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:eb0c6ad7bac22621efd8f7c6bfde56e44aa6c8f05d28dcecc3d1b696c0a48b6c
+oid sha256:fb4aa2667068b7e14a21ae322f2b6af7ba44dde6e82e2a08acef916bf45d0780
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a7658f18572bb6ac8360a86d3daa70f114f78a78fd88a7838d30a29cdcc619
+oid sha256:6c0b70dacbd41aa5f9ac96488d1a9ec03aab2951b8ed8318cb84b0f15f7487a0
 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": 1.3056749105453491,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.2944581508636475,
+  "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": 15.299,
       "eval_steps_per_second": 1.918,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.1257,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.2944581508636475,
+      "eval_runtime": 126.2031,
+      "eval_samples_per_second": 15.293,
+      "eval_steps_per_second": 1.918,
+      "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
 }