Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8128cb144156b6713ad9fee72f3d9f6160922fed9d6651ea16d7d1277033064a
+oid sha256:4143cdca5d588e520e35fe5870fcbc2debac6a937681bb741d2c4638aca9cb03
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9f24128755a2364bfb00af47677574ae69fb1ff3f784612f4a3251bc3bcdad
+oid sha256:a1a0a0e7c7881ae88418745634b58185339277e5b7209c8eff59d2b3cfff6ef6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8075501918792725,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.037383177570093455,
+  "best_metric": 0.7909897565841675,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07476635514018691,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.595,
       "eval_steps_per_second": 2.318,
       "step": 10
+    },
+    {
+      "epoch": 0.044859813084112146,
+      "grad_norm": 4.276338577270508,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.2567,
+      "step": 12
+    },
+    {
+      "epoch": 0.056074766355140186,
+      "grad_norm": 6.961503505706787,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.2903,
+      "step": 15
+    },
+    {
+      "epoch": 0.056074766355140186,
+      "eval_loss": 0.7992917895317078,
+      "eval_runtime": 25.1132,
+      "eval_samples_per_second": 4.5,
+      "eval_steps_per_second": 2.27,
+      "step": 15
+    },
+    {
+      "epoch": 0.06728971962616823,
+      "grad_norm": 24.969470977783203,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.3394,
+      "step": 18
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "eval_loss": 0.7909897565841675,
+      "eval_runtime": 25.3961,
+      "eval_samples_per_second": 4.449,
+      "eval_steps_per_second": 2.244,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515647493406720.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null