Training in progress, step 6500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a554f35b6a17be128fce6b6dde18077ae472e710857689bc82a3a107a5064b70
+oid sha256:4ecef08c15acbbcafdbd18353f8fac26c3a385caa8d1e0800b9015c88eca7688
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7489e1764b16dc1b56ae149e381b65054da7550c9735ed9c2fdc8fc794efba0e
+oid sha256:3ff134a511b0525e97d92ca6b0df4a29b3c192a8c38ede989f92d5a4599a5387
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c22be93200b6ea29a5a43fdc896fd16b0e2c374bfcbb275fb907bb85c40cd3
+oid sha256:44c02dc0791054ba042a754ce4b193305b8c58f3c6ec32c6d59f64ae1e19274a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6914f08d038d2fd5583fe9d1dfb74316a740319f66641c1d86781bc3fc4b8381
+oid sha256:df1b3ae13e2a70e8f07dd9d7c74ac5ab9a7fad8c5d805908d310a8c82d08cad1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f20cc39b1ac70cfd962157cd5b033ae7e76e9f02816bf84f00fd90791d769ab
+oid sha256:4505e6ebc4cb5953ed365ab7de48d1737346198587960aabd24a26dc3d267d0c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 5000,
   "best_metric": 4.414160251617432,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-5000",
-  "epoch": 0.4615029613106684,
+  "epoch": 0.4999615414198908,
   "eval_steps": 250,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1040,6 +1040,92 @@
       "eval_samples_per_second": 53.084,
       "eval_steps_per_second": 13.271,
       "step": 6000
+    },
+    {
+      "epoch": 0.46534881932159067,
+      "grad_norm": 3.6767919063568115,
+      "learning_rate": 0.00010941730083452813,
+      "loss": 4.5798,
+      "step": 6050
+    },
+    {
+      "epoch": 0.4691946773325129,
+      "grad_norm": 3.8597254753112793,
+      "learning_rate": 0.00010915995735450901,
+      "loss": 4.5867,
+      "step": 6100
+    },
+    {
+      "epoch": 0.4730405353434351,
+      "grad_norm": 2.8041980266571045,
+      "learning_rate": 0.0001089026138744899,
+      "loss": 4.4825,
+      "step": 6150
+    },
+    {
+      "epoch": 0.47688639335435734,
+      "grad_norm": 3.3872950077056885,
+      "learning_rate": 0.00010864527039447078,
+      "loss": 4.5624,
+      "step": 6200
+    },
+    {
+      "epoch": 0.4807322513652796,
+      "grad_norm": 3.698118209838867,
+      "learning_rate": 0.00010838792691445166,
+      "loss": 4.4889,
+      "step": 6250
+    },
+    {
+      "epoch": 0.4807322513652796,
+      "eval_loss": 4.451441287994385,
+      "eval_runtime": 19.2349,
+      "eval_samples_per_second": 51.989,
+      "eval_steps_per_second": 12.997,
+      "step": 6250
+    },
+    {
+      "epoch": 0.4845781093762018,
+      "grad_norm": 3.7140421867370605,
+      "learning_rate": 0.00010813058343443254,
+      "loss": 4.4654,
+      "step": 6300
+    },
+    {
+      "epoch": 0.48842396738712407,
+      "grad_norm": 3.095348834991455,
+      "learning_rate": 0.00010787323995441342,
+      "loss": 4.4761,
+      "step": 6350
+    },
+    {
+      "epoch": 0.4922698253980463,
+      "grad_norm": 3.289018392562866,
+      "learning_rate": 0.00010761589647439432,
+      "loss": 4.5459,
+      "step": 6400
+    },
+    {
+      "epoch": 0.49611568340896856,
+      "grad_norm": 3.9891817569732666,
+      "learning_rate": 0.0001073585529943752,
+      "loss": 4.3685,
+      "step": 6450
+    },
+    {
+      "epoch": 0.4999615414198908,
+      "grad_norm": 4.315449237823486,
+      "learning_rate": 0.00010710120951435608,
+      "loss": 4.4197,
+      "step": 6500
+    },
+    {
+      "epoch": 0.4999615414198908,
+      "eval_loss": 4.4507598876953125,
+      "eval_runtime": 18.8652,
+      "eval_samples_per_second": 53.008,
+      "eval_steps_per_second": 13.252,
+      "step": 6500
     }
   ],
   "logging_steps": 50,