Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5813d56d0aba386abdc9b79ca3a9d7b3cc33cdb3efdf07cf8e70c15b5e8acf78
+oid sha256:e104ba8a7758c4f7b3c974e1b0b628cd7ea3d7133d7aaf5a760b93c3a2a2f500
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53e0b76705822a6bcba0011ce7a2a3a6712d01f8e34e3e7d72c6506936e6e39
+oid sha256:29bf51ec5941e7ee53fc3bd868066fdfa02315352cf2f67c97788e4ef4fc20da
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d75c7dd0aed4dd831c43c8a6f52fbed675f5f4e205b9be1ecf0cfba00f87b077
+oid sha256:adef7d7f20fa9ff06fd7afdb08466880f74c943a65b32941c1ded7330e524374
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd10496d8a5f7e45002ec724483dbe1d4186b3c7101bd21f93cd0629ecfe77be
+oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.6901915073394775,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.048579062424095217,
+  "epoch": 0.07286859363614283,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 16.719,
       "eval_steps_per_second": 4.185,
       "step": 100
+    },
+    {
+      "epoch": 0.053436968666504735,
+      "grad_norm": 13.869400978088379,
+      "learning_rate": 0.00019422486395072398,
+      "loss": 2.8832,
+      "step": 110
+    },
+    {
+      "epoch": 0.05829487490891426,
+      "grad_norm": 14.071908950805664,
+      "learning_rate": 0.0001911191806751811,
+      "loss": 2.2136,
+      "step": 120
+    },
+    {
+      "epoch": 0.06315278115132378,
+      "grad_norm": 18.943180084228516,
+      "learning_rate": 0.00018757688175987723,
+      "loss": 2.9134,
+      "step": 130
+    },
+    {
+      "epoch": 0.0680106873937333,
+      "grad_norm": 22.638784408569336,
+      "learning_rate": 0.00018361522492905716,
+      "loss": 3.348,
+      "step": 140
+    },
+    {
+      "epoch": 0.07286859363614283,
+      "grad_norm": 23.163434982299805,
+      "learning_rate": 0.00017925351097657625,
+      "loss": 3.1821,
+      "step": 150
+    },
+    {
+      "epoch": 0.07286859363614283,
+      "eval_loss": 1.734904170036316,
+      "eval_runtime": 51.755,
+      "eval_samples_per_second": 16.752,
+      "eval_steps_per_second": 4.193,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.78874751123456e+16,
+  "total_flos": 2.68312126685184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null