Training in progress, step 8000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbb6880d1881c67658cfa63c684e343fb06877abae1e3d1bb7df536e89b3486
+oid sha256:8feea685a107f8ccd353fa0c6a7247dc35bf0b9ab63a5ddc15a9bb4d1290d199
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b194834b162d096162d9becaaa7df444d7c084623419d3e2f2bdc489c1f6464b
+oid sha256:66b6610111b8d0f3342d2760bc32d4c23e23f0a918f9dd58106e340817cbdd89
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d18ab5183ebf11753d526532b8569bec6f06614d4e88fe8e90cb6ae5b6d98c0
-size 14244
+oid sha256:0d6bc30a519d7cae432bede0d2778a805102f7cbeae9a244275827f72067499b
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bf8247b38694054da5df7ade6fe4af76b98c8b2246b36ed484d9dbaae0ad6d
+oid sha256:bfe40af48d21f2cca8886bf415fbb1d77078d013ee962c12ffd6bac84ee28801
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef16a0ad411b4ae4cfd3838e745cbacbb07d632abeb0359b1bec5b6523b89c0
+oid sha256:1d34cb07567bc31e1dbbaa78fe1d8a500cecd9a370ce5d35295b9afb817d2e6c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 7250,
   "best_metric": 4.4039154052734375,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-7000",
-  "epoch": 0.5768787016383355,
+  "epoch": 0.6153372817475579,
   "eval_steps": 250,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1298,6 +1298,92 @@
       "eval_samples_per_second": 53.19,
       "eval_steps_per_second": 13.298,
       "step": 7500
+    },
+    {
+      "epoch": 0.5807245596492577,
+      "grad_norm": 3.4961936473846436,
+      "learning_rate": 0.00010170214330355501,
+      "loss": 4.5194,
+      "step": 7550
+    },
+    {
+      "epoch": 0.58457041766018,
+      "grad_norm": 2.529500961303711,
+      "learning_rate": 0.00010144479982353589,
+      "loss": 4.3337,
+      "step": 7600
+    },
+    {
+      "epoch": 0.5884162756711022,
+      "grad_norm": 3.346160888671875,
+      "learning_rate": 0.00010118745634351679,
+      "loss": 4.5422,
+      "step": 7650
+    },
+    {
+      "epoch": 0.5922621336820244,
+      "grad_norm": 3.8311049938201904,
+      "learning_rate": 0.00010093011286349765,
+      "loss": 4.4191,
+      "step": 7700
+    },
+    {
+      "epoch": 0.5961079916929467,
+      "grad_norm": 4.324901580810547,
+      "learning_rate": 0.00010067276938347853,
+      "loss": 4.4613,
+      "step": 7750
+    },
+    {
+      "epoch": 0.5961079916929467,
+      "eval_loss": 4.4118547439575195,
+      "eval_runtime": 18.9517,
+      "eval_samples_per_second": 52.766,
+      "eval_steps_per_second": 13.191,
+      "step": 7750
+    },
+    {
+      "epoch": 0.5999538497038689,
+      "grad_norm": 3.888192653656006,
+      "learning_rate": 0.00010041542590345943,
+      "loss": 4.5492,
+      "step": 7800
+    },
+    {
+      "epoch": 0.6037997077147912,
+      "grad_norm": 2.718320608139038,
+      "learning_rate": 0.0001001580824234403,
+      "loss": 4.5371,
+      "step": 7850
+    },
+    {
+      "epoch": 0.6076455657257134,
+      "grad_norm": 3.5970869064331055,
+      "learning_rate": 9.99007389434212e-05,
+      "loss": 4.4835,
+      "step": 7900
+    },
+    {
+      "epoch": 0.6114914237366357,
+      "grad_norm": 4.563399314880371,
+      "learning_rate": 9.964339546340208e-05,
+      "loss": 4.4494,
+      "step": 7950
+    },
+    {
+      "epoch": 0.6153372817475579,
+      "grad_norm": 5.080177307128906,
+      "learning_rate": 9.938605198338294e-05,
+      "loss": 4.6072,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6153372817475579,
+      "eval_loss": 4.428142547607422,
+      "eval_runtime": 18.8815,
+      "eval_samples_per_second": 52.962,
+      "eval_steps_per_second": 13.241,
+      "step": 8000
     }
   ],
   "logging_steps": 50,