Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1615a27846e2fc7e29e90ffc163230511731ab45b760a836e71cf204236e624d
+oid sha256:0f77dbb7c6bf6487a48a714e4c4e440e388d69a8afa7310e97fc320615f989a6
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df96e6756fb0b0f050ff10208655f563c96fccd6a701602a5e90ccbd1e235e0
+oid sha256:b1814592ba74cdcca20fb08c3ea7e5ee573986aff77c3810b20a982bd1be5d78
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74818f2f3daacf3c0fca3dde38a211872e713dacdefaa18d7435559b30dc197d
-size 14244
+oid sha256:0cdad770e6415de25f2503b80a04125ce36c191e7ebbe40cc70935c15b3079b5
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc76fea5e634e306eb2d4aa830b8059981049eb83bd4681631ccd02732a47898
+oid sha256:a9aa9825ab5c6a64b78405ab88bd271bc07d34d8fb6641eef252a11c55bfe386
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8c94e41b1ac1e8ac4ea58294a516d2e00679d859d84c40c165bc9d685fc309
+oid sha256:0276c75f304794326dfbdfec2d07b2898318c16d7455e1133773ea583662ada9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2500,
-  "best_metric": 4.558788776397705,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-2500",
-  "epoch": 0.19229290054611184,
+  "best_global_step": 3000,
+  "best_metric": 4.55267858505249,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-3000",
+  "epoch": 0.2307514806553342,
   "eval_steps": 250,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -438,6 +438,92 @@
       "eval_samples_per_second": 52.664,
       "eval_steps_per_second": 13.166,
       "step": 2500
+    },
+    {
+      "epoch": 0.19613875855703408,
+      "grad_norm": 2.456908702850342,
+      "learning_rate": 0.00012742105069666555,
+      "loss": 4.3847,
+      "step": 2550
+    },
+    {
+      "epoch": 0.19998461656795632,
+      "grad_norm": 5.154629707336426,
+      "learning_rate": 0.00012716370721664645,
+      "loss": 4.6019,
+      "step": 2600
+    },
+    {
+      "epoch": 0.20383047457887854,
+      "grad_norm": 3.0423479080200195,
+      "learning_rate": 0.0001269063637366273,
+      "loss": 4.4796,
+      "step": 2650
+    },
+    {
+      "epoch": 0.20767633258980078,
+      "grad_norm": 4.218437194824219,
+      "learning_rate": 0.00012664902025660819,
+      "loss": 4.5566,
+      "step": 2700
+    },
+    {
+      "epoch": 0.21152219060072303,
+      "grad_norm": 5.20380163192749,
+      "learning_rate": 0.0001263916767765891,
+      "loss": 4.3311,
+      "step": 2750
+    },
+    {
+      "epoch": 0.21152219060072303,
+      "eval_loss": 4.574987888336182,
+      "eval_runtime": 18.8565,
+      "eval_samples_per_second": 53.032,
+      "eval_steps_per_second": 13.258,
+      "step": 2750
+    },
+    {
+      "epoch": 0.21536804861164527,
+      "grad_norm": 4.369246482849121,
+      "learning_rate": 0.00012613433329656997,
+      "loss": 4.4131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.21921390662256748,
+      "grad_norm": 5.0442376136779785,
+      "learning_rate": 0.00012587698981655085,
+      "loss": 4.5027,
+      "step": 2850
+    },
+    {
+      "epoch": 0.22305976463348973,
+      "grad_norm": 3.6387200355529785,
+      "learning_rate": 0.00012561964633653173,
+      "loss": 4.6659,
+      "step": 2900
+    },
+    {
+      "epoch": 0.22690562264441197,
+      "grad_norm": 3.7960562705993652,
+      "learning_rate": 0.0001253623028565126,
+      "loss": 4.4826,
+      "step": 2950
+    },
+    {
+      "epoch": 0.2307514806553342,
+      "grad_norm": 4.273965835571289,
+      "learning_rate": 0.0001251049593764935,
+      "loss": 4.5869,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2307514806553342,
+      "eval_loss": 4.55267858505249,
+      "eval_runtime": 18.9735,
+      "eval_samples_per_second": 52.705,
+      "eval_steps_per_second": 13.176,
+      "step": 3000
     }
   ],
   "logging_steps": 50,