Training in progress, step 14000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0fec3c5b1e7e374b9bebda92218a1bdc7fadf77f9f2fd358d7738c92849ab15
+oid sha256:2519845d79c6f7a60a8e8bd9f60470c958586532b21af582e2a347c3d21c6c1a
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961d4f3f88c2859e92add0976bc93ab8db0649cc3da6695526e297d735998366
+oid sha256:88aaf6b4c11b0e46f6cdd9f050476f7085d7e9069b7435c1b07136131ebac754
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81ec269cbd23a3955804ddaef963a9e0d68f2087a109e239da5baed50032493e
+oid sha256:5de168b313b50f7920582863eb6c48735221da70f052aa0c3517b7e8965981bd
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861918ef9bae87f3c0647e76fd5a519763415c2dba1ede7121af8dc80bfb456a
+oid sha256:523d1d97459ff6f5c0b6df3436b48935f386618f5677e95bde450bb198a23ba7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483cd8caa2794b8eb45fe09567d024ef71ee8ff6f6ba358a1febd749509b4c7e
+oid sha256:f36f6a58b58358dbb293c95ffa30cf143673db61f43b28cc950d65ff91360f28
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 13000,
-  "best_metric": 1.5033278465270996,
+  "best_global_step": 13750,
+  "best_metric": 1.5006794929504395,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-13000",
-  "epoch": 1.038381662949004,
+  "epoch": 1.0768402430582262,
   "eval_steps": 250,
-  "global_step": 13500,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2330,6 +2330,92 @@
       "eval_samples_per_second": 55.13,
       "eval_steps_per_second": 13.782,
       "step": 13500
+    },
+    {
+      "epoch": 1.042227520959926,
+      "grad_norm": 2.8053858280181885,
+      "learning_rate": 7.083121944046175e-05,
+      "loss": 1.5338,
+      "step": 13550
+    },
+    {
+      "epoch": 1.0460733789708483,
+      "grad_norm": 1.2761131525039673,
+      "learning_rate": 7.057387596044263e-05,
+      "loss": 1.4137,
+      "step": 13600
+    },
+    {
+      "epoch": 1.0499192369817707,
+      "grad_norm": 1.614910364151001,
+      "learning_rate": 7.03165324804235e-05,
+      "loss": 1.4634,
+      "step": 13650
+    },
+    {
+      "epoch": 1.0537650949926929,
+      "grad_norm": 1.8560376167297363,
+      "learning_rate": 7.00591890004044e-05,
+      "loss": 1.5173,
+      "step": 13700
+    },
+    {
+      "epoch": 1.057610953003615,
+      "grad_norm": 1.3471609354019165,
+      "learning_rate": 6.980184552038528e-05,
+      "loss": 1.4887,
+      "step": 13750
+    },
+    {
+      "epoch": 1.057610953003615,
+      "eval_loss": 1.5006794929504395,
+      "eval_runtime": 18.2151,
+      "eval_samples_per_second": 54.9,
+      "eval_steps_per_second": 13.725,
+      "step": 13750
+    },
+    {
+      "epoch": 1.0614568110145373,
+      "grad_norm": 1.661996841430664,
+      "learning_rate": 6.954450204036616e-05,
+      "loss": 1.4428,
+      "step": 13800
+    },
+    {
+      "epoch": 1.0653026690254597,
+      "grad_norm": 1.2982336282730103,
+      "learning_rate": 6.928715856034704e-05,
+      "loss": 1.4565,
+      "step": 13850
+    },
+    {
+      "epoch": 1.0691485270363819,
+      "grad_norm": 0.9250918626785278,
+      "learning_rate": 6.902981508032792e-05,
+      "loss": 1.5353,
+      "step": 13900
+    },
+    {
+      "epoch": 1.072994385047304,
+      "grad_norm": 1.8084945678710938,
+      "learning_rate": 6.877247160030881e-05,
+      "loss": 1.5047,
+      "step": 13950
+    },
+    {
+      "epoch": 1.0768402430582262,
+      "grad_norm": 1.1049927473068237,
+      "learning_rate": 6.851512812028969e-05,
+      "loss": 1.5058,
+      "step": 14000
+    },
+    {
+      "epoch": 1.0768402430582262,
+      "eval_loss": 1.5043680667877197,
+      "eval_runtime": 18.1464,
+      "eval_samples_per_second": 55.107,
+      "eval_steps_per_second": 13.777,
+      "step": 14000
     }
   ],
   "logging_steps": 50,