Training in progress, step 7500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3903c059a7b663d5bfd566efc9974ae82cc96ac9d5b539705078e742f56c337d
+oid sha256:bdbb6880d1881c67658cfa63c684e343fb06877abae1e3d1bb7df536e89b3486
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c871c606d134fb7ce2c803972d6df79093d0f6a67161c6b1b4060e6eb55be6
+oid sha256:b194834b162d096162d9becaaa7df444d7c084623419d3e2f2bdc489c1f6464b
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4acfd5fa4964d8f20ab734945eda1f469ecfbbe259a3fd74f731ec4baabed1
+oid sha256:1d18ab5183ebf11753d526532b8569bec6f06614d4e88fe8e90cb6ae5b6d98c0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6777a8c32c870836be295ac0aa7f4cc3d40129a0ebc96e1b375fa98ce8275f00
+oid sha256:74bf8247b38694054da5df7ade6fe4af76b98c8b2246b36ed484d9dbaae0ad6d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61aefcf58c021497ade44ee93d84da1168bb6593c3269faeaeb7e7cace70ca34
+oid sha256:fef16a0ad411b4ae4cfd3838e745cbacbb07d632abeb0359b1bec5b6523b89c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 7000,
-  "best_metric": 4.411437034606934,
+  "best_global_step": 7250,
+  "best_metric": 4.4039154052734375,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-7000",
-  "epoch": 0.5384201215291131,
+  "epoch": 0.5768787016383355,
   "eval_steps": 250,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1212,6 +1212,92 @@
       "eval_samples_per_second": 52.997,
       "eval_steps_per_second": 13.249,
       "step": 7000
+    },
+    {
+      "epoch": 0.5422659795400354,
+      "grad_norm": 5.943952560424805,
+      "learning_rate": 0.00010427557810374618,
+      "loss": 4.3737,
+      "step": 7050
+    },
+    {
+      "epoch": 0.5461118375509576,
+      "grad_norm": 4.010414123535156,
+      "learning_rate": 0.00010401823462372706,
+      "loss": 4.5472,
+      "step": 7100
+    },
+    {
+      "epoch": 0.5499576955618799,
+      "grad_norm": 3.5218944549560547,
+      "learning_rate": 0.00010376089114370794,
+      "loss": 4.5854,
+      "step": 7150
+    },
+    {
+      "epoch": 0.5538035535728021,
+      "grad_norm": 9.44631290435791,
+      "learning_rate": 0.00010350354766368883,
+      "loss": 4.3883,
+      "step": 7200
+    },
+    {
+      "epoch": 0.5576494115837243,
+      "grad_norm": 4.5443434715271,
+      "learning_rate": 0.00010324620418366971,
+      "loss": 4.6685,
+      "step": 7250
+    },
+    {
+      "epoch": 0.5576494115837243,
+      "eval_loss": 4.4039154052734375,
+      "eval_runtime": 18.856,
+      "eval_samples_per_second": 53.034,
+      "eval_steps_per_second": 13.258,
+      "step": 7250
+    },
+    {
+      "epoch": 0.5614952695946466,
+      "grad_norm": 3.646768569946289,
+      "learning_rate": 0.0001029888607036506,
+      "loss": 4.5259,
+      "step": 7300
+    },
+    {
+      "epoch": 0.5653411276055688,
+      "grad_norm": 3.510744571685791,
+      "learning_rate": 0.00010273151722363148,
+      "loss": 4.4461,
+      "step": 7350
+    },
+    {
+      "epoch": 0.5691869856164911,
+      "grad_norm": 3.874558687210083,
+      "learning_rate": 0.00010247417374361235,
+      "loss": 4.3743,
+      "step": 7400
+    },
+    {
+      "epoch": 0.5730328436274132,
+      "grad_norm": 2.755722761154175,
+      "learning_rate": 0.00010221683026359324,
+      "loss": 4.4979,
+      "step": 7450
+    },
+    {
+      "epoch": 0.5768787016383355,
+      "grad_norm": 3.5653252601623535,
+      "learning_rate": 0.00010195948678357412,
+      "loss": 4.5442,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5768787016383355,
+      "eval_loss": 4.44308614730835,
+      "eval_runtime": 18.8004,
+      "eval_samples_per_second": 53.19,
+      "eval_steps_per_second": 13.298,
+      "step": 7500
     }
   ],
   "logging_steps": 50,