa32530c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c92f7f30fc1a44edb3f7fd8e9ac7797d23e6025081b95a0976cf1d49452e0ac
+oid sha256:507a4c7824eb049c393e024a09056bc497095509fcf829728511c895844bea52
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe94f3c099526d2d0ffee989f862b44e24dbf9220e583fff14c71db11059188
+oid sha256:92942cd27ddd53a4c545428e2cc49f7db59067ae104a2b7a947f9d90e3f8e9f3
 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": 1.5133259296417236,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.500829815864563,
+  "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": 15.558,
       "eval_steps_per_second": 1.951,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.2661,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.500829815864563,
+      "eval_runtime": 93.3122,
+      "eval_samples_per_second": 15.55,
+      "eval_steps_per_second": 1.95,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.753797686280192e+16,
+  "total_flos": 2.340946069733376e+16,
   "trial_name": null,
   "trial_params": null
 }