Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e1220db04deef41f91568f272c1af454dc6f61e06bc94a4ba989feda28e453
+oid sha256:122ccdb771777d311f4df0d632e03dfd710be79ef4e1a07e7d4e93041c5005e2
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d14378f3c767e181a50e533483452d111e7a068d3293efc9ec3131c7e65096
+oid sha256:422634442396657d71e42d07c13e73332c11a9a67f9ff214f80a86316671f301
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b826697970fb037ea33b7c8bd23266efd49eb797e41a5119728b7a543f6d062b
+oid sha256:fe52fad03b1d7423050e4de33705f5ea4a9ce890e0d3705ed02d3e79ee484257
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
+oid sha256:f924e37bc06756f5535d9fa2079568e2b7869291abee642e58937943662c2f6f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.082609176635742,
-  "best_model_checkpoint": "miner_id_24/checkpoint-30",
-  "epoch": 0.0013559015615466317,
+  "best_metric": 11.076553344726562,
+  "best_model_checkpoint": "miner_id_24/checkpoint-40",
+  "epoch": 0.0018078687487288422,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,92 @@
       "eval_samples_per_second": 52.857,
       "eval_steps_per_second": 26.431,
       "step": 30
+    },
+    {
+      "epoch": 0.0014010982802648527,
+      "grad_norm": 0.7027749419212341,
+      "learning_rate": 0.00019909497617679348,
+      "loss": 44.3391,
+      "step": 31
+    },
+    {
+      "epoch": 0.0014462949989830739,
+      "grad_norm": 0.735598087310791,
+      "learning_rate": 0.0001990068775649202,
+      "loss": 44.3645,
+      "step": 32
+    },
+    {
+      "epoch": 0.0014914917177012948,
+      "grad_norm": 0.7152600288391113,
+      "learning_rate": 0.00019891470916809362,
+      "loss": 44.3478,
+      "step": 33
+    },
+    {
+      "epoch": 0.001536688436419516,
+      "grad_norm": 0.6983291506767273,
+      "learning_rate": 0.00019881847477499557,
+      "loss": 44.3252,
+      "step": 34
+    },
+    {
+      "epoch": 0.001581885155137737,
+      "grad_norm": 0.6892045140266418,
+      "learning_rate": 0.00019871817834144504,
+      "loss": 44.2998,
+      "step": 35
+    },
+    {
+      "epoch": 0.001581885155137737,
+      "eval_loss": 11.079712867736816,
+      "eval_runtime": 176.1378,
+      "eval_samples_per_second": 52.896,
+      "eval_steps_per_second": 26.451,
+      "step": 35
+    },
+    {
+      "epoch": 0.0016270818738559581,
+      "grad_norm": 0.7166262865066528,
+      "learning_rate": 0.0001986138239902355,
+      "loss": 44.3485,
+      "step": 36
+    },
+    {
+      "epoch": 0.001672278592574179,
+      "grad_norm": 0.7545002102851868,
+      "learning_rate": 0.0001985054160109657,
+      "loss": 44.2613,
+      "step": 37
+    },
+    {
+      "epoch": 0.0017174753112924003,
+      "grad_norm": 0.7944263219833374,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 44.2665,
+      "step": 38
+    },
+    {
+      "epoch": 0.0017626720300106212,
+      "grad_norm": 0.7216903567314148,
+      "learning_rate": 0.0001982764571596004,
+      "loss": 44.3546,
+      "step": 39
+    },
+    {
+      "epoch": 0.0018078687487288422,
+      "grad_norm": 0.7492774128913879,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 44.3223,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018078687487288422,
+      "eval_loss": 11.076553344726562,
+      "eval_runtime": 176.1866,
+      "eval_samples_per_second": 52.881,
+      "eval_steps_per_second": 26.444,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -301,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 315201945600.0,
+  "total_flos": 420269260800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null