Training in progress, step 750, checkpoint

last-checkpoint/lora_top/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c935a4db11d9954248a9ac8c7f1ed129a2d53ead6a4137b79d300258c6b6fd
+oid sha256:d5999d72c1222f72a4968e4d8e4eb3c8728c8d56481f4f0e1e0c0a1f3c5ff835
 size 12591264

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c794acd8ed44a50952d429716499bc5f43af1db5a3592ccabf56d02c4146e251
+oid sha256:611b03eef46d707027dae04702e351acde7c973d8bf2ea65e1a47d8aa941d2d4
 size 25206586

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe75e0f6d5068d897d45b2b460d1ca19c86e7c11996a5acadcd9e0af782efe20
+oid sha256:e6b729b9def64816500ff70c349edf6d0ea9335a9d5fd4690519f3e17c4cb8e3
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e6f142d93dbd6e62ebe01d74ed2ceb68210344a36e52cda5c9422f1f0eeb827
+oid sha256:e4bd676352a42650ddef3ebd028841320ee20dd5d83b6e34b1d1463e0d94bcf5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.631777286529541,
-  "best_model_checkpoint": "./output/checkpoint-600",
-  "epoch": 0.9259259259259259,
+  "best_metric": 3.404348134994507,
+  "best_model_checkpoint": "./output/checkpoint-750",
+  "epoch": 1.1574074074074074,
   "eval_steps": 150,
-  "global_step": 600,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -459,6 +459,119 @@
       "eval_samples_per_second": 34.423,
       "eval_steps_per_second": 34.423,
       "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 3.062471866607666,
+      "learning_rate": 0.0002920523948642432,
+      "loss": 3.4515,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 2.787814140319824,
+      "learning_rate": 0.00029174058845931434,
+      "loss": 3.6189,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 2.71366810798645,
+      "learning_rate": 0.0002914229556539539,
+      "loss": 3.4178,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 2.544954776763916,
+      "learning_rate": 0.00029109950950480235,
+      "loss": 3.5334,
+      "step": 640
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 2.5218825340270996,
+      "learning_rate": 0.00029077026330746403,
+      "loss": 3.3136,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 3.377516746520996,
+      "learning_rate": 0.00029043523059596053,
+      "loss": 3.0759,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 3.7312910556793213,
+      "learning_rate": 0.00029009442514217447,
+      "loss": 3.0688,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 3.517127513885498,
+      "learning_rate": 0.00028974786095528306,
+      "loss": 3.1925,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 3.9042561054229736,
+      "learning_rate": 0.00028939555228118277,
+      "loss": 3.1548,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 3.7608659267425537,
+      "learning_rate": 0.0002890375136019032,
+      "loss": 3.0335,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 3.591569662094116,
+      "learning_rate": 0.0002886737596350122,
+      "loss": 3.1341,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.2849345207214355,
+      "learning_rate": 0.0002883043053330106,
+      "loss": 2.9512,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 3.238452196121216,
+      "learning_rate": 0.0002879291658827176,
+      "loss": 2.9095,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 4.236405849456787,
+      "learning_rate": 0.00028754835670464677,
+      "loss": 2.9601,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 3.696310043334961,
+      "learning_rate": 0.00028716189345237184,
+      "loss": 2.9871,
+      "step": 750
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "eval_loss": 3.404348134994507,
+      "eval_runtime": 13.6336,
+      "eval_samples_per_second": 36.674,
+      "eval_steps_per_second": 36.674,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -478,7 +591,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2268906529357824.0,
+  "total_flos": 2848396981714944.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null