Training in progress, step 15500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e8b88b22335eff4aa95a5db7b6615364abd358d14317af2dec16bcdb2efc61
+oid sha256:6067e5da0c9bf8b752e4ae8c8bf60db131ffcb5bdc72c1bef0c50cf034756793
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a93a0264eb6605e0d626be93ba5f8dee38234bcac32f7e6d5d1cccc2a1057f
+oid sha256:70b3ce160c7b776e775a166f1cb68bd1487d55fdb2e7ccd66b23097de2464f87
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c298ef220b2440e2c8688c2918aba70637e9e1c8a2951767772c4969343135c8
-size 14308
+oid sha256:4e443e4b8c749db54f7826bd4573803e0f05009235443f881fa9932376e1aba8
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08eda93be407e2e8125df91c801018bcedfb4cde17a8cf02b9f76837f9ade1c1
+oid sha256:c46d93b856d73467b22e6683f2d8e760cc9d35c9e6261e9397f7ae15ef306957
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a00183886b48331e49cfb9b953bfa8a92696629d3ac41c1b27b8636569368855
+oid sha256:682c1f39bde20c90a4373af21bd5402ac0e8e55951fcfe8f05caeac3b074ab9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 14750,
-  "best_metric": 1.4990500211715698,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-13000",
-  "epoch": 1.153757403276671,
+  "best_global_step": 15500,
+  "best_metric": 1.4925825595855713,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
+  "epoch": 1.1922159833858934,
   "eval_steps": 250,
-  "global_step": 15000,
+  "global_step": 15500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2588,6 +2588,92 @@
       "eval_samples_per_second": 55.799,
       "eval_steps_per_second": 13.95,
       "step": 15000
+    },
+    {
+      "epoch": 1.1576032612875933,
+      "grad_norm": 1.5460007190704346,
+      "learning_rate": 6.311091503988823e-05,
+      "loss": 1.442,
+      "step": 15050
+    },
+    {
+      "epoch": 1.1614491192985155,
+      "grad_norm": 1.001439094543457,
+      "learning_rate": 6.285357155986911e-05,
+      "loss": 1.5308,
+      "step": 15100
+    },
+    {
+      "epoch": 1.1652949773094377,
+      "grad_norm": 0.8740602731704712,
+      "learning_rate": 6.259622807985e-05,
+      "loss": 1.455,
+      "step": 15150
+    },
+    {
+      "epoch": 1.16914083532036,
+      "grad_norm": 2.034207820892334,
+      "learning_rate": 6.233888459983088e-05,
+      "loss": 1.5089,
+      "step": 15200
+    },
+    {
+      "epoch": 1.1729866933312822,
+      "grad_norm": 1.8656599521636963,
+      "learning_rate": 6.208154111981176e-05,
+      "loss": 1.5368,
+      "step": 15250
+    },
+    {
+      "epoch": 1.1729866933312822,
+      "eval_loss": 1.4986381530761719,
+      "eval_runtime": 18.1736,
+      "eval_samples_per_second": 55.025,
+      "eval_steps_per_second": 13.756,
+      "step": 15250
+    },
+    {
+      "epoch": 1.1768325513422044,
+      "grad_norm": 1.2697277069091797,
+      "learning_rate": 6.182419763979266e-05,
+      "loss": 1.4239,
+      "step": 15300
+    },
+    {
+      "epoch": 1.1806784093531266,
+      "grad_norm": 1.1131771802902222,
+      "learning_rate": 6.156685415977354e-05,
+      "loss": 1.4309,
+      "step": 15350
+    },
+    {
+      "epoch": 1.1845242673640488,
+      "grad_norm": 1.5322145223617554,
+      "learning_rate": 6.130951067975442e-05,
+      "loss": 1.4793,
+      "step": 15400
+    },
+    {
+      "epoch": 1.1883701253749712,
+      "grad_norm": 1.1703407764434814,
+      "learning_rate": 6.10521671997353e-05,
+      "loss": 1.4761,
+      "step": 15450
+    },
+    {
+      "epoch": 1.1922159833858934,
+      "grad_norm": 1.4056655168533325,
+      "learning_rate": 6.079482371971618e-05,
+      "loss": 1.5311,
+      "step": 15500
+    },
+    {
+      "epoch": 1.1922159833858934,
+      "eval_loss": 1.4925825595855713,
+      "eval_runtime": 18.2116,
+      "eval_samples_per_second": 54.91,
+      "eval_steps_per_second": 13.727,
+      "step": 15500
     }
   ],
   "logging_steps": 50,