Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655af0c18f1aa994a08b0e274a1eb9611d19724a533e86fe9b7b5ab0e6a537e3
+oid sha256:7f7ac2629d421b57c5bb2709234a62bab48ae7f4feaca05be73f6705b0fd962d
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aaf5e4fa2794ca13b2259eb4054a51f627c559800326b07adeb37bf8c8680fe
+oid sha256:ac2cb0591eb5b0f05cbb3c8ab8c6024d6b7f9dd98e3417733f89efab313bbf3d
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc62614d66705b8b13a0d65984d823126f5707ef0d8b71f73a02375c1eb0a11
+oid sha256:b6354a4b04feedc19b821f8af1464ec698fc5ee0df4728119ed85d846a048e2a
 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": 1.3046056032180786,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.2946586608886719,
+  "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": 15.089,
       "eval_steps_per_second": 1.892,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.1256,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.2946586608886719,
+      "eval_runtime": 128.2992,
+      "eval_samples_per_second": 15.043,
+      "eval_steps_per_second": 1.886,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0639944335081472e+16,
+  "total_flos": 1.4194150656786432e+16,
   "trial_name": null,
   "trial_params": null
 }