Training in progress, step 27301, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ecb2f2e99a3f55ce283ec3c73dc04b2a38b8d596c5eb8a739f6b0463f816d0e
+oid sha256:0c0c310c1ea72db9327b79c3262d5c740e995fdf0b4ee984a5e16a1808195ffd
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa7532d5b46ff1991d1c3ddb490b4cebca7a510adb0c584bc416f8e750a93e4
+oid sha256:18e6a3fff60354b408c8d516a28100919c40cc962e313e3c5944958f8dce11df
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7cb9cecde71619f5455094db9dbc10b01ced14b7fff166fcfd1f46df6e480f1
+oid sha256:a29b39a8e376f23acf3c1b4114f67a384379a770783936ae950c5b920178bb90
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e8022c7f3002679e6fa3f97f4fe89fb5c796e6e8d168c42ccf78f18e8bd32d
+oid sha256:119728a071df48b2f95f13bda28fdcc42605f68fc14083a4d008966987fd7a1b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d9c773d9d655234bd445b24c5fab29b1818f6d34a0b08096443007d2a42d37
+oid sha256:3f622dd98ef6fc2bcd7320e2559be8d58ca57d1000667a66610f8a68cd0ffa59
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 24500,
   "best_metric": 1.4431298971176147,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-24500",
-  "epoch": 2.076763325898008,
+  "epoch": 2.09991539112376,
   "eval_steps": 250,
-  "global_step": 27000,
+  "global_step": 27301,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4652,6 +4652,56 @@
       "eval_samples_per_second": 55.107,
       "eval_steps_per_second": 13.777,
       "step": 27000
+    },
+    {
+      "epoch": 2.0806091839089302,
+      "grad_norm": 0.9924139380455017,
+      "learning_rate": 1.3587735745009373e-06,
+      "loss": 1.5088,
+      "step": 27050
+    },
+    {
+      "epoch": 2.084455041919852,
+      "grad_norm": 1.1177709102630615,
+      "learning_rate": 1.1014300944818204e-06,
+      "loss": 1.4285,
+      "step": 27100
+    },
+    {
+      "epoch": 2.0883008999307746,
+      "grad_norm": 1.7112759351730347,
+      "learning_rate": 8.440866144627034e-07,
+      "loss": 1.433,
+      "step": 27150
+    },
+    {
+      "epoch": 2.0921467579416966,
+      "grad_norm": 1.9338856935501099,
+      "learning_rate": 5.867431344435866e-07,
+      "loss": 1.4008,
+      "step": 27200
+    },
+    {
+      "epoch": 2.095992615952619,
+      "grad_norm": 3.0200393199920654,
+      "learning_rate": 3.2939965442446964e-07,
+      "loss": 1.4285,
+      "step": 27250
+    },
+    {
+      "epoch": 2.095992615952619,
+      "eval_loss": 1.4686814546585083,
+      "eval_runtime": 18.028,
+      "eval_samples_per_second": 55.469,
+      "eval_steps_per_second": 13.867,
+      "step": 27250
+    },
+    {
+      "epoch": 2.0998384739635414,
+      "grad_norm": 1.5137439966201782,
+      "learning_rate": 7.205617440535274e-08,
+      "loss": 1.4596,
+      "step": 27300
     }
   ],
   "logging_steps": 50,
@@ -4666,7 +4716,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }