Training in progress, step 11000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4324a3a5915156493f27435981bc5e067e17329d248df8e005af28872089db08
+oid sha256:0355dc1903f621175efb8489eb47a7c37c5bff9cb7109326e9981d55521c5a79
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:586643082c797c6471cec4d99035ab6336a6eec2692a30ba5ac6aa1ea78f1ad3
+oid sha256:6da8cff90cb20d49e633651c8eacef51daa69bb2f0ab5dff6d6115d2c7b51d28
 size 1544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435157f2e32de040f237ef44fcb2f7d2ce0740bd523e00f2682e862fe6e5b77b
+oid sha256:f9d988b8500be5654d081e2939fa8df78c5f27a1a3b79fa26f57611a14b3851f
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:371a8ee92df296caadab094d1243e6f6a8e33531055d940b9b2beb58c3296d37
-size 14180
+oid sha256:3d7167878bddb7c0a88c66ad0b0be73885dac80e1980348d5e68d660c4a16ce9
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b29e642bf24d79ebcf705888b6c986c0f26a1dd38cc2f292d82caae0977305
+oid sha256:7ba0e34e1ad6da2db5da67e847d92cda308dc91647db7b3e13d90fd53261cd77
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d497e82650965830e0a6f7b87b60635133c5dcd48d2ca0d74cebf5c5827dfab0
+oid sha256:1aa74d2c9c42f12a34e14e605ae41a06b5b6cec868a4a2206366586ebba8210c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9500,
-  "best_metric": 4.357193470001221,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-fixed/checkpoint-9500",
-  "epoch": 0.8076301822936697,
+  "best_global_step": 11000,
+  "best_metric": 4.352676868438721,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-fixed/checkpoint-11000",
+  "epoch": 0.8460887624028921,
   "eval_steps": 250,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1814,6 +1814,92 @@
       "eval_samples_per_second": 54.063,
       "eval_steps_per_second": 13.516,
       "step": 10500
+    },
+    {
+      "epoch": 0.811476040304592,
+      "grad_norm": 4.379317760467529,
+      "learning_rate": 0.00014784821961925045,
+      "loss": 4.6715,
+      "step": 10550
+    },
+    {
+      "epoch": 0.8153218983155142,
+      "grad_norm": 3.034796714782715,
+      "learning_rate": 0.00014758849959743396,
+      "loss": 4.4511,
+      "step": 10600
+    },
+    {
+      "epoch": 0.8191677563264365,
+      "grad_norm": 3.8016927242279053,
+      "learning_rate": 0.00014732877957561748,
+      "loss": 4.2966,
+      "step": 10650
+    },
+    {
+      "epoch": 0.8230136143373586,
+      "grad_norm": 4.330080509185791,
+      "learning_rate": 0.00014706905955380102,
+      "loss": 4.6496,
+      "step": 10700
+    },
+    {
+      "epoch": 0.8268594723482809,
+      "grad_norm": 8.032389640808105,
+      "learning_rate": 0.00014680933953198453,
+      "loss": 4.2758,
+      "step": 10750
+    },
+    {
+      "epoch": 0.8268594723482809,
+      "eval_loss": 4.388455867767334,
+      "eval_runtime": 18.481,
+      "eval_samples_per_second": 54.11,
+      "eval_steps_per_second": 13.527,
+      "step": 10750
+    },
+    {
+      "epoch": 0.8307053303592031,
+      "grad_norm": 3.1724319458007812,
+      "learning_rate": 0.00014654961951016807,
+      "loss": 4.405,
+      "step": 10800
+    },
+    {
+      "epoch": 0.8345511883701254,
+      "grad_norm": 3.529196262359619,
+      "learning_rate": 0.00014628989948835155,
+      "loss": 4.4433,
+      "step": 10850
+    },
+    {
+      "epoch": 0.8383970463810476,
+      "grad_norm": 4.758362293243408,
+      "learning_rate": 0.00014603017946653507,
+      "loss": 4.5747,
+      "step": 10900
+    },
+    {
+      "epoch": 0.8422429043919698,
+      "grad_norm": 3.524068832397461,
+      "learning_rate": 0.0001457704594447186,
+      "loss": 4.3469,
+      "step": 10950
+    },
+    {
+      "epoch": 0.8460887624028921,
+      "grad_norm": 4.452401161193848,
+      "learning_rate": 0.00014551073942290212,
+      "loss": 4.3767,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8460887624028921,
+      "eval_loss": 4.352676868438721,
+      "eval_runtime": 18.5817,
+      "eval_samples_per_second": 53.816,
+      "eval_steps_per_second": 13.454,
+      "step": 11000
     }
   ],
   "logging_steps": 50,