Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d639cf1e66f96ec287a3a492ccf32327954427cdbbc122d0061b092203c93e
+oid sha256:f477a95ac79dba800dc0818ec773ad48ec3a9bdab04358c4b3fc32843a992149
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4afd11d8b95ef043c3d768da66bd78d65812608fc10163042d0a549c75e36551
+oid sha256:b9e12b14daa13d9d2ee3a08fe5b1893a8a650a497642cc015ef7037a61863681
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec7fddaa93b8a5104562fd596c16565abf5deb95425dbc4839aa86c8fa34863
+oid sha256:0c68f05fddafe7d9625cc40fb5e03db579f2837d87b6225adf6c39031a56218a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
+oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.756880521774292,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0477326968973747,
+  "best_metric": 0.7373384237289429,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07159904534606205,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,92 @@
       "eval_samples_per_second": 1.996,
       "eval_steps_per_second": 1.004,
       "step": 20
+    },
+    {
+      "epoch": 0.050119331742243436,
+      "grad_norm": 0.7394424676895142,
+      "learning_rate": 0.00019975141040730207,
+      "loss": 0.7499,
+      "step": 21
+    },
+    {
+      "epoch": 0.05250596658711217,
+      "grad_norm": 0.4532185196876526,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 0.4935,
+      "step": 22
+    },
+    {
+      "epoch": 0.05489260143198091,
+      "grad_norm": 0.3705839514732361,
+      "learning_rate": 0.00019965285344390184,
+      "loss": 0.7115,
+      "step": 23
+    },
+    {
+      "epoch": 0.057279236276849645,
+      "grad_norm": 0.3674144446849823,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 0.6629,
+      "step": 24
+    },
+    {
+      "epoch": 0.059665871121718374,
+      "grad_norm": 0.9410332441329956,
+      "learning_rate": 0.00019953791129491983,
+      "loss": 0.6523,
+      "step": 25
+    },
+    {
+      "epoch": 0.059665871121718374,
+      "eval_loss": 0.7463199496269226,
+      "eval_runtime": 89.0491,
+      "eval_samples_per_second": 1.988,
+      "eval_steps_per_second": 0.999,
+      "step": 25
+    },
+    {
+      "epoch": 0.06205250596658711,
+      "grad_norm": 0.4582875669002533,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 0.8828,
+      "step": 26
+    },
+    {
+      "epoch": 0.06443914081145585,
+      "grad_norm": 1.0290837287902832,
+      "learning_rate": 0.00019940660285944803,
+      "loss": 0.7447,
+      "step": 27
+    },
+    {
+      "epoch": 0.06682577565632458,
+      "grad_norm": 0.24490249156951904,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 0.5415,
+      "step": 28
+    },
+    {
+      "epoch": 0.06921241050119331,
+      "grad_norm": 0.6698419451713562,
+      "learning_rate": 0.0001992589497275665,
+      "loss": 0.7669,
+      "step": 29
+    },
+    {
+      "epoch": 0.07159904534606205,
+      "grad_norm": 1.0689176321029663,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 1.0212,
+      "step": 30
+    },
+    {
+      "epoch": 0.07159904534606205,
+      "eval_loss": 0.7373384237289429,
+      "eval_runtime": 88.6141,
+      "eval_samples_per_second": 1.997,
+      "eval_steps_per_second": 1.004,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -215,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+16,
+  "total_flos": 4.476062712987648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null