Training in progress, step 9000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620de4edf53add8da5dbe95866a8bac876c40a3dc9c90cedc8474a386ec15455
+oid sha256:eecb66b5b687b2480b18fa49a3a7093840558d372a33d29f18cc9ddc9d5973f6
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8995b41577d3d005c4fed5c2507e98c14db04d3eb6c0cbf4dcde21e469d9590
+oid sha256:246b4fcf33df56c5b498c44dfc6d12184de263d7f241a380037b6387910c9a75
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a993eb83d217882b8d4270d606bf3996e74fd8745c32e817e4ed4a0c36ae01a8
+oid sha256:b68f148982346537acf196edf0aa44542990dee8efc3893aa00dae2ca2e993b5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929f0b36206c13ecf045b54d1e7d9597c22d5c9d16a63b3190a152cdd52e97ae
+oid sha256:83c5d85e32786b1e35a549f6e7bfc25b63f0617678a2a77d09f7e94475702a2a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7dbaa01ecd0154e55c0c938d1611846e23b19dc766ea41b92962589d9d1b91a
+oid sha256:a9af065edeaca88f16d8fcf52e4c33f05f28955d2f4f45d569975711d2168cd7
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 8500,
   "best_metric": 4.392988204956055,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-8500",
-  "epoch": 0.6537958618567803,
+  "epoch": 0.6922544419660026,
   "eval_steps": 250,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1470,6 +1470,92 @@
       "eval_samples_per_second": 53.079,
       "eval_steps_per_second": 13.27,
       "step": 8500
+    },
+    {
+      "epoch": 0.6576417198677025,
+      "grad_norm": 2.6913883686065674,
+      "learning_rate": 9.656042057277304e-05,
+      "loss": 4.4409,
+      "step": 8550
+    },
+    {
+      "epoch": 0.6614875778786247,
+      "grad_norm": 3.749894618988037,
+      "learning_rate": 9.630307709275394e-05,
+      "loss": 4.5101,
+      "step": 8600
+    },
+    {
+      "epoch": 0.665333435889547,
+      "grad_norm": 4.93977165222168,
+      "learning_rate": 9.604573361273482e-05,
+      "loss": 4.4504,
+      "step": 8650
+    },
+    {
+      "epoch": 0.6691792939004692,
+      "grad_norm": 4.311313152313232,
+      "learning_rate": 9.578839013271571e-05,
+      "loss": 4.4857,
+      "step": 8700
+    },
+    {
+      "epoch": 0.6730251519113915,
+      "grad_norm": 3.646656036376953,
+      "learning_rate": 9.553104665269659e-05,
+      "loss": 4.387,
+      "step": 8750
+    },
+    {
+      "epoch": 0.6730251519113915,
+      "eval_loss": 4.401506423950195,
+      "eval_runtime": 18.7931,
+      "eval_samples_per_second": 53.211,
+      "eval_steps_per_second": 13.303,
+      "step": 8750
+    },
+    {
+      "epoch": 0.6768710099223136,
+      "grad_norm": 4.352843284606934,
+      "learning_rate": 9.527370317267746e-05,
+      "loss": 4.5279,
+      "step": 8800
+    },
+    {
+      "epoch": 0.6807168679332359,
+      "grad_norm": 3.890216827392578,
+      "learning_rate": 9.501635969265835e-05,
+      "loss": 4.4485,
+      "step": 8850
+    },
+    {
+      "epoch": 0.6845627259441581,
+      "grad_norm": 3.4119713306427,
+      "learning_rate": 9.475901621263923e-05,
+      "loss": 4.4428,
+      "step": 8900
+    },
+    {
+      "epoch": 0.6884085839550804,
+      "grad_norm": 7.813595294952393,
+      "learning_rate": 9.450167273262012e-05,
+      "loss": 4.3308,
+      "step": 8950
+    },
+    {
+      "epoch": 0.6922544419660026,
+      "grad_norm": 3.079829692840576,
+      "learning_rate": 9.4244329252601e-05,
+      "loss": 4.368,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6922544419660026,
+      "eval_loss": 4.393312931060791,
+      "eval_runtime": 18.7727,
+      "eval_samples_per_second": 53.269,
+      "eval_steps_per_second": 13.317,
+      "step": 9000
     }
   ],
   "logging_steps": 50,