Training in progress, step 9500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eecb66b5b687b2480b18fa49a3a7093840558d372a33d29f18cc9ddc9d5973f6
+oid sha256:f99a737d1188d26749e1f79393398cf632ff62d367413aa544169176d1155d64
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:246b4fcf33df56c5b498c44dfc6d12184de263d7f241a380037b6387910c9a75
+oid sha256:0bfc7b1dae63d312ce05a66fb9cd5a96fb16e5d6a11cfa4ba0f11944d2a8a072
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b68f148982346537acf196edf0aa44542990dee8efc3893aa00dae2ca2e993b5
+oid sha256:1c4598e219bb7f2bb5d2c34aa1d6d86aefb320efdbbe18af0ce36833a2da16e9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c5d85e32786b1e35a549f6e7bfc25b63f0617678a2a77d09f7e94475702a2a
+oid sha256:c80bec9d89af6c0ab5db061d313a8506f3b43411e72ccae614261263d0bf59b7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9af065edeaca88f16d8fcf52e4c33f05f28955d2f4f45d569975711d2168cd7
+oid sha256:10022e052ca5e66e7d62da25b0a5c62caae94a4e337df0aab0b25e792e2f0920
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 8500,
-  "best_metric": 4.392988204956055,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-8500",
-  "epoch": 0.6922544419660026,
+  "best_global_step": 9500,
+  "best_metric": 4.328299045562744,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-9500",
+  "epoch": 0.7307130220752249,
   "eval_steps": 250,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1556,6 +1556,92 @@
       "eval_samples_per_second": 53.269,
       "eval_steps_per_second": 13.317,
       "step": 9000
+    },
+    {
+      "epoch": 0.6961002999769248,
+      "grad_norm": 9.26623821258545,
+      "learning_rate": 9.39869857725819e-05,
+      "loss": 4.3073,
+      "step": 9050
+    },
+    {
+      "epoch": 0.6999461579878471,
+      "grad_norm": 3.5981953144073486,
+      "learning_rate": 9.372964229256276e-05,
+      "loss": 4.3923,
+      "step": 9100
+    },
+    {
+      "epoch": 0.7037920159987693,
+      "grad_norm": 3.734813690185547,
+      "learning_rate": 9.347229881254364e-05,
+      "loss": 4.2449,
+      "step": 9150
+    },
+    {
+      "epoch": 0.7076378740096916,
+      "grad_norm": 5.646871566772461,
+      "learning_rate": 9.321495533252453e-05,
+      "loss": 4.3953,
+      "step": 9200
+    },
+    {
+      "epoch": 0.7114837320206138,
+      "grad_norm": 4.284733295440674,
+      "learning_rate": 9.295761185250541e-05,
+      "loss": 4.475,
+      "step": 9250
+    },
+    {
+      "epoch": 0.7114837320206138,
+      "eval_loss": 4.348310470581055,
+      "eval_runtime": 19.0285,
+      "eval_samples_per_second": 52.553,
+      "eval_steps_per_second": 13.138,
+      "step": 9250
+    },
+    {
+      "epoch": 0.7153295900315361,
+      "grad_norm": 5.92791223526001,
+      "learning_rate": 9.27002683724863e-05,
+      "loss": 4.5493,
+      "step": 9300
+    },
+    {
+      "epoch": 0.7191754480424583,
+      "grad_norm": 4.768808841705322,
+      "learning_rate": 9.244292489246719e-05,
+      "loss": 4.2508,
+      "step": 9350
+    },
+    {
+      "epoch": 0.7230213060533806,
+      "grad_norm": 3.473097562789917,
+      "learning_rate": 9.218558141244805e-05,
+      "loss": 4.4534,
+      "step": 9400
+    },
+    {
+      "epoch": 0.7268671640643027,
+      "grad_norm": 10.189091682434082,
+      "learning_rate": 9.192823793242895e-05,
+      "loss": 4.3883,
+      "step": 9450
+    },
+    {
+      "epoch": 0.7307130220752249,
+      "grad_norm": 1.9577853679656982,
+      "learning_rate": 9.167089445240982e-05,
+      "loss": 4.3191,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7307130220752249,
+      "eval_loss": 4.328299045562744,
+      "eval_runtime": 18.8631,
+      "eval_samples_per_second": 53.014,
+      "eval_steps_per_second": 13.253,
+      "step": 9500
     }
   ],
   "logging_steps": 50,