Training in progress, step 14500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2519845d79c6f7a60a8e8bd9f60470c958586532b21af582e2a347c3d21c6c1a
+oid sha256:048b14e8250392932daba4d22d09a460365951dbb6b68b5a41a1a0e5ce624541
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88aaf6b4c11b0e46f6cdd9f050476f7085d7e9069b7435c1b07136131ebac754
+oid sha256:3b29852e5d0ff827b5e17125c299364e88ca1c70914de6e2a1ee93e58f54b613
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de168b313b50f7920582863eb6c48735221da70f052aa0c3517b7e8965981bd
+oid sha256:f8ea42701e6bd5369fc7af2447cde260122e2711abf45d46209ed918523c1a2c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523d1d97459ff6f5c0b6df3436b48935f386618f5677e95bde450bb198a23ba7
+oid sha256:bbaf929d345a2a40a03fb2b8f0c27dc126d0b7d5e2424d21837b1af94ede355e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36f6a58b58358dbb293c95ffa30cf143673db61f43b28cc950d65ff91360f28
+oid sha256:c3969f570a31885b978deed67646d88ac34c614ef8cb8214e9d16328676e8af9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 13750,
   "best_metric": 1.5006794929504395,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-13000",
-  "epoch": 1.0768402430582262,
+  "epoch": 1.1152988231674485,
   "eval_steps": 250,
-  "global_step": 14000,
+  "global_step": 14500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2416,6 +2416,92 @@
       "eval_samples_per_second": 55.107,
       "eval_steps_per_second": 13.777,
       "step": 14000
+    },
+    {
+      "epoch": 1.0806861010691486,
+      "grad_norm": 1.7406409978866577,
+      "learning_rate": 6.825778464027057e-05,
+      "loss": 1.3945,
+      "step": 14050
+    },
+    {
+      "epoch": 1.0845319590800708,
+      "grad_norm": 1.1657389402389526,
+      "learning_rate": 6.800044116025146e-05,
+      "loss": 1.4528,
+      "step": 14100
+    },
+    {
+      "epoch": 1.088377817090993,
+      "grad_norm": 1.380635380744934,
+      "learning_rate": 6.774309768023234e-05,
+      "loss": 1.442,
+      "step": 14150
+    },
+    {
+      "epoch": 1.0922236751019152,
+      "grad_norm": 1.7555848360061646,
+      "learning_rate": 6.748575420021322e-05,
+      "loss": 1.5061,
+      "step": 14200
+    },
+    {
+      "epoch": 1.0960695331128374,
+      "grad_norm": 1.6465975046157837,
+      "learning_rate": 6.72284107201941e-05,
+      "loss": 1.5004,
+      "step": 14250
+    },
+    {
+      "epoch": 1.0960695331128374,
+      "eval_loss": 1.5090863704681396,
+      "eval_runtime": 18.0174,
+      "eval_samples_per_second": 55.502,
+      "eval_steps_per_second": 13.876,
+      "step": 14250
+    },
+    {
+      "epoch": 1.0999153911237598,
+      "grad_norm": 2.0214383602142334,
+      "learning_rate": 6.697106724017498e-05,
+      "loss": 1.5436,
+      "step": 14300
+    },
+    {
+      "epoch": 1.103761249134682,
+      "grad_norm": 1.399170160293579,
+      "learning_rate": 6.671372376015588e-05,
+      "loss": 1.5242,
+      "step": 14350
+    },
+    {
+      "epoch": 1.1076071071456042,
+      "grad_norm": 2.1806626319885254,
+      "learning_rate": 6.645638028013676e-05,
+      "loss": 1.4609,
+      "step": 14400
+    },
+    {
+      "epoch": 1.1114529651565264,
+      "grad_norm": 1.1671562194824219,
+      "learning_rate": 6.619903680011763e-05,
+      "loss": 1.3789,
+      "step": 14450
+    },
+    {
+      "epoch": 1.1152988231674485,
+      "grad_norm": 1.0041520595550537,
+      "learning_rate": 6.594169332009851e-05,
+      "loss": 1.4909,
+      "step": 14500
+    },
+    {
+      "epoch": 1.1152988231674485,
+      "eval_loss": 1.509366750717163,
+      "eval_runtime": 18.0148,
+      "eval_samples_per_second": 55.51,
+      "eval_steps_per_second": 13.877,
+      "step": 14500
     }
   ],
   "logging_steps": 50,