Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab1bb3627cc70d3f793c1674b89569940fd0d294d1861d4f2e8a5063da65d85
+oid sha256:73ac3b40666acc39eb3aa799a782c5c87769b3f7aac3c3418071a6f8511817f8
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f10f8945f4f1ac7b87abaa9bd0351a1c4399d9a3df2c21db0cd0750bdc3f81
+oid sha256:c697d6e55d1ce928440ce95657a8b888ddfaea0a4a64fd3a8254feb3ebd0c0d7
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8738a2a0f9ec2835267482ae9a12017a1e7529560555a83c2fbc924dd0f3e1f4
+oid sha256:02c4433626c40a7d0f8dca7db70caa8a2291973e480a55daae623f702a6055a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.909342765808105,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05734767025089606,
+  "best_metric": 11.905759811401367,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.08602150537634409,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 72.273,
       "eval_steps_per_second": 18.191,
       "step": 20
+    },
+    {
+      "epoch": 0.060215053763440864,
+      "grad_norm": 0.25910457968711853,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9114,
+      "step": 21
+    },
+    {
+      "epoch": 0.06881720430107527,
+      "grad_norm": 0.2539565861225128,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9101,
+      "step": 24
+    },
+    {
+      "epoch": 0.07168458781362007,
+      "eval_loss": 11.906322479248047,
+      "eval_runtime": 4.0818,
+      "eval_samples_per_second": 72.028,
+      "eval_steps_per_second": 18.129,
+      "step": 25
+    },
+    {
+      "epoch": 0.07741935483870968,
+      "grad_norm": 0.27296075224876404,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9081,
+      "step": 27
+    },
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 0.27018794417381287,
+      "learning_rate": 0.0,
+      "loss": 11.9075,
+      "step": 30
+    },
+    {
+      "epoch": 0.08602150537634409,
+      "eval_loss": 11.905759811401367,
+      "eval_runtime": 4.2884,
+      "eval_samples_per_second": 68.557,
+      "eval_steps_per_second": 17.256,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 20312217354240.0,
+  "total_flos": 25517223051264.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null