Training in progress, step 17500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441effd53b237a6d55d25ad93a62aed9e9a9b704129f5cc8576e5b658221b597
+oid sha256:5fd64b4fff9be5f0c3e2f6b4d9919b9e6375df4b9f578e7ba32211a7c5285de9
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d99045a76b65192b2e41aefcf5abebda18e67ecc70d381cfe9c7b19f1066bfd
+oid sha256:2d27c5a577064cfc46e35c17df10152b71102230382c1124b730922de85a7cde
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9d5359cc143881ecdb88768e105d086fd2336ed10ecf8c85dd03dc0e505da1
+oid sha256:5c6f63d896b1e09539b72ac15eabafd681bf824376794bc90d0981fb00940917
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5daa13f981d2fdcf2543f987afffb899e74fcea4fd93baa2e74fd8a3169ecb99
+oid sha256:1a3d47a33fe410d7c39aed7512ee64bb9c07ee05e603db567ade52fed1bf5077
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd0711c5430aa1d8a873bb88a5b6bcc960ba760770a1807e688afccd4facc3e
+oid sha256:3fefc995528f5d0eb5c6c7d885b8cddef853e490bf4df60e860a20196ce82f7a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 16750,
   "best_metric": 1.4708431959152222,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
-  "epoch": 1.3075917237135606,
+  "epoch": 1.346050303822783,
   "eval_steps": 250,
-  "global_step": 17000,
+  "global_step": 17500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2932,6 +2932,92 @@
       "eval_samples_per_second": 55.488,
       "eval_steps_per_second": 13.872,
       "step": 17000
+    },
+    {
+      "epoch": 1.3114375817244828,
+      "grad_norm": 1.732088327407837,
+      "learning_rate": 5.281717583912356e-05,
+      "loss": 1.5014,
+      "step": 17050
+    },
+    {
+      "epoch": 1.315283439735405,
+      "grad_norm": 2.144697427749634,
+      "learning_rate": 5.2559832359104435e-05,
+      "loss": 1.4436,
+      "step": 17100
+    },
+    {
+      "epoch": 1.3191292977463271,
+      "grad_norm": 1.649965763092041,
+      "learning_rate": 5.230248887908532e-05,
+      "loss": 1.4334,
+      "step": 17150
+    },
+    {
+      "epoch": 1.3229751557572493,
+      "grad_norm": 0.8667518496513367,
+      "learning_rate": 5.204514539906621e-05,
+      "loss": 1.487,
+      "step": 17200
+    },
+    {
+      "epoch": 1.3268210137681717,
+      "grad_norm": 1.4567649364471436,
+      "learning_rate": 5.178780191904709e-05,
+      "loss": 1.4714,
+      "step": 17250
+    },
+    {
+      "epoch": 1.3268210137681717,
+      "eval_loss": 1.479749321937561,
+      "eval_runtime": 17.9466,
+      "eval_samples_per_second": 55.721,
+      "eval_steps_per_second": 13.93,
+      "step": 17250
+    },
+    {
+      "epoch": 1.330666871779094,
+      "grad_norm": 1.8523489236831665,
+      "learning_rate": 5.1530458439027974e-05,
+      "loss": 1.4718,
+      "step": 17300
+    },
+    {
+      "epoch": 1.3345127297900161,
+      "grad_norm": 1.091204047203064,
+      "learning_rate": 5.127311495900886e-05,
+      "loss": 1.4012,
+      "step": 17350
+    },
+    {
+      "epoch": 1.3383585878009385,
+      "grad_norm": 1.8271427154541016,
+      "learning_rate": 5.101577147898973e-05,
+      "loss": 1.4547,
+      "step": 17400
+    },
+    {
+      "epoch": 1.3422044458118605,
+      "grad_norm": 1.8682465553283691,
+      "learning_rate": 5.075842799897062e-05,
+      "loss": 1.4373,
+      "step": 17450
+    },
+    {
+      "epoch": 1.346050303822783,
+      "grad_norm": 2.1932857036590576,
+      "learning_rate": 5.0501084518951506e-05,
+      "loss": 1.4628,
+      "step": 17500
+    },
+    {
+      "epoch": 1.346050303822783,
+      "eval_loss": 1.4871113300323486,
+      "eval_runtime": 17.9165,
+      "eval_samples_per_second": 55.814,
+      "eval_steps_per_second": 13.954,
+      "step": 17500
     }
   ],
   "logging_steps": 50,