Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7899771a087474a43e06bd28a8f45f3cd059337cd48735439b8ca48c96012a96
+oid sha256:e5115a33042e3fd397dd32d66d32a19c0c16be57ac770db5f8d1d1f33faa5fc9
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e871bc1215fd69846b0c86915f65f94a04012ae84b81406e0748cd8df5d5c493
+oid sha256:cec98cd6c428dfc7f63b47f4b24f7c520934f5445ba14cb6244683725a7da0cd
 size 323298107

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d01b6bcf1ce8d302bf604d2caa30f647c31e144636452ecbabe94efa6e1ff85
+oid sha256:3b7b75229400998a7d66acd1bde59e0297fb4e980d83e44d61fd3bb4d4fabf86
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1b94068eaea136d63c62e77d4a2297e17922006283b618e301589c374ba369
+oid sha256:acdc4719af55e3178da4e7dfea565c4d31664a72cb7973326a772c14ba81cc93
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a843a996a1f9dfcf8170c57ee770c1bf26ad7bacf1e9c3a455b70d583baef0
+oid sha256:e3defd38fd8f62a7a3f6971d154c9135f2e1818e83bbd2a48dbbd5417f2bd284
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446221154b37e4dc88e7ffc37fc20cc194db931246268ef3708102ef7a9ef6f4
+oid sha256:aca282f4652e04d966ebc751281f63a231106b830e64c0934d14aac4688fe840
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 400,
-  "best_metric": 0.2940136194229126,
-  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-400",
-  "epoch": 0.943952802359882,
+  "best_global_step": 450,
+  "best_metric": 0.29345282912254333,
+  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-450",
+  "epoch": 1.0613569321533922,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,49 @@
       "eval_samples_per_second": 3.134,
       "eval_steps_per_second": 0.784,
       "step": 400
+    },
+    {
+      "epoch": 0.967551622418879,
+      "grad_norm": 1.4067103862762451,
+      "learning_rate": 1.0493642866720528e-05,
+      "loss": 0.206,
+      "step": 410
+    },
+    {
+      "epoch": 0.9911504424778761,
+      "grad_norm": 2.350339651107788,
+      "learning_rate": 1.0151831192678511e-05,
+      "loss": 0.2531,
+      "step": 420
+    },
+    {
+      "epoch": 1.0141592920353983,
+      "grad_norm": 2.0622878074645996,
+      "learning_rate": 9.807219538334829e-06,
+      "loss": 0.2002,
+      "step": 430
+    },
+    {
+      "epoch": 1.0377581120943953,
+      "grad_norm": 1.5239025354385376,
+      "learning_rate": 9.460392046819943e-06,
+      "loss": 0.1457,
+      "step": 440
+    },
+    {
+      "epoch": 1.0613569321533922,
+      "grad_norm": 1.3972654342651367,
+      "learning_rate": 9.11193661727792e-06,
+      "loss": 0.1686,
+      "step": 450
+    },
+    {
+      "epoch": 1.0613569321533922,
+      "eval_loss": 0.29345282912254333,
+      "eval_runtime": 376.3252,
+      "eval_samples_per_second": 3.136,
+      "eval_steps_per_second": 0.784,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -371,7 +414,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.618911528799437e+16,
+  "total_flos": 1.0824644623440282e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null