Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6188fa0d8ae9597f85177797fa8d9b83163cf54aa74de23c1939d2178de6b050
+oid sha256:5949541b1ad8fd09a9dd4413d642932d63116d1631bc3b3360a60a0ab5e2ff2c
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946233cace4a01e0a4e820c9df3544a2af989a590b6bbe5da7498b6f5a8b04c3
+oid sha256:a023d218402e5a64769bdc9fdbc1d2042f73fc6deecceb97dcf112258cd25de2
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58f5ac165e5678059cd985932013893e4fb182dbc304ff1d5f693b3e637f83aa
+oid sha256:ffe10c0fda7b2cbc1c8cce71a81fac6cd9406b77de1c83fae718df8c48fcb175
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6230b755f4852be6522ac6887b301425bcc73ea51d582d18275898487101896f
+oid sha256:0b7a2a3377a3bac2dd1df5dd024428a9251cce0a6f3f0aeba82613607d91eab6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5309c228274080a3a52f158c0e502ee703cc4e65609982464e4fd123b371918
+oid sha256:db6fe233426e5726a9f2a30df10960c0e1d8ec3d256eb618aa02ecbd5e2e9bba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2323a50ddfd73a5283152809f5b8a1f2d2b14634cd4f7f8c1cf8c95596b4fa3b
+oid sha256:abefb3bc912922f012d4a5cfefb9b116316b6e8dc0ace3695e5f8806dfa030f2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c220d2fbe9a2870f9ac93749b3d4b3852ce94b5983d948fa8de3d35e453f98ce
+oid sha256:7312f49c1e1b01f68cdaee175129535fda49cd22ed1f251a2745d2c8c42996be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.374110221862793,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.197802197802198,
+  "epoch": 2.989010989010989,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 461.241,
       "eval_steps_per_second": 119.923,
       "step": 25
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.03684426099061966,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 13.628,
+      "step": 26
+    },
+    {
+      "epoch": 2.3736263736263736,
+      "grad_norm": 0.037405263632535934,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 10.976,
+      "step": 27
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.027308689430356026,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.2903,
+      "step": 28
+    },
+    {
+      "epoch": 2.5494505494505493,
+      "grad_norm": 0.04180492088198662,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 14.0577,
+      "step": 29
+    },
+    {
+      "epoch": 2.6373626373626373,
+      "grad_norm": 0.04389217123389244,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.2631,
+      "step": 30
+    },
+    {
+      "epoch": 2.7252747252747254,
+      "grad_norm": 0.03337155282497406,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 5.6936,
+      "step": 31
+    },
+    {
+      "epoch": 2.813186813186813,
+      "grad_norm": 0.041730139404535294,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 14.3063,
+      "step": 32
+    },
+    {
+      "epoch": 2.901098901098901,
+      "grad_norm": 0.043961212038993835,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 10.7842,
+      "step": 33
+    },
+    {
+      "epoch": 2.989010989010989,
+      "grad_norm": 0.050427090376615524,
+      "learning_rate": 1e-05,
+      "loss": 12.5246,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21384029798400.0,
+  "total_flos": 29082280525824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null