Training in progress, step 11500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78684fe66423fcc71792a533cdf4a615150a5d7719cd88fbc583e2cf7207b1f2
+oid sha256:66d99b0cb397502b025a6c7417fc75e69557e2db9d4b2101658c2730782a54e5
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d827d0c5de1fe1d4d42261146337ddfecdb8784573ad919f9058a14e73074cb
+oid sha256:eacebe9389e2329614f557172e304528d2b5b66f68c1b3c5e68453452e430f51
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b118dfa8e1001390c89e0eac0d61d9f1d84255e6c68db2d2cc7fd7107e67ae24
+oid sha256:a032319df626b2b110bd852b78fc23d492586d6fccaeb0841874a11adbfaea49
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1422ca832a4908b348152649eb6c40e62866db2c96015a75fe3a4ed0effd72
-size 14180
+oid sha256:1a16095fe7c7a01fb5cdfa33bc3b7f9026f465c5d2d551f188966908ce9a84c9
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71aebdeeb32cab8c73c6ce65908475546106933ecd5ef49363bd4d3f77b4ba2
+oid sha256:2124619b96ef0628e278d9139421c199b6678f87b3a0cfd00afb352c22439c91
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d6a033c9c4c6cee23163acb32007f6f866e5b846f8755100cbc84bc6fe976e
+oid sha256:129303cede08862e45aff723e13523f2863b1a8c5dd6144e719bcbf05975af10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 11000,
-  "best_metric": 1.3456926345825195,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-11000",
-  "epoch": 0.8460887624028921,
+  "best_global_step": 11500,
+  "best_metric": 1.3371928930282593,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-11500",
+  "epoch": 0.8845473425121144,
   "eval_steps": 250,
-  "global_step": 11000,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1900,6 +1900,92 @@
       "eval_samples_per_second": 59.571,
       "eval_steps_per_second": 14.893,
       "step": 11000
+    },
+    {
+      "epoch": 0.8499346204138143,
+      "grad_norm": 1.5268698930740356,
+      "learning_rate": 0.00014523024179934033,
+      "loss": 1.3185,
+      "step": 11050
+    },
+    {
+      "epoch": 0.8537804784247366,
+      "grad_norm": 1.5343180894851685,
+      "learning_rate": 0.00014497052177752385,
+      "loss": 1.4061,
+      "step": 11100
+    },
+    {
+      "epoch": 0.8576263364356588,
+      "grad_norm": 1.1495877504348755,
+      "learning_rate": 0.00014471080175570736,
+      "loss": 1.3393,
+      "step": 11150
+    },
+    {
+      "epoch": 0.8614721944465811,
+      "grad_norm": 1.5720888376235962,
+      "learning_rate": 0.00014445108173389087,
+      "loss": 1.3666,
+      "step": 11200
+    },
+    {
+      "epoch": 0.8653180524575033,
+      "grad_norm": 2.1202750205993652,
+      "learning_rate": 0.00014419655611251072,
+      "loss": 1.3463,
+      "step": 11250
+    },
+    {
+      "epoch": 0.8653180524575033,
+      "eval_loss": 1.3461755514144897,
+      "eval_runtime": 16.8798,
+      "eval_samples_per_second": 59.242,
+      "eval_steps_per_second": 14.811,
+      "step": 11250
+    },
+    {
+      "epoch": 0.8691639104684256,
+      "grad_norm": 1.0920432806015015,
+      "learning_rate": 0.00014393683609069424,
+      "loss": 1.3401,
+      "step": 11300
+    },
+    {
+      "epoch": 0.8730097684793477,
+      "grad_norm": 1.1317682266235352,
+      "learning_rate": 0.00014367711606887775,
+      "loss": 1.3506,
+      "step": 11350
+    },
+    {
+      "epoch": 0.8768556264902699,
+      "grad_norm": 0.7948962450027466,
+      "learning_rate": 0.0001434173960470613,
+      "loss": 1.3906,
+      "step": 11400
+    },
+    {
+      "epoch": 0.8807014845011922,
+      "grad_norm": 0.8204107880592346,
+      "learning_rate": 0.0001431576760252448,
+      "loss": 1.3556,
+      "step": 11450
+    },
+    {
+      "epoch": 0.8845473425121144,
+      "grad_norm": 1.5152668952941895,
+      "learning_rate": 0.00014289795600342831,
+      "loss": 1.3396,
+      "step": 11500
+    },
+    {
+      "epoch": 0.8845473425121144,
+      "eval_loss": 1.3371928930282593,
+      "eval_runtime": 16.8684,
+      "eval_samples_per_second": 59.282,
+      "eval_steps_per_second": 14.821,
+      "step": 11500
     }
   ],
   "logging_steps": 50,