Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d4bb6a956fb56cd0088dc28547952d24c08f2eb86d2aec9d4b21483adb9177
+oid sha256:b3ebae6745992a9891531c7f9dc21af61684fec4cad0bdb8ec71e2d7e0190098
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc10445b82405fb6d37d22c7fe973fefbd6d5e7a4eae5c80f3b4858a86a96da
+oid sha256:086c8bf4279e90d468163e6119ad5a62eca1c60efa475a439bfc8e41ebe89eaa
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d872420bc3dc74bb7836dfa2f4957583cebe65bc0ce2ca2cd3f24b22a86bb602
+oid sha256:93b715727f08f3bec1a4243110369e5be33fa530d65244e67bf09606e5d6da48
 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": 1.6503487825393677,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 0.011295446523120367,
+  "best_metric": 1.6434087753295898,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.014119308153900459,
   "eval_steps": 10,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -327,6 +327,84 @@
       "eval_samples_per_second": 5.592,
       "eval_steps_per_second": 5.592,
       "step": 40
+    },
+    {
+      "epoch": 0.011577832686198376,
+      "grad_norm": 1.9744967222213745,
+      "learning_rate": 0.00019803133943336874,
+      "loss": 2.3377,
+      "step": 41
+    },
+    {
+      "epoch": 0.011860218849276386,
+      "grad_norm": 1.438886046409607,
+      "learning_rate": 0.0001979027334832293,
+      "loss": 1.4721,
+      "step": 42
+    },
+    {
+      "epoch": 0.012142605012354394,
+      "grad_norm": 3.23305082321167,
+      "learning_rate": 0.00019777010313517518,
+      "loss": 1.7882,
+      "step": 43
+    },
+    {
+      "epoch": 0.012424991175432405,
+      "grad_norm": 5.8521013259887695,
+      "learning_rate": 0.00019763345384112043,
+      "loss": 1.2744,
+      "step": 44
+    },
+    {
+      "epoch": 0.012707377338510413,
+      "grad_norm": 5.29448127746582,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 1.0265,
+      "step": 45
+    },
+    {
+      "epoch": 0.012989763501588421,
+      "grad_norm": 3.448343515396118,
+      "learning_rate": 0.00019734812104845047,
+      "loss": 2.1143,
+      "step": 46
+    },
+    {
+      "epoch": 0.013272149664666432,
+      "grad_norm": 2.209937810897827,
+      "learning_rate": 0.00019719944927874881,
+      "loss": 1.325,
+      "step": 47
+    },
+    {
+      "epoch": 0.01355453582774444,
+      "grad_norm": 1.200800895690918,
+      "learning_rate": 0.0001970467820203915,
+      "loss": 1.8635,
+      "step": 48
+    },
+    {
+      "epoch": 0.01383692199082245,
+      "grad_norm": 1.2242612838745117,
+      "learning_rate": 0.00019689012554893154,
+      "loss": 1.7063,
+      "step": 49
+    },
+    {
+      "epoch": 0.014119308153900459,
+      "grad_norm": 1.140673279762268,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 1.315,
+      "step": 50
+    },
+    {
+      "epoch": 0.014119308153900459,
+      "eval_loss": 1.6434087753295898,
+      "eval_runtime": 133.392,
+      "eval_samples_per_second": 5.593,
+      "eval_steps_per_second": 5.593,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -355,7 +433,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3915214340751360.0,
+  "total_flos": 4894017925939200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null