Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122ccdb771777d311f4df0d632e03dfd710be79ef4e1a07e7d4e93041c5005e2
+oid sha256:7a0ce744c574dde5ff01d54cbde9aaf4826321e6dbab34fba0301d723d5f12af
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422634442396657d71e42d07c13e73332c11a9a67f9ff214f80a86316671f301
+oid sha256:a74aa14ddf23ce2fdd4b7f8ae4bf9b779c8c56b388e745f1fc77cb88b58b464a
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe52fad03b1d7423050e4de33705f5ea4a9ce890e0d3705ed02d3e79ee484257
+oid sha256:6d70924c232436c800df90f52f87adf6e3125c020b3b0e481f02d258de1cd8e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f924e37bc06756f5535d9fa2079568e2b7869291abee642e58937943662c2f6f
+oid sha256:cfc2bf0eccc6c4e85c949c664a83bcd160767da77920eebf352a6f7f7c4c9b2e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.076553344726562,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 0.0018078687487288422,
+  "best_metric": 11.067892074584961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.002259835935911053,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,92 @@
       "eval_samples_per_second": 52.881,
       "eval_steps_per_second": 26.444,
       "step": 40
+    },
+    {
+      "epoch": 0.0018530654674470634,
+      "grad_norm": 0.8118460774421692,
+      "learning_rate": 0.00019803133943336874,
+      "loss": 44.3122,
+      "step": 41
+    },
+    {
+      "epoch": 0.0018982621861652843,
+      "grad_norm": 0.7527559399604797,
+      "learning_rate": 0.0001979027334832293,
+      "loss": 44.3061,
+      "step": 42
+    },
+    {
+      "epoch": 0.0019434589048835055,
+      "grad_norm": 0.7425262331962585,
+      "learning_rate": 0.00019777010313517518,
+      "loss": 44.2408,
+      "step": 43
+    },
+    {
+      "epoch": 0.0019886556236017264,
+      "grad_norm": 0.753101646900177,
+      "learning_rate": 0.00019763345384112043,
+      "loss": 44.3362,
+      "step": 44
+    },
+    {
+      "epoch": 0.0020338523423199476,
+      "grad_norm": 0.767737090587616,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 44.2864,
+      "step": 45
+    },
+    {
+      "epoch": 0.0020338523423199476,
+      "eval_loss": 11.072389602661133,
+      "eval_runtime": 175.9667,
+      "eval_samples_per_second": 52.948,
+      "eval_steps_per_second": 26.477,
+      "step": 45
+    },
+    {
+      "epoch": 0.002079049061038169,
+      "grad_norm": 0.7275786995887756,
+      "learning_rate": 0.00019734812104845047,
+      "loss": 44.3542,
+      "step": 46
+    },
+    {
+      "epoch": 0.0021242457797563895,
+      "grad_norm": 0.6908650994300842,
+      "learning_rate": 0.00019719944927874881,
+      "loss": 44.3377,
+      "step": 47
+    },
+    {
+      "epoch": 0.0021694424984746107,
+      "grad_norm": 0.7260599136352539,
+      "learning_rate": 0.0001970467820203915,
+      "loss": 44.2621,
+      "step": 48
+    },
+    {
+      "epoch": 0.002214639217192832,
+      "grad_norm": 0.7138715982437134,
+      "learning_rate": 0.00019689012554893154,
+      "loss": 44.2338,
+      "step": 49
+    },
+    {
+      "epoch": 0.002259835935911053,
+      "grad_norm": 0.7867954969406128,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 44.3044,
+      "step": 50
+    },
+    {
+      "epoch": 0.002259835935911053,
+      "eval_loss": 11.067892074584961,
+      "eval_runtime": 176.5244,
+      "eval_samples_per_second": 52.78,
+      "eval_steps_per_second": 26.393,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -387,7 +473,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 420269260800.0,
+  "total_flos": 525336576000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null