Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650e7763fed76b1945cdf62f6ca95002ad4b2286a0f7d13b6b6483cc972301b9
+oid sha256:de741ef7f34a5eb7de98448fda69402f3b613549cb58dc7303e87f6cde138f8b
 size 58680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72d83a056486c9820f3aa9a64499b07d24a2113fc9f059a209d00a7fd462863
+oid sha256:76f7b8a11f097eb57a6b8a9d16d6cf63426a1290306dca39c128a5ba493e953a
 size 127270

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836a960b0907dbf055de9b1f6c0fbca8a81c8acbe0abf3d62594ebaf9d089b0f
+oid sha256:f7ced3441efbaac8e8068b5e942efb4d6961a89dd8de37cdf9f39574a4495d7e
 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": 10.308439254760742,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.002809817502353222,
+  "best_metric": 10.306268692016602,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.004214726253529834,
   "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": 252.467,
       "eval_steps_per_second": 63.129,
       "step": 100
+    },
+    {
+      "epoch": 0.0030907992525885442,
+      "grad_norm": 0.20467126369476318,
+      "learning_rate": 0.00019422486395072398,
+      "loss": 20.6304,
+      "step": 110
+    },
+    {
+      "epoch": 0.0033717810028238665,
+      "grad_norm": 0.2518371343612671,
+      "learning_rate": 0.0001911191806751811,
+      "loss": 20.6217,
+      "step": 120
+    },
+    {
+      "epoch": 0.0036527627530591887,
+      "grad_norm": 0.1735089272260666,
+      "learning_rate": 0.00018757688175987723,
+      "loss": 20.6238,
+      "step": 130
+    },
+    {
+      "epoch": 0.003933744503294511,
+      "grad_norm": 0.17584048211574554,
+      "learning_rate": 0.00018361522492905716,
+      "loss": 20.6006,
+      "step": 140
+    },
+    {
+      "epoch": 0.004214726253529834,
+      "grad_norm": 0.20633459091186523,
+      "learning_rate": 0.00017925351097657625,
+      "loss": 20.6024,
+      "step": 150
+    },
+    {
+      "epoch": 0.004214726253529834,
+      "eval_loss": 10.306268692016602,
+      "eval_runtime": 59.8224,
+      "eval_samples_per_second": 250.492,
+      "eval_steps_per_second": 62.635,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4249740902400.0,
+  "total_flos": 6381069926400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null